medical-nlp

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

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.

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

Score ASR models on YOUR data, no ground-truth transcript needed. Build a lexicon from your field's literature, then measure hallucinated words vs real words captured.

Employed Large Language Models to generate accurate wording for the "impression" section in the medical reports

An AI-powered system that matches patient profiles to relevant clinical trials using semantic understanding of medical language, combining transformer embeddings with rule-based clinical eligibility logic.

Repo for Turkish Vitamins and Supplements NER dataset.

RAG pipeline for medical question-answering. Fuses lexical and dense retrieval (MedCPT, Contriever, Specter + FAISS) with OpenAI, Gemini, and HuggingFace LLMs. Supports iterative multi-round reasoning, strict typing, structured observability, and a clean layered architecture

Multimodal medical RAG: ColPali visual retrieval + Google Gemini + a Mondo Knowledge Graph, evaluated on the MIRAGE benchmark.

Adversarial clinical AI evals suite : physician-curated golden test cases exposing safety-critical failure modes in healthcare AI pipelines. SOAP notes, LLM judge, ambient scribe.

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

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.

Public Streamlit demo for structuring synthetic clinical notes using open-source NLP

Fix GPLinker (Chinese medical entity & relation extraction) for modern Colab. Run old 2022 project on transformers 4.x / Python 3.12 with zero manual fixes. CMeIE dataset, one-click training, 43 medical relations.

Agentic AI system for generating evidence-backed clinical discharge summaries with conflict detection, medication reconciliation, clinician escalation, confidence scoring, and iterative learning from reviewer feedback.

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

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.

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

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

Retrieval-Augmented Generation system for querying clinical documents with grounded, cited, zero-hallucination answers. 100% local, no cloud APIs