Paying attention to cardiac surgical risk: An interpretable machine learning approach using an uncertainty-aware attentive neural network
PLOS ONE · 2023
DOI: 10.1371/journal.pone.0289930 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS ONE, 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, Vic, Australia. Hauptthemen laut MEDLINE: Cardiac Surgical Procedures, Lepidoptera. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Health and Medical Research Council, National Health and Medical Research Council Principal Research Fellowship.
Abstract (Originalsprache)
Machine learning (ML) is increasingly applied to predict adverse postoperative outcomes in cardiac surgery. Commonly used ML models fail to translate to clinical practice due to absent model explainability, limited uncertainty quantification, and no flexibility to missing data. We aimed to develop and benchmark a novel ML approach, the uncertainty-aware attention network (UAN), to overcome these common limitations. Two Bayesian uncertainty quantification methods were tested, generalized variational inference (GVI) or a posterior network (PN). The UAN models were compared with an ensemble of XGBoost models and a Bayesian logistic regression model (LR) with imputation. The derivation datasets consisted of 153,932 surgery events from the Australian and New Zealand Society of Cardiac and Thoracic Surgeons (ANZSCTS) Cardiac Surgery Database. An external validation consisted of 7343 surgery events which were extracted from the Medical Information Mart for Intensive Care (MIMIC) III critical care dataset. The highest performing model on the external validation dataset was a UAN-GVI with an area under the receiver operating characteristic curve (AUC) of 0.78 (0.01). Model performance improved on high confidence samples with an AUC of 0.81 (0.01). Confidence calibration for aleatoric uncertainty was excellent for all models. Calibration for epistemic uncertainty was more variable, with an ensemble of XGBoost models performing the best with an AUC of 0.84 (0.08). Epistemic uncertainty was improved using the PN approach, compared to GVI. UAN is able to use an interpretable and flexible deep learning approach to provide estimates of model uncertainty alongside state-of-the-art predictions. The model has been made freely available as an easy-to-use web application demonstrating that by designing uncertainty-aware models with innately explainable predictions deep learning may become more suitable for routine clinical use.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Surgery, School of Clinical Sciences at Monash Health, Monash University, Melbourne, Vic, Australia.
- Department of Computer Science and Artificial Intelligence, University of Granada, Granada, Spain.
- Department of Data Science and Artificial Intelligence, Faculty of Information Technology, Monash University, Melbourne, Vic, Australia.
- Department of Epidemiology and Preventive Medicine, Monash University, Melbourne, Vic, Australia.
ORCID-Profile: Jahan C Penny-Dimri, Julian A Smith
Förderung
- National Health and Medical Research Council
- National Health and Medical Research Council Principal Research Fellowship
Zitieren
APA
Penny-Dimri, J. C., Bergmeir, C., Reid, C. M., Williams-Spence, J., Cochrane, A. D., & Smith, J. A. (2023). Paying attention to cardiac surgical risk: An interpretable machine learning approach using an uncertainty-aware attentive neural network. PLOS ONE. https://doi.org/10.1371/journal.pone.0289930
Vancouver
Penny-Dimri JC, Bergmeir C, Reid CM, Williams-Spence J, Cochrane AD, Smith JA. Paying attention to cardiac surgical risk: An interpretable machine learning approach using an uncertainty-aware attentive neural network. PLOS ONE. 2023. doi:10.1371/journal.pone.0289930
BibTeX
@article{PennyDimri2023,
author = {Penny-Dimri, Jahan C and Bergmeir, Christoph and Reid, Christopher M and Williams-Spence, Jenni and Cochrane, Andrew D and Smith, Julian A},
title = {Paying attention to cardiac surgical risk: An interpretable machine learning approach using an uncertainty-aware attentive neural network},
journal = {PLOS ONE},
year = {2023},
doi = {10.1371/journal.pone.0289930}
}
EUVIMED