Medical Question Answering Dataset of 47,457 QA pairs created from 12 NIH websites

In this we finetuned the Gemini model with our own medical NER dataset and used to recognize Name Entities

AI-powered system for mapping clinical text to Human Phenotype Ontology (HPO) terms using Retrieval-Augmented Generation (RAG). Features Python CLI/library, FastAPI backend, and Vue.js frontend for interactive phenotype extraction from medical texts.

Repo for Turkish Vitamins and Supplements NER dataset.

AI-powered Clinical EMR platform for Indian healthcare. Features real-time voice-to-text transcription, clinical NLP extraction, live drug safety checks, and offline-first capabilities.

Repo for Turkish sentiment analysis dataset, "Vitamins and Supplements Customer Reviews"

Medical Entity Extraction from Clinical Notes using BERT & DNC - NLP, Healthcare AI

Code and resources for training and evaluating Named Entity Recognition (NER) models for Chinese medical texts.

Build a production‑grade, modular pipeline for fine‑tuning large language models with LoRA on domain‑specific tasks (e.g., legal QA, medical summarization, financial reasoning).

MedNER: A deep learning tool for medical NER. Fine-tune transformer models (BERT/BioBERT) to extract entities like diseases, treatments, and medications from clinical texts. Enjoy GPU-accelerated training, TensorBoard visualization, and an easy inference pipeline.

An interactive pipeline that extracts and summarizes clinical trial PDFs using advanced NLP models

This project aims to tackle data scarcity in a specific task by training a single base model with multiple heads, each dedicated to a different NLP task. These "supporting tasks" aim to leverage shared knowledge across domains, enhancing the model's performance and robustness.

DiagnoAI: Medical RAG Assistant - Educational AI system for healthcare information retrieval using multi-source medical knowledge and advanced search. FOR LEARNING AND RESEARCH ONLY.

Local medical AI experimentation and drug repurposing research tools inspired by Every Cure's MATRIX platform

QLoRA fine-tuning of Llama 3.2 3B on MedQA with full LoRA rank ablation study (r=4/8/16/32), quantization benchmarking, and Gradio demo on HuggingFace Spaces.

QLoRA fine-tuning of Phi-3-mini (3.8B) for medical triage — 64% accuracy, 100% EMERGENCY recall. Live demo on Hugging Face Spaces.

Global Healthcare AI Framework | Multimodal Medical Analysis + Semantic Search | Singapore Case Study: SGD $42M 5-Year Value | Enterprise ML Architecture Demo

Rule-based clinical NLP dashboard for breast cancer phenotyping using spaCy, medspaCy, and Dash, with fully auditable evidence extraction.

Automated pipeline for extracting drug safety information from FDA Structured Product Labels (SPL) using NLP and MedDRA mapping for pharmacovigilance research.

Clinical-domain chatbot for symptom understanding and medical information support using NLP and real clinical text data.

An AI-powered multi-agent clinical copilot that automates patient verification, clinical documentation, and secure EHR workflows with human-in-the-loop control.

Gemma3 4B LLM Fine Tuned on 100K Doctor-Patient QA Dataset

Production-grade clinical intelligence system speedrun: 95% accuracy, full explainability, zero pretrained models. Trained on class-weighted data, tested with real anxiety, deployed to impress recruiters.

Clinical trial matching system using advanced NLP and intelligent scoring algorithms to match patients with relevant clinical trials. Features real-time data integration, geographic filtering, and comprehensive analytics dashboard.