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
This project implements a machine learning-based triage system for emergency rooms, which classifies patients based on their symptoms and vitals using a Random Forest Classifier. The system features real-time patient data integration, a user-friendly GUI built with Tkinter, and secure patient data encryption using Fernet from the cryptography lib
Real-time emergency blood matching system using Graph Theory and Greedy Allocation to prioritize critical patients and ensure zero-error medical compatibility.
Clinical Decision Support System (CDSS) for Emergency Triage. Python implementation of regional healthcare protocols featuring complex logic, input normalization, and automated clinical pathways
Still Mind is an explainable, rule-based mental health triage and resource allocation system that prioritizes students for counseling using structured clinical assessments and intelligent decision logic under real-world constraints.
An NLP-driven Clinical Decision Support System (CDSS) designed to automate patient triage, featuring automated data ingestion, risk-engine logic, and stress-testing modules for clinical reliability.
A deterministic, safety-first microservice for parsing free-form bKash customer complaints (English, Bengali, Banglish) into structured triage data. Built with FastAPI, featuring a hybrid rule/LLM engine, local NLP normalization, and deep input/output guardrails.
A modular, terminal-based support triage system that processes tickets across multiple domains using TF-IDF retrieval and extractive responses. Designed for safety, determinism, and zero hallucination.
Developed a high-concurrency HealthTech Progressive Web App (PWA) during a 24-hour national-level hackathon, Navonmesh 2026, securing 22nd place out of ~300 initial teams. The platform automates medical triage and streamlines ambulance dispatching to reduce critical response times during Mass Casualty Incidents (MCIs).
A safe, bilingual (English/Arabic) AI support triage system powered by Groq LLaMA 3.3. It uses a grounded RAG framework and Pydantic validation to transform chaotic customer queries into deterministic, structured JSON with built-in safety escalation guardrails.