Explainable Preoperative Automated Machine Learning Prediction Model for Cardiac Surgery-Associated Acute Kidney Injury

Abstract

Background: We aimed to develop and validate an automated machine learning (autoML) prediction model for cardiac surgery-associated acute kidney injury (CSA-AKI). Methods: Using 69 preoperative variables, we developed several models to predict post-operative AKI in adult patients undergoing cardiac surgery. Models included autoML and non-autoML types, including decision tree (DT), random forest (RF), extreme gradient boosting (XGBoost), and artificial neural network (ANN), as well as a logistic regression prediction model. We then compared model performance using area under the receiver operating characteristic curve (AUROC) and assessed model calibration using Brier score on the independent testing dataset. Results: The incidence of CSA-AKI was 36%. Stacked ensemble autoML had the highest predictive performance among autoML models, and was chosen for comparison with other non-autoML and multivariable logistic regression models. The autoML had the highest AUROC (0.79), followed by RF (0.78), XGBoost (0.77), multivariable logistic regression (0.77), ANN (0.75), and DT (0.64). The autoML had comparable AUROC with RF and outperformed the other models. The autoML was well-calibrated. The Brier score for autoML, RF, DT, XGBoost, ANN, and multivariable logistic regression was 0.18, 0.18, 0.21, 0.19, 0.19, and 0.18, respectively. We applied SHAP and LIME algorithms to our autoML prediction model to extract an explanation of the variables that drive patient-specific predictions of CSA-AKI. Conclusion: We were able to present a preoperative autoML prediction model for CSA-AKI that provided high predictive performance that was comparable to RF and superior to other ML and multivariable logistic regression models. The novel approaches of the proposed explainable preoperative autoML prediction model for CSA-AKI may guide clinicians in advancing individualized medicine plans for patients under cardiac surgery.

Machine-learning predictions for acute kidney injuries after coronary artery bypass grafting: A real-life muticenter retrospective cohort study

“…Preoperative eGFR as an independent risk factor for AKI after CABG surgery has been con rmed by some studies [3,35,36]. Charat et al listed eGFR as an important risk factor in their ML model for predicting postoperative AKI of cardiac surgery [37]. Nevertheless, more research is needed to determine if body surface area (BSA) is an independent risk factor for postoperative AKI of CABG surgery, although there is no doubt that eGFR, Scr, and BSA are inextricably linked.…”

Assessment of Risk Factors for Acute Kidney Injury with Machine Learning Tools in Children Undergoing Hematopoietic Stem Cell Transplantation

“…Artificial intelligence (AI) tools have already been used to assess the risk factors for AKI development in specific groups of patients, including those after cardiosurgery or on intensive care units [12][13][14]. AI implementation in the analysis of pediatric AKI has been highly successful in the neonatal population, but has not covered the issue of post-HSCT AKI sufficiently [15].…”

Development of interpretable machine learning models for prediction of acute kidney injury after noncardiac surgery: a retrospective cohort study

“…A growing number of studies have utilized machine learning to develop prediction models for postoperative complications 9 – 13 , including AKI 11 , 14 . However, most studies for predicting AKI focus solely on cardiac surgery 15 – 18 and cannot be directly applied to patients undergoing noncardiac surgery. Additionally, prior machine learning-based AKI prediction models had several limitations, such as a narrow focus on specific procedures and small sample sizes 19 – 21 , as well as the absence of key variables 10 , 11 .…”