Shu Xin, Li Yujie, Zhu Yiziting, Yang Zhiyong, Liu Xiang, Hu Xiaoyan, Yang Chunyong, Zhao Lei, Zhu Tao, Chen Yuwen, Yi Bin
Department of Anesthesiology, Southwest Hospital, Third Military Medical University, Chongqing, China.
Department of Anesthesiology, Xuan Wu Hospital, Capital Medical University, Beijing, China.
Arch Med Sci. 2024 Jun 6;21(1):138-152. doi: 10.5114/aoms/189505. eCollection 2025.
Although their importance has gained attention, the clinical applications of methods for screening patients at high risk of sepsis after abdominal surgery have been restricted. Therefore, we aimed to develop and validate models for screening patients at high risk of sepsis after abdominal surgery based on machine learning with routine variables.
The whole dataset was composed of three representative academic hospitals in China and the Medical Information Mart for Intensive Care IV (MIMIC-IV) database. Routine clinical variables were implemented for model development. The Boruta algorithm was applied for feature selection. Afterwards, ensemble learning and eight other conventional algorithms were used for model fitting and validation based on all features and selected features. The area under the receiver operating characteristic curves (ROC AUC), sensitivity, specificity, F1 score, accuracy, net reclassification index (NRI), integrated discrimination improvement (IDI), decision curve analysis (DCA), and calibration curves were used for model evaluation.
A total of 955 patients undergoing abdominal surgery were finally analyzed (sepsis: 285, non-sepsis: 670). After feature selection, the ensemble learning model constructed by integrating k-Nearest Neighbor (KNN) and Support Vector Machine (SVM) yielded the ROC AUC of 0.892 (0.841-0.944) and accuracy of 85.0% on the test data, and the ROC AUC of 0.782 (0.727-0.838) and accuracy of 68.1% on the validation data, which performed best. Albumin, ASA score, neutrophil-lymphocyte ratio, age, and glucose were the top features associated with postoperative sepsis by KNN and SVM.
We developed a new and potential generalizable model to preoperatively screen patients at high risk of sepsis after abdominal surgery, with the advantages of a representative training cohort and routine variables.
尽管腹部手术后脓毒症高危患者筛查方法的重要性已受到关注，但其临床应用仍受到限制。因此，我们旨在基于机器学习和常规变量开发并验证用于腹部手术后脓毒症高危患者筛查的模型。
整个数据集由中国的三家代表性学术医院以及重症监护医学信息集市IV（MIMIC-IV）数据库组成。采用常规临床变量进行模型开发。应用博鲁塔算法进行特征选择。之后，基于所有特征和选定特征，使用集成学习和其他八种传统算法进行模型拟合与验证。采用受试者操作特征曲线下面积（ROC AUC）、灵敏度、特异度、F1分数、准确度、净重新分类指数（NRI）、综合判别改善（IDI）、决策曲线分析（DCA）和校准曲线对模型进行评估。
最终分析了955例接受腹部手术的患者（脓毒症患者285例，非脓毒症患者670例）。特征选择后，通过整合k近邻（KNN）和支持向量机（SVM）构建的集成学习模型在测试数据上的ROC AUC为0.892（0.841 - 0.944），准确度为85.0%，在验证数据上的ROC AUC为0.782（0.727 - 0.838），准确度为68.1%，表现最佳。白蛋白、美国麻醉医师协会（ASA）评分、中性粒细胞与淋巴细胞比值、年龄和血糖是KNN和SVM确定的与术后脓毒症相关的最重要特征。
我们开发了一种新的、具有潜在通用性的模型，用于术前筛查腹部手术后脓毒症高危患者，该模型具有代表性的训练队列和常规变量的优势。
