Change search
Refine search result
12 1 - 50 of 52
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Rows per page
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sort
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
Select
The maximal number of hits you can export is 250. When you want to export more records please use the Create feeds function.
  • 1.
    Andersson Hagiwara, Magnus
    et al.
    University of Borås, School of Health Science.
    Suserud, Björn-Ove
    University of Borås, School of Health Science.
    Andersson-Gare, Boel
    Sjöqvist, Bengt-Arne
    Henricson, Maria
    Jonsson, Anders
    University of Borås, School of Health Science.
    The effect of a Computerised Decision Support System (CDSS) on compliance with the prehospital assessment process: results of an interrupted time-series study2014In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 14, no 70Article in journal (Refereed)
    Abstract [en]

    BACKGROUND:Errors in the decision-making process are probably the main threat to patient safety in the prehospital setting. The reason can be the change of focus in prehospital care from the traditional "scoop and run" practice to a more complex assessment and this new focus imposes real demands on clinical judgment. The use of Clinical Guidelines (CG) is a common strategy for cognitively supporting the prehospital providers. However, there are studies that suggest that the compliance with CG in some cases is low in the prehospital setting. One possible way to increase compliance with guidelines could be to introduce guidelines in a Computerized Decision Support System (CDSS). There is limited evidence relating to the effect of CDSS in a prehospital setting. The present study aimed to evaluate the effect of CDSS on compliance with the basic assessment process described in the prehospital CG and the effect of On Scene Time (OST).METHODS:In this time-series study, data from prehospital medical records were collected on a weekly basis during the study period. Medical records were rated with the guidance of a rating protocol and data on OST were collected. The difference between baseline and the intervention period was assessed by a segmented regression.RESULTS:In this study, 371 patients were included. Compliance with the assessment process described in the prehospital CG was stable during the baseline period. Following the introduction of the CDSS, compliance rose significantly. The post-intervention slope was stable. The CDSS had no significant effect on OST.CONCLUSIONS:The use of CDSS in prehospital care has the ability to increase compliance with the assessment process of patients with a medical emergency. This study was unable to demonstrate any effects of OST.

  • 2. Backlund, L
    et al.
    Skånér, Y
    Montgomery, H
    Bring, J
    Strender, L-E
    GPs' decisions on drug treatment for patients with high cholesterol values: A think-aloud study2004In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 4, no 23Article in journal (Other academic)
    Abstract [en]

    Background The purpose was to examine how General Practitioners (GPs) use clinical information and rules from guidelines in their decisions on drug treatment for high cholesterol values. Methods Twenty GPs were presented with six case vignettes and were instructed to think aloud while successively more information about a case was presented, and finally to decide if a drug should be prescribed or not. The statements were coded for the clinical information to which they referred and for favouring or not favouring prescription. Results The evaluation of clinical information was compatible with decision-making as a search for reasons or arguments. Lifestyle-related information like smoking and overweight seemed to be evaluated from different perspectives. A patient's smoking favoured treatment for some GPs and disfavoured treatment for others. Conclusions The method promised to be useful for understanding why doctors differ in their decisions on the same patient descriptions and why rules from the guidelines are not followed strictly.

  • 3. Bagattini, Francesco
    et al.
    Karlsson, Isak
    Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences.
    Rebane, Jonathan
    Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences.
    Papapetrou, Panagiotis
    Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences.
    A classification framework for exploiting sparse multi-variate temporal features with application to adverse drug event detection in medical records2019In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 19, article id 7Article in journal (Refereed)
    Abstract [en]

    Background: Adverse drug events (ADEs) as well as other preventable adverse events in the hospital setting incur a yearly monetary cost of approximately $3.5 billion, in the United States alone. Therefore, it is of paramount importance to reduce the impact and prevalence of ADEs within the healthcare sector, not only since it will result in reducing human suffering, but also as a means to substantially reduce economical strains on the healthcare system. One approach to mitigate this problem is to employ predictive models. While existing methods have been focusing on the exploitation of static features, limited attention has been given to temporal features.

    Methods: In this paper, we present a novel classification framework for detecting ADEs in complex Electronic health records (EHRs) by exploiting the temporality and sparsity of the underlying features. The proposed framework consists of three phases for transforming sparse and multi-variate time series features into a single-valued feature representation, which can then be used by any classifier. Moreover, we propose and evaluate three different strategies for leveraging feature sparsity by incorporating it into the new representation.

    Results: A large-scale evaluation on 15 ADE datasets extracted from a real-world EHR system shows that the proposed framework achieves significantly improved predictive performance compared to state-of-the-art. Moreover, our framework can reveal features that are clinically consistent with medical findings on ADE detection.

    Conclusions: Our study and experimental findings demonstrate that temporal multi-variate features of variable length and with high sparsity can be effectively utilized to predict ADEs from EHRs. Two key advantages of our framework are that it is method agnostic, i.e., versatile, and of low computational cost, i.e., fast; hence providing an important building block for future exploitation within the domain of machine learning from EHRs.

  • 4.
    Berglund, Erik
    et al.
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Public Health and Caring Sciences, Social Medicine.
    Westerling, Ragnar
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Public Health and Caring Sciences, Social Medicine.
    Sundström, Johan
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Medical Sciences, Clinical Epidemiology. Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Medicinska och farmaceutiska vetenskapsområdet, centrumbildningar mm, UCR-Uppsala Clinical Research Center.
    Lytsy, Per
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Public Health and Caring Sciences, Social Medicine.
    Length of time periods in treatment effect descriptions and willingness to initiate preventive therapy: a randomised survey experiment2018In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 18, article id 106Article in journal (Refereed)
    Abstract [en]

    Background Common measures used to describe preventive treatment effects today are proportional, i.e. they compare the proportions of events in relative or absolute terms, however they are not easily interpreted from the patient's perspective and different magnitudes do not seem to clearly discriminate between levels of effect presented to people. Methods In this randomised cross-sectional survey experiment, performed in a Swedish population-based sample (n=1041, response rate 58.6%), the respondents, aged between 40 and 75years were given information on a hypothetical preventive cardiovascular treatment. Respondents were randomised into groups in which the treatment was described as having the effect of delaying a heart attack for different periods of time (Delay of Event,DoE): 1month, 6months or 18months. Respondents were thereafter asked about their willingness to initiate such therapy, as well as questions about how they valued the proposed therapy. ResultsLonger DoE:s were associated with comparatively greater willingness to initiate treatment. The proportions accepting treatment were 81, 71 and 46% when postponement was 18months, 6months and 1month respectively. In adjusted binary logistic regression models the odds ratio for being willing to take therapy was 4.45 (95% CI 2.72-7.30) for a DoE of 6months, and 6.08 (95% CI 3.61-10.23) for a DoE of 18months compared with a DoE of 1month. Greater belief in the necessity of medical treatment increased the odds of being willing to initiate therapy. ConclusionsLay people's willingness to initiate preventive therapy was sensitive to the magnitude of the effect presented as DoE. The results indicate that DoE is a comprehensible effect measure, of potential value in shared clinical decision-making.

  • 5.
    Cakici, Baki
    et al.
    KTH.
    Hebing, Kenneth
    Swedish Institute for Infectious Control (SMI).
    Grünewald, Maria
    Swedish Institute for Infectious Control (SMI).
    Saretok, Paul
    Swedish Institute for Infectious Control (SMI).
    Hulth, Anette
    Swedish Institute for Infectious Control (SMI).
    CASE: A Framework for Computer Supported Outbreak Detection2010In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 10, no 14Article in journal (Refereed)
    Abstract [en]

    Background: In computer supported outbreak detection, a statistical method is applied to a collection of cases to detect any excess cases for a particular disease. Whether a detected aberration is a true outbreak is decided by a human expert. We present a technical framework designed and implemented at the Swedish Institute for Infectious Disease Control for computer supported outbreak detection, where a database of case reports for a large number of infectious diseases can be processed using one or more statistical methods selected by the user.

    Results: Based on case information, such as diagnosis and date, different statistical algorithms for detecting outbreaks can be applied, both on the disease level and the subtype level. The parameter settings for the algorithms can be configured independently for different diagnoses using the provided graphical interface. Input generators and output parsers are also provided for all supported algorithms. If an outbreak signal is detected, an email notification is sent to the persons listed as receivers for that particular disease.

    Conclusions: The framework is available as open source software, licensed under GNU General Public License Version 3. By making the code open source, we wish to encourage others to contribute to the future development of computer supported outbreak detection systems, and in particular to the development of the CASE framework.

  • 6.
    Cakici, Baki
    et al.
    KTH, School of Information and Communication Technology (ICT), Communication: Services and Infrastucture, Software and Computer Systems, SCS.
    Hebing, Kenneth
    Swedish Institute for Infectious Control (SMI), Solna, Sweden.
    Grünewald, Maria
    Swedish Institute for Infectious Control (SMI), Solna, Sweden.
    Saretok, Paul
    Swedish Institute for Infectious Control (SMI), Solna, Sweden.
    Hulth, Anette
    Swedish Institute for Infectious Control (SMI), Solna, Sweden.
    CASE: a framework for computer supported outbreak detection2010In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 10, p. 14-Article in journal (Refereed)
    Abstract [en]

    Background: In computer supported outbreak detection, a statistical method is applied to a collection of cases to detect any excess cases for a particular disease. Whether a detected aberration is a true outbreak is decided by a human expert. We present a technical framework designed and implemented at the Swedish Institute for Infectious Disease Control for computer supported outbreak detection, where a database of case reports for a large number of infectious diseases can be processed using one or more statistical methods selected by the user. Results: Based on case information, such as diagnosis and date, different statistical algorithms for detecting outbreaks can be applied, both on the disease level and the subtype level. The parameter settings for the algorithms can be configured independently for different diagnoses using the provided graphical interface. Input generators and output parsers are also provided for all supported algorithms. If an outbreak signal is detected, an email notification is sent to the persons listed as receivers for that particular disease. Conclusions: The framework is available as open source software, licensed under GNU General Public License Version 3. By making the code open source, we wish to encourage others to contribute to the future development of computer supported outbreak detection systems, and in particular to the development of the CASE framework.

  • 7.
    Chen, Rong
    et al.
    Department of Microbiology, Tumor and Cell Biology, Karolinska Institutet, Stockholm, Sweden.
    Enberg, G.
    Department of Neurobiology, Care Sciences and Society, Karolinska Institutet, Stockholm, Sweden.
    Klein, Gunnar O.
    Department of Microbiology, Tumor and Cell Biology, Karolinska Institutet, Stockholm, Sweden + Department of Medicine, Karolinska Institutet, Stockholm, Sweden.
    Julius - a template based supplementary electronic health record system2007In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 7, no 10Article in journal (Refereed)
    Abstract [en]

    BACKGROUND: EHR systems are widely used in hospitals and primary care centres but it is usually difficult to share information and to collect patient data for clinical research. This is partly due to the different proprietary information models and inconsistent data quality. Our objective was to provide a more flexible solution enabling the clinicians to define which data to be recorded and shared for both routine documentation and clinical studies. The data should be possible to reuse through a common set of variable definitions providing a consistent nomenclature and validation of data. Another objective was that the templates used for the data entry and presentation should be possible to use in combination with the existing EHR systems.

    METHODS: We have designed and developed a template based system (called Julius) that was integrated with existing EHR systems. The system is driven by the medical domain knowledge defined by clinicians in the form of templates and variable definitions stored in a common data repository. The system architecture consists of three layers. The presentation layer is purely web-based, which facilitates integration with existing EHR products. The domain layer consists of the template design system, a variable/clinical concept definition system, the transformation and validation logic all implemented in Java. The data source layer utilizes an object relational mapping tool and a relational database.

    RESULTS: The Julius system has been implemented, tested and deployed to three health care units in Stockholm, Sweden. The initial responses from the pilot users were positive. The template system facilitates patient data collection in many ways. The experience of using the template system suggests that enabling the clinicians to be in control of the system, is a good way to add supplementary functionality to the present EHR systems.

    CONCLUSION: The approach of the template system in combination with various local EHR systems can facilitate the sharing and reuse of validated clinical information from different health care units. However, future system developments for these purposes should consider using the openEHR/CEN models with shareable archetypes.

  • 8.
    Chen, Rong
    et al.
    Karolinska Institutet.
    Enberg, Gösta
    Department of Neurobiology, Care Sciences and Society, Karolinska Institutet, Stockholm, Sweden.
    Klein, Gunnar
    Department of Neurobiology, Care Sciences and Society, Karolinska Institutet, Stockholm, Sweden.
    Julius--a template based supplementary electronic health record system2007In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 7, no 10Article in journal (Refereed)
    Abstract [en]

    Background: EHR systems are widely used in hospitals and primary care centres but it is usually difficult to share information and to collect patient data for clinical research. This is partly due to the different proprietary information models and inconsistent data quality. Our objective was to provide a more flexible solution enabling the clinicians to define which data to be recorded and shared for both routine documentation and clinical studies. The data should be possible to reuse through a common set of variable definitions providing a consistent nomenclature and validation of data. Another objective was that the templates used for the data entry and presentation should be possible to use in combination with the existing EHR systems.

    Methods: We have designed and developed a template based system (called Julius) that was integrated with existing EHR systems. The system is driven by the medical domain knowledge defined by clinicians in the form of templates and variable definitions stored in a common data repository. The system architecture consists of three layers. The presentation layer is purely webbased, which facilitates integration with existing EHR products. The domain layer consists of the template design system, a variable/clinical concept definition system, the transformation and validation logic all implemented in Java. The data source layer utilizes an object relational mapping tool and a relational database.

