Idiopathic Normal Pressure Hydrocephalus (iNPH) is a neurodegenerative disorder that targets people of older age groups. It is a result of abnormal cerebrospinal fluid (CSF) buildup. To combat that, iNPH can be treated with a shunt surgery. However, predicting the success of the surgery remains a challenge due to the variability in patient outcomes. This study explores the use of machine learning (ML) to predict post-surgical outcomes in iNPH patients by utilizing clinical data from the Swedish Hydrocephalus Quality Registry (SHQR). Several ML models were tested, including random forest, decision trees, logistic regression, support vector machines (SVM), k-nearest neighbors (KNN), and gradient boosting, with random forest chosen as the final model due to its ability to handle of missing data. The results indicate that while ML models provide promising predictions, challenges such as higher rates of missing data, variations in measurement methods across years, and limitations in the availability of further descriptive features for the input set affect model accuracy. The final model achieved an accuracy of 66% and a macro F1-score of 64%, demonstrating the potential of ML in predicting iNPH surgical outcomes but highlighting the need for further refinement.