Multi-horizon predictive models for guiding extracorporeal resource allocation in critically ill COVID-19 patients
Journal of the American Medical Informatics Association · 16.03.2023 · 30 (4) · 656-667
DOI: 10.1093/jamia/ocac256 ↗Kurz gefasst
Multizentrische Studie in der Zeitschrift Journal of the American Medical Informatics Association, online erschienen