Laohawetwanit Thiyaphat, Namboonlue Chutimon, Apornvirat Sompon
Division of Pathology, Chulabhorn International College of Medicine, Thammasat University, Pathum Thani, Thailand
Division of Pathology, Thammasat University Hospital, Pathum Thani, Thailand.
J Clin Pathol. 2025 Feb 18;78(3):202-207. doi: 10.1136/jcp-2023-209304.
To evaluate the accuracy of Chat Generative Pre-trained Transformer (ChatGPT) powered by GPT-4 in histopathological image detection and classification of colorectal adenomas using the diagnostic consensus provided by pathologists as a reference standard.
A study was conducted with 100 colorectal polyp photomicrographs, comprising an equal number of adenomas and non-adenomas, classified by two pathologists. These images were analysed by classic GPT-4 for 1 time in October 2023 and custom GPT-4 for 20 times in December 2023. GPT-4's responses were compared against the reference standard through statistical measures to evaluate its proficiency in histopathological diagnosis, with the pathologists further assessing the model's descriptive accuracy.
GPT-4 demonstrated a median sensitivity of 74% and specificity of 36% for adenoma detection. The median accuracy of polyp classification varied, ranging from 16% for non-specific changes to 36% for tubular adenomas. Its diagnostic consistency, indicated by low kappa values ranging from 0.06 to 0.11, suggested only poor to slight agreement. All of the microscopic descriptions corresponded with their diagnoses. GPT-4 also commented about the limitations in its diagnoses (eg, slide diagnosis best done by pathologists, the inadequacy of single-image diagnostic conclusions, the need for clinical data and a higher magnification view).
GPT-4 showed high sensitivity but low specificity in detecting adenomas and varied accuracy for polyp classification. However, its diagnostic consistency was low. This artificial intelligence tool acknowledged its diagnostic limitations, emphasising the need for a pathologist's expertise and additional clinical context.
以病理学家提供的诊断共识为参考标准，评估由GPT-4驱动的聊天生成预训练变换器（ChatGPT）在结直肠腺瘤组织病理学图像检测和分类中的准确性。
对100张结直肠息肉显微照片进行研究，其中腺瘤和非腺瘤数量相等，由两名病理学家进行分类。这些图像于2023年10月由经典GPT-4分析1次，于2023年12月由定制GPT-4分析20次。通过统计方法将GPT-4的回答与参考标准进行比较，以评估其在组织病理学诊断方面的熟练程度，病理学家进一步评估该模型的描述准确性。
GPT-4在腺瘤检测中的中位敏感性为74%，特异性为36%。息肉分类的中位准确率各不相同，从非特异性改变的16%到管状腺瘤的36%不等。其诊断一致性较低，kappa值在0.06至0.11之间，表明一致性仅为差到一般。所有微观描述均与其诊断结果相符。GPT-4还对其诊断中的局限性发表了评论（例如，玻片诊断最好由病理学家完成，单图像诊断结论的不足，需要临床数据和更高放大倍数的视野）。
GPT-4在腺瘤检测中显示出高敏感性，但特异性较低，息肉分类的准确率也各不相同。然而，其诊断一致性较低。这种人工智能工具认识到其诊断局限性，强调需要病理学家的专业知识和更多临床背景信息。
