VitaAI

Overview

Doctors make life-or-death decisions under time pressure with incomplete information. VitaAI is an AI-assisted medical diagnosis platform built for doctors, not patients. Input a patient's symptoms, and the system predicts the top 10 most likely diseases ranked by severity, generates SHAP-based clinical reasoning for each prediction, and translates that reasoning into a plain-language medical report via IBM WatsonX. Doctors can generate prescriptions directly. Patients can schedule appointments and access their reports. Validated and tested end-to-end by 16 real-world doctors. Won the Deloitte Capstone Project Award.

The Problem

A junior doctor spends years learning to do one thing well: look at a set of symptoms, rank the possible diagnoses by likelihood and severity, and explain the clinical reasoning behind each. Most hospitals don't have enough junior doctors. Most clinics can't afford them at all. VitaAI was built to fill that gap, not to replace doctors, but to give every doctor a tireless, explainable AI assistant that does the differential diagnosis groundwork instantly, so the doctor can focus on the decision rather than the derivation.

How It Was Built

The Problem Worth Solving

Differential diagnosis, the process of ranking possible diseases against a patient's symptoms, is one of the most cognitively demanding tasks in medicine. A doctor needs to simultaneously consider dozens of conditions, weigh symptom combinations, account for severity, and articulate their reasoning clearly enough to document and defend. Junior doctors spend years developing this skill. VitaAI compresses that process into seconds, with full explainability.

Crucially, VitaAI was not built for patients. It was built for doctors. The distinction matters, a system that hands a patient a list of ten possible diseases creates anxiety and misuse. A system that hands a doctor a ranked, reasoned differential with clinical language they can act on creates value.

How It Works — The Doctor's Flow

A doctor opens VitaAI and enters a patient's symptoms through an interactive chatbot interface. The system then runs a three-stage pipeline:

Stage 1 — Disease Prediction: An XGBoost classifier trained on clinical symptom-disease data predicts the top 10 most likely diseases. Critically, the ranking is not purely by probability, it is weighted by severity. A rare but life-threatening condition with moderate symptom overlap will rank higher than a common but benign one. This is the correct clinical prioritisation: a doctor needs to rule out the worst thing first.

Stage 2 — SHAP-Based Clinical Reasoning: For each of the top 10 predicted diseases, a SHAP explainer generates a detailed feature attribution breakdown, which symptoms contributed positively to this diagnosis, which worked against it, and by how much. This is the equivalent of a junior doctor saying "I'm thinking sepsis because of the fever and elevated heart rate, but the absence of localised pain makes it less certain." The same logic, made quantitative and consistent.

Stage 3 — IBM WatsonX Narrative Report: The SHAP bar charts and feature values are passed to IBM WatsonX, which converts the quantitative reasoning into a clinically worded narrative report for each disease. The doctor receives not just a ranked list but a readable, documentable explanation for every prediction, the kind of summary they would write themselves, generated in seconds.

The Doctor Can Then: review the top 10 ranked predictions with full reasoning, generate a prescription directly from the platform, and share reports with the patient through the patient-facing portal.

How It Works — The Patient's Flow

On the patient side, the interface is intentionally minimal. Patients can schedule appointments, view doctor-generated reports, and access their prescriptions. They cannot see the raw diagnostic predictions, that information belongs in a clinical context, not a consumer one.

The Validation Story — 16 Real Doctors

This is the detail that separates VitaAI from most medical AI projects built in academic settings. Before launch, the prediction model's outputs were shared with 16 practising doctors. They reviewed the top 10 predictions across a range of symptom combinations, provided feedback on ranking accuracy and clinical plausibility, and their input was used to boost and align the model's predictions to real-world clinical judgment.

Those same 16 doctors then tested the full system end-to-end, entering symptoms, reviewing the SHAP reports, testing the prescription flow. The final system reflects their feedback at every layer. This is not a model trained on a dataset and shipped. It is a model trained, validated, corrected, and endorsed by people who actually practice medicine.

Architecture

The system is a full MERN stack application. React handles the doctor and patient frontends. Node.js and Express.js form the API gateway, orchestrating calls between the frontend, the Python ML backend, and the IBM WatsonX API. MongoDB handles user data, appointment scheduling, prescriptions, and report storage. JWT-based authentication separates doctor and patient access scopes.

The Python ML pipeline, XGBoost inference, SHAP computation, and WatsonX report generation, runs as a modular backend service, callable from the Node.js layer. The same decoupled architecture used in AgriVerse: ML model updates don't require touching the API or frontend.

Recognition

VitaAI won the Deloitte Capstone Project Award, selected from competing teams across the institution. The judges specifically cited the clinical validation approach and the explainability architecture as distinguishing factors.