Digitala Vetenskapliga Arkivet

Change search
CiteExportLink to record
Permanent link

Direct 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
Large Language Models As Genetic Counselors: AI-DRIVEN TOOLS FOR HEALTH MANAGEMENT
Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology.
2024 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

This thesis, in collaboration with Arkus-AI, explores the development of an AI-driven genetic counselor designed to enhance genetic counseling services at Eiira. By utilizing advanced large language models, this project aims to improve the quality and accessibility of genetic counseling for individuals at risk of inherited cancers.  

Genetic counseling involves providing individuals or families with information and guidance about genetic conditions. Typically conducted by healthcare professionals trained in genetics and counseling, its main objectives are to assess the risk of inheritable genes, provide information about these genes, assist in making informed decisions about genetic testing and management, and offer emotional support.  

The core objective of this research is to create an AI-based conversational genetic counselor that assists patients by answering questions related to their medical or cancer history. This research leverages pre-trained Large Language Models (LLaMA2 and Phi-3) and utilizes Transformer architecture with a document-based generation approach to optimize the performance of these models during counseling sessions.  

Integrating AI/LLM technology into genetic counseling aims to enhance the precision, personalization, and accuracy of the advice provided to Eiira’s clients, empowering them to make well-informed health decisions. This project seeks to combine the analytical capabilities of AI with the specific requirements of genetic counseling, aiming to set a new standard in personalized medical consultation.  

To achieve this goal, the methodology employed is Retrieval-Augmented Generation (RAG). Initially, data embeddings are created and stored in vector databases. The genetic counselor then reviews the user's medical report and generates a summary using the models and LLMChains(the process of linking multiple large language models (LLMs) together in a sequential manner to accomplish complex tasks), which link multiple large language models sequentially to handle complex tasks. This summary explains identified gene variants and suggested medications from the report. The summary is then presented to the user and stored in the context history of the conversation. When a patient submits a query, the relevant information is retrieved from the stored embeddings and sources and presented to the user.  

This research tested and compared two models, LLaMA2 and Phi-3, finding that LLaMA2 outperformed Phi-3. The models' performance was evaluated using metrics such as perplexity, Rouge-1, cosine, and Jaccard similarity. While LLaMA2 required more time to generate responses due to its larger size and needed more powerful GPUs, substantial memory, and increased energy consumption, it demonstrated superior effectiveness overall.

Place, publisher, year, edition, pages
2024.
Series
IT ; mDA 24 014
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:uu:diva-536003OAI: oai:DiVA.org:uu-536003DiVA, id: diva2:1888227
External cooperation
Arkus AI
Supervisors
Examiners
Available from: 2024-08-12 Created: 2024-08-12 Last updated: 2024-08-12Bibliographically approved

Open Access in DiVA

fulltext(3221 kB)297 downloads
File information
File name FULLTEXT01.pdfFile size 3221 kBChecksum SHA-512
f0d09532b498961749d68d403c3b8861171bcac629a09a55ea2604f70eb47157b8b6233a4814fc9dce9e72b14e7d212bd68f0197c305dd2f578caadc0caa9ded
Type fulltextMimetype application/pdf

By organisation
Department of Information Technology
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 299 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 1259 hits
CiteExportLink to record
Permanent link

Direct 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