Tree-based survival analysis improves mortality prediction in cardiac surgery

Jahan C Penny-Dimri; Christoph Bergmeir; Christopher M Reid; Jenni Williams-Spence; Luke A Perry; Julian A Smith

doi:10.3389/fcvm.2023.1211600

Tree-based survival analysis improves mortality prediction in cardiac surgery

Front Cardiovasc Med. 2023 Jul 10:10:1211600. doi: 10.3389/fcvm.2023.1211600. eCollection 2023.

Authors

Jahan C Penny-Dimri¹, Christoph Bergmeir^{2

3}, Christopher M Reid^{1

4}, Jenni Williams-Spence^{1

4}, Luke A Perry⁵, Julian A Smith¹

Affiliations

¹ Department of Surgery, School of Clinical Sciences at Monash Health, Monash University, Melbourne, Australia.
² Department of Data Science and Artificial Intelligence, Faculty of Information Technology, Monash University, Melbourne, Australia.
³ Department of Computer Science and Artificial Intelligence, University of Granada, Melbourne, Spain.
⁴ Department of Epidemiology and Preventive Medicine, Monash University, Melbourne, Vic, Australia.
⁵ Department of Anaesthesia, Victorian Heart Hospital, Monash Health, Clayton, Vic, Australia.

Abstract

Objectives: Machine learning (ML) classification tools are known to accurately predict many cardiac surgical outcomes. A novel approach, ML-based survival analysis, remains unstudied for predicting mortality after cardiac surgery. We aimed to benchmark performance, as measured by the concordance index (C-index), of tree-based survival models against Cox proportional hazards (CPH) modeling and explore risk factors using the best-performing model.

Methods: 144,536 patients with 147,301 surgery events from the Australian and New Zealand Society of Cardiac and Thoracic Surgeons (ANZSCTS) national database were used to train and validate models. Univariate analysis was performed using Student's T-test for continuous variables, Chi-squared test for categorical variables, and stratified Kaplan-Meier estimation of the survival function. Three ML models were tested, a decision tree (DT), random forest (RF), and gradient boosting machine (GBM). Hyperparameter tuning was performed using a Bayesian search strategy. Performance was assessed using 2-fold cross-validation repeated 5 times.

Results: The highest performing model was the GBM with a C-index of 0.803 (0.002), followed by RF with 0.791 (0.003), DT with 0.729 (0.014), and finally CPH with 0.596 (0.042). The 5 most predictive features were age, type of procedure, length of hospital stay, drain output in the first 4 h (ml), and inotrope use greater than 4 h postoperatively.

Conclusion: Tree-based learning for survival analysis is a non-parametric and performant alternative to CPH modeling. GBMs offer interpretable modeling of non-linear relationships, promising to expose the most relevant risk factors and uncover new questions to guide future research.

Keywords: cardiac surgery; machine learning; mortality; survival analaysis; tree-based machine learning.

Grants and funding

The ANZSCTS National Cardiac Surgery Database Program is funded by the Department of Health (Victoria), the Clinical Excellence Commission (NSW), Queensland Health (QLD), and funding from individual cardiac surgical units participating in the registry. ANZSCTS Database Research activities are supported through a National Health and Medical Research Council Principal Research Fellowship (APP 1136372) and Program Grant (APP 1092642) awarded to C.M. Reid. The Database thanks all of the investigators, data managers, and institutions that participate in the Program.