AI Triage - AI Pipeline

An AI pipeline for symptom analysis, test recommendation, evidence evaluation, and condition prediction.

Details

Role

Solo Full-Stack Developer

Project Type

Internship Project

Duration

1 Month

Status

Completed

Core Features

AI Symptom Analysis
Dataset-Driven Diagnosis
Lab Test Recommendation
Evidence-Based Evaluation

Tech Stack

JavaScript

Next.js

React.js

Chakra UI

HTML

CSS

Node.js

Express.js

MongoDB

Ollama

MedGemma 1.5 4B

Overview

An AI-powered triage pipeline that analyzes patient symptoms, recommends relevant laboratory tests, and supports diagnostic reasoning through a structured, dataset-driven workflow. It combines curated medical datasets with a language model to identify potential conditions, suggest relevant tests, and interpret available results through a controlled multi-stage process, demonstrated through a simple simulation interface.

Outcome and Impact

Combines structured medical data with AI reasoning instead of relying entirely on generative responses. Demonstrates a more controlled approach to AI-assisted clinical decision support by organizing symptoms, possible conditions, test recommendations, and results into a clear workflow.

Screenshots

Simulation UI

Top section

Symptom input, suggested diagnostic tests, and laboratory result entry interface.