Tree-based survival analysis improves mortality prediction in cardiac surgery
Frontiers in Cardiovascular Medicine · 10.07.2023 · 10
DOI: 10.3389/fcvm.2023.1211600 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Cardiovascular Medicine, online erschienen am 10.07.2023. Verfasst von Jahan C Penny-Dimri und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Surgery, School of Clinical Sciences at Monash Health, Monash University, Melbourne, Australia. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
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.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Surgery, School of Clinical Sciences at Monash Health, Monash University, Melbourne, Australia.
- Department of Data Science and Artificial Intelligence, Faculty of Information Technology, Monash University, Melbourne, Australia.
- Department of Computer Science and Artificial Intelligence, University of Granada, Melbourne, Spain.
- Department of Epidemiology and Preventive Medicine, Monash University, Melbourne, Vic, Australia.
- Department of Anaesthesia, Victorian Heart Hospital, Monash Health, Clayton, Vic, Australia.
Zitieren
APA
Penny-Dimri, J. C., Bergmeir, C., Reid, C. M., Williams-Spence, J., Perry, L. A., & Smith, J. A. (2023). Tree-based survival analysis improves mortality prediction in cardiac surgery. Frontiers in Cardiovascular Medicine, 10. https://doi.org/10.3389/fcvm.2023.1211600
Vancouver
Penny-Dimri JC, Bergmeir C, Reid CM, Williams-Spence J, Perry LA, Smith JA. Tree-based survival analysis improves mortality prediction in cardiac surgery. Frontiers in Cardiovascular Medicine. 2023;10. doi:10.3389/fcvm.2023.1211600
BibTeX
@article{PennyDimri2023,
author = {Penny-Dimri, Jahan C and Bergmeir, Christoph and Reid, Christopher M and Williams-Spence, Jenni and Perry, Luke A and Smith, Julian A},
title = {Tree-based survival analysis improves mortality prediction in cardiac surgery},
journal = {Frontiers in Cardiovascular Medicine},
year = {2023},
volume = {10},
doi = {10.3389/fcvm.2023.1211600}
}
EUVIMED