首页|University of Health Sciences Reports Findings in Artificial Intelligence (Compa rative performance of artificial intelligence models in rheumatology board-level questions: evaluating Google Gemini and ChatGPT-4o)
University of Health Sciences Reports Findings in Artificial Intelligence (Compa rative performance of artificial intelligence models in rheumatology board-level questions: evaluating Google Gemini and ChatGPT-4o)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Artificial Intelligenc e is the subject of a report. According to news originating from Istanbul, Turke y, by NewsRx correspondents, research stated, “This study evaluates the performa nce of AI models, ChatGPT-4o and Google Gemini, in answering rheumatology board- level questions, comparing their effectiveness, reliability, and applicability i n clinical practice. A cross-sectional study was conducted using 420 rheumatolog y questions from the BoardVitals question bank, excluding 27 visual data questio ns.” Our news journalists obtained a quote from the research from the University of H ealth Sciences, “Both artificial intelligence models categorized the questions a ccording to difficulty (easy, medium, hard) and answered them. In addition, the reliability of the answers was assessed by asking the questions a second time. T he accuracy, reliability, and difficulty categorization of the AI models’ respon se to the questions were analyzed. ChatGPT-4o answered 86.9% of th e questions correctly, significantly outperforming Google Gemini’s 60.2% accuracy (p <0.001). When the questions were asked a secon d time, the success rate was 86.7% for ChatGPT-4o and 60.5% for Google Gemini. Both models mainly categorized questions as medium difficulty . ChatGPT-4o showed higher accuracy in various rheumatology subfields, notably i n Basic and Clinical Science (p = 0.028), Osteoarthritis (p = 0.023), and Rheuma toid Arthritis (p <0.001). ChatGPT-4o significantly outper formed Google Gemini in rheumatology board-level questions. This demonstrates th e success of ChatGPT-4o in situations requiring complex and specialized knowledg e related to rheumatological diseases. The performance of both AI models decreas ed as the question difficulty increased. This study demonstrates the potential o f AI in clinical applications and suggests that its use as a tool to assist clin icians may improve healthcare efficiency in the future. Future studies using rea l clinical scenarios and real board questions are recommended.”
IstanbulTurkeyEurasiaArtificial In telligenceEmerging TechnologiesHealth and MedicineMachine LearningRheuma tology
NETL
NSTL
