基于机器学习的心血管手术后早期感染诊断模型的开发、验证及临床评估（DEICS）：一项多中心队列研究

Development, validation, and clinical evaluation of a machine-learning based model for diagnosing early infection after cardiovascular surgery (DEICS): a multi-center cohort study.

作者信息

Pan Tuo, Zhang Haitao, Wang Chuangshi, Wang Hanghang, Matniyaz Yusanjian, Lv Zhi-Kang, Zhu Tong Tong, Wang Ya-Peng, Song Zhi-Zhao, Tang Yu-Xian, Zhang He, Pan Hao-Dong, Li Chen, Yang Lin-Shan, Guan Shi-Yu, Bian Wen, Hafu Xiateke, Li Xiang, Li Yang, Wu Xiao-Ting, Fan Zhi-Wei, Luo Yuan-Xi, Jiang Yi, Gao Ya-Xuan, Wang Wen-Zhe, Xue Yun-Xing, Fan Fu-Dong, Pan Jun, Zhou Qing, Zhang Bo-Min, Wang Wei, Wang Qiang, Fan Guo-Liang, Wang Dong-Jin

机构信息

Department of Cardiac Surgery, Nanjing Drum Tower Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, China.

Department of Cardiac Surgery, Nanjing Drum Tower Hospital, Peking Union Medical College & Chinese Academy of Medical Sciences, Graduate School of Peking Union Medical College, Nanjing, China.

出版信息

Int J Surg. 2025 Apr 1;111(4):2862-2871. doi: 10.1097/JS9.0000000000002287.

DOI:10.1097/JS9.0000000000002287

PMID:39903565

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC12175805/

Abstract

BACKGROUND

This study addresses the critical need for timely and accurate diagnosis of early postoperative infection (EPI) following cardiac surgery. EPI significantly impacts patient outcomes and healthcare costs, making its early detection vital.

OBJECTIVES

To develop, validate, and clinically implement a machine-learning-based model for diagnosing EPI post-cardiac surgery, enhancing postoperative care.

METHODS

In this multi-center cohort study spanning 2020 to 2022, data from four medical centers involved 2001 participants. Of these, 1400 were used for trainingand 601 for validation. Several machines-learning algorithms, including XGBoost, random forest, support vector machines, least absolute shrinkage and selection operator, and single-layer neural networks, were applied to develop predictive models. These were compared against a traditional logistic regression model. The model with the highest area under the receiver operating characteristic curve (AUROC) was deemed optimal. Implemented across four centers since 1 January 2023, a retrospective real-world study assessed its clinical applicability. Among 400 patients with an estimated EPI risk above 10%, identified by the optimal model, 55 followed its antibiotic upgrade recommendations (DEICS group). The remaining 345 patients upgraded antibiotics empirically, with 55 in the control group, matched 1:1 with the DEICS group. Clinical utility was evaluated through antibiotic use density (AUD), hospital costs, and ICU stay duration.

RESULTS

The XGBoost model achieved the highest performance with an AUROC of 0.96 (95% CI: 0.93-0.98). The calibration curve exhibited strong agreement with Brier scores of 0.02. According to the XGBoost model, the DEICS group significantly demonstrated reduced AUD ( P < 0.01) in the matched cohort, along with decreased ICU stay time (median: 5 vs. 6 days, P = 0.01) and hospital costs (median: ¥150 000 vs. median: ¥200 000, P = 0.01) in the EPI cohort.

CONCLUSION

The successful implementation of the XGBoost model facilitates accurate EPI diagnosis, improves postoperative recovery, and lowers hospital costs.

摘要

背景

本研究旨在满足心脏手术后及时、准确诊断早期术后感染（EPI）的迫切需求。EPI对患者预后和医疗成本有重大影响，因此早期检测至关重要。

目的

开发、验证并临床应用基于机器学习的模型来诊断心脏手术后的EPI，以改善术后护理。

方法

在这项涵盖2020年至2022年的多中心队列研究中，来自四个医疗中心的数据涉及2001名参与者。其中，1400名用于训练，601名用于验证。应用了几种机器学习算法，包括XGBoost、随机森林、支持向量机、最小绝对收缩和选择算子以及单层神经网络，来开发预测模型。将这些模型与传统逻辑回归模型进行比较。受试者工作特征曲线下面积（AUROC）最高的模型被认为是最优的。自2023年1月1日起在四个中心实施，一项回顾性真实世界研究评估了其临床适用性。在由最优模型确定的估计EPI风险高于10%的400名患者中，55名遵循其抗生素升级建议（DEICS组）。其余345名患者根据经验升级抗生素，其中55名在对照组，与DEICS组1:1匹配。通过抗生素使用密度（AUD）、医院成本和重症监护病房（ICU）住院时间来评估临床效用。

结果

XGBoost模型表现最佳，AUROC为0.96（95%CI：0.93 - 0.98）。校准曲线与Brier评分为0.02表现出高度一致性。根据XGBoost模型，在匹配队列中，DEICS组的AUD显著降低（P < 0.01），在EPI队列中，ICU住院时间也缩短（中位数：5天对6天，P = 0.01），医院成本降低（中位数：150000元对200000元，P = 0.01）。