A Machine Learning-Based Prediction of Hospital Mortality in Patients With Postoperative Sepsis

Ren-Qi Yao; Xin Jin; Guo-Wei Wang; Yue Yu; Guo-Sheng Wu; Yi-Bing Zhu; Lin Li; Yu-Xuan Li; Peng-Yue Zhao; Sheng-Yu Zhu; Zhao-Fan Xia; Chao Ren; Yong-Ming Yao

doi:10.3389/fmed.2020.00445

A Machine Learning-Based Prediction of Hospital Mortality in Patients With Postoperative Sepsis

Front Med (Lausanne). 2020 Aug 11:7:445. doi: 10.3389/fmed.2020.00445. eCollection 2020.

Authors

Ren-Qi Yao^{1

2}, Xin Jin³, Guo-Wei Wang⁴, Yue Yu⁵, Guo-Sheng Wu², Yi-Bing Zhu⁶, Lin Li⁴, Yu-Xuan Li⁷, Peng-Yue Zhao⁷, Sheng-Yu Zhu⁷, Zhao-Fan Xia², Chao Ren¹, Yong-Ming Yao¹

Affiliations

¹ Trauma Research Center, Fourth Medical Center of the Chinese PLA General Hospital, Beijing, China.
² Department of Burn Surgery, Changhai Hospital, Naval Medical University, Shanghai, China.
³ School of Mathematics and Statistics, Beijing Institute of Technology, Beijing, China.
⁴ School of Computer Science and Technology, Wuhan University of Technology, Wuhan, China.
⁵ Department of Cardiothoracic Surgery, Changzheng Hospital, Naval Medical University, Shanghai, China.
⁶ Medical Research and Biometrics Center, Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.
⁷ Department of General Surgery, First Medical Center of Chinese PLA General Hospital, Beijing, China.

Abstract

Introduction: The incidence of postoperative sepsis is continually increased, while few studies have specifically focused on the risk factors and clinical outcomes associated with the development of sepsis after surgical procedures. The present study aimed to develop a mathematical model for predicting the in-hospital mortality among patients with postoperative sepsis. Materials and Methods: Surgical patients in Medical Information Mart for Intensive Care (MIMIC-III) database who simultaneously fulfilled Sepsis 3.0 and Agency for Healthcare Research and Quality (AHRQ) criteria at ICU admission were incorporated. We employed both extreme gradient boosting (XGBoost) and stepwise logistic regression model to predict the in-hospital mortality among patients with postoperative sepsis. Consequently, the model performance was assessed from the angles of discrimination and calibration. Results: We included 3,713 patients who fulfilled our inclusion criteria, in which 397 (10.7%) patients died during hospitalization, and 3,316 (89.3%) patients survived through discharge. Fluid-electrolyte disturbance, coagulopathy, renal replacement therapy (RRT), urine output, and cardiovascular surgery were important features related to the in-hospital mortality. The XGBoost model had a better performance in both discriminatory ability (c-statistics, 0.835 vs. 0.737 and 0.621, respectively; AUPRC, 0.418 vs. 0.280 and 0.237, respectively) and goodness of fit (visualized by calibration curve) compared to the stepwise logistic regression model and baseline model. Conclusion: XGBoost model has a better performance in predicting hospital mortality among patients with postoperative sepsis in comparison to the stepwise logistic regression model. Machine learning-based algorithm might have significant application in the development of early warning system for septic patients following major operations.

Keywords: coagulation; extreme gradient boosting; intensive care unit; postoperative sepsis; prediction.