You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
🩸 DonorSync – A web-based platform that directly connects blood donors with hospitals, and links hospitals to patients and NGOs, enabling faster, more efficient blood donation. Originally built as a prototype for the GDSC Solution Challenge 2025, addressing the problem of limited healthcare access in underserved communities. 🛠
🩺 AstraMed: A Clinical Risk Intelligence Platform. Powered by SOTA Ensemble ML & BioMistral-7B for predictive medical analytics and explainable risk scoring.
MERN hospital management system with role-based portals (admin/doctor/patient), a blood bank module, and an online pharmacy. Includes a RAG-based AI assistant - MiniLM embeddings, parent-child chunking, MongoDB Atlas vector search - that answers from live hospital data and auto-refreshes when records change. Dockerized for deployment.
MedVision is an AI-powered web platform for medical researchers, combining tabular data and medical image analysis in one intuitive interface. It automates preprocessing, model training (including 3D U-Net), and evaluation with experiment tracking—designed to accelerate research while maintaining reproducibility.
A role-based cross-platform mobile application developed with Flutter, Dart, and Flask (Python) designed for daily diabetes tracking and management, featuring customized dashboards for patients and real-time alerts for healthcare providers .
Explainable no-show risk scoring and cancellation-slot recovery for clinics and appointment-based businesses. Built with FastAPI, SQLAlchemy, immutable workflows, and bounded cascade scheduling.
The official frontend application for Skolyn. Redefining medical imaging through Explainable Artificial Intelligence (XAI) using a serverless Full-Stack AWS architecture.
A memory-safe, monolithic CLI hospital management system in C. Operates on a custom flat-file database engine with automated clinical routing and secure cryptographic credential obfuscation.
A privacy-preserving, localized NLP pipeline for extracting structured clinical entitites from unstructured medical documents using OCR and constrained LLM generation.
End-to-end Machine Learning web application for early mental health detection. Features an optimized AdaBoost classifier, SHAP Explainable AI (XAI), PHQ-9 clinical screening safety overrides, and a containerized Flask/Docker architecture.
A high-performance, TypeScript-based cardiovascular healthcare portal featuring a modular Vite + React architecture, serverless Netlify Functions, and a custom Tailwind CSS design system for a seamless, app-like user experience.