PySTRIPA

PySTRIPA is the reimagined STRIPA rule-based knowledge system for medication reviews as developed last year by LUdev students: https://portfolio.ludev.nl/projects/2024/14/project.php.

STRIPA (Systematic Tool to Reduce Inappropriate Prescribing Assistant) is a clinical decision support system that helps general practitioners and pharmacists make safer and more effective medication decisions for older adults (70+) who take five or more medicines at the same time. It uses medical guidelines, such as the START/STOPP criteria, to review a patient's treatment. The START rules help find useful medicines that are missing, while the STOPP rules point out medicines that may no longer be safe.

The LUdev students built a new version of STRIPA using a custom Python rule engine. This engine checks patient data (like age, conditions, and medications) against the START/STOPP rules. The system then shows medication advice in a simple web interface where doctors can review, accept, or reject the suggestions, and add notes if needed. Our version makes STRIPA easier to use, easier to update, and ready for use in modern medical practices.

Nevertheless, this is merely a solid proof-of-concept version.

The PySTRIPA project aim is to improve PySTRIPA such that it can become tested by general practioners with real paitent data. This requires work on the following aspects:

[1] Implement missing core functionalities: add dosages, add adverse side effects. [2] Optimise rule inference engine, currently no optimisation has been done and the app is therefore simply unusable;-) [3] Abstract layer for rule engine hot swapping, at least with Python Knowledge Engine (PyKE). This also facilitates the technical validation process.

Beyond the MVP tasks above, a complete system would also require: [4] GUI design in collaboration with GPs as intended endusers [5] Deployment component for non-technical endusers both as python package and Docker image [6] Facilitate data import of SHR patient records (export/import, screenscraping, etc) [7] Building upon [5], embedding the PySTRIPA engine within the original STRIPA platform (based on Tomcat Drools and jQuery)