The Application of Large Language Models in Online Medical Consultations

Abstract

With the rapid development of large language models, more and more people began to explore their application in the medical field. In this study, we want to compare the diagnostic accuracy of different models and analyze their reliability, so as to find out the most suitable big language model for online medical treatment. The focus of the study is to compare the differences in diagnostic efficiency and accuracy between large language models and human doctors, and to observe the advantages and disadvantages of different models in online consultation. We found that in some medical scenes, the diagnostic efficiency of some large language models is higher than that of human doctors, and they can maintain high accuracy. Overall, Claude 3.5 Sonnet is the most suitable large language model for online consultation. Popularizing the application of Claude 3.5 Sonnet in online consultation is expected to improve the efficiency of medical services and reduce the pressure on primary medical resources.