Accepted for/Published in: JMIR Medical Informatics
Date Submitted: Feb 13, 2025
Date Accepted: Oct 8, 2025
Predicting Delayed Extubation After General Anesthesia in PACU Patients Using Machine Learning: Model Development
ABSTRACT
Background:
Delayed extubation after general anesthesia increases complications like longer hospital stays and higher mortality. Current risk assessments often rely on subjective judgment or simple tools, while machine learning offers potential for real-time evaluation, though research is limited and typically uses single-algorithm models.
Objective:
The aim of this study were to identify the risk factors for delayed extubation after general anesthesia in the sample and to construct a risk prediction model for delayed extubation in this population.
Methods:
Data from 4779 patients admitted to the PACU between September 2023 and May 2024 were used to develop prediction models for delayed extubation using K-Nearest Neighbor, Decision Tree, Extreme Gradient Boosting, Random Forest, LightGBM, and Neural Networks. Model performance was assessed using AUROC, Sensitivity, and Specificity.
Results:
The XGBoost model showed the highest AUROC (0.766), Sensitivity (0.911), and Specificity (0.551). Shapley Additive Explanations ranked feature importance.
Conclusions:
These machine learning models enable early identification of delayed extubation risk, supporting personalized clinical decisions and optimizing PACU resource allocation. Clinical Trial: This study was approved by the Chinese Clinical Trial Registry (ChiCTR2400090247).
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.