Mascarenhas Miguel, Mendes Francisco, Fonseca Filipa, Carvalho Eduardo, Santos Andre, Cavadas Daniela, Barbosa Guilherme, Pinto da Costa Antonio, Martins Miguel, Bunaiyan Abdullah, Vasconcelos Maísa, Feitosa Marley Ribeiro, Willoughby Shay, Ahmed Shakil, Javed Muhammad Ahsan, Ramião Nilza, Macedo Guilherme, Limbert Manuel
Precision Medicine Unit, Department of Gastroenterology, Unidade Local de Saúde São João, 4200-319 Porto, Portugal.
WGO Gastroenterology and Hepatology Training Center, 4200-427 Porto, Portugal.
J Clin Med. 2025 Aug 3;14(15):5462. doi: 10.3390/jcm14155462.
: Colorectal anastomotic leak (CAL) is one of the most severe postoperative complications in colorectal surgery, impacting patient morbidity and mortality. Current risk assessment methods rely on clinical and intraoperative factors, but no real-time predictive tool exists. This study aimed to develop an artificial intelligence model based on intraoperative laparoscopic recording of the anastomosis for CAL prediction. : A convolutional neural network (CNN) was trained with annotated frames from colorectal surgery videos across three international high-volume centers (Instituto Português de Oncologia de Lisboa, Hospital das Clínicas de Ribeirão Preto, and Royal Liverpool University Hospital). The dataset included a total of 5356 frames from 26 patients, 2007 with CAL and 3349 showing normal anastomosis. Four CNN architectures (EfficientNetB0, EfficientNetB7, ResNet50, and MobileNetV2) were tested. The models' performance was evaluated using their sensitivity, specificity, accuracy, and area under the receiver operating characteristic (AUROC) curve. Heatmaps were generated to identify key image regions influencing predictions. : The best-performing model achieved an accuracy of 99.6%, AUROC of 99.6%, sensitivity of 99.2%, specificity of 100.0%, PPV of 100.0%, and NPV of 98.9%. The model reliably identified CAL-positive frames and provided visual explanations through heatmaps. : To our knowledge, this is the first AI model developed to predict CAL using intraoperative video analysis. Its accuracy suggests the potential to redefine surgical decision-making by providing real-time risk assessment. Further refinement with a larger dataset and diverse surgical techniques could enable intraoperative interventions to prevent CAL before it occurs, marking a paradigm shift in colorectal surgery.
结直肠吻合口漏（CAL）是结直肠手术中最严重的术后并发症之一，影响患者的发病率和死亡率。目前的风险评估方法依赖于临床和术中因素，但尚无实时预测工具。本研究旨在基于吻合口的术中腹腔镜记录开发一种人工智能模型，用于预测CAL。
一个卷积神经网络（CNN）使用来自三个国际大容量中心（里斯本葡萄牙肿瘤研究所、里贝朗普雷图临床医院和皇家利物浦大学医院）的结直肠手术视频的标注帧进行训练。该数据集包括来自26例患者的总共5356帧，其中2007帧为CAL，3349帧显示吻合口正常。测试了四种CNN架构（EfficientNetB0、EfficientNetB7、ResNet50和MobileNetV2）。使用模型的敏感性、特异性、准确性和受试者操作特征（AUROC）曲线下面积评估模型的性能。生成热图以识别影响预测的关键图像区域。
表现最佳的模型准确率达到99.6%，AUROC为99.6%，敏感性为99.2%，特异性为100.0%，阳性预测值为100.0%，阴性预测值为98.9%。该模型可靠地识别出CAL阳性帧，并通过热图提供视觉解释。
据我们所知，这是第一个利用术中视频分析开发的用于预测CAL的人工智能模型。其准确性表明通过提供实时风险评估重新定义手术决策的潜力。使用更大的数据集和多样的手术技术进行进一步优化，可以在CAL发生前进行术中干预以预防其发生，这标志着结直肠手术的范式转变。
