M. El Haj, C. Boutoleau-Bretonnière, K. Gallouj, Nathalie Wagemann, Pascal Antoine, Dimitrios Kapogiannis, G. Chapelet
{"title":"ChatGPT as a Diagnostic Aid in Alzheimer’s Disease: An Exploratory Study","authors":"M. El Haj, C. Boutoleau-Bretonnière, K. Gallouj, Nathalie Wagemann, Pascal Antoine, Dimitrios Kapogiannis, G. Chapelet","doi":"10.3233/adr-230191","DOIUrl":null,"url":null,"abstract":"Background: The potential of ChatGPT in medical diagnosis has been explored in various medical conditions. Objective: We assessed whether ChatGPT can contribute to the diagnosis of Alzheimer’s disease (AD). Methods: We provided ChatGPT with four generated cases (mild, moderate, or advanced stage AD dementia, or mild cognitive impairment), including descriptions of their complaints, physical examinations, as well as biomarker, neuroimaging, and neuropsychological data. Results: ChatGPT accurately diagnosed the test cases similarly to two blinded specialists. Conclusions: While the use of generated cases can be a limitation to our study, our findings demonstrate that ChatGPT can be a useful tool for symptom assessment and the diagnosis of AD. However, while the use of ChatGPT in AD diagnosis is promising, it should be seen as an adjunct to clinical judgment rather than a replacement.","PeriodicalId":73594,"journal":{"name":"Journal of Alzheimer's disease reports","volume":null,"pages":null},"PeriodicalIF":2.8000,"publicationDate":"2024-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Alzheimer's disease reports","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3233/adr-230191","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"NEUROSCIENCES","Score":null,"Total":0}
引用次数: 0
Abstract
Background: The potential of ChatGPT in medical diagnosis has been explored in various medical conditions. Objective: We assessed whether ChatGPT can contribute to the diagnosis of Alzheimer’s disease (AD). Methods: We provided ChatGPT with four generated cases (mild, moderate, or advanced stage AD dementia, or mild cognitive impairment), including descriptions of their complaints, physical examinations, as well as biomarker, neuroimaging, and neuropsychological data. Results: ChatGPT accurately diagnosed the test cases similarly to two blinded specialists. Conclusions: While the use of generated cases can be a limitation to our study, our findings demonstrate that ChatGPT can be a useful tool for symptom assessment and the diagnosis of AD. However, while the use of ChatGPT in AD diagnosis is promising, it should be seen as an adjunct to clinical judgment rather than a replacement.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
