{"title":"[ARTIFICIAL INTELLIGENCE TOOLS AND THEIR USE IN MEDICINE CHATGPT - NOT THE ONLY PLAYER IN THE ARENA].","authors":"Zvi Weizman, Or Degany, Yehuda Shoenfeld","doi":"","DOIUrl":null,"url":null,"abstract":"<p><strong>Introduction: </strong>In recent years, there has been a remarkable growth in the development and use of artificial intelligence tools in medicine based on large language models. This review will describe the main existing tools and their various applications for medical staff and patients. Despite its popularity, we will show that ChatGPT is not the only tool and that other tools are sometimes preferable. We will review research comparisons between different tools' effectiveness in various tasks. It will be shown that these tools lack specific performances, such as accuracy and reliability in providing information, understanding clinical context, and making diagnoses. The number of studies on these topics is small, and sometimes their presented results contradict each other. Additional quality research is needed to characterize and improve these tools and designate specific tools for different medical uses. Despite the many advantages and enormous potential inherent in these models, they should be used cautiously, as they only aid the treating physician and do not replace his knowledge, professional experience, and human judgment.</p>","PeriodicalId":101459,"journal":{"name":"Harefuah","volume":"164 5","pages":"276-280"},"PeriodicalIF":0.0000,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Harefuah","FirstCategoryId":"1085","ListUrlMain":"","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Introduction: In recent years, there has been a remarkable growth in the development and use of artificial intelligence tools in medicine based on large language models. This review will describe the main existing tools and their various applications for medical staff and patients. Despite its popularity, we will show that ChatGPT is not the only tool and that other tools are sometimes preferable. We will review research comparisons between different tools' effectiveness in various tasks. It will be shown that these tools lack specific performances, such as accuracy and reliability in providing information, understanding clinical context, and making diagnoses. The number of studies on these topics is small, and sometimes their presented results contradict each other. Additional quality research is needed to characterize and improve these tools and designate specific tools for different medical uses. Despite the many advantages and enormous potential inherent in these models, they should be used cautiously, as they only aid the treating physician and do not replace his knowledge, professional experience, and human judgment.