    Results: The Julius system has been implemented, tested and deployed to three health care units in Stockholm, Sweden. The initial responses from the pilot users were positive. The template system facilitates patient data collection in many ways. The experience of using the template system suggests that enabling the clinicians to be in control of the system, is a good way to add supplementary functionality to the present EHR systems.

    Conclusion: The approach of the template system in combination with various local EHR systems can facilitate the sharing and reuse of validated clinical information from different health care units. However, future system developments for these purposes should consider using the openEHR/CEN models with shareable archetypes.

  • 9.
    Chen, Rong
    et al.
    Department of Microbiology, Tumor and Cell Biology, Karolinska Institutet, Stockholm.
    Enberg, Gösta
    Department of Neurobiology, Care Sciences and Society, Karolinska Institutet, Stockholm.
    Klein, Gunnar O.
    Department of Microbiology, Tumor and Cell Biology, Karolinska Institutet, Stockholm; Department of Medicine, Karolinska Institutet, Stockholm.
    Julius: a template based supplementary electronic health record system2007In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 7, article id 10Article in journal (Refereed)
    Abstract [en]

    Background: EHR systems are widely used in hospitals and primary care centres but it is usually difficult to share information and to collect patient data for clinical research. This is partly due to the different proprietary information models and inconsistent data quality. Our objective was to provide a more flexible solution enabling the clinicians to define which data to be recorded and shared for both routine documentation and clinical studies. The data should be possible to reuse through a common set of variable definitions providing a consistent nomenclature and validation of data. Another objective was that the templates used for the data entry and presentation should be possible to use in combination with the existing EHR systems.

    Methods: We have designed and developed a template based system (called Julius) that was integrated with existing EHR systems. The system is driven by the medical domain knowledge defined by clinicians in the form of templates and variable definitions stored in a common data repository. The system architecture consists of three layers. The presentation layer is purely web-based, which facilitates integration with existing EHR products. The domain layer consists of the template design system, a variable/clinical concept definition system, the transformation and validation logic all implemented in Java. The data source layer utilizes an object relational mapping tool and a relational database.

    Results: The Julius system has been implemented, tested and deployed to three health care units in Stockholm, Sweden. The initial responses from the pilot users were positive. The template system facilitates patient data collection in many ways. The experience of using the template system suggests that enabling the clinicians to be in control of the system, is a good way to add supplementary functionality to the present EHR systems.

    Conclusion: The approach of the template system in combination with various local EHR systems can facilitate the sharing and reuse of validated clinical information from different health care units. However, future system developments for these purposes should consider using the openEHR/CEN models with shareable archetypes.

  • 10.
    Chen, Rong
    et al.
    Linköping University, Linköping, Sweden; Cambio Healthcare System, Linköping, Sweden.
    Klein, Gunnar O.
    Karolinska Institutet, Solna, Sweden.
    Sundvall, Erik
    Linköping University, Linköping, Sweden.
    Karlsson, Daniel
    Linköping University, Linköping, Sweden.
    Åhlfeldt, Hans
    Linköping University, Linköping, Sweden.
    Archetype-based conversion of EHR content models: pilot experience with a regional EHR system2009In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 9, p. 33-, article id 33Article in journal (Refereed)
    Abstract [en]

    BACKGROUND: Exchange of Electronic Health Record (EHR) data between systems from different suppliers is a major challenge. EHR communication based on archetype methodology has been developed by openEHR and CEN/ISO. The experience of using archetypes in deployed EHR systems is quite limited today. Currently deployed EHR systems with large user bases have their own proprietary way of representing clinical content using various models. This study was designed to investigate the feasibility of representing EHR content models from a regional EHR system as openEHR archetypes and inversely to convert archetypes to the proprietary format.

    METHODS: The openEHR EHR Reference Model (RM) and Archetype Model (AM) specifications were used. The template model of the Cambio COSMIC, a regional EHR product from Sweden, was analyzed and compared to the openEHR RM and AM. This study was focused on the convertibility of the EHR semantic models. A semantic mapping between the openEHR RM/AM and the COSMIC template model was produced and used as the basis for developing prototype software that performs automated bi-directional conversion between openEHR archetypes and COSMIC templates.

    RESULTS: Automated bi-directional conversion between openEHR archetype format and COSMIC template format has been achieved. Several archetypes from the openEHR Clinical Knowledge Repository have been imported into COSMIC, preserving most of the structural and terminology related constraints. COSMIC templates from a large regional installation were successfully converted into the openEHR archetype format. The conversion from the COSMIC templates into archetype format preserves nearly all structural and semantic definitions of the original content models. A strategy of gradually adding archetype support to legacy EHR systems was formulated in order to allow sharing of clinical content models defined using different formats.

    CONCLUSION: The openEHR RM and AM are expressive enough to represent the existing clinical content models from the template based EHR system tested and legacy content models can automatically be converted to archetype format for sharing of knowledge. With some limitations, internationally available archetypes could be converted to the legacy EHR models. Archetype support can be added to legacy EHR systems in an incremental way allowing a migration path to interoperability based on standards.

  • 11.
    Chen, Rong
    et al.
    Linköping University, Department of Biomedical Engineering, Medical Informatics. Linköping University, The Institute of Technology.
    Klein, Gunnar O
    Department of Microbiology, Tumor and Cell Biology, Karolinska Institutet, Solna, Sweden.
    Sundvall, Erik
    Linköping University, Department of Biomedical Engineering, Medical Informatics. Linköping University, The Institute of Technology.
    Karlsson, Daniel
    Linköping University, Department of Biomedical Engineering, Medical Informatics. Linköping University, The Institute of Technology.
    Åhlfeldt, Hans
    Linköping University, Department of Biomedical Engineering, Medical Informatics. Linköping University, The Institute of Technology.
    Archetype-based conversion of EHR content models: pilot experience with a regional EHR system2009In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 9, no 33Article in journal (Refereed)
    Abstract [en]

    Background: Exchange of Electronic Health Record (EHR) data between systems from different suppliers is a major challenge. EHR communication based on archetype methodology has been developed by openEHR and CEN/ISO. The experience of using archetypes in deployed EHR systems is quite limited today. Currently deployed EHR systems with large user bases have their own proprietary way of representing clinical content using various models. This study was designed to investigate the feasibility of representing EHR content models from a regional EHR system as openEHR archetypes and inversely to convert archetypes to the proprietary format. Methods: The openEHR EHR Reference Model (RM) and Archetype Model (AM) specifications were used. The template model of the Cambio COSMIC, a regional EHR product from Sweden, was analyzed and compared to the openEHR RM and AM. This study was focused on the convertibility of the EHR semantic models. A semantic mapping between the openEHR RM/AM and the COSMIC template model was produced and used as the basis for developing prototype software that performs automated bidirectional conversion between openEHR archetypes and COSMIC templates. Results: Automated bi-directional conversion between openEHR archetype format and COSMIC template format has been achieved. Several archetypes from the openEHR Clinical Knowledge Repository have been imported into COSMIC, preserving most of the structural and terminology related constraints. COSMIC templates from a large regional installation were successfully converted into the openEHR archetype format. The conversion from the COSMIC templates into archetype format preserves nearly all structural and semantic definitions of the original content models. A strategy of gradually adding archetype support to legacy EHR systems was formulated in order to allow sharing of clinical content models defined using different formats. Conclusion: The openEHR RM and AM are expressive enough to represent the existing clinical content models from the template based EHR system tested and legacy content models can automatically be converted to archetype format for sharing of knowledge. With some limitations, internationally available archetypes could be converted to the legacy EHR models. Archetype support can be added to legacy EHR systems in an incremental way allowing a migration path to interoperability based on standards.

  • 12. Davoody, Nadia
    et al.
    Koch, Sabine
    Krakau, Ingvar
    Hägglund, Maria
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Women's and Children's Health, Research group (Dept. of women´s and children´s health), Clinical Psychology in Healthcare.
    Accessing and sharing health information for post-discharge stroke care through a national health information exchange platform: a case study2019In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 19, no 1, article id 95Article in journal (Refereed)
    Abstract [en]

    BACKGROUND:

    Patients and citizens need access to their health information to get a retrospective as well as a prospective view on their care and rehabilitation processes. However, patients' health information is stored in several health information systems and interoperability problems often hamper accessibility. In Sweden a national health information exchange (HIE) platform has been developed that enables information exchange between different health information systems. The aim of this study is to explore the opportunities and limitations of accessing and interacting with important health information through the Swedish national HIE platform.

    METHODS:

    A single case study approach was used for this study as an in-depth understanding of the subject was needed. A fictive patient case with a pseudo-name was created based on an interview with a stroke coordinator in Stockholm County. Information access through the national health information exchange platform and available service contracts and application programming interfaces were studied using different scenarios.

    RESULTS:

    Based on the scenarios created in this study, patients would be able to access some health related information from their electronic health records using the national health information exchange platform. However, there is necessary information which is not retrievable as it is either stored in electronic health records and eHealth services which are not connected to the national health information exchange platform or there is no service contract developed for these types of information. In addition, patients are not able to share information with healthcare professionals.

    CONCLUSION:

    The national Swedish HIE platform provides the building blocks needed to allow patients online access to their health information in a fragmented and distributed health system. However, more complex interaction scenarios allowing patients to communicate with their health care providers or to update their health related information are not yet supported. Therefore it is of great importance to involve patients throughout the design and evaluation of eHealth services on both national and local levels to ensure that their needs for interoperability and information exchange are met.

  • 13. Davoody, Nadia
    et al.
    Koch, Sabine
    Krakau, Ingvar
    Hägglund, Maria
    Post-discharge stroke patients' information needs as input to proposing patient-centred eHealth services.2016In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 16, article id 66Article in journal (Refereed)
    Abstract [en]

    BACKGROUND: Despite the potential of eHealth services to revolutionize the way healthcare and prevention is provided many applications developed for patients fail to deliver their promise. Therefore, the aim of this study is to use patient journey mapping to explore post-discharge stroke patients' information needs to propose eHealth services that meet their needs throughout their care and rehabilitation processes.

    METHODS: Three focus groups with younger (<65 years) and older (> = 65 years) stroke patients were performed. Content analysis was used to analyse the data. Stroke patients' information needs was explored using patient journey model.

    RESULTS: Four main events (discharge from hospital, discharge from rehab clinic, coming home, and clinical encounters) and two phases (at rehab clinic, at home) have been identified in patients' post-discharge journey. The main categories identified in this study indicate that patients not only need to have access to health related information about their care and rehabilitation processes but also practical guidance through healthcare and community services. Patients also have different information needs at different events and during different phases. Potential supportive eHealth services were suggested by the researchers considering different parts of the patients' journeys.

    CONCLUSIONS: Patient journey models and qualitative analysis of patients' information needs are powerful tools that can be used to improve healthcare from a patient perspective. As patients' understanding of their illness changes over time, their need of more flexible support throughout the care and rehabilitation processes increases. To design appropriate eHealth services that meet patients' information needs, it is imperative to understand the current care and rehabilitation processes and identify patients' information needs throughout their journey.

  • 14.
    de Vries, Arjen E.
    et al.
    University of Medical Centre Groningen, Netherlands.
    van der Wal, Martje H L.
    University of Medical Centre Groningen, Netherlands.
    Nieuwenhuis, Maurice M W.
    University of Medical Centre Groningen, Netherlands.
    de Jong, Richard M:
    University of Medical Centre Groningen, Netherlands.
    van Dijk, Rene B.
    Martini Hospital, Netherlands.
    Jaarsma, Tiny
    Linköping University, Department of Social and Welfare Studies, Division of Health, Activity and Care. Linköping University, Faculty of Health Sciences.
    Hillege, Hans L.
    University of Medical Centre Groningen, Netherlands.
    Jorna, Rene J.
    University of Groningen, Netherlands.
    Perceived barriers of heart failure nurses and cardiologists in using clinical decision support systems in the treatment of heart failure patients2013In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 13, no 54Article in journal (Refereed)
    Abstract [en]

    Background

    Clinical Decision Support Systems (CDSSs) can support guideline adherence in heart failure (HF) patients. However, the use of CDSSs is limited and barriers in working with CDSSs have been described as a major obstacle. It is unknown if barriers to CDSSs are present and differ between HF nurses and cardiologists. Therefore the aims of this study are; 1. Explore the type and number of perceived barriers of HF nurses and cardiologists to use a CDSS in the treatment of HF patients. 2. Explore possible differences in perceived barriers between two groups. 3. Assess the relevance and influence of knowledge management (KM) on Responsibility/Trust (R&T) and Barriers/Threats (B&T).

    Methods

    A questionnaire was developed including; B&T, R&T, and KM. For analyses, descriptive techniques, 2-tailed Pearson correlation tests, and multiple regression analyses were performed.

    Results

    The response- rate of 220 questionnaires was 74%. Barriers were found for cardiologists and HF nurses in all the constructs. Sixty-five percent did not want to be dependent on a CDSS. Nevertheless thirty-six percent of HF nurses and 50% of cardiologists stated that a CDSS can optimize HF medication. No relationship between constructs and age; gender; years of work experience; general computer experience and email/internet were observed. In the group of HF nurses a positive correlation (r .33, P<.01) between years of using the internet and R&T was found. In both groups KM was associated with the constructs B&T (B=.55, P=<.01) and R&T (B=.50, P=<.01).

    Conclusions

    Both cardiologists and HF-nurses perceived barriers in working with a CDSS in all of the examined constructs. KM has a strong positive correlation with perceived barriers, indicating that increasing knowledge about CDSSs can decrease their barriers.

