手术结合化疗/放疗是局部晚期食管癌的标准治疗方法。即使在引入微创技术之后，食管切除术的发病率和死亡率仍然很高。食管切除术最常见和最令人担心的并发症之一是吻合口漏（AL）。我们的工作旨在开发一种结合 CT 衍生数据和临床数据的多模式机器学习模型，用于预测食管癌食管切除术后的 AL。前瞻性纳入了总共 471 名患者（2010 年 1 月至 2022 年 12 月）。术前计算机断层扫描（CT）用于评估腹腔干狭窄和血管钙化。临床变量，包括人口统计、疾病分期、手术细节、术后 CRP 和分期，与 CT 数据相结合，建立 AL 预测模型。数据被分为 80%:20% 用于训练和测试，并开发了具有 10 倍交叉验证和早期停止功能的 XGBoost 模型。计算ROC曲线和相应的曲线下面积（AUC）、敏感性、特异性、PPV、NPV和F1评分。共有117名患者（24.8%）出现术后AL。 XGboost 模型的 AUC 为 79.2% (95%CI 69%-89.4%)，特异性为 77.46%，敏感性为 65.22%，PPV 为 48.39%，NPV 为 87.3%，F1 得分为 56%。 Shapley 加法解释分析显示了各个变量对模型结果的影响。决策曲线分析表明，该模型对于 15% 到 48% 之间的阈值概率特别有利。临床相关的多模态模型可以预测 AL，这对于 AL 临床概率较低的病例尤其有价值。版权所有 © 2024 The Association of University Radinauts 。由爱思唯尔公司出版。保留所有权利。

Surgery in combination with chemo/radiotherapy is the standard treatment for locally advanced esophageal cancer. Even after the introduction of minimally invasive techniques, esophagectomy carries significant morbidity and mortality. One of the most common and feared complications of esophagectomy is anastomotic leakage (AL). Our work aimed to develop a multimodal machine-learning model combining CT-derived and clinical data for predicting AL following esophagectomy for esophageal cancer.A total of 471 patients were prospectively included (Jan 2010-Dec 2022). Preoperative computed tomography (CT) was used to evaluate celia trunk stenosis and vessel calcification. Clinical variables, including demographics, disease stage, operation details, postoperative CRP, and stage, were combined with CT data to build a model for AL prediction. Data was split into 80%:20% for training and testing, and an XGBoost model was developed with 10-fold cross-validation and early stopping. ROC curves and respective areas under the curve (AUC), sensitivity, specificity, PPV, NPV, and F1-scores were calculated.A total of 117 patients (24.8%) exhibited post-operative AL. The XGboost model achieved an AUC of 79.2% (95%CI 69%-89.4%) with a specificity of 77.46%, a sensitivity of 65.22%, PPV of 48.39%, NPV of 87.3%, and F1-score of 56%. Shapley Additive exPlanation analysis showed the effect of individual variables on the result of the model. Decision curve analysis showed that the model was particularly beneficial for threshold probabilities between 15% and 48%.A clinically relevant multimodal model can predict AL, which is especially valuable in cases with low clinical probability of AL.Copyright © 2024 The Association of University Radiologists. Published by Elsevier Inc. All rights reserved.