A production-grade clinical decision support system combining RAG, Reinforcement Learning, and LLM synthesis to help physicians find, evaluate, and apply peer-reviewed medical evidence.
Every clinical question passes through a sequential pipeline — no stage is skipped, no data is simulated.
Built for physicians, researchers, and clinical coders — not just as a demo.
CLIS V2 never flattens the evidence pyramid. Every article shows its GRADE level. A physician can immediately see whether a recommendation comes from a systematic review of RCTs or a single expert opinion.
All results from 5-seed experiments. p-values computed via Welch's t-test.
Tested across 5 seeds, 200 rounds each. The bandit learns domain-optimal query strategies through exploration, consistently outperforming random arm selection.
Each notebook is self-contained and reproducible. All results match the reported metrics.
Every component uses free APIs, free tiers, or open source libraries.
Clinical AI safety is engineering, not an afterthought. Every feature reflects a specific safety decision.
Including TC10 — the hallucination trap. A query about the CARDIAC-PREVENT trial, which does not exist. The system must refuse to fabricate results.
10-slide deck covering the problem, solution, pipeline, RL results, benchmarks, ethics, and tech stack.
All code, notebooks, trained models, and results are publicly available on GitHub.