  • 15.
    Dentler, Kathrin
    et al.
    Vrije University of Amsterdam, Netherlands University of Amsterdam, Netherlands .
    Cornet, Ronald
    Linköping University, Department of Biomedical Engineering. Linköping University, The Institute of Technology. University of Amsterdam, Netherlands.
    ten Teije, Annette
    Vrije University of Amsterdam, Netherlands .
    Tanis, Pieter
    University of Amsterdam, Netherlands .
    Klinkenbijl, Jean
    University of Amsterdam, Netherlands .
    Tytgat, Kristien
    University of Amsterdam, Netherlands .
    de Keizer, Nicolette
    University of Amsterdam, Netherlands .
    Influence of data quality on computed Dutch hospital quality indicators: a case study in colorectal cancer surgery2014In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 14, no 32Article in journal (Refereed)
    Abstract [en]

    Background: Our study aims to assess the influence of data quality on computed Dutch hospital quality indicators, and whether colorectal cancer surgery indicators can be computed reliably based on routinely recorded data from an electronic medical record (EMR). Methods: Cross-sectional study in a department of gastrointestinal oncology in a university hospital, in which a set of 10 indicators is computed (1) based on data abstracted manually for the national quality register Dutch Surgical Colorectal Audit (DSCA) as reference standard and (2) based on routinely collected data from an EMR. All 75 patients for whom data has been submitted to the DSCA for the reporting year 2011 and all 79 patients who underwent a resection of a primary colorectal carcinoma in 2011 according to structured data in the EMR were included. Comparison of results, investigating the causes for any differences based on data quality analysis. Main outcome measures are the computability of quality indicators, absolute percentages of indicator results, data quality in terms of availability in a structured format, completeness and correctness. Results: All indicators were fully computable based on the DSCA dataset, but only three based on EMR data, two of which were percentages. For both percentages, the difference in proportions computed based on the two datasets was significant. All required data items were available in a structured format in the DSCA dataset. Their average completeness was 86%, while the average completeness of these items in the EMR was 50%. Their average correctness was 87%. Conclusions: Our study showed that data quality can significantly influence indicator results, and that our EMR data was not suitable to reliably compute quality indicators. EMRs should be designed in a way so that the data required for audits can be entered directly in a structured and coded format.

  • 16. Ellervall, Eva
    et al.
    Brehmer, Berndt
    Swedish Defence University, Department of Military Studies, War Studies Division.
    Knutsson, Kerstin
    How confident are general dental practitioners in their decision to administer antibiotic prophylaxis?: A questionnaire study2008In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 8, p. 57-Article in journal (Refereed)
    Abstract [en]

    Background: Common dental procedures induce bacteremia. To prevent infectious complications from bacteremia in patients with specific medical conditions, antibiotic prophylaxis is considered. Recommendations are often unclear and ambiguous. In a previous study we reported wide variations in general dental practitioners' (GDPs') administrations of antibiotic prophylaxis. We hypothesized that within such a conflicting clinical area, decisions are made with a high level of personal uncertainty. This study examined GDPs' confidence in their decisions and analyzed the extent to which case-related factors might explain individual variations in confidence. Methods: Postal questionnaires in combination with telephone interviews were used. The response rate was 51% (101/200). There were no significant differences between respondents and non-respondents regarding sex, age, or place of work. The GDPs were presented to patient cases of different medical conditions, where some should receive antibiotic prophylaxis according to recommendations when performing dental procedures that could cause gingival bleeding. The GDPs assessed on visual analogue scales how confident they were in their decisions. The extent to which case-related factors, medical condition and dental procedure, could explain individual variation in confidence was analyzed. Results: Overall the GDPs exhibited high confidence in their decisions regardless of whether they administered antibiotic prophylaxis or not, or whether their decisions were in accordance with recommendations or not. The case-related factors could explain between 30-100% of the individual variation in GDPs' confidence. For 46%, the medical condition significantly explained the individual variation in confidence. However, for most of these GDPs, lower confidence was not presented for conditions where recommendations are unclear and higher confidence was not presented for conditions where recommendations are more clear. For 8% the dental procedure significantly explained the variation, although all procedures could cause bacteremia. For 46% neither the medical condition nor the dental procedure could significantly explain the individual variation in confidence. Conclusion: The GDPs presented high confidence in their decisions, and the majority of GDPs did not present what could be considered a justified varied level of confidence according to the clarity of recommendations. Clinicians who are overconfident in their decisions may be less susceptible to modifications of their behavior to more evidence-based strategies.

  • 17.
    Fors, Uno
    et al.
    Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences.
    Kamwesiga, Julius T.
    Eriksson, Gunilla M.
    von Koch, Lena
    Guidetti, Susanne
    User evaluation of a novel SMS-based reminder system for supporting post-stroke rehabilitation2019In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 19, article id 122Article in journal (Refereed)
    Abstract [en]

    Background: According to WHO stroke is a growing societal challenge and the third leading cause of global disease-burden estimated using disability-adjusted life years. Rehabilitation after stroke is an area of mutual interest for health care in many countries. Within the health care sector there is a growing emphasis on ICT services to provide clients with easier access to information, self-evaluation, and self-management. ICT-supported care programs possible to use in clients' home environments are also recommended when there are long distances to the health care specialists. The aim of this study was to evaluate the technical usability of a SMS-based reminder system as well as user opinions when using such a system to assist clients to remember to perform daily rehabilitation activities, to rate their performance and to allow Occupational therapists (OT's) to track and follow-up clients' results over time. Methods: Fifteen persons with stroke were invited to participate in the study and volunteered to receive daily SMS-based reminders regarding three activities to perform on a daily basis as well as answer daily SMS-based questions about their success rate during eight weeks. Clients, a number of family members, as well as OTs were interviewed to evaluate their opinions of using the reminder system. Results: All clients were positive to the reminder system and felt that it helped them to regain their abilities. Their OTs agreed that the reminder and follow-up system was of benefit in the rehabilitation process. However, some technical and other issues were limiting the use of the system for some clients. The issues were mostly linked to the fact that the SMS system was based on a Swedish phone number, so that all messages needed to be sent internationally. Conclusion: In conclusion, it seems that this type of SMS-based reminder systems could be of good use in the rehabilitation process after stroke, even in low income counties where few clients have access to Internet or smart phones, and where access to healthcare services is limited. However, since the results are based on clients', OTs' and family members' expressed beliefs, we suggest that future research objectively investigate the intervention's beneficial effects on the clients' physical and cognitive health.

  • 18.
    Fors, Uno
    et al.
    Stockholm Univ, Dept Comp & Syst Sci DSV, Stockholm, Sweden.
    Kamwesiga, Julius T.
    Uganda Allied Hlth Examinat Board, Kampala, Uganda;Karolinska Inst, Div Occupat Therapy, Dept Neurobiol Care Sci & Soc, Stockholm, Sweden.
    Eriksson, Gunilla
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Public Health and Caring Sciences, Research in Disability and Habilitation. Karolinska Inst, Div Occupat Therapy, Dept Neurobiol Care Sci & Soc, Stockholm, Sweden.
    von Koch, Lena
    Karolinska Inst, Div Occupat Therapy, Dept Neurobiol Care Sci & Soc, Stockholm, Sweden;Karolinska Univ Hosp, Theme Neuro, Stockholm, Sweden.
    Guidetti, Susanne
    Karolinska Inst, Div Occupat Therapy, Dept Neurobiol Care Sci & Soc, Stockholm, Sweden.
    User evaluation of a novel SMS-based reminder system for supporting post-stroke rehabilitation2019In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 19, article id 122Article in journal (Refereed)
    Abstract [en]

    Background: According to WHO stroke is a growing societal challenge and the third leading cause of global disease-burden estimated using disability-adjusted life years. Rehabilitation after stroke is an area of mutual interest for health care in many countries. Within the health care sector there is a growing emphasis on ICT services to provide clients with easier access to information, self-evaluation, and self-management. ICT-supported care programs possible to use in clients' home environments are also recommended when there are long distances to the health care specialists. The aim of this study was to evaluate the technical usability of a SMS-based reminder system as well as user opinions when using such a system to assist clients to remember to perform daily rehabilitation activities, to rate their performance and to allow Occupational therapists (OT's) to track and follow-up clients' results over time.

    Methods: Fifteen persons with stroke were invited to participate in the study and volunteered to receive daily SMS-based reminders regarding three activities to perform on a daily basis as well as answer daily SMS-based questions about their success rate during eight weeks. Clients, a number of family members, as well as OTs were interviewed to evaluate their opinions of using the reminder system.

    Results: All clients were positive to the reminder system and felt that it helped them to regain their abilities. Their OTs agreed that the reminder and follow-up system was of benefit in the rehabilitation process. However, some technical and other issues were limiting the use of the system for some clients. The issues were mostly linked to the fact that the SMS system was based on a Swedish phone number, so that all messages needed to be sent internationally.

    Conclusion: In conclusion, it seems that this type of SMS-based reminder systems could be of good use in the rehabilitation process after stroke, even in low income counties where few clients have access to Internet or smart phones, and where access to healthcare services is limited. However, since the results are based on clients', OTs' and family members' expressed beliefs, we suggest that future research objectively investigate the intervention's beneficial effects on the clients' physical and cognitive health.

  • 19. Gund, Anna
    et al.
    Lindecrantz, Kaj
    KTH, School of Technology and Health (STH), Medical sensors, signals and systems (MSSS).
    Schaufelberger, Maria
    Patel, Harshida
    Sjöqvist, Bengt Arne
    Attitudes among healthcare professionals towards ICT and home follow-up in chronic heart failure care2012In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 12, no 1, p. 138-Article in journal (Refereed)
    Abstract [en]

    Background: eHealth applications for out-of-hospital monitoring and treatment follow-up have been advocated for many years as a promising tool to improve treatment compliance, promote individualized care and obtain a person-centred care. Despite these benefits and a large number of promising projects, a major breakthrough in everyday care is generally still lacking. Inappropriate organization for eHealth technology, reluctance from users in the introduction of new working methods, and resistance to information and communication technology (ICT) in general could be reasons for this. Another reason may be attitudes towards the potential in out-of-hospital eHealth applications. It is therefore of interest to study the general opinions among healthcare professionals to ICT in healthcare, as well as the attitudes towards using ICT as a tool for patient monitoring and follow-up at home. One specific area of interest is in-home follow-up of elderly patients with chronic heart failure (CHF). The aim of this paper is to investigate the attitudes towards ICT, as well as distance monitoring and follow-up, among healthcare professionals working with this patient group. Method: This paper covers an attitude survey study based on responses from 139 healthcare professionals working with CHF care in Swedish hospital departments, i.e. cardiology and medicine departments. Comparisons between physicians and nurses, and in some cases between genders, on attitudes towards ICT tools and follow-up at home were performed. Results: Out of the 425 forms sent out, 139 were collected, and 17 out of 21 counties and regions were covered in the replies. Among the respondents, 66% were nurses, 30% physicians and 4% others. As for gender, 90% of nurses were female and 60% of physicians were male. Internet was used daily by 67% of the respondents. Attitudes towards healthcare ICT were found positive as 74% were positive concerning healthcare ICT today, 96% were positive regarding the future of healthcare ICT, and 54% had high confidence in healthcare ICT. Possibilities for distance monitoring/follow-up are good according to 63% of the respondents, 78% thought that this leads to increased patient involvement, and 80% thought it would improve possibilities to deliver better care. Finally, 72% of the respondents said CHF patients would benefit from home monitoring/follow-up to some extent, and 19% to a large extent. However, the best method of follow-up was considered to be home visits by nurse, or phone contact. Conclusion: The results indicate that a majority of the healthcare professionals in this study are positive to both current and future use of ICT tools in healthcare and home follow-up. Consequently other factors have to play an important role in the slow penetration of out-of-hospital eHealth applications in daily healthcare practice.

  • 20. Gund, Anna
    et al.
    Sjöqvist, Bengt Arne
    Wigert, Helena
    Hentz, Elisabet
    Lindecrantz, Kaj
    KTH, School of Technology and Health (STH), Medical sensors, signals and systems (MSSS).
    Bry, Kristina
    A randomized controlled study about the use of eHealth in the home health care of premature infants2013In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 13, no 1, p. 22-Article in journal (Refereed)
    Abstract [en]

    Background: One area where the use of information and communication technology (ICT), or eHealth, could be developed is the home health care of premature infants. The aim of this randomized controlled study was to investigate whether the use of video conferencing or a web application improves parents' satisfaction in taking care of a premature infant at home and decreases the need of home visits. In addition, nurses' attitudes regarding the use of these tools were examined. Method: Thirty-four families were randomized to one of three groups before their premature infant was discharged from the hospital to home health care: a control group receiving standard home health care (13 families); a web group receiving home health care supplemented with the use of a web application (12 families); a video group with home health care supplemented with video conferencing using Skype (9 families). Families and nursing staff answered questionnaires about the usefulness of ICT. In addition, semi-structured interviews were conducted with 16 families. Results: All the parents in the web group found the web application easy to use. 83% of the families thought it was good to have access to their child's data through the application. All the families in the video group found Skype easy to use and were satisfied with the video calls. 88% of the families thought that video calls were better than ordinary phone calls. 33% of the families in the web group and 75% of those in the video group thought the need for home visits was decreased by the web application or Skype. 50% of the families in the web group and 100% of those in the video group thought the web application or the video calls had helped them feel more confident in caring for their child. Most of the nurses were motivated to use ICT but some were reluctant and avoided using the web application and video conferencing. Conclusion: The families were satisfied with both the web application and video conferencing. The families readily embraced the use of ICT, whereas motivating some of the nurses to accept and use ICT was a major challenge.

