MadhanTamilarasan/clinical-decision-support
AI-powered multi-agent clinical decision support system built with Azure OpenAI, Semantic Kernel, RAG, and FHIR — enabling intelligent diagnosis, treatment planning, and healthcare workflow automation
SUMMARY AI summary by gpt-5-mini
Healware is a production-grade multi-agent clinical decision support system for clinicians that generates ranked differential diagnoses and evidence-based treatment recommendations from live patient data and indexed medical knowledge. It’s intended for physicians, nurses, and specialists within role-based workflows. Key features: - Four AI agents (Symptoms Analyzer, Lab Interpreter, Treatment Planner, Drug Interaction Checker) orchestrated in a 4‑phase pipeline with parallel execution for lower latency. - Retrieval-augmented generation using Azure OpenAI (GPT-4o) + embeddings and Azure AI Search over multiple vector indexes (conditions, guidelines, drugs, labs). - Full FHIR R4 integration for patient data, SignalR for real-time streaming, and Blazor Server UI. - Audit logging and session storage in Cosmos DB, Microsoft Entra role-based access, and serverless safety guardrails (hard drug interaction blocks). - Plugins for ICD-10 resolution, guideline retrieval, lab references, and literature; PDF export and RBAC-enforced workflows.
DETECTED Detected AI stack
AI-related keywords found in this repo's description, topics, or README summary — grouped by category. Each badge links to the corresponding ranking detail page.
GitHub Topics
Language breakdown (by bytes)
Owner
Dates
| Created on GitHub | 2026-05-09 |
| Last push | 2026-05-09 |
| First seen here | 2026-05-09 |
| Last fetched | 2026-05-09 18:16 |