Random forest algorithm for predicting postoperative delirium in older patients

Weixuan Sheng; Xianshi Tang; Xiaoyun Hu; Pengfei Liu; Lei Liu; Huihui Miao; Dongxin Wang; Tianzuo Li

doi:10.3389/fneur.2023.1325941

Random forest algorithm for predicting postoperative delirium in older patients

Front Neurol. 2024 Jan 11:14:1325941. doi: 10.3389/fneur.2023.1325941. eCollection 2023.

Authors

Weixuan Sheng¹, Xianshi Tang², Xiaoyun Hu¹, Pengfei Liu¹, Lei Liu³, Huihui Miao¹, Dongxin Wang⁴, Tianzuo Li¹

Affiliations

¹ Department of Anesthesiology, Beijing Shijitan Hospital, Capital Medical University, Beijing, China.
² Key Laboratory of National Health Commission on Parasitic Disease Control and Prevention, Key Laboratory of Jiangsu Province on Parasite and Vector Control Technology, Jiangsu Institute of Parasitic Diseases, Wuxi, China.
³ Department of Science and Technology, Beijing Shijitan Hospital, Capital Medical University, Beijing, China.
⁴ Department of Anesthesiology, Peking University First Hospital, Beijing, China.

Abstract

Objective: In this study, we were aimed to identify important variables via machine learning algorithms and predict postoperative delirium (POD) occurrence in older patients.

Methods: This study was to make the secondary analysis of data from a randomized controlled trial. The Boruta function was used to screen relevant basic characteristic variables. Four models including Logistic Regression (LR), K-Nearest Neighbor (KNN), the Classification and Regression Tree (CART), and Random Forest (RF) were established from the data set using repeated cross validation, hyper-parameter optimization, and Smote technique (Synthetic minority over-sampling technique, Smote), with the calculation of confusion matrix parameters and the plotting of Receiver operating characteristic curve (ROC), Precision recall curve (PRC), and partial dependence graph for further analysis and evaluation.

Results: The basic characteristic variables resulting from Boruta screening included grouping, preoperative Mini-Mental State Examination(MMSE), CHARLSON score, preoperative HCT, preoperative serum creatinine, intraoperative bleeding volume, intraoperative urine volume, anesthesia duration, operation duration, postoperative morphine dosage, intensive care unit (ICU) duration, tracheal intubation duration, and 7-day postoperative rest and move pain score (median and max; VAS-Rest-M, VAS-Move-M, VAS-Rest-Max, and VAS-Move-Max). And Random Forest (RF) showed the best performance in the testing set among the 4 models with Accuracy: 0.9878; Matthews correlation coefficient (MCC): 0.8763; Area under ROC curve (AUC-ROC): 1.0; Area under the PRC Curve (AUC-PRC): 1.0.

Conclusion: A high-performance algorithm was established and verified in this study demonstrating the degree of POD risk changes in perioperative elderly patients. And the major risk factors for the development of POD were CREA and VAS-Move-Max.

Keywords: confusion matrix; older patient; partial dependence graph; postoperative delirium; random forest.

Grants and funding

The author(s) declare financial support was received for the research, authorship, and/or publication of this article. This work is supported by the National Natural Science Foundation of China (82071180 and 82271206) and Natural Science Foundation of Beijing (7212023).