  • 21.
    Hagiwara, Magnus
    et al.
    Jönköping University, School of Health and Welfare, HHJ, Quality Improvement and Leadership in Health and Welfare.
    Suserud, Björn-Ove
    University of Borås, School of Health Sciences, 501 90 Borås, Sweden.
    Andersson-Gäre, Boel
    Jönköping University, School of Health and Welfare, HHJ, Quality Improvement and Leadership in Health and Welfare.
    Sjöqvist, Bengt-Arne
    Department of Signals and Systems, Chalmers University of Technology, Gothenburg, Sweden.
    Henricson, Maria
    Jönköping University, School of Health and Welfare.
    Jonsson, Anders
    University of Borås, School of Health Sciences, 501 90 Borås, Sweden.
    The effect of a Computerised Decision Support System (CDSS) on compliance with the prehospital assessment process: results of an interrupted time-series study2014In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 14, no 70, p. 1-9Article in journal (Refereed)
    Abstract [en]

    BACKGROUND:

    Errors in the decision-making process are probably the main threat to patient safety in the prehospital setting. The reason can be the change of focus in prehospital care from the traditional "scoop and run" practice to a more complex assessment and this new focus imposes real demands on clinical judgment. The use of Clinical Guidelines (CG) is a common strategy for cognitively supporting the prehospital providers. However, there are studies that suggest that the compliance with CG in some cases is low in the prehospital setting. One possible way to increase compliance with guidelines could be to introduce guidelines in a Computerized Decision Support System (CDSS). There is limited evidence relating to the effect of CDSS in a prehospital setting. The present study aimed to evaluate the effect of CDSS on compliance with the basic assessment process described in the prehospital CG and the effect of On Scene Time (OST).

    METHODS:

    In this time-series study, data from prehospital medical records were collected on a weekly basis during the study period. Medical records were rated with the guidance of a rating protocol and data on OST were collected. The difference between baseline and the intervention period was assessed by a segmented regression.

    RESULTS:

    In this study, 371 patients were included. Compliance with the assessment process described in the prehospital CG was stable during the baseline period. Following the introduction of the CDSS, compliance rose significantly. The post-intervention slope was stable. The CDSS had no significant effect on OST.

    CONCLUSIONS:

    The use of CDSS in prehospital care has the ability to increase compliance with the assessment process of patients with a medical emergency. This study was unable to demonstrate any effects of OST.

  • 22.
    Hamberg, Anna-Karin
    et al.
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Medical Sciences, Clinical pharmacogenomics and osteoporosis.
    Hellman, Jacob
    Uppsala University, Disciplinary Domain of Science and Technology, Technology, Department of Engineering Sciences, Nanotechnology and Functional Materials.
    Dahlberg, Jonny
    Uppsala University, Disciplinary Domain of Science and Technology, Technology, Department of Engineering Sciences, Nanotechnology and Functional Materials.
    Jonsson, E Niclas
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Pharmacy, Department of Pharmaceutical Biosciences.
    Wadelius, Mia
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Medical Sciences, Clinical pharmacogenomics and osteoporosis.
    A Bayesian decision support tool for efficient dose individualization of warfarin in adults and children2015In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 15, no 7Article in journal (Refereed)
    Abstract [en]

    Warfarin is the most widely prescribed anticoagulant for prevention and treatment of thromboembolic events. Although highly effective, the use of warfarin is limited by a narrow therapeutic range combined with a more than ten-fold difference in the dose required for adequate anticoagulation in adults. For each patient, an optimal dose that leads to a favourable balance between the wanted antithrombotic effect and the risk of bleeding, measured as the prothrombin time International Normalised Ratio (INR), must be found. A model capable of describing the time-course of the INR response to warfarin therapy can be used to aid dose selection, both before starting therapy (a priori dose prediction) and after therapy has been initiated (a posteriori dose revision). In this paper we describe the transfer of a population PKPD-model for warfarin developed in NONMEM to a platform independent decision support tool written in Java. The tool proved capable of solving a system of differential equations representing the pharmacokinetics and pharmacodynamics of warfarin, with a performance comparable to NONMEM. To estimate an a priori dose the user provides information on body weight, age, CYP2C9 and VKORC1 genotype, baseline and target INR. With addition of information about previous doses and INR observations, the tool will use a Bayesian forecasting method to suggest an a posteriori dose, i.e. the dose with the highest probability to result in the desired INR. Results are displayed as the predicted dose per day and per week, and graphically as the predicted INR curve. The tool can also be used to predict INR following any given dose regimen, e.g. a loading-dose regimen. We believe it will provide a clinically useful tool for initiating and maintaining warfarin therapy in the clinic. It will ensure consistent dose adjustment practices between prescribers, and provide more efficient individualization of warfarin dosing in both children and adults.

  • 23.
    Hellström, Lina
    et al.
    University of Kalmar, eHealth Institute, School of Human Sciences, University of Kalmar,.
    Waern, Karolina
    University of Kalmar, eHealth Institute, School of Human Sciences, University of Kalmar,.
    Montelius, Emelie
    University of Kalmar, eHealth Institute, School of Human Sciences, University of Kalmar,.
    Åstrand, Bengt
    University of Kalmar, School of Pure and Applied Natural Sciences.
    Rydberg, Tony
    University of Kalmar, eHealth Institute, School of Human Sciences, University of Kalmar,.
    Petersson, Göran
    University of Kalmar, eHealth Institute, School of Human Sciences, University of Kalmar,.
    Physicians' attitudes towards ePrescribing: evaluation of a Swedish full-scale implementation2009In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 9, no August, p. Article number: 37-Article in journal (Refereed)
    Abstract [en]

    BACKGROUND: The penetration rate of Electronic Health Record (EHR) systems in health care is increasing. However, many different EHR-systems are used with varying ePrescription designs and functionalities. The aim of the present study was to evaluate experienced ePrescribers' attitudes towards ePrescribing for suggesting improvements. METHODS: Physicians (n = 431) from seven out of the 21 Swedish health care regions, using one of the six most widely implemented EHR-systems with integrated electronic prescribing modules, were recruited from primary care centers and hospital clinics of internal medicine, orthopaedics and surgery. The physicians received a web survey that comprised eight questions on background data and 19 items covering attitudes towards ePrescribing. Forty-two percent (n = 199) of the physicians answered the questionnaire; 90% (n = 180) of the respondents met the inclusion criteria and were included in the final analysis. RESULTS: A majority of the respondents regarded their EHR-system easy to use in general (81%), and for the prescribing of drugs (88%). Most respondents believed they were able to provide the patients better service by ePrescribing (92%), and regarded ePrescriptions to be time saving (91%) and to be safer (83%), compared to handwritten prescriptions. Some of the most frequently reported weaknesses were: not clearly displayed price of drugs (43%), complicated drug choice (21%), and the perception that it was possible to handle more than one patient at a time when ePrescribing (13%). Moreover, 62% reported a lack of receipt from the pharmacy after successful transmission of an ePrescription. Although a majority (73%) of the physicians reported that they were always or often checking the ePrescription a last time before transmitting, 25% declared that they were seldom or never doing a last check. The respondents suggested a number of improvements, among others, to simplify the drug choice and the cancellation of ePrescriptions. CONCLUSION: The Swedish physicians in the group studied were generally satisfied with their specific EHR-system and with ePrescribing as such. However, identified weaknesses warrant improvements of the EHR-systems as well as of their implementation in the individual health care organisation.

  • 24.
    Henriksson, Aron
    et al.
    Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences.
    Zhao, Jing
    Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences.
    Dalianis, Hercules
    Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences.
    Boström, Henrik
    Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences.
    Ensembles of randomized trees using diverse distributed representations of clinical events2016In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 16, article id 69Article in journal (Refereed)
    Abstract [en]

    Background: Learning deep representations of clinical events based on their distributions in electronic health records has been shown to allow for subsequent training of higher-performing predictive models compared to the use of shallow, count-based representations. The predictive performance may be further improved by utilizing multiple representations of the same events, which can be obtained by, for instance, manipulating the representation learning procedure. The question, however, remains how to make best use of a set of diverse representations of clinical events – modeled in an ensemble of semantic spaces – for the purpose of predictive modeling. Methods: Three different ways of exploiting a set of (ten) distributed representations of four types of clinical events – diagnosis codes, drug codes, measurements, and words in clinical notes – are investigated in a series of experiments using ensembles of randomized trees. Here, the semantic space ensembles are obtained by varying the context window size in the representation learning procedure. The proposed method trains a forest wherein each tree is built from a bootstrap replicate of the training set whose entire original feature set is represented in a randomly selected set of semantic spaces – corresponding to the considered data types – of a given context window size. Results: The proposed method significantly outperforms concatenating the multiple representations of the bagged dataset; it also significantly outperforms representing, for each decision tree, only a subset of the features in a randomly selected set of semantic spaces. A follow-up analysis indicates that the proposed method exhibits less diversity while significantly improving average tree performance. It is also shown that the size of the semantic space ensemble has a significant impact on predictive performance and that performance tends to improve as the size increases. Conclusions: The strategy for utilizing a set of diverse distributed representations of clinical events when constructing ensembles of randomized trees has a significant impact on predictive performance. The most successful strategy – significantly outperforming the considered alternatives – involves randomly sampling distributed representations of the clinical events when building each decision tree in the forest.

  • 25.
    Henriksson, Aron
    et al.
    Stockholms universitet, Institutionen för data- och systemvetenskap.
    Zhao, Jing
    Stockholms universitet, Institutionen för data- och systemvetenskap.
    Dalianis, Hercules
    Stockholms universitet, Institutionen för data- och systemvetenskap.
    Boström, Henrik
    Stockholms universitet, Institutionen för data- och systemvetenskap.
    Ensembles of randomized trees using diverse distributed representations of clinical events2016In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 16, no 2, article id 69Article in journal (Refereed)
    Abstract [en]

    Background: Learning deep representations of clinical events based on their distributions in electronic health records has been shown to allow for subsequent training of higher-performing predictive models compared to the use of shallow, count-based representations. The predictive performance may be further improved by utilizing multiple representations of the same events, which can be obtained by, for instance, manipulating the representation learning procedure. The question, however, remains how to make best use of a set of diverse representations of clinical events – modeled in an ensemble of semantic spaces – for the purpose of predictive modeling. Methods: Three different ways of exploiting a set of (ten) distributed representations of four types of clinical events – diagnosis codes, drug codes, measurements, and words in clinical notes – are investigated in a series of experiments using ensembles of randomized trees. Here, the semantic space ensembles are obtained by varying the context window size in the representation learning procedure. The proposed method trains a forest wherein each tree is built from a bootstrap replicate of the training set whose entire original feature set is represented in a randomly selected set of semantic spaces – corresponding to the considered data types – of a given context window size. Results: The proposed method significantly outperforms concatenating the multiple representations of the bagged dataset; it also significantly outperforms representing, for each decision tree, only a subset of the features in a randomly selected set of semantic spaces. A follow-up analysis indicates that the proposed method exhibits less diversity while significantly improving average tree performance. It is also shown that the size of the semantic space ensemble has a significant impact on predictive performance and that performance tends to improve as the size increases. Conclusions: The strategy for utilizing a set of diverse distributed representations of clinical events when constructing ensembles of randomized trees has a significant impact on predictive performance. The most successful strategy – significantly outperforming the considered alternatives – involves randomly sampling distributed representations of the clinical events when building each decision tree in the forest.

  • 26.
    Jama Mahmud, Amina
    et al.
    Blekinge Institute of Technology, School of Health Science.
    Olander, Ewy
    Blekinge Institute of Technology, School of Health Science.
    Eriksén, Sara
    Blekinge Institute of Technology, School of Computing.
    Haglund, Bo
    Health communication in primary health care -A case study of ICT development for health promotion2013In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 13, no 17, p. 1-15Article in journal (Refereed)
    Abstract [en]

    Background Developing Information and Communication Technology (ICT) supported health communication in PHC could contribute to increased health literacy and empowerment, which are foundations for enabling people to increase control over their health, as a way to reduce increasing lifestyle related ill health. However, to increase the likelihood of success of implementing ICT supported health communication, it is essential to conduct a detailed analysis of the setting and context prior to the intervention. The aim of this study was to gain a better understanding of health communication for health promotion in PHC with emphasis on the implications for a planned ICT supported interactive health channel. Methods A qualitative case study, with a multi-methods approach was applied. Field notes, document study and focus groups were used for data collection. Data was then analyzed using qualitative content analysis. Results Health communication is an integral part of health promotion practice in PHC in this case study. However, there was a lack of consensus among health professionals on what a health promotion approach was, causing discrepancy in approaches and practices of health communication. Two themes emerged from the data analysis: Communicating health and environment for health communication. The themes represented individual and organizational factors that affected health communication practice in PHC and thus need to be taken into consideration in the development of the planned health channel. Conclusions Health communication practiced in PHC is individual based, preventive and reactive in nature, as opposed to population based, promotive and proactive in line with a health promotion approach. The most significant challenge in developing an ICT supported health communication channel for health promotion identified in this study, is profiling a health promotion approach in PHC. Addressing health promotion values and principles in the design of ICT supported health communication channel could facilitate health communication for promoting health, i.e. ‘health promoting communication’.

