medication-safety-and-interaction-assistant Awaiting Review

InterSystems does not provide technical support for this project. Please contact its developer for the technical assistance.

0 reviews

Awards

Views

IPM installs

Details

Releases (1)

Reviews

Issues

AI-enabled FHIR medication safety assistant

What's new in this version

Medication Safety and Interaction Assistant is an AI-enabled, explainable FHIR application built on InterSystems IRIS AI Hub.
It analyzes patient context from standard FHIR resources (including MedicationRequest, MedicationStatement, AllergyIntolerance, Condition, and Observation) and produces clinically useful safety guidance in two tiers: strict warnings first, then conservative warnings with additional context.

Key capabilities include:

Drug interaction and duplicate therapy detection
Allergy and contraindication checks
Risk-category findings (including black-box and population-relevant risks)
Lab-threshold safety checks
QT-risk analysis, including amplification when potassium is low
Anticholinergic burden scoring
Explainable reasoning for every finding (clear “why this was flagged”)
Structured recommended actions with urgency metadata (actionType, priority, slaHours, sourceRisk)
The project includes reproducible synthetic test profiles and consolidated per-patient case artifacts demonstrating input resources and assistant output, enabling transparent validation and easy review for contest judging.

Medication Safety and Interaction Assistant

Contest submission for InterSystems Programming Contest: AI Agents for FHIR.

Repository

GitHub/GitLab URL: use this repository root URL in the submission form
License: see LICENSE

Team

Team lead: Gil Tavassy (InterSystems Developer Community profile: https://community.intersystems.com/user/gil-tavassy)
LinkedIn: https://www.linkedin.com/in/gil-tavassy-5703b311b

Submission mode: solo project.

What This App Does

Given FHIR patient context, the assistant produces:

Strict warnings first, then conservative warnings with extra context
Explainable findings with explicit reasoning text
Interaction, allergy, black-box/population, lab-threshold, QT-risk, and anticholinergic burden findings
Structured recommended actions with urgency SLA (actionType, priority, slaHours, sourceRisk)

Main Implementation

objectscript/cls/Sample/AI/Tools/MedicationSafetyReadOnly.cls
objectscript/cls/Sample/AI/Examples/MedicationSafetyAssistant.cls
scripts/create_medication_safety_profiles.py
scripts/consolidate_med_safety_cases.py
med_safety_io/*-case.json

Quick Runbook

Start InterSystems IRIS / IRIS for Health CE with FHIR endpoint available.
Compile ObjectScript classes in your IRIS instance.
Generate and post synthetic profiles:

python scripts/create_medication_safety_profiles.py

Run assistant per generated patient profile in IRIS.
Consolidate input/output into single per-patient artifacts:

python scripts/consolidate_med_safety_cases.py

Review outputs under med_safety_io/.

Demo

Option A: add a video link with a short walk-through of setup, run, and outputs.
Option B: use this README as detailed written walk-through.

Example Artifacts

med_safety_io/med-safe-interaction-001-case.json
med_safety_io/med-safe-lab-001-case.json
med_safety_io/med-safe-qt-001-case.json
med_safety_io/med-safe-anticholinergic-001-case.json

Made with

Python

Repository Documentation License

Version

1.0.026 May, 2026

Ideas portal