The field of medicine is witnessing significant advancements with the integration of large language models (LLMs). Recent studies have demonstrated the potential of LLMs in various medical applications, including electronic fetal monitoring analysis, clinical trial matching, and medical coding. The use of LLMs has shown promising results in improving the accuracy and efficiency of these tasks. Notably, the performance of LLMs has been found to surpass that of domain-specific architectures in certain areas, such as antepartum electronic fetal monitoring analysis. Furthermore, the development of specialized LLMs for specific medical domains, such as Traditional Chinese Medicine, has also shown great promise. While there are still challenges to be addressed, such as the risk of hallucinations and the need for high-quality training data, the overall direction of the field is towards increased adoption and exploration of LLMs in medical applications. Noteworthy papers include the study on Large language models surpassing domain-specific architectures for antepartum electronic fetal monitoring analysis, which demonstrated the superior performance of LLMs in this area. Another notable paper is TianHui: A Domain-Specific Large Language Model for Diverse Traditional Chinese Medicine Scenarios, which presented a specialized LLM for Traditional Chinese Medicine and achieved top results in several benchmarks.
Large Language Models in Medicine
Sources
Multilingual LLM Prompting Strategies for Medical English-Vietnamese Machine Translation
EHR-MCP: Real-world Evaluation of Clinical Information Retrieval by Large Language Models via Model Context Protocol
Large language models surpass domain-specific architectures for antepartum electronic fetal monitoring analysis
Advances in Large Language Models for Medicine
Are Smaller Open-Weight LLMs Closing the Gap to Proprietary Models for Biomedical Question Answering?
Model selection meets clinical semantics: Optimizing ICD-10-CM prediction via LLM-as-Judge evaluation, redundancy-aware sampling, and section-aware fine-tuning
Systematic Comparative Analysis of Large Pretrained Language Models on Contextualized Medication Event Extraction
FHIR-AgentBench: Benchmarking LLM Agents for Realistic Interoperable EHR Question Answering
Readme_AI: Dynamic Context Construction for Large Language Models
A systematic review of trial-matching pipelines using large language models
How Model Size, Temperature, and Prompt Style Affect LLM-Human Assessment Score Alignment
Performance of Large Language Models in Answering Critical Care Medicine Questions
Nano Bio-Agents (NBA): Small Language Model Agents for Genomics
TianHui: A Domain-Specific Large Language Model for Diverse Traditional Chinese Medicine Scenarios
Scan-do Attitude: Towards Autonomous CT Protocol Management using a Large Language Model Agent