  • 27.
    Josefsson, Ulrika
    et al.
    Sahlgrenska Academy at University of Gothenburg, Institute of Health and Care Sciences, Sweden & Angered Hospital, Angered, Sweden .
    Berg, Marie
    Sahlgrenska Academy at University of Gothenburg, Institute of Health and Care Sciences, Gothenburg, Sweden & School of Health Sciences, University of Borås, Borås, Sweden.
    Koinberg, Ingalill
    Sahlgrenska Academy at University of Gothenburg, Institute of Health and Care Sciences, Gothenburg, Sweden.
    Hellström, Anna-Lena
    Sahlgrenska Academy at University of Gothenburg, Institute of Health and Care Sciences, Gothenburg, Sweden.
    Jenholt Nolbris, Margareta
    Sahlgrenska Academy at University of Gothenburg, Institute of Health and Care Sciences, Gothenburg, Sweden.
    Ranerup, Agneta
    Department of Applied IT, University of Gothenburg, Gothenburg, Sweden.
    Sparud-Lundin, Carina
    Sahlgrenska Academy at University of Gothenburg, Institute of Health and Care Sciences, Gothenburg, Sweden.
    Skärsäter, Ingela
    Halmstad University, School of Health and Welfare, Centre of Research on Welfare, Health and Sport (CVHI). Sahlgrenska Academy at University of Gothenburg, Institute of Health and Care Sciences, Gothenburg, Sweden.
    Person-centred web-based support - development through a Swedish multi-case study2013In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 13, article id 119Article in journal (Refereed)
    Abstract [en]

    Background

    Departing from the widespread use of the internet in modern society and the emerging use of web applications in healthcare this project captures persons’ needs and expectations in order to develop highly usable web recourses. The purpose of this paper is to outline a multi-case research project focused on the development and evaluation of person-centred web-based support for people with long-term illness. To support the underlying idea to move beyond the illness, we approach the development of web support from the perspective of the emergent area of person-centred care. The project aims to contribute to the ongoing development of web-based supports in health care and to the emerging field of person-centred care.

    Methods/Design

    The research design uses a meta-analytical approach through its focus on synthesizing experiences from four Swedish regional and national cases of design and use of web-based support in long-term illness. The cases include children (bladder dysfunction and urogenital malformation), young adults (living close to persons with mental illness), and two different cases of adults (women with breast cancer and childbearing women with type 1 diabetes). All of the cases are ongoing, though in different stages of design, implementation, and analysis. This, we argue, will lead to a synthesis of results on a meta-level not yet described.

    Discussion

    To allow valid comparisons between the four cases we explore and problematize them in relation to four main aspects: 1) The use of people’s experiences and needs; 2) The role of use of theories in the design of person-centred web-based supports; 3) The evaluation of the effects of health outcomes for the informants involved and 4) The development of a generic person-centred model for learning and social support for people with long-term illness and their significant others. Person-centred web-based support is a new area and few studies focus on how web-based interventions can contribute to the development of person-centred care. In summary, the main intention of the project outlined here is to contribute with both a synthesis of results on meta-level from four cases and a substantial contribution to the field person-centred care.

  • 28. Lamarche-Vadel, Agathe
    et al.
    Pavillon, Gérard
    Aouba, Albertine
    Johansson, Lars Age
    Swedish National Board of Health and Welfare, Center for Epidemiology, Stockholm, Sweden .
    Meyer, Laurence
    Jougla, Eric
    Rey, Grégoire
    Automated comparison of last hospital main diagnosis and underlying cause of death ICD10 codes, France, 2008-20092014In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 14, p. 44-Article in journal (Refereed)
    Abstract [en]

    BACKGROUND: In the age of big data in healthcare, automated comparison of medical diagnoses in large scale databases is a key issue. Our objectives were: 1) to formally define and identify cases of independence between last hospitalization main diagnosis (MD) and death registry underlying cause of death (UCD) for deceased subjects hospitalized in their last year of life; 2) to study their distribution according to socio-demographic and medico-administrative variables; 3) to discuss the interest of this method in the specific context of hospital quality of care assessment.

    METHODS: 1) Elaboration of an algorithm comparing MD and UCD, relying on Iris, a coding system based on international standards. 2) Application to 421,460 beneficiaries of the general health insurance regime (which covers 70% of French population) hospitalized and deceased in 2008-2009.

    RESULTS: 1) Independence, was defined as MD and UCD belonging to different trains of events leading to death 2) Among the deaths analyzed automatically (91.7%), 8.5% of in-hospital deaths and 19.5% of out-of-hospital deaths were classified as independent. Independence was more frequent in elder patients, as well as when the discharge-death time interval grew (14.3% when death occurred within 30 days after discharge and 27.7% within 6 to 12 months) and for UCDs other than neoplasms.

    CONCLUSION: Our algorithm can identify cases where death can be considered independent from the pathology treated in hospital. Excluding these deaths from the ones allocated to the hospitalization process could contribute to improve post-hospital mortality indicators. More generally, this method has the potential of being developed and used for other diagnoses comparisons across time periods or databases.

  • 29. Lee, K S Kylie
    et al.
    Wilson, Scott
    Perry, Jimmy
    Room, Robin
    Stockholm University, Faculty of Social Sciences, Department of Public Health Sciences. La Trobe University, Australia.
    Callinan, Sarah
    Assan, Robert
    Hayman, Noel
    Chikritzhs, Tanya
    Gray, Dennis
    Wilkes, Edward
    Jack, Peter
    Conigrave, Katherine M
    Developing a tablet computer-based application ('App') to measure self-reported alcohol consumption in Indigenous Australians2018In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 18, no 1, article id 8Article in journal (Refereed)
    Abstract [en]

    BACKGROUND: The challenges of assessing alcohol consumption can be greater in Indigenous communities where there may be culturally distinct approaches to communication, sharing of drinking containers and episodic patterns of drinking. This paper discusses the processes used to develop a tablet computer-based application ('App') to collect a detailed assessment of drinking patterns in Indigenous Australians. The key features of the resulting App are described.

    METHODS: An iterative consultation process was used (instead of one-off focus groups), with Indigenous cultural experts and clinical experts. Regular (weekly or more) advice was sought over a 12-month period from Indigenous community leaders and from a range of Indigenous and non-Indigenous health professionals and researchers.

    RESULTS: The underpinning principles, selected survey items, and key technical features of the App are described. Features include culturally appropriate questioning style and gender-specific voice and images; community-recognised events used as reference points to 'anchor' time periods; 'translation' to colloquial English and (for audio) to traditional language; interactive visual approaches to estimate quantity of drinking; images of specific brands of alcohol, rather than abstract description of alcohol type (e.g. 'spirits'); images of make-shift drinking containers; option to estimate consumption based on the individual's share of what the group drank.

    CONCLUSIONS: With any survey platform, helping participants to accurately reflect on and report their drinking presents a challenge. The availability of interactive, tablet-based technologies enables potential bridging of differences in culture and lifestyle and enhanced reporting.

  • 30. Lindhagen, Lars
    et al.
    Van Hemelrijck, Mieke
    Robinson, David
    Stattin, Pär
    Umeå University, Faculty of Medicine, Department of Surgical and Perioperative Sciences, Urology and Andrology.
    Garmo, Hans
    How to model temporal changes in comorbidity for cancer patients using prospective cohort data2015In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 15, article id 96Article in journal (Refereed)
    Abstract [en]

    Background: The presence of comorbid conditions is strongly related to survival and also affects treatment choices in cancer patients. This comorbidity is often quantified by the Charlson Comorbidity Index (CCI) using specific weights (1, 2, 3, or 6) for different comorbidities. It has been shown that the CCI increases at different times and with different sizes, so that traditional time to event analysis is not adequate to assess these temporal changes. Here, we present a method to model temporal changes in CCI in cancer patients using data from PCBaSe Sweden, a nation-wide population-based prospective cohort of men diagnosed with prostate cancer. Our proposed model is based on the assumption that a change in comorbidity, as quantified by the CCI, is an irreversible one-way process, i.e., CCI accumulates over time and cannot decrease.

    Methods: CCI was calculated based on 17 disease categories, which were defined using ICD-codes for discharge diagnoses in the National Patient Register. A state transition model in discrete time steps (i.e., four weeks) was applied to capture all changes in CCI. The transition probabilities were estimated from three modelling steps: 1) Logistic regression model for vital status, 2) Logistic regression model to define any changes in CCI, and 3) Poisson regression model to determine the size of CCI change, with an additional logistic regression model for CCI changes ≥ 6. The four models combined yielded parameter estimates to calculate changes in CCI with their confidence intervals.

    Results: These methods were applied to men with low-risk prostate cancer who received active surveillance (AS), radical prostatectomy (RP), or curative radiotherapy (RT) as primary treatment. There were large differences in CCI changes according to treatment.

    Conclusions: Our method to model temporal changes in CCI efficiently captures changes in comorbidity over time with a small number of regression analyses to perform – which would be impossible with tradition time to event analyses. However, our approach involves a simulation step that is not yet included in standard statistical software packages. In our prostate cancer example we showed that there are large differences in development of comorbidities among men receiving different treatments for prostate cancer.

  • 31.
    Lindhagen, Lars
    et al.
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Medicinska och farmaceutiska vetenskapsområdet, centrumbildningar mm, UCR-Uppsala Clinical Research Center.
    Van Hemelrijck, Mieke
    Kings Coll London, Sch Med, Canc Epidemiol Grp, Div Canc Studies,Res Oncol,Guys Hosp, London SE1 9RT, England.;Karolinska Inst, Inst Environm Med, S-10401 Stockholm, Sweden..
    Robinson, David
    Ryhov Cty Hosp, Dept Urol, Jonkoping, Sweden..
    Stattin, Pär
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Surgical Sciences, Urology. Umea Univ, Dept Surg & Perioperat Sci Urol & Androl, Umea, Sweden..
    Garmo, Hans
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Medicinska och farmaceutiska vetenskapsområdet, centrumbildningar mm, UCR-Uppsala Clinical Research Center. Kings Coll London, Sch Med, Canc Epidemiol Grp, Div Canc Studies,Res Oncol,Guys Hosp, London SE1 9RT, England.
    How to model temporal changes in comorbidity for cancer patients using prospective cohort data2015In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 15, article id 96Article in journal (Refereed)
    Abstract [en]

    Background: The presence of comorbid conditions is strongly related to survival and also affects treatment choices in cancer patients. This comorbidity is often quantified by the Charlson Comorbidity Index (CCI) using specific weights (1, 2, 3, or 6) for different comorbidities. It has been shown that the CCI increases at different times and with different sizes, so that traditional time to event analysis is not adequate to assess these temporal changes. Here, we present a method to model temporal changes in CCI in cancer patients using data from PCBaSe Sweden, a nation-wide population-based prospective cohort of men diagnosed with prostate cancer. Our proposed model is based on the assumption that a change in comorbidity, as quantified by the CCI, is an irreversible one-way process, i.e., CCI accumulates over time and cannot decrease. Methods: CCI was calculated based on 17 disease categories, which were defined using ICD-codes for discharge diagnoses in the National Patient Register. A state transition model in discrete time steps (i.e., four weeks) was applied to capture all changes in CCI. The transition probabilities were estimated from three modelling steps: 1) Logistic regression model for vital status, 2) Logistic regression model to define any changes in CCI, and 3) Poisson regression model to determine the size of CCI change, with an additional logistic regression model for CCI changes >= 6. The four models combined yielded parameter estimates to calculate changes in CCI with their confidence intervals. Results: These methods were applied to men with low-risk prostate cancer who received active surveillance (AS), radical prostatectomy (RP), or curative radiotherapy (RT) as primary treatment. There were large differences in CCI changes according to treatment. Conclusions: Our method to model temporal changes in CCI efficiently captures changes in comorbidity over time with a small number of regression analyses to perform - which would be impossible with tradition time to event analyses. However, our approach involves a simulation step that is not yet included in standard statistical software packages. In our prostate cancer example we showed that there are large differences in development of comorbidities among men receiving different treatments for prostate cancer.

