Assessing the utility of deep neural networks in predicting postoperative surgical complications: a retrospective study.
Journal:
The Lancet. Digital health
PMID:
34215564
Abstract
BACKGROUND: Early detection of postoperative complications, including organ failure, is pivotal in the initiation of targeted treatment strategies aimed at attenuating organ damage. In an era of increasing health-care costs and limited financial resources, identifying surgical patients at a high risk of postoperative complications and providing personalised precision medicine-based treatment strategies provides an obvious pathway for reducing patient morbidity and mortality. We aimed to leverage deep learning to create, through training on structured electronic health-care data, a multilabel deep neural network to predict surgical postoperative complications that would outperform available models in surgical risk prediction.
Authors
Keywords
Adolescent
Adult
Aged
Area Under Curve
Biomedical Technology
Data Analysis
Data Management
Databases, Factual
Female
Forecasting
Humans
Male
Middle Aged
Models, Biological
Neural Networks, Computer
Postoperative Complications
Postoperative Period
Retrospective Studies
Risk Assessment
Risk Factors
ROC Curve