01
Full-Stack AI Application
Clinical Follow-Up Detector
Turning clinical follow-up instructions into structured, reviewable actions.
A demonstration application that analyzes fictional clinical text notes and extracts explicit treatment and follow-up instructions into structured, reviewable actions.
What I built
- Implemented note input, .txt upload validation, analyze flow, and review UI states
- Designed Node as the application boundary for validation, workflow, and SQLite persistence
- Isolated AI concerns in a Python FastAPI service with structured output validation
- Treated LLM output as untrusted input with Zod validation and evidence checks
Demo only · not clinically validated · not for medical decisions or real patient data · not HIPAA compliant · human review required · AI never auto-confirmed Static portfolio demonstration only — no OpenAI requests.
Fictional note → structured actions
Repeat CBC in seven days and schedule an oncology follow-up next month.
- Follow-uponcology follow-up
- Lab testRepeat CBC
- Review requiredseven days
React / TypeScript / Vite / Vitest / Testing Library / Node.js / Express / Zod / better-sqlite3 / SQLite / Python / FastAPI / Pydantic / OpenAI SDK