  • 32.
    Mugisha, Alice
    et al.
    Univ Bergen, Norway; Makerere Univ, Uganda.
    Nankabirwa, Victoria
    Makerere Univ, Uganda; Univ Bergen, Norway.
    Tylleskar, Thorkild
    Univ Bergen, Norway.
    Babic, Ankica
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Faculty of Science & Engineering. Univ Bergen, Norway.
    A usability design checklist for Mobile electronic data capturing forms: the validation process2019In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 19, article id 4Article in journal (Refereed)
    Abstract [en]

    BackgroundNew Specific Application Domain (SAD) heuristics or design principles are being developed to guide the design and evaluation of mobile applications in a bid to improve on the usability of these applications. This is because the existing heuristics are rather generic and are often unable to reveal a large number of mobile usability issues related to mobile specific interfaces and characteristics. Mobile Electronic Data Capturing Forms (MEDCFs) are one of such applications that are being used to collect health data particularly in hard to reach areas, but with a number of usability challenges especially when used in rural areas by semi literate users. Existing SAD design principles are often not used to evaluate mobile forms because their focus on features specific to data capture is minimal. In addition, some of these lists are extremely long rendering them difficult to use during the design and development of the mobile forms. The main aim of this study therefore was to generate a usability evaluation checklist that can be used to design and evaluate Mobile Electronic Data Capturing Forms in a bid to improve their usability. We also sought to compare the novice and expert developers views regarding usability criteria.MethodsWe conducted a literature review in August 2016 using key words on articles and gray literature, and those with a focus on heuristics for mobile applications, user interface designs of mobile devices and web forms were eligible for review. The data bases included the ACM digital library, IEEE-Xplore and Google scholar. We had a total of 242 papers after removing duplicates and a total of 10 articles which met the criteria were finally reviewed. This review resulted in an initial usability evaluation checklist consisting of 125 questions that could be adopted for designing MEDCFs. The questions that handled the five main categories in data capture namely; form content, form layout, input type, error handling and form submission were considered. A validation study was conducted with both novice and expert developers using a validation tool in a bid to refine the checklist which was based on 5 criteria. The criteria for the validation included utility, clarity, question naming, categorization and measurability, with utility and measurability having a higher weight respectively. We then determined the proportion of participants who agreed (scored 4 or 5), disagreed (scored 1 or 2) and were neutral (scored 3) to a given criteria regarding a particular question for each of the experts and novice developers. Finally, we selected questions that had an average of 85% agreement (scored 4 or 5) across all the 5 criteria by both novice and expert developers. Agreement stands for capturing the same views or sentiments about theperceived likeness of an evaluation question.ResultsThe validation study reduced the initial 125 usability evaluation questions to 30 evaluation questions with the form layout category having the majority questions. Results from the validation showed higher levels of affirmativeness from the expert developers compared to those of the novice developers across the different criteria; however the general trend of agreement on relevance of usability questionswas similar across all the criteria for the developers. The evaluation questions that were being validated were found to be useful, clear, properly named and categorized, however the measurability of the questions was found not to be satisfactory by both sets of developers. The developers attached great importance to the use of appropriate language and to the visibility of the help function, but in addition expert developers felt that indication of mandatory and optional fields coupled with the use of device information like the Global Positioning System (GPS) was equally important. And for both sets of developers, utility had the highest scores while measurability scored least.ConclusionThe generated checklist indicated the design features the software developers found necessary to improve the usability of mobile electronic data collection tools. In the future, we thus propose to test the effectiveness of the measure for suitability and performance based on this generated checklist, and test it on the end users (data collectors) with a purpose of picking their design requirements. Continuous testing with the end users will help refine the checklist to include only that which is most important in improving the data collectors experience.

  • 33. Nilseng, Jessica
    et al.
    Gustafsson, Lars L.
    Nungu, Amos
    KTH, School of Information and Communication Technology (ICT). Dar Es Salaam Institute of Technology, Tanzania .
    Bastholm-Rahmner, Pia
    Mazali, Dennis
    Pehrson, Björn
    KTH, School of Information and Communication Technology (ICT), Communication Systems, CoS, Network Systems Laboratory (NS Lab).
    Eriksen, Jaran
    KTH, School of Information and Communication Technology (ICT). Karolinska University Hospital, Sweden.
    A cross-sectional pilot study assessing needs and attitudes to implementation of Information and Communication Technology for rational use of medicines among healthcare staff in rural Tanzania2014In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 14, no 1, p. 78-Article in journal (Refereed)
    Abstract [en]

    Background: In resource-poor countries access to essential medicines, suboptimal prescribing and use of medicines are major problems. Health workers lack updated medical information and treatment support. Information and Communication Technology (ICT) could help tackle this. The impact of ICT on health systems in resource-poor countries is likely to be significant and transform the practice of medicine just as in high-income countries. However, research for finding the best way of doing this is needed. We aimed to assess current approaches to and use of ICT among health workers in two rural districts of Tanzania in relation to the current drug distribution practices, drug stock and continuing medical information (CME), as well as assessing the feasibility of using ICT to improve ordering and use of medicines. Methods: This pilot study was conducted in 2010-2011, mapping the drug distribution chain in Tanzania, including problems and barriers. The study was conducted in Bunda and Serengeti districts, both part of the ICT4RD (ICT for rural development) project. Health workers involved in drug procurement and use at 13 health facilities were interviewed on use and knowledge of ICT, and their attitudes to its use in their daily work. They were also shown and interviewed about their thoughts on an android tablet application prototype for drug stock inventory and drug ordering, based on the Tanzanian Medical Stores Department (MSD) current paper forms. Results: The main challenge was a stable supply of essential medicines. Drug supplies were often delayed and incomplete, resulting in stock-outs. All 20 interviewed health workers used mobile phones, 8 of them Smartphones with Internet connection. The Health workers were very positive to the tablet application and saw its potential in reducing drug stock-outs. They also expressed a great need and wish for CME by distance. Conclusion: The tablet application was easily used and appreciated by health workers, and thus has the potential to save time and effort, reduce transportation costs and minimise drug stock-outs. Furthermore, the android tablet could be used to reach out with CME programs to health care workers at remote health facilities, as well as those in towns.

  • 34.
    Nordmark, Sofi
    et al.
    Luleå University of Technology, Department of Health Sciences, Nursing Care.
    Zingmark, Karin
    Luleå University of Technology, Department of Health Sciences, Nursing Care.
    Lindberg, Inger
    Luleå University of Technology, Department of Health Sciences, Nursing Care.
    Process evaluation of discharge planning implementation in healthcare using normalization process theory2016In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 16, no 1, article id 48Article in journal (Refereed)
    Abstract [en]

    BackgroundDischarge planning is a care process that aims to secure the transfer of care for the patient at transition from home to the hospital and back home. Information exchange and collaboration between care providers are essential, but deficits are common. A wide range of initiatives to improve the discharge planning process have been developed and implemented for the past three decades. However, there are still high rates of reported medical errors and adverse events related to failures in the discharge planning. Using theoretical frameworks such as Normalization Process Theory (NPT) can support evaluations of complex interventions and processes in healthcare. The aim of this study was to explore the embedding and integration of the DPP from the perspective of registered nurses, district nurses and homecare organizers.MethodsThe study design was explorative, using the NPT as a framework to explore the embedding and integration of the DPP. Data consisted of written documentation from; workshops with staff, registered adverse events and system failures, web based survey and individual interviews with staff.ResultsUsing the NPT as a framework to explore the embedding and integration of discharge planning after 10 years in use showed that the staff had reached a consensus of opinion of what the process was (coherence) and how they evaluated the process (reflexive monitoring). However, they had not reached a consensus of opinion of who performed the process (cognitive participation) and how it was performed (collective action). This could be interpreted as the process had not become normalized in daily practice.ConclusionThe result shows necessity to observe the implementation of old practices to better understand the needs of new ones before developing and implementing new practices or supportive tools within healthcare to reach the aim of development and to accomplish sustainable implementation. The NPT offers a generalizable framework for analysis, which can explain and shape the implementation process of old practices, before further development of new practices or supportive tools.

  • 35.
    Nyström, Mikael
    et al.
    Linköping University, The Institute of Technology. Linköping University, Department of Biomedical Engineering, Medical Informatics.
    Merkel, Magnus
    Linköping University, The Institute of Technology. Linköping University, Department of Computer and Information Science, NLPLAB - Natural Language Processing Laboratory.
    Ahrenberg, Lars
    Linköping University, The Institute of Technology. Linköping University, Department of Computer and Information Science, NLPLAB - Natural Language Processing Laboratory.
    Zweigenbaum, Pierre
    Petersson, Håkan
    Linköping University, The Institute of Technology. Linköping University, Department of Biomedical Engineering, Medical Informatics.
    Åhlfeldt, Hans
    Linköping University, The Institute of Technology. Linköping University, Department of Biomedical Engineering, Medical Informatics.
    Creating a medical English-Swedish dictionary using interactive word alignment2006In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 6, no 35Article in journal (Refereed)
    Abstract [en]

    Background: This paper reports on a parallel collection of rubrics from the medical terminology systems ICD-10, ICF, MeSH, NCSP and KSH97-P and its use for semi-automatic creation of an English-Swedish dictionary of medical terminology. The methods presented are relevant for many other West European language pairs than English-Swedish. Methods: The medical terminology systems were collected in electronic format in both English and Swedish and the rubrics were extracted in parallel language pairs. Initially, interactive word alignment was used to create training data from a sample. Then the training data were utilised in automatic word alignment in order to generate candidate term pairs. The last step was manual verification of the term pair candidates. Results: A dictionary of 31,000 verified entries has been created in less than three man weeks, thus with considerably less time and effort needed compared to a manual approach, and without compromising quality. As a side effect of our work we found 40 different translation problems in the terminology systems and these results indicate the power of the method for finding inconsistencies in terminology translations. We also report on some factors that may contribute to making the process of dictionary creation with similar tools even more expedient. Finally, the contribution is discussed in relation to other ongoing efforts in constructing medical lexicons for non-English languages. Conclusion: In three man weeks we were able to produce a medical English-Swedish dictionary consisting of 31,000 entries and also found hidden translation errors in the utilized medical terminology systems. © 2006 Nyström et al, licensee BioMed Central Ltd.

  • 36.
    Nyström, Mikael
    et al.
    Linköping University, The Institute of Technology. Linköping University, Department of Biomedical Engineering, Medical Informatics.
    Merkel, Magnus
    Linköping University, The Institute of Technology. Linköping University, Department of Computer and Information Science, NLPLAB - Natural Language Processing Laboratory.
    Petersson, Håkan
    Linköping University, The Institute of Technology. Linköping University, Department of Biomedical Engineering, Medical Informatics.
    Åhlfeldt, Hans
    Linköping University, The Institute of Technology. Linköping University, Department of Biomedical Engineering, Medical Informatics.
    Creating a medical dictionary using word alignment: The influence of sources and resources2007In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 7, no 37Article in journal (Refereed)
    Abstract [en]

    Background. Automatic word alignment of parallel texts with the same content in different languages is among other things used to generate dictionaries for new translations. The quality of the generated word alignment depends on the quality of the input resources. In this paper we report on automatic word alignment of the English and Swedish versions of the medical terminology systems ICD-10, ICF, NCSP, KSH97-P and parts of MeSH and how the terminology systems and type of resources influence the quality. Methods. We automatically word aligned the terminology systems using static resources, like dictionaries, statistical resources, like statistically derived dictionaries, and training resources, which were generated from manual word alignment. We varied which part of the terminology systems that we used to generate the resources, which parts that we word aligned and which types of resources we used in the alignment process to explore the influence the different terminology systems and resources have on the recall and precision. After the analysis, we used the best configuration of the automatic word alignment for generation of candidate term pairs. We then manually verified the candidate term pairs and included the correct pairs in an English-Swedish dictionary. Results. The results indicate that more resources and resource types give better results but the size of the parts used to generate the resources only partly affects the quality. The most generally useful resources were generated from ICD-10 and resources generated from MeSH were not as general as other resources. Systematic inter-language differences in the structure of the terminology system rubrics make the rubrics harder to align. Manually created training resources give nearly as good results as a union of static resources, statistical resources and training resources and noticeably better results than a union of static resources and statistical resources. The verified English-Swedish dictionary contains 24,000 term pairs in base forms. Conclusion. More resources give better results in the automatic word alignment, but some resources only give small improvements. The most important type of resource is training and the most general resources were generated from ICD-10. © 2007 Nyström et al, licensee BioMed Central Ltd.

  • 37.
    Rahimi, Bahlol
    et al.
    Linköping University, Department of Computer and Information Science, MDALAB - Human Computer Interfaces. Linköping University, The Institute of Technology.
    Timpka, Toomas
    Linköping University, Department of Medicine and Health Sciences, Division of Preventive and Social Medicine and Public Health Science. Linköping University, Faculty of Health Sciences. Östergötlands Läns Landsting, Centre for Public Health Sciences.
    Vimarlund, Vivian
    Linköping University, Department of Computer and Information Science, MDALAB - Human Computer Interfaces. Linköping University, The Institute of Technology.
    Uppugunduri, Srinivas
    Linköping University, Department of Clinical and Experimental Medicine, Clinical Chemistry. Linköping University, Faculty of Health Sciences. Östergötlands Läns Landsting, Centre for Laboratory Medicine, Department of Clinical Chemistry.
    Svensson, Mikael
    Östergötland County Council, Drug and Therapeut Comm, Linkoping, Sweden .
    Organization-wide adoption of computerized provider order entry systems: a study based on diffusion of innovations theory2009In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 9, no 52Article in journal (Refereed)
    Abstract [en]

    Background: Computerized provider order entry (CPOE) systems have been introduced to reduce medication errors, increase safety, improve work-flow efficiency, and increase medical service quality at the moment of prescription. Making the impact of CPOE systems more observable may facilitate their adoption by users. We set out to examine factors associated with the adoption of a CPOE system for inter-organizational and intra-organizational care. Methods: The diffusion of innovation theory was used to understand physicians and nurses attitudes and thoughts about implementation and use of the CPOE system. Two online survey questionnaires were distributed to all physicians and nurses using a CPOE system in county-wide healthcare organizations. The number of complete questionnaires analyzed was 134 from 200 nurses (67.0%) and 176 from 741 physicians (23.8%). Data were analyzed using descriptive-analytical statistical methods. Results: More nurses (56.7%) than physicians (31.3%) stated that the CPOE system introduction had worked well in their clinical setting (P andlt; 0.001). Similarly, more physicians (73.9%) than nurses (50.7%) reported that they found the system not adapted to their specific professional practice (P = andlt; 0.001). Also more physicians (25.0%) than nurses (13.4%) stated that they did want to return to the previous system (P = 0.041). We found that in particular the received relative advantages of the CPOE system were estimated to be significantly (P andlt; 0.001) higher among nurses (39.6%) than physicians (16.5%). However, physicians agreements with the compatibility of the CPOE and with its complexity were significantly higher than the nurses (P andlt; 0.001). Conclusions: Qualifications for CPOE adoption as defined by three attributes of diffusion of innovation theory were not satisfied in the study setting. CPOE systems are introduced as a response to the present limitations in paper-based systems. In consequence, user expectations are often high on their relative advantages as well as on a low level of complexity. Building CPOE systems therefore requires designs that can provide rather important additional advantages, e. g. by preventing prescription errors and ultimately improving patient safety and safety of clinical work. The decision-making process leading to the implementation and use of CPOE systems in healthcare therefore has to be improved. As any change in health service settings usually faces resistance, we emphasize that CPOE system designers and healthcare decision-makers should continually collect users feedback about the systems, while not forgetting that it also is necessary to inform the users about the potential benefits involved.

