Digestive Disease Center, Showa University Northern Yokohama Hospital, Yokohama, Japan.
Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore.
Ann Surg. 2024 Nov 1;280(5):850-857. doi: 10.1097/SLA.0000000000006469. Epub 2024 Jul 30.
To develop and externally validate an updated artificial intelligence (AI) prediction system for stratifying the risk of lymph node metastasis (LNM) in T2 colorectal cancer (CRC).
Recent technical advances allow complete local excision of T2 CRC, traditionally treated with surgical resection. Yet, the widespread adoption of this approach is hampered by the inability to stratify the risk of LNM.
Data from patients with pT2 CRC undergoing surgical resection between April 2000 and May 2022 at one Japanese and one Italian center were analyzed. Primary goal was AI system development for accurate LNM prediction. Predictors encompassed 7 variables: age, sex, tumor size, tumor location, lymphovascular invasion, histologic differentiation, and carcinoembryonic antigen level. The tool's discriminating power was assessed through area under the curve, sensitivity, and specificity.
Out of 735 initial patients, 692 were eligible. Training and validation cohorts comprised of 492 and 200 patients, respectively. The AI model displayed an area under the curve of 0.75 in the combined validation data set. Sensitivity for LNM prediction was 97.8%, and specificity was 15.6%. The positive and the negative predictive value were 25.7% and 96%, respectively. The false negative rate was 2.2%, and the false positive was 84.4%.
Our AI model, based on easily accessible clinical and pathologic variables, moderately predicts LNM in T2 CRC. However, the risk of false negative needs to be considered. The training of the model including more patients across western and eastern centers - differentiating between colon and rectal cancers - may improve its performance and accuracy.
开发和外部验证一种更新的人工智能（AI）预测系统，以对 T2 结直肠癌（CRC）的淋巴结转移（LNM）风险进行分层。
最近的技术进步允许对 T2 CRC 进行完全局部切除，传统上采用手术切除。然而，由于无法分层 LNM 的风险，这种方法的广泛采用受到了阻碍。
分析了 2000 年 4 月至 2022 年 5 月期间在一家日本和一家意大利中心接受手术切除的 pT2CRC 患者的数据。主要目标是开发用于准确预测 LNM 的 AI 系统。预测因素包括 7 个变量：年龄、性别、肿瘤大小、肿瘤位置、淋巴血管侵犯、组织学分化和癌胚抗原水平。通过曲线下面积、敏感性和特异性评估工具的辨别能力。
在最初的 735 名患者中，有 692 名符合条件。培训和验证队列分别包含 492 名和 200 名患者。AI 模型在联合验证数据集的曲线下面积为 0.75。LNM 预测的敏感性为 97.8%，特异性为 15.6%。阳性和阴性预测值分别为 25.7%和 96%。假阴性率为 2.2%，假阳性率为 84.4%。
我们的 AI 模型基于易于获得的临床和病理变量，适度预测 T2CRC 的 LNM。然而，需要考虑假阴性的风险。通过在包括更多来自东西方中心的患者（区分结肠癌和直肠癌）的模型训练，可以提高其性能和准确性。
