本研究旨在评估 ChatGPT 使用组织病理学图像准确诊断肝胆肿瘤的有效性。该研究比较了 GPT-4 模型的诊断准确性，提供相同的图像集和 2 种不同的输入提示。第一个提示是形态学方法，旨在模仿病理学家分析组织形态的方法。相比之下，第二个提示在没有结合这种形态分析功能的情况下起作用。分析诊断的准确性和一致性。总共使用了120张显微照片，由每个肝胆肿瘤和非肿瘤性肝组织的60张图像组成。研究结果表明，形态学方法显着提高了人工智能（AI）的诊断准确性和一致性。该版本在识别肝细胞癌（平均准确度：62.0% vs 27.3%）、胆管腺瘤（10.7% vs 3.3%）和胆管癌（68.7% vs 16.0%）以及区分非肿瘤性肝组织方面尤其准确。 （77.3% 与 37.5%）（Ps ≤ .01）。它还表现出比没有形态学分析的其他模型更高的诊断一致性（κ：0.46 vs 0.27）。这项研究强调了将病理学家的诊断方法纳入人工智能以提高医疗诊断的准确性和一致性的重要性。它主要展示了人工智能在复制专家诊断过程时的组织病理学前景。© 作者 2024。由牛津大学出版社代表美国临床病理学会出版。版权所有。如需商业重复使用，请联系 reprints@oup.com 获取转载和转载的翻译权。所有其他权限都可以通过我们网站文章页面上的权限链接通过我们的 RightsLink 服务获得 - 如需了解更多信息，请联系journals.permissions@oup.com。

This research aimed to evaluate the effectiveness of ChatGPT in accurately diagnosing hepatobiliary tumors using histopathologic images.The study compared the diagnostic accuracies of the GPT-4 model, providing the same set of images and 2 different input prompts. The first prompt, the morphologic approach, was designed to mimic pathologists' approach to analyzing tissue morphology. In contrast, the second prompt functioned without incorporating this morphologic analysis feature. Diagnostic accuracy and consistency were analyzed.A total of 120 photomicrographs, composed of 60 images of each hepatobiliary tumor and nonneoplastic liver tissue, were used. The findings revealed that the morphologic approach significantly enhanced the diagnostic accuracy and consistency of the artificial intelligence (AI). This version was particularly more accurate in identifying hepatocellular carcinoma (mean accuracy: 62.0% vs 27.3%), bile duct adenoma (10.7% vs 3.3%), and cholangiocarcinoma (68.7% vs 16.0%), as well as in distinguishing nonneoplastic liver tissues (77.3% vs 37.5%) (Ps ≤ .01). It also demonstrated higher diagnostic consistency than the other model without a morphologic analysis (κ: 0.46 vs 0.27).This research emphasizes the importance of incorporating pathologists' diagnostic approaches into AI to enhance accuracy and consistency in medical diagnostics. It mainly showcases the AI's histopathologic promise when replicating expert diagnostic processes.© The Author(s) 2024. Published by Oxford University Press on behalf of American Society for Clinical Pathology. All rights reserved. For commercial re-use, please contact reprints@oup.com for reprints and translation rights for reprints. All other permissions can be obtained through our RightsLink service via the Permissions link on the article page on our site—for further information please contact journals.permissions@oup.com.