  • 38.
    Razavi, Amir R
    et al.
    Linköping University, Department of Biomedical Engineering, Medical Informatics. Linköping University, The Institute of Technology.
    Gill, Hans
    Linköping University, Department of Biomedical Engineering, Medical Informatics. Linköping University, The Institute of Technology.
    Åhlfeldt, Hans
    Linköping University, Department of Biomedical Engineering, Medical Informatics. Linköping University, The Institute of Technology.
    Shahsavar, Nosrat
    Linköping University, Department of Biomedical Engineering, Medical Informatics. Linköping University, The Institute of Technology.
    Non-compliance with a postmastectomy radiotherapy guideline: Decision tree and cause analysis2008In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 8, no 41Article in journal (Refereed)
    Abstract [en]

    Background: The guideline for postmastectomy radiotherapy (PMRT), which is prescribed to reduce recurrence of breast cancer in the chest wall and improve overall survival, is not always followed. Identifying and extracting important patterns of non-compliance are crucial in maintaining the quality of care in Oncology.

    Methods: Analysis of 759 patients with malignant breast cancer using decision tree induction (DTI) found patterns of non-compliance with the guideline. The PMRT guideline was used to separate cases according to the recommendation to receive or not receive PMRT. The two groups of patients were analyzed separately. Resulting patterns were transformed into rules that were then compared with the reasons that were extracted by manual inspection of records for the non-compliant cases.

    Results: Analyzing patients in the group who should receive PMRT according to the guideline did not result in a robust decision tree. However, classification of the other group, patients who should not receive PMRT treatment according to the guideline, resulted in a tree with nine leaves and three of them were representing non-compliance with the guideline. In a comparison between rules resulting from these three non-compliant patterns and manual inspection of patient records, the following was found:

    In the decision tree, presence of perigland growth is the most important variable followed by number of malignantly invaded lymph nodes and level of Progesterone receptor. DNA index, age, size of the tumor and level of Estrogen receptor are also involved but with less importance. From manual inspection of the cases, the most frequent pattern for non-compliance is age above the threshold followed by near cut-off values for risk factors and unknown reasons.

    Conclusion: Comparison of patterns of non-compliance acquired from data mining and manual inspection of patient records demonstrates that not all of the non-compliances are repetitive or important. There are some overlaps between important variables acquired from manual inspection of patient records and data mining but they are not identical. Data mining can highlight non-compliance patterns valuable for guideline authors and for medical audit. Improving guidelines by using feedback from data mining can improve the quality of care in oncology.

  • 39. Revenas, Asa
    et al.
    Opava, Christina H.
    Åsenlöf, Pernilla
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Neuroscience, Physiotheraphy.
    Lead users' ideas on core features to support physical activity in rheumatoid arthritis: a first step in the development of an internet service using participatory design2014In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 14, p. 21-Article in journal (Refereed)
    Abstract [en]

    Background: Despite the growing evidence of the benefits of physical activity (PA) in individuals with rheumatoid arthritis (RA), the majority is not physically active enough. An innovative strategy is to engage lead users in the development of PA interventions provided over the internet. The aim was to explore lead users' ideas and prioritization of core features in a future internet service targeting adoption and maintenance of healthy PA in people with RA. Methods: Six focus group interviews were performed with a purposively selected sample of 26 individuals with RA. Data were analyzed with qualitative content analysis and quantification of participants' prioritization of most important content. Results: Six categories were identified as core features for a future internet service: up-to-date and evidence-based information and instructions, self-regulation tools, social interaction, personalized set-up, attractive design and content, and access to the internet service. The categories represented four themes, or core aspects, important to consider in the design of the future service: (1) content, (2) customized options, (3) user interface and (4) access and implementation. Conclusions: This is, to the best of our knowledge, the first study involving people with RA in the development of an internet service to support the adoption and maintenance of PA. Participants helped identifying core features and aspects important to consider and further explore during the next phase of development. We hypothesize that involvement of lead users will make transfer from theory to service more adequate and user-friendly and therefore will be an effective mean to facilitate PA behavior change.

  • 40. Riggare, Sara
    et al.
    Scott Duncan, Therese
    Hvitfeldt, Helena
    Hägglund, Maria
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Medical Sciences. Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Women's and Children's Health, Research group (Dept. of women´s and children´s health), Clinical Psychology in Healthcare.
    “You have to know why you're doing this”: a mixed methods study of the benefits and burdens of self-tracking in Parkinson's disease2019In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 19, no 1Article in journal (Refereed)
    Abstract [en]

    This study explores opinions and experiences of people with Parkinson’s disease (PwP) in Sweden of using self-tracking. Parkinson’s disease (PD) is a neurodegenerative condition entailing varied and changing symptoms and side effects that can be a challenge to manage optimally. Patients’ self-tracking has demonstrated potential in other diseases, but we know little about PD self-tracking. The aim of this study was therefore to explore the opinions and experiences of PwP in Sweden of using self-tracking for PD.

  • 41.
    Seyyedi, Navisa
    et al.
    Urmia Univ Med Sci, Iran.
    Rahimi, Bahlol
    Urmia Univ Med Sci, Iran.
    Eslamlou, Hamid Reza Farrokh
    Urmia Univ Med Sci, Iran.
    Timpka, Toomas
    Linköping University, Department of Medical and Health Sciences, Division of Community Medicine. Linköping University, Faculty of Medicine and Health Sciences. Region Östergötland, Center for Business support and Development, Department of Health and Care Development.
    Afshar, Hadi Lotfnezhad
    Urmia Univ Med Sci, Iran.
    Mobile phone applications to overcome malnutrition among preschoolers: a systematic review2019In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 19, article id 83Article, review/survey (Refereed)
    Abstract [en]

    BackgroundMalnutrition is one of the most important reasons for child mortality in developing countries, especially during the first 5years of life. We set out to systematically review evaluations of interventions that use mobile phone applications to overcome malnutrition among preschoolers.MethodsThe review was conducted and reported according to the Preferred Reporting Items for Systematic reviews and Meta-Analyses: the PRISMA statement. To be eligible, the study had to have evaluated mobile phone interventions to increase nutrition knowledge or enhance behavior related to nutrition in order to cope with malnutrition (under nutrition or overweight) in preschoolers. Articles addressing other research topics, older children or adults, review papers, theoretical and conceptual articles, editorials, and letters were excluded. The PubMed, Web of Science and Scopus databases covering both medical and technical literature were searched for studies addressing preschoolers malnutrition using mobile technology.ResultsSeven articles were identified that fulfilled the review criteria. The studies reported in the main positive signals concerning the acceptance of mobile phone based nutritional interventions addressing preschoolers. Important infrastructural and technical limitations to implement mHealth in low and middle income countries (LMICs) were also communicated, ranging from low network capacity and low access to mobile phones to specific technical barriers. Only one study was identified evaluating primary anthropometric outcomes.ConclusionsThe review findings indicated a need for more controlled evaluations using anthropometric primary endpoints and put relevance to the suggestion that cooperation between government organizations, academia, and industry is necessary to provide sufficient infrastructure support for mHealth use against malnutrition in LMICs.

  • 42.
    Sundvall, Erik
    et al.
    Linköping University, Department of Biomedical Engineering, Medical Informatics. Linköping University, The Institute of Technology.
    Nyström, Mikael
    Linköping University, Department of Biomedical Engineering, Medical Informatics. Linköping University, The Institute of Technology.
    Karlsson, Daniel
    Linköping University, Department of Biomedical Engineering, Medical Informatics. Linköping University, The Institute of Technology.
    Eneling, Martin
    Linköping University, The Institute of Technology. Linköping University, Department of Biomedical Engineering, Medical Informatics.
    Chen, Rong
    Cambio Healthcare Systems.
    Örman, Håkan
    Linköping University, The Institute of Technology. Linköping University, Department of Biomedical Engineering, Medical Informatics.
    Applying representational state transfer (REST) architecture to archetype-based electronic health record systems2013In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 13, no 57Article in journal (Refereed)
    Abstract [en]

    Background

    The openEHR project and the closely related ISO 13606 standard have defined structures supporting the content of Electronic Health Records (EHRs). However, there is not yet any finalized openEHR specification of a service interface to aid application developers in creating, accessing, and storing the EHR content.

    The aim of this paper is to explore how the Representational State Transfer (REST) architectural style can be used as a basis for a platform-independent, HTTP-based openEHR service interface. Associated benefits and tradeoffs of such a design are also explored.

    Results

    The main contribution is the formalization of the openEHR storage, retrieval, and version-handling semantics and related services into an implementable HTTP-based service interface. The modular design makes it possible to prototype, test, replicate, distribute, cache, and load-balance the system using ordinary web technology. Other contributions are approaches to query and retrieval of the EHR content that takes caching, logging, and distribution into account. Triggering on EHR change events is also explored.

    A final contribution is an open source openEHR implementation using the above-mentioned approaches to create LiU EEE, an educational EHR environment intended to help newcomers and developers experiment with and learn about the archetype-based EHR approach and enable rapid prototyping.

    Conclusions

    Using REST addressed many architectural concerns in a successful way, but an additional messaging component was needed to address some architectural aspects. Many of our approaches are likely of value to other archetype-based EHR implementations and may contribute to associated service model specifications.

  • 43.
    Sundvall, Erik
    et al.
    Linköping University, Department of Biomedical Engineering, Medical Informatics. Linköping University, The Institute of Technology.
    Qamar, Rahil
    Department of Computer Science University of Manchester, UK.
    Nyström, Mikael
    Linköping University, Department of Biomedical Engineering, Medical Informatics. Linköping University, The Institute of Technology.
    Forss, Mattias
    Linköping University, The Institute of Technology. Linköping University, Department of Biomedical Engineering, Medical Informatics.
    Petersson, Håkan
    Linköping University, The Institute of Technology. Linköping University, Department of Biomedical Engineering, Medical Informatics.
    Åhlfeldt, Hans
    Linköping University, The Institute of Technology. Linköping University, Department of Biomedical Engineering, Medical Informatics.
    Rector, Alan
    Department of Computer Science University of Manchester, UK.
    Integration of Tools for Binding Archetypes to SNOMED CT2008In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 8, no S7Article in journal (Refereed)
    Abstract [en]

    Background

    The Archetype formalism and the associated Archetype Definition Language have been proposed as an ISO standard for specifying models of components of electronic healthcare records as a means of achieving interoperability between clinical systems. This paper presents an archetype editor with support for manual or semi-automatic creation of bindings between archetypes and terminology systems.

    Methods

    Lexical and semantic methods are applied in order to obtain automatic mapping suggestions. Information visualisation methods are also used to assist the user in exploration and selection of mappings.

    Results

    An integrated tool for archetype authoring, semi-automatic SNOMED CT terminology binding assistance and terminology visualization was created and released as open source.

    Conclusion

    Finding the right terms to bind is a difficult task but the effort to achieve terminology bindings may be reduced with the help of the described approach. The methods and tools presented are general, but here only bindings between SNOMED CT and archetypes based on the openEHR reference model are presented in detail.

    Background

    The Archetype formalism and the associated Archetype Definition Language have been proposed as an ISO standard for specifying models of components of electronic healthcare records as a means of achieving interoperability between clinical systems. This paper presents an archetype editor with support for manual or semi-automatic creation of bindings between archetypes and terminology systems.

    Methods

    Lexical and semantic methods are applied in order to obtain automatic mapping suggestions. Information visualisation methods are also used to assist the user in exploration and selection of mappings.

    Results

    An integrated tool for archetype authoring, semi-automatic SNOMED CT terminology binding assistance and terminology visualization was created and released as open source.

    Conclusion

    Finding the right terms to bind is a difficult task but the effort to achieve terminology bindings may be reduced with the help of the described approach. The methods and tools presented are general, but here only bindings between SNOMED CT and archetypes based on the openEHR reference model are presented in detail.

