ChatGPT-4.0在口腔颌面部病变组织病理学描述分析中的诊断性能：与病理学家的比较研究。

IF 2 3区医学 Q2 DENTISTRY, ORAL SURGERY & MEDICINE

Oral Surgery Oral Medicine Oral Pathology Oral Radiology Pub Date : 2024-11-28 DOI:10.1016/j.oooo.2024.11.087

Maria Cuevas-Nunez DMD, DMSc , Valentina Ignacia Alvarez Silberberg , Maria Arregui DDS, PhD , Bruno C. Jham DDS, MS, PhD , Rosa Ballester-Victoria MD , Inessa Koptseva MD , María José Biosca Gómez de Tejada MD, DMD , Rodolfo Posada-Caez MD , Victor Gil Manich DMD , Javier Bara-Casaus MD, DDS, PhD , Maria-Teresa Fernández-Figueras MD

{"title":"ChatGPT-4.0在口腔颌面部病变组织病理学描述分析中的诊断性能：与病理学家的比较研究。","authors":"Maria Cuevas-Nunez DMD, DMSc , Valentina Ignacia Alvarez Silberberg , Maria Arregui DDS, PhD , Bruno C. Jham DDS, MS, PhD , Rosa Ballester-Victoria MD , Inessa Koptseva MD , María José Biosca Gómez de Tejada MD, DMD , Rodolfo Posada-Caez MD , Victor Gil Manich DMD , Javier Bara-Casaus MD, DDS, PhD , Maria-Teresa Fernández-Figueras MD","doi":"10.1016/j.oooo.2024.11.087","DOIUrl":null,"url":null,"abstract":"<div><h3>Objective</h3><div>To evaluate the diagnostic performance of ChatGPT-4.0 in histopathological diagnoses of oral and maxillofacial lesions and compare its performance with pathologists.</div></div><div><h3>Study Design</h3><div>A retrospective analysis of 102 histopathological descriptions was conducted. Data, including site, age and sex, were anonymized from the General University Hospital's Department of Pathology. ChatGPT-4.0 provided diagnoses, which were categorized as correct, similar, or different compared to pathologists' diagnoses. Descriptive statistics, Chi-squared tests, correlation, and regression analyses were used to assess accuracy and the influence of age and gender.</div></div><div><h3>Results</h3><div>ChatGPT-4.0 correctly diagnosed 61 out of 102 cases, yielding an accuracy of 59.8%. The distribution of diagnostic scores did not significantly deviate from expectations (Chi-squared Statistic: 0.0, <em>P</em> = 1.0). A moderate negative correlation between age and diagnostic scores (r = −0.33) was observed, with age significantly predicting scores (<em>P</em> = .001). No significant difference was found between genders (<em>P</em> = .26). ChatGPT-4.0 performed worst with granuloma and inflammation cases (100% incorrect) and best with mucocele cases (93.3% correct).</div></div><div><h3>Conclusion</h3><div>ChatGPT-4.0 shows moderate accuracy in histopathological diagnosis of oral and maxillofacial lesions, with performance varying by lesion type. Improvements are needed to enhance its clinical reliability.</div></div>","PeriodicalId":49010,"journal":{"name":"Oral Surgery Oral Medicine Oral Pathology Oral Radiology","volume":"139 4","pages":"Pages 453-461"},"PeriodicalIF":2.0000,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Diagnostic performance of ChatGPT-4.0 in histopathological description analysis of oral and maxillofacial lesions: a comparative study with pathologists\",\"authors\":\"Maria Cuevas-Nunez DMD, DMSc , Valentina Ignacia Alvarez Silberberg , Maria Arregui DDS, PhD , Bruno C. Jham DDS, MS, PhD , Rosa Ballester-Victoria MD , Inessa Koptseva MD , María José Biosca Gómez de Tejada MD, DMD , Rodolfo Posada-Caez MD , Victor Gil Manich DMD , Javier Bara-Casaus MD, DDS, PhD , Maria-Teresa Fernández-Figueras MD\",\"doi\":\"10.1016/j.oooo.2024.11.087\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><h3>Objective</h3><div>To evaluate the diagnostic performance of ChatGPT-4.0 in histopathological diagnoses of oral and maxillofacial lesions and compare its performance with pathologists.</div></div><div><h3>Study Design</h3><div>A retrospective analysis of 102 histopathological descriptions was conducted. Data, including site, age and sex, were anonymized from the General University Hospital's Department of Pathology. ChatGPT-4.0 provided diagnoses, which were categorized as correct, similar, or different compared to pathologists' diagnoses. Descriptive statistics, Chi-squared tests, correlation, and regression analyses were used to assess accuracy and the influence of age and gender.</div></div><div><h3>Results</h3><div>ChatGPT-4.0 correctly diagnosed 61 out of 102 cases, yielding an accuracy of 59.8%. The distribution of diagnostic scores did not significantly deviate from expectations (Chi-squared Statistic: 0.0, <em>P</em> = 1.0). A moderate negative correlation between age and diagnostic scores (r = −0.33) was observed, with age significantly predicting scores (<em>P</em> = .001). No significant difference was found between genders (<em>P</em> = .26). ChatGPT-4.0 performed worst with granuloma and inflammation cases (100% incorrect) and best with mucocele cases (93.3% correct).</div></div><div><h3>Conclusion</h3><div>ChatGPT-4.0 shows moderate accuracy in histopathological diagnosis of oral and maxillofacial lesions, with performance varying by lesion type. Improvements are needed to enhance its clinical reliability.</div></div>\",\"PeriodicalId\":49010,\"journal\":{\"name\":\"Oral Surgery Oral Medicine Oral Pathology Oral Radiology\",\"volume\":\"139 4\",\"pages\":\"Pages 453-461\"},\"PeriodicalIF\":2.0000,\"publicationDate\":\"2024-11-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Oral Surgery Oral Medicine Oral Pathology Oral Radiology\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2212440324009015\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"DENTISTRY, ORAL SURGERY & MEDICINE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Oral Surgery Oral Medicine Oral Pathology Oral Radiology","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2212440324009015","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"DENTISTRY, ORAL SURGERY & MEDICINE","Score":null,"Total":0}

