{"title":"大语言模型可帮助通过骨闪烁扫描诊断 SAPHO 综合征。","authors":"Yu Mori, Takuya Izumiyama, Ryuichi Kanabuchi, Naoko Mori, Toshimi Aizawa","doi":"10.1093/mr/road115","DOIUrl":null,"url":null,"abstract":"<p><strong>Objective: </strong>In this study, we employed a large language model to evaluate the diagnostic efficacy of radiology reports of bone scintigraphy in the context of identifying SAPHO syndrome, and further examined the potential of such a model to augment the diagnostic procedure.</p><p><strong>Methods: </strong>Imaging data and clinical information of 151 patients (105/46 women/men, mean age: 53.5 years) who underwent bone scintigraphy for suspected Synovitis, Acne, Pustulosis, Hyperostosis, and Osteitis (SAPHO) syndrome between January 2007 and December 2022 were retrospectively reviewed. ChatGPT-4.0 was used as the large language model. The diagnostic performance of the large language model was verified by comparing the cases judged to have SAPHO syndrome that fulfilled Kahn's classification criteria based on a combination of concise radiology reports and skin lesions such as palmoplantar pustulosis, with cases diagnosed with SAPHO syndrome by rheumatologists based on all clinical information.</p><p><strong>Results: </strong>The diagnostic accuracy of a large language model for analysing bone scintigraphy radiology reports in conjunction with information about skin symptoms, such as palmoplantar pustulosis, achieved a sensitivity of 83.5%, specificity of 69.4%, and an overall accuracy of 76.8%.</p><p><strong>Conclusion: </strong>This research indicates the prospective value of extensive language models in scrutinizing radiology accounts from bone scintigraphy for the diagnosis of SAPHO syndrome.</p>","PeriodicalId":18705,"journal":{"name":"Modern Rheumatology","volume":null,"pages":null},"PeriodicalIF":1.8000,"publicationDate":"2024-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Large language model may assist diagnosis of SAPHO syndrome by bone scintigraphy.\",\"authors\":\"Yu Mori, Takuya Izumiyama, Ryuichi Kanabuchi, Naoko Mori, Toshimi Aizawa\",\"doi\":\"10.1093/mr/road115\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Objective: </strong>In this study, we employed a large language model to evaluate the diagnostic efficacy of radiology reports of bone scintigraphy in the context of identifying SAPHO syndrome, and further examined the potential of such a model to augment the diagnostic procedure.</p><p><strong>Methods: </strong>Imaging data and clinical information of 151 patients (105/46 women/men, mean age: 53.5 years) who underwent bone scintigraphy for suspected Synovitis, Acne, Pustulosis, Hyperostosis, and Osteitis (SAPHO) syndrome between January 2007 and December 2022 were retrospectively reviewed. ChatGPT-4.0 was used as the large language model. The diagnostic performance of the large language model was verified by comparing the cases judged to have SAPHO syndrome that fulfilled Kahn's classification criteria based on a combination of concise radiology reports and skin lesions such as palmoplantar pustulosis, with cases diagnosed with SAPHO syndrome by rheumatologists based on all clinical information.</p><p><strong>Results: </strong>The diagnostic accuracy of a large language model for analysing bone scintigraphy radiology reports in conjunction with information about skin symptoms, such as palmoplantar pustulosis, achieved a sensitivity of 83.5%, specificity of 69.4%, and an overall accuracy of 76.8%.</p><p><strong>Conclusion: </strong>This research indicates the prospective value of extensive language models in scrutinizing radiology accounts from bone scintigraphy for the diagnosis of SAPHO syndrome.</p>\",\"PeriodicalId\":18705,\"journal\":{\"name\":\"Modern Rheumatology\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.8000,\"publicationDate\":\"2024-08-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Modern Rheumatology\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1093/mr/road115\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"RHEUMATOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Modern Rheumatology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1093/mr/road115","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"RHEUMATOLOGY","Score":null,"Total":0}
Large language model may assist diagnosis of SAPHO syndrome by bone scintigraphy.
Objective: In this study, we employed a large language model to evaluate the diagnostic efficacy of radiology reports of bone scintigraphy in the context of identifying SAPHO syndrome, and further examined the potential of such a model to augment the diagnostic procedure.
Methods: Imaging data and clinical information of 151 patients (105/46 women/men, mean age: 53.5 years) who underwent bone scintigraphy for suspected Synovitis, Acne, Pustulosis, Hyperostosis, and Osteitis (SAPHO) syndrome between January 2007 and December 2022 were retrospectively reviewed. ChatGPT-4.0 was used as the large language model. The diagnostic performance of the large language model was verified by comparing the cases judged to have SAPHO syndrome that fulfilled Kahn's classification criteria based on a combination of concise radiology reports and skin lesions such as palmoplantar pustulosis, with cases diagnosed with SAPHO syndrome by rheumatologists based on all clinical information.
Results: The diagnostic accuracy of a large language model for analysing bone scintigraphy radiology reports in conjunction with information about skin symptoms, such as palmoplantar pustulosis, achieved a sensitivity of 83.5%, specificity of 69.4%, and an overall accuracy of 76.8%.
Conclusion: This research indicates the prospective value of extensive language models in scrutinizing radiology accounts from bone scintigraphy for the diagnosis of SAPHO syndrome.
期刊介绍:
Modern Rheumatology publishes original papers in English on research pertinent to rheumatology and associated areas such as pathology, physiology, clinical immunology, microbiology, biochemistry, experimental animal models, pharmacology, and orthopedic surgery.
Occasional reviews of topics which may be of wide interest to the readership will be accepted. In addition, concise papers of special scientific importance that represent definitive and original studies will be considered.
Modern Rheumatology is currently indexed in Science Citation Index Expanded (SciSearch), Journal Citation Reports/Science Edition, PubMed/Medline, SCOPUS, EMBASE, Chemical Abstracts Service (CAS), Google Scholar, EBSCO, CSA, Academic OneFile, Current Abstracts, Elsevier Biobase, Gale, Health Reference Center Academic, OCLC, SCImago, Summon by Serial Solutions