  • 44.
    Timpka, Toomas
    et al.
    Linköping University, Faculty of Health Sciences. Linköping University, Department of Medicine and Health Sciences, Division of Preventive and Social Medicine and Public Health Science. Östergötlands Läns Landsting, Centre for Public Health Sciences, Centre for Public Health Sciences.
    Eriksson, Henrik
    Linköping University, The Institute of Technology. Linköping University, Department of Computer and Information Science, MDALAB - Human Computer Interfaces.
    Ludvigsson, Johnny
    Linköping University, Faculty of Health Sciences. Linköping University, Department of Clinical and Experimental Medicine, Pediatrics . Östergötlands Läns Landsting, Centre of Paediatrics and Gynecology and Obstetrics, Department of Paediatrics in Linköping.
    Ekberg, Joakim
    Linköping University, Faculty of Health Sciences. Linköping University, Department of Medicine and Health Sciences, Division of Preventive and Social Medicine and Public Health Science.
    Nordfeldt, Sam
    Linköping University, Faculty of Health Sciences. Linköping University, Department of Clinical and Experimental Medicine, Pediatrics .
    Hanberger, Lena
    Linköping University, Faculty of Health Sciences. Linköping University, Department of Clinical and Experimental Medicine, Pediatrics .
    Web 2.0 systems supporting childhood chronic disease management: A pattern language representation of a general architecture2008In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 8Article in journal (Refereed)
    Abstract [en]

    Background. Chronic disease management is a global health concern. By the time they reach adolescence, 10-15% of all children live with a chronic disease. The role of educational interventions in facilitating adaptation to chronic disease is receiving growing recognition, and current care policies advocate greater involvement of patients in self-care. Web 2.0 is an umbrella term for new collaborative Internet services characterized by user participation in developing and managing content. Key elements include Really Simple Syndication (RSS) to rapidly disseminate awareness of new information, weblogs (blogs) to describe new trends, wikis to share knowledge, and podcasts to make information available on personal media players. This study addresses the potential to develop Web 2.0 services for young persons with a chronic disease. It is acknowledged that the management of childhood chronic disease is based on interplay between initiatives and resources on the part of patients, relatives, and health care professionals, and where the balance shifts over time to the patients and their families. Methods. Participatory action research was used to stepwise define a design specification in the form of a pattern language. Support for children diagnosed with diabetes Type 1 was used as the example area. Each individual design pattern was determined graphically using card sorting methods, and textually in the form Title, Context, Problem, Solution, Examples and References. Application references were included at the lowest level in the graphical overview in the pattern language but not specified in detail in the textual descriptions. Results. The design patterns are divided into functional and non-functional design elements, and formulated at the levels of organizational, system, and application design. The design elements specify access to materials for development of the competences needed for chronic disease management in specific community settings, endorsement of self-learning through online peer-to-peer communication, and systematic accreditation and evaluation of materials and processes. Conclusion. The use of design patterns allows representing the core design elements of a Web 2.0 system upon which an 'ecological' development of content respecting these constraints can be built. Future research should include evaluations of Web 2.0 systems implemented according to the architecture in practice settings.

  • 45.
    Velupillai, Sumithra
    et al.
    Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences.
    Duneld, Martin
    Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences.
    Henriksson, Aron
    Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences.
    Kvist, Maria
    Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences.
    Skeppstedt, Maria
    Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences.
    Dalianis, Hercules
    Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences.
    Louhi 2014: Special issue on health text mining and information analysis: introduction2015In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 2, no SI, p. 1-3Article in journal (Refereed)
  • 46.
    Ventimiglia, Eugenio
    et al.
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Surgical Sciences, Urology. IRCCS, Osped San Raffaele, Div Expt Oncol, Unit Urol, Milan, Italy.
    Van Hemelrijck, Mieke
    Kings Coll London, Sch Canc & Pharmaceut Sci, Translat Oncol & Urol Res Tour, Guys Hosp, 3rd Floor, London SE1 9RT, England.
    Lindhagen, Lars
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Medicinska och farmaceutiska vetenskapsområdet, centrumbildningar mm, UCR-Uppsala Clinical Research Center.
    Stattin, Pär
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Surgical Sciences, Urology.
    Garmo, Hans
    Kings Coll London, Sch Canc & Pharmaceut Sci, Translat Oncol & Urol Res Tour, Guys Hosp, 3rd Floor, London SE1 9RT, England;Uppsala Orebro, Reg Canc Ctr, Uppsala, Sweden.
    How to measure temporal changes in care pathways for chronic diseases using health care registry data2019In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 19, article id 103Article in journal (Refereed)
    Abstract [en]

    Background: Disease trajectories for chronic diseases can span over several decades, with several time-dependent factors affecting treatment decisions. Thus, there is a need for long-term predictions of disease trajectories to inform patients and healthcare professionals on the long-term outcomes and provide information on the need of future health care. Here, we propose a state transition model to describe and predict disease trajectories up to 25 years after diagnosis in men with prostate cancer (PCa), as a proof of principle. Methods: States, state transitions, and transition probabilities were identified and estimated in Prostate Cancer data Base of Sweden (PCBaSeTraject), using nationwide population-based data from 118,743 men diagnosed with PCa. A state transition model in discrete time steps (i.e., 4 weeks) was developed and applied to capture all possible transitions (PCBaSeSim). Transition probabilities were estimated for changes in both treatment and comorbidity. These models combined yielded parameter estimates to run an individual-level simulation based on the state-transition model to obtain prediction estimates. Predicted estimates were then compared to real world data in PCBaSeTraject. Results: PCBaSeSim estimates for the cumulative incidence of first and second transitions, death from PCa and death from other causes were compared to observed transitions in PCBaSeTraject. A good agreement was found between simulated and observed estimates. Conclusions: We developed a reliable and accurate simulation tool, PCBaSeSim that provides information on disease trajectories for subjects with a chronic disease on an individual and population-based level.

  • 47.
    Wallert, John
    et al.
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Women's and Children's Health, Clinical Psychology in Healthcare. Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Public Health and Caring Sciences.
    Tomasoni, Mattia
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Public Health and Caring Sciences.
    Madison, Guy
    Department of Psychology, Umeå University.
    Held, Claes
    Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Medicinska och farmaceutiska vetenskapsområdet, centrumbildningar mm, UCR-Uppsala Clinical Research Center. Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Medicine, Department of Medical Sciences.
    Predicting two-year survival versus non-survival after first myocardial infarction using machine learning and Swedish national register data2017In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 17, p. 1-11, article id 99Article in journal (Refereed)
    Abstract [en]

    Background: Machine learning algorithms hold potential for improved prediction of all-cause mortality in cardiovascular patients, yet have not previously been developed with high-quality population data. This study compared four popular machine learning algorithms trained on unselected, nation-wide population data from Sweden to solve the binary classification problem of predicting survival versus non-survival 2 years after first myocardial infarction (MI).

    Methods: This prospective national registry study for prognostic accuracy validation of predictive models used data from 51,943 complete first MI cases as registered during 6 years (2006–2011) in the national quality register SWEDEHEART/RIKS-HIA (90% coverage of all MIs in Sweden) with follow-up in the Cause of Death register (> 99% coverage). Primary outcome was AUROC (C-statistic) performance of each model on the untouched test set (40% of cases) after model development on the training set (60% of cases) with the full (39) predictor set. Model AUROCs were bootstrapped and compared, correcting the P-values for multiple comparisons with the Bonferroni method. Secondary outcomes were derived when varying sample size (1–100% of total) and predictor sets (39, 10, and 5) for each model. Analyses were repeated on 79,869 completed cases after multivariable imputation of predictors.

    Results: A Support Vector Machine with a radial basis kernel developed on 39 predictors had the highest complete cases performance on the test set (AUROC = 0.845, PPV = 0.280, NPV = 0.966) outperforming Boosted C5.0 (0.845 vs. 0. 841, P = 0.028) but not significantly higher than Logistic Regression or Random Forest. Models converged to the point of algorithm indifference with increased sample size and predictors. Using the top five predictors also produced good classifiers. Imputed analyses had slightly higher performance.

    Conclusions: Improved mortality prediction at hospital discharge after first MI is important for identifying high-risk individuals eligible for intensified treatment and care. All models performed accurately and similarly and because of the superior national coverage, the best model can potentially be used to better differentiate new patients, allowing for improved targeting of limited resources. Future research should focus on further model development and investigate possibilities for implementation. 

  • 48. Wallert, John
    et al.
    Tomasoni, Mattia
    Madison, Guy
    Umeå University, Faculty of Social Sciences, Department of Psychology.
    Held, Claes
    Predicting two-year survival versus non-survival after first myocardial infarction using machine learning and Swedish national register data2017In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 17, article id 99Article in journal (Refereed)
    Abstract [en]

    Background: Machine learning algorithms hold potential for improved prediction of all-cause mortality in cardiovascular patients, yet have not previously been developed with high-quality population data. This study compared four popular machine learning algorithms trained on unselected, nation-wide population data from Sweden to solve the binary classification problem of predicting survival versus non-survival 2 years after first myocardial infarction (MI).

    Methods: This prospective national registry study for prognostic accuracy validation of predictive models used data from 51,943 complete first MI cases as registered during 6 years (2006-2011) in the national quality register SWEDEHEART/RIKS-HIA (90% coverage of all MIs in Sweden) with follow-up in the Cause of Death register (> 99% coverage). Primary outcome was AUROC (C-statistic) performance of each model on the untouched test set (40% of cases) after model development on the training set (60% of cases) with the full (39) predictor set. Model AUROCs were bootstrapped and compared, correcting the P-values for multiple comparisons with the Bonferroni method. Secondary outcomes were derived when varying sample size (1-100% of total) and predictor sets (39, 10, and 5) for each model. Analyses were repeated on 79,869 completed cases after multivariable imputation of predictors.

    Results: A Support Vector Machine with a radial basis kernel developed on 39 predictors had the highest complete cases performance on the test set (AUROC = 0.845, PPV = 0.280, NPV = 0.966) outperforming Boosted C5.0 (0.845 vs. 0. 841, P = 0.028) but not significantly higher than Logistic Regression or Random Forest. Models converged to the point of algorithm indifference with increased sample size and predictors. Using the top five predictors also produced good classifiers. Imputed analyses had slightly higher performance.

    Conclusions: Improved mortality prediction at hospital discharge after first MI is important for identifying high-risk individuals eligible for intensified treatment and care. All models performed accurately and similarly and because of the superior national coverage, the best model can potentially be used to better differentiate new patients, allowing for improved targeting of limited resources. Future research should focus on further model development and investigate possibilities for implementation.

  • 49.
    Zhao, Jing
    et al.
    Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences.
    Henriksson, Aron
    Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences.
    Learning temporal weights of clinical events using variable importance2016In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 16, no Suppl. 2, article id 71Article in journal (Refereed)
    Abstract [en]

    Background: Longitudinal data sources, such as electronic health records (EHRs), are very valuable for monitoring adverse drug events (ADEs). However, ADEs are heavily under-reported in EHRs. Using machine learning algorithms to automatically detect patients that should have had ADEs reported in their health records is an efficient and effective solution. One of the challenges to that end is how to take into account the temporality of clinical events, which are time stamped in EHRs, and providing these as features for machine learning algorithms to exploit. Previous research on this topic suggests that representing EHR data as a bag of temporally weighted clinical events is promising; however, the weights were in that case pre-assigned according to their time stamps, which is limited and potentially less accurate. This study therefore focuses on how to learn weights that effectively take into account the temporality and importance of clinical events for ADE detection. Methods: Variable importance obtained from the random forest learning algorithm is used for extracting temporal weights. Two strategies are proposed for applying the learned weights: weighted aggregation and weighted sampling. The first strategy aggregates the weighted clinical events from different time windows to form new features; the second strategy retains the original features but samples them by using their weights as probabilities when building each tree in the forest. The predictive performance of random forest models using the learned weights with the two strategies is compared to using pre-assigned weights. In addition, to assess the sensitivity of the weight-learning procedure, weights from different granularity levels are evaluated and compared. Results: In the weighted sampling strategy, using learned weights significantly improves the predictive performance, in comparison to using pre-assigned weights; however, there is no significant difference between them in the weighted aggregation strategy. Moreover, the granularity of the weight learning procedure has a significant impact on the former, but not on the latter. Conclusions: Learning temporal weights is significantly beneficial in terms of predictive performance with the weighted sampling strategy. Moreover, weighted aggregation generally diminishes the impact of temporal weighting of the clinical events, irrespective of whether the weights are pre-assigned or learned.

  • 50.
    Zhao, Jing
    et al.
    Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences.
    Henriksson, Aron
    Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences.
    Asker, Lars
    Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences.
    Boström, Henrik
    Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences.
    Predictive modeling of structured electronic health records for adverse drug event detection2015In: BMC Medical Informatics and Decision Making, ISSN 1472-6947, E-ISSN 1472-6947, Vol. 15, no SIArticle in journal (Refereed)
    Abstract [en]

    Background: The digitization of healthcare data, resulting from the increasingly widespread adoption of electronic health records, has greatly facilitated its analysis by computational methods and thereby enabled large-scale secondary use thereof. This can be exploited to support public health activities such as pharmacovigilance, wherein the safety of drugs is monitored to inform regulatory decisions about sustained use. To that end, electronic health records have emerged as a potentially valuable data source, providing access to longitudinal observations of patient treatment and drug use. A nascent line of research concerns predictive modeling of healthcare data for the automatic detection of adverse drug events, which presents its own set of challenges: it is not yet clear how to represent the heterogeneous data types in a manner conducive to learning high-performing machine learning models. Methods: Datasets from an electronic health record database are used for learning predictive models with the purpose of detecting adverse drug events. The use and representation of two data types, as well as their combination, are studied: clinical codes, describing prescribed drugs and assigned diagnoses, and measurements. Feature selection is conducted on the various types of data to reduce dimensionality and sparsity, while allowing for an in-depth feature analysis of the usefulness of each data type and representation. Results: Within each data type, combining multiple representations yields better predictive performance compared to using any single representation. The use of clinical codes for adverse drug event detection significantly outperforms the use of measurements; however, there is no significant difference over datasets between using only clinical codes and their combination with measurements. For certain adverse drug events, the combination does, however, outperform using only clinical codes. Feature selection leads to increased predictive performance for both data types, in isolation and combined. Conclusions: We have demonstrated how machine learning can be applied to electronic health records for the purpose of detecting adverse drug events and proposed solutions to some of the challenges this presents, including how to represent the various data types. Overall, clinical codes are more useful than measurements and, in specific cases, it is beneficial to combine the two.

12 1 - 50 of 52
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf