Interpretable machine learning models for early prediction of acute kidney injury after cardiac surgery

Jicheng Jiang; Xinyun Liu; Zhaoyun Cheng; Qianjin Liu; Wenlu Xing

doi:10.1186/s12882-023-03324-w

Interpretable machine learning models for early prediction of acute kidney injury after cardiac surgery

BMC Nephrol. 2023 Nov 7;24(1):326. doi: 10.1186/s12882-023-03324-w.

Authors

Jicheng Jiang¹, Xinyun Liu¹, Zhaoyun Cheng², Qianjin Liu³, Wenlu Xing¹

Affiliations

¹ Department of Big Data Center for Cardiovascular Disease, Heart Center of Henan Provincial People's Hospital, Fuwai Central China Cardiovascular Hospital, Central China Fuwai Hospital of Zhengzhou University, Zhengzhou, China.
² Department of Cardiovascular Surgery, Heart Center of Henan Provincial People's Hospital, Fuwai Central China Cardiovascular Hospital, Central China Fuwai Hospital of Zhengzhou University, Zhengzhou, China. chengzhy@zzu.edu.cn.
³ Department of Cardiovascular Surgery, Heart Center of Henan Provincial People's Hospital, Fuwai Central China Cardiovascular Hospital, Central China Fuwai Hospital of Zhengzhou University, Zhengzhou, China.

Abstract

Objective: Postoperative acute kidney injury (PO-AKI) is a common complication after cardiac surgery. We aimed to evaluate whether machine learning algorithms could significantly improve the risk prediction of PO-AKI.

Methods: The retrospective cohort study included 2310 adult patients undergoing cardiac surgery in a tertiary teaching hospital, China. Postoperative AKI and severe AKI were identified by the modified KDIGO definition. The sample was randomly divided into a derivation set and a validation set based on a ratio of 4:1. Exploiting conventional logistic regression (LR) and five ML algorithms including decision tree, random forest, gradient boosting classifier (GBC), Gaussian Naive Bayes and multilayer perceptron, we developed and validated the prediction models of PO-AKI. We implemented the interpretation of models using SHapley Additive exPlanation (SHAP) analysis.

Results: Postoperative AKI and severe AKI occurred in 1020 (44.2%) and 286 (12.4%) patients, respectively. Compared with the five ML models, LR model for PO-AKI exhibited the largest AUC (0.812, 95%CI: 0.756, 0.860, all P < 0.05), sensitivity (0.774, 95%CI: 0.719, 0.813), accuracy (0.753, 95%CI: 0.719, 0.781) and Youden index (0.513, 95%CI: 0.451, 0.573). Regarding severe AKI, GBC algorithm showed a significantly higher AUC than the other four ML models (all P < 0.05). Although no significant difference (P = 0.173) was observed in AUCs between GBC (0.86, 95%CI: 0.808, 0.902) and conventional logistic regression (0.803, 95%CI: 0.746, 0.852), GBC achieved greater sensitivity, accuracy and Youden index than conventional LR. Notably, SHAP analyses showed that preoperative serum creatinine, hyperlipidemia, lipid-lowering agents and assisted ventilation time were consistently among the top five important predictors for both postoperative AKI and severe AKI.

Conclusion: Logistic regression and GBC algorithm demonstrated moderate to good discrimination and superior performance in predicting PO-AKI and severe AKI, respectively. Interpretation of the models identified the key contributors to the predictions, which could potentially inform clinical interventions.

Keywords: Acute kidney Injury; Cardiac surgery; Machine learning; Predictive model.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Acute Kidney Injury* / diagnosis
Acute Kidney Injury* / etiology
Adult
Bayes Theorem
Cardiac Surgical Procedures* / adverse effects
Humans
Machine Learning
Retrospective Studies
Risk Assessment
Risk Factors