The field of medical diagnosis and healthcare is witnessing significant advancements with the integration of large language models (LLMs). Recent studies have focused on improving the interactive diagnostic abilities of LLMs, enhancing their performance in evidence-based medicine, and developing novel frameworks for patient-centric healthcare. The development of knowledge graphs, retrieval-augmented generation, and multi-agent systems has shown promising results in addressing the challenges of medical diagnosis and healthcare. These innovative approaches have the potential to revolutionize the field by providing more accurate and personalized diagnoses, improving patient outcomes, and enhancing the overall quality of healthcare. Noteworthy papers include Improving Interactive Diagnostic Ability of a Large Language Model Agent Through Clinical Experience Learning, which achieved a 30% improvement in diagnostic accuracy, and MedAgent-Pro, which demonstrated superiority in multi-modal medical diagnosis tasks. Overall, the field is moving towards more sophisticated and effective applications of LLMs in medical diagnosis and healthcare.
Advancements in Large Language Models for Medical Diagnosis and Healthcare
Sources
Improving Interactive Diagnostic Ability of a Large Language Model Agent Through Clinical Experience Learning
Enhancing LLM Generation with Knowledge Hypergraph for Evidence-Based Medicine
From Patient Consultations to Graphs: Leveraging LLMs for Patient Journey Knowledge Graph Construction
Empowering Medical Multi-Agents with Clinical Consultation Flow for Dynamic Diagnosis
Accelerating Antibiotic Discovery with Large Language Models and Knowledge Graphs
Follow-up Question Generation For Enhanced Patient-Provider Conversations
GPBench: A Comprehensive and Fine-Grained Benchmark for Evaluating Large Language Models as General Practitioners
Satisfactory Medical Consultation based on Terminology-Enhanced Information Retrieval and Emotional In-Context Learning
MedPlan:A Two-Stage RAG-Based System for Personalized Medical Plan Generation
Experience Retrieval-Augmentation with Electronic Health Records Enables Accurate Discharge QA
SciClaims: An End-to-End Generative System for Biomedical Claim Analysis
Self-Reported Confidence of Large Language Models in Gastroenterology: Analysis of Commercial, Open-Source, and Quantized Models
MedAgent-Pro: Towards Multi-modal Evidence-based Medical Diagnosis via Reasoning Agentic Workflow
Explainable ICD Coding via Entity Linking
DEMENTIA-PLAN: An Agent-Based Framework for Multi-Knowledge Graph Retrieval-Augmented Generation in Dementia Care
Clean & Clear: Feasibility of Safe LLM Clinical Guidance
Alleviating LLM-based Generative Retrieval Hallucination in Alipay Search
Fine-Tuning LLMs on Small Medical Datasets: Text Classification and Normalization Effectiveness on Cardiology reports and Discharge records
Leveraging LLMs for Predicting Unknown Diagnoses from Clinical Notes
Self-Evolving Multi-Agent Simulations for Realistic Clinical Interactions