Accepted for/Published in: JMIR Medical Informatics
Date Submitted: Aug 10, 2021
Open Peer Review Period: Aug 10, 2021 - Aug 17, 2021
Date Accepted: Oct 3, 2021
Date Submitted to PubMed: Oct 5, 2021
(closed for review but you can still tweet)
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Optimal triage for COVID-19 patients under limited healthcare resources: Development of a parsimonious machine learning prediction model and threshold optimization using discrete-event simulation
ABSTRACT
Background:
The coronavirus disease 2019 (COVID-19) pandemic has caused an unprecedented burden on healthcare systems.
Objective:
To effectively triage COVID-19 patients within situations of limited data availability and to explore optimal thresholds to minimize mortality rates while maintaining the healthcare system capacity.
Methods:
A nationwide sample of 5601 patients confirmed for COVID-19 up until April 2020 was retrospectively reviewed. XGBoost and logistic regression analysis were used to develop prediction models for the patients’ maximum clinical severity during hospitalization, classified according to the WHO Ordinal Scale for Clinical Improvement (OSCI). The recursive feature elimination technique was used to evaluate the extent of the model performance’s maintenance when clinical and laboratory variables are eliminated. Using populations based on hypothetical patient influx scenarios, discrete-event simulation was performed to find the optimal threshold within limited resource environments that minimizes mortality rates.
Results:
The cross-validated area under the receiver operating characteristics (AUROC) of the baseline XGBoost model that utilized all 37 variables was 0.965 for OSCI ≥ 6. Compared to the baseline model’s performance, the AUROC of the feature-eliminated model that utilized 17 variables was maintained at 0.963 with statistical insignificance. Our prediction model was provided online for clinical implementation. Optimal thresholds were found to minimize mortality rates in a hypothetical patient influx scenario. The benefit of utilizing an optimal triage threshold was clear, reducing mortality up to 18.1% compared to the conventional Youden Index.
Conclusions:
Our adaptive triage model and its threshold optimization capability reveal that COVID-19 management can be integrated using both medical and healthcare management sectors to guarantee maximum treatment efficacy.
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.