引用次数: 0

摘要

目的：评价ChatGPT-4.0在口腔颌面部病变组织病理学诊断中的诊断价值，并与病理学家进行比较。研究设计：对102例组织病理学描述进行回顾性分析。包括地点、年龄和性别在内的数据来自综合大学医院病理科。ChatGPT-4.0提供了诊断，与病理学家的诊断相比，这些诊断被分类为正确、相似或不同。使用描述性统计、卡方检验、相关性和回归分析来评估准确性以及年龄和性别的影响。结果：ChatGPT-4.0在102例中正确诊断61例，准确率为59.8%。诊断评分的分布没有明显偏离预期（卡方统计量：0.0,P = 1.0）。年龄与诊断评分呈中度负相关（r = -0.33），年龄显著预测评分（P = .001）。性别间无显著差异（P = 0.26）。ChatGPT-4.0在肉芽肿和炎症病例中表现最差（100%错误），在粘液囊肿病例中表现最好（93.3%正确）。结论：ChatGPT-4.0对口腔颌面部病变的组织病理学诊断准确率中等，不同病变类型表现不同。其临床可靠性有待进一步提高。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Diagnostic performance of ChatGPT-4.0 in histopathological description analysis of oral and maxillofacial lesions: a comparative study with pathologists

Objective

To evaluate the diagnostic performance of ChatGPT-4.0 in histopathological diagnoses of oral and maxillofacial lesions and compare its performance with pathologists.

Study Design

A retrospective analysis of 102 histopathological descriptions was conducted. Data, including site, age and sex, were anonymized from the General University Hospital's Department of Pathology. ChatGPT-4.0 provided diagnoses, which were categorized as correct, similar, or different compared to pathologists' diagnoses. Descriptive statistics, Chi-squared tests, correlation, and regression analyses were used to assess accuracy and the influence of age and gender.

Results

ChatGPT-4.0 correctly diagnosed 61 out of 102 cases, yielding an accuracy of 59.8%. The distribution of diagnostic scores did not significantly deviate from expectations (Chi-squared Statistic: 0.0, P = 1.0). A moderate negative correlation between age and diagnostic scores (r = −0.33) was observed, with age significantly predicting scores (P = .001). No significant difference was found between genders (P = .26). ChatGPT-4.0 performed worst with granuloma and inflammation cases (100% incorrect) and best with mucocele cases (93.3% correct).

Conclusion

ChatGPT-4.0 shows moderate accuracy in histopathological diagnosis of oral and maxillofacial lesions, with performance varying by lesion type. Improvements are needed to enhance its clinical reliability.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Oral Surgery Oral Medicine Oral Pathology Oral Radiology DENTISTRY, ORAL SURGERY & MEDICINE-

CiteScore

3.80

自引率

6.90%

发文量

1217

审稿时长

2-4 weeks

期刊介绍： Oral Surgery, Oral Medicine, Oral Pathology and Oral Radiology is required reading for anyone in the fields of oral surgery, oral medicine, oral pathology, oral radiology or advanced general practice dentistry. It is the only major dental journal that provides a practical and complete overview of the medical and surgical techniques of dental practice in four areas. Topics covered include such current issues as dental implants, treatment of HIV-infected patients, and evaluation and treatment of TMJ disorders. The official publication for nine societies, the Journal is recommended for initial purchase in the Brandon Hill study, Selected List of Books and Journals for the Small Medical Library.