A machine learning-based prediction model for postoperative delirium in cardiac valve surgery using electronic health records

Abstract

Abstract Background: Previous models for predicting delirium after cardiac surgery remained inadequate. This study aimed to develop and validate a machine learning-based prediction model for postoperative delirium (POD) in cardiac valve surgery patients. Methods: The electronic medical information of the cardiac surgical intensive care unit (CSICU) was extracted from a tertiary and major referral hospital in southern China over 1 year, from June 2019 to June 2020. A total of 507 patients admitted to the CSICU after cardiac valve surgery were included in this study. Seven classical machine learning algorithms (logistic regression, support vector machine, K-nearest neighbors, Naïve Bayes classifier, perceptron, decision tree classifier, and random forest classifier) were used to develop delirium prediction models under full (n=32) and simple (n=20) feature sets, respectively. Result: The area under the receiver operating characteristic curve (AUC) was higher under the full feature set (ranging from 0.61 to 0.85) than under the simple feature set (ranging from 0.31 to 0.76). Among all machine learning methods, the random forest classifier showed excellent potential for predicting delirium in patients using the full or simple feature set. Conclusions: We established machine learning-based prediction models to predict POD in patients undergoing cardiac valve surgery. The random forest model has the best predictive performance in prediction and can help improve the prognosis of patients with POD.