Edward Itelman, Einat Birk, Ayelet Machtei, Rafael Hirsch, Nili Schamroth Pravda
{"title":"Comparative analysis of diagnostic accuracy in adult congenital heart disease: A study of three physician groups and ChatGPT","authors":"Edward Itelman, Einat Birk, Ayelet Machtei, Rafael Hirsch, Nili Schamroth Pravda","doi":"10.1016/j.ijcchd.2024.100547","DOIUrl":null,"url":null,"abstract":"<div><div>This research letter evaluates the diagnostic accuracy of three physician groups—pediatric cardiologists, adult congenital heart disease (ACHD) specialists, and general cardiologists—and compares it to the performance of an AI (Artificial Intelligence) LLM model. Based on eight targeted questions in adult congenital heart disease, the analysis highlights significant disparities in correct answer rates, with congenital specialists achieving the highest accuracy and the AI model – the lowest.</div></div>","PeriodicalId":73429,"journal":{"name":"International journal of cardiology. Congenital heart disease","volume":"18 ","pages":"Article 100547"},"PeriodicalIF":0.8000,"publicationDate":"2024-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International journal of cardiology. Congenital heart disease","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2666668524000569","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"CARDIAC & CARDIOVASCULAR SYSTEMS","Score":null,"Total":0}
引用次数: 0
Abstract
This research letter evaluates the diagnostic accuracy of three physician groups—pediatric cardiologists, adult congenital heart disease (ACHD) specialists, and general cardiologists—and compares it to the performance of an AI (Artificial Intelligence) LLM model. Based on eight targeted questions in adult congenital heart disease, the analysis highlights significant disparities in correct answer rates, with congenital specialists achieving the highest accuracy and the AI model – the lowest.