A machine learning approach to predicting 30-day mortality following paediatric cardiac surgery: findings from the Australia New Zealand Congenital Outcomes Registry for Surgery (ANZCORS)
European Journal of Cardio-Thoracic Surgery · 2023
DOI: 10.1093/ejcts/ezad160 ↗Kurz gefasst
Fachartikel in der Zeitschrift European Journal of Cardio-Thoracic Surgery, 2023. Verfasst von Kim S Betts und 8 weiteren Autor:innen. Beteiligte Einrichtung: Queensland Paediatric Cardiac Research (QPCR), Brisbane, QLD, Australia. Hauptthemen laut MEDLINE: Thoracic Surgery, Cardiac Surgical Procedures. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 30 Literaturangaben.
Abstract (Originalsprache)
OBJECTIVES We aim to develop the first risk prediction model for 30-day mortality for the Australian and New Zealand patient populations and examine whether machine learning (ML) algorithms outperform traditional statistical approaches. METHODS Data from the Australia New Zealand Congenital Outcomes Registry for Surgery, which contains information on every paediatric cardiac surgical encounter in Australian and New Zealand for patients aged <18 years between January 2013 and December 2021, were analysed (n = 14 343). The outcome was mortality within the 30-day period following a surgical encounter, with ∼30% of the observations randomly selected to be used for validation of the final model. Three different ML methods were used, all of which employed five-fold cross-validation to prevent overfitting, with model performance judged primarily by the area under the receiver operating curve (AUC). RESULTS Among the 14 343 30-day periods, there were 188 deaths (1.3%). In the validation data, the gradient-boosted tree obtained the best performance [AUC = 0.87, 95% confidence interval = (0.82, 0.92); calibration = 0.97, 95% confidence interval = (0.72, 1.27)], outperforming penalized logistic regression and artificial neural networks (AUC of 0.82 and 0.81, respectively). The strongest predictors of mortality in the gradient boosting trees were patient weight, STAT score, age and gender. CONCLUSIONS Our risk prediction model outperformed logistic regression and achieved a level of discrimination comparable to the PRAiS2 and Society of Thoracic Surgery Congenital Heart Surgery Database mortality risk models (both which obtained AUC = 0.86). Non-linear ML methods can be used to construct accurate clinical risk prediction tools.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Queensland Paediatric Cardiac Research (QPCR), Brisbane, QLD, Australia.
- School of Population Health, Curtin University, Perth, WA, Australia.
- Queensland Paediatric Cardiac Service (QPCS), Queensland Children's Hospital, Brisbane, QLD, Australia.
- School of Clinical Medicine, Children's Health Queensland Clinical Unit, University of Queensland, Brisbane, QLD, Australia.
- Royal Children's Hospital, Melbourne, VIC, Australia.
- Starship Children's Hospital, Auckland, New Zealand.
ORCID-Profile: Kim S Betts, Prem Venugopal, Nelson Alphonso
Zitieren
APA
Betts, K. S., Marathe, S. P., Chai, K., Konstantinov, I., Iyengar, A., Suna, J., ANZCORS Collaborative, Venugopal, P., & Alphonso, N. (2023). A machine learning approach to predicting 30-day mortality following paediatric cardiac surgery: findings from the Australia New Zealand Congenital Outcomes Registry for Surgery (ANZCORS). European Journal of Cardio-Thoracic Surgery. https://doi.org/10.1093/ejcts/ezad160
Vancouver
Betts KS, Marathe SP, Chai K, Konstantinov I, Iyengar A, Suna J, et al. A machine learning approach to predicting 30-day mortality following paediatric cardiac surgery: findings from the Australia New Zealand Congenital Outcomes Registry for Surgery (ANZCORS). European Journal of Cardio-Thoracic Surgery. 2023. doi:10.1093/ejcts/ezad160
BibTeX
@article{Betts2023,
author = {Betts, Kim S and Marathe, Supreet P and Chai, Kevin and Konstantinov, Igor and Iyengar, Ajay and Suna, Jessica and ANZCORS Collaborative, ANZCORS Collaborative and Venugopal, Prem and Alphonso, Nelson},
title = {A machine learning approach to predicting 30-day mortality following paediatric cardiac surgery: findings from the Australia New Zealand Congenital Outcomes Registry for Surgery (ANZCORS)},
journal = {European Journal of Cardio-Thoracic Surgery},
year = {2023},
doi = {10.1093/ejcts/ezad160}
}
EUVIMED