Predicting the Prognosis of Patients in the Coronary Care Unit via Machine Learning Using XGBoost

Abstract

Background: Early prediction and classification of prognosis is essential for patients in the coronary care unit (CCU). We applied a machine learning (ML) model using the XGBoost algorithm to prognosticate CCU patients, and compared XGBoost with traditional classification models. Methods: CCU patients’ data were extracted from the MIMIC-III v1.4 clinical database, and divided into four groups based on the time to death: <30 days, 30 days–1 year, 1 year–5 years, and ≥5 years. Variables were displayed and compared between groups using the STATA software. Four classification models, including XGBoost, naive Bayes (NB), logistic regression (LR), and support vector machine (SVM) were constructed using the Python software. These four models were tested and compared for accuracy, F1 score, Matthews correlation coefficient (MCC), and area under the curve (AUC) of the receiver operating characteristic curves. We also constructed sub-models of each model based on the different categories of death time and compared the differences by decision curve analysis. The optimal model was further analysed using a clinical impact curve. Findings: A total of 5360 CCU patients were included. Compared to NB, LR, and SVM, the XGBoost model performed better in accuracy (0.663, 0.605, 0.632, and 0.622), micro-AUCs (0.873, 0.811, 0.841 and 0.818), and MCC (0.337, 0.317, 0.250, and 0.182). The decision curve and clinical impact curve analyses verified the clinical utility of the XGBoost model for different category of patients. Interpretation: For CCU physicians, ML technique by XGBoost is a potential predictive tool for patients with fast changing condition, and it may provide them with-assistance of prognosis improvements. Funding: National Natural Science Foundation of China, Natural Science Foundation of Zhejiang Province, and Medical and Health Science Program of Zhejiang Province. Declaration of Interest: All authors declare that they have no competing interest.