bowang-lab/MedRAX
MedRAX is a versatile AI agent that integrates advanced chest X-ray analysis tools and multimodal large language models to provide comprehensive medical reasoning and interpretation for complex clinical queries.
Awesome AI Agents › Medical & Healthcare
gersteinlab/MedAgents
MedAgents is a project that introduces a Multi-disciplinary Collaboration (MC) framework designed to leverage large language models as collaborators for zero-shot medical reasoning. The framework is structured into five key stages: expert gathering, analysis proposition, report summarization, collaborative consultation, and decision making. Initially, experts from various disciplines relevant to a clinical question are gathered. Each domain expert then contributes their analysis based on their expertise. These analyses are synthesized into a summarized report, which is iteratively discussed and refined by the experts until a unanimous agreement is reached. The final stage involves deriving a conclusive decision from the agreed-upon report. This approach aims to enhance medical reasoning by simulating a collaborative environment among experts, facilitated by advanced language models. The project evaluates the MC framework using benchmark datasets such as MedQA, MedMCQA, and PubMedQA, along with six medical-related subtasks from the MMLU datasets, including anatomy, clinical knowledge, college medicine, medical genetics, professional medicine, and college biology. The implementation requires Python dependencies and an OpenAI API key for running inference scripts. The project is supported by a research paper available on arXiv, which details the methodology and findings. MedAgents is significant for its innovative use of AI to mimic expert collaboration in medical decision-making, potentially improving the accuracy and reliability of medical reasoning without requiring extensive labeled data. It provides a structured, iterative process for expert consultation and consensus building, which is crucial in complex medical scenarios. The project is well-documented, with clear instructions for setup and evaluation, making it accessible for further research and development in AI-assisted medical reasoning.
https://github.com/gersteinlab/MedAgents
Also in Medical & Healthcare
souvikmajumder26/Multi-Agent-Medical-Assistant
Multi-Agent Medical Assistant is an AI-powered chatbot system that integrates multi-agent orchestration, advanced retrieval-augmented generation, and medical image analysis to assist healthcare professionals, researchers, and patients with medical diagnosis and healthcare research.
mims-harvard/TxAgent
TxAgent is an AI agent that leverages multi-step reasoning and a comprehensive toolbox of biomedical tools to provide personalized and precise therapeutic treatment recommendations based on real-time biomedical knowledge and clinical guidelines.
AQ-MedAI/MedResearcher-R1
MedResearcher-R1 is a medical deep research agent plus the knowledge-informed trajectory synthesis pipeline that trained it, turning a domain knowledge graph into multi-hop question-answer pairs and tool-using reasoning trajectories.
mingze-yuan/Awesome-LLM-Healthcare
A curated repository of research papers and resources reviewing the transformative applications and challenges of Large Language Models in medicine and healthcare.