MediSense AI

Inspiration

What it does

How we built it

Challenges we ran into

Accomplishments that we're proud of

What we learned

What's next for MediSense AI

MediSense AI is a dual-module healthcare web application built to bridge the gap between patients and medical understanding.

Module 1 — Smart Triage: Users describe their symptoms via a chat interface. The AI asks follow-up questions and generates a risk score (Low / Moderate / High) along with an urgency recommendation — self-care, consult a doctor, or visit the ER.

Module 2 — Report Simplifier: Users upload a lab report (PDF or image). The AI extracts and explains each value in plain language, flags abnormal results, and feeds the data back into the triage engine for a more personalised risk assessment.

The two modules work together — making MediSense AI more than just a symptom checker or a report reader. No existing free tool combines both in one flow.

Tech Stack: React.js, FastAPI (Python), Google Gemini API, LangChain + FAISS (RAG pipeline), PyMuPDF, Azure / Vercel.

Target Users: Patients in rural/semi-urban India, first-gen smartphone users, and caregivers managing elderly family members.

Built With

• azure
• faiss
• fastapi
• google-gemini
• langchain
• pymupdf
• python
• rag
• react