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
mims-harvard/TxAgent
TxAgent is an advanced AI agent designed for therapeutic reasoning by leveraging a comprehensive universe of biomedical tools. It integrates multi-step reasoning and real-time knowledge retrieval to provide personalized treatment recommendations tailored to individual patient characteristics such as age, genetic factors, and disease progression. The system evaluates drug interactions at molecular, pharmacokinetic, and clinical levels, identifies contraindications based on patient comorbidities and concurrent medications, and synthesizes evidence from multiple biomedical sources to refine treatment strategies. TxAgent operates by selecting appropriate tools from a toolbox of 211 tools consolidated in the ToolUniverse, which includes all US FDA-approved drugs since 1939 and validated clinical insights from trusted sources like Open Targets. This enables TxAgent to perform structured function calls and solve complex therapeutic tasks requiring clinical reasoning and cross-source validation. The project demonstrates superior performance compared to leading large language models (LLMs) and other reasoning agents across five benchmarks covering thousands of drug reasoning tasks and personalized treatment scenarios. TxAgent achieves high accuracy in open-ended drug reasoning tasks and maintains consistency across different drug name variants and descriptions. The system is designed to run optimally on high-performance hardware such as an H100 GPU with over 80GB memory and requires internet connectivity for ToolUniverse. Pretrained models and embeddings are available on HuggingFace, and the project provides easy installation via pip or source code, along with example scripts and a Gradio demo for interactive use. TxAgent represents a significant advancement in AI-driven precision therapeutics by ensuring treatment recommendations align with clinical guidelines and real-world evidence, thereby reducing adverse events and improving therapeutic decision-making.
https://github.com/mims-harvard/TxAgent
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.
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.
gersteinlab/MedAgents
MedAgents is a Multi-disciplinary Collaboration framework leveraging large language models to facilitate zero-shot medical reasoning through expert gathering, iterative analysis, and consensus-driven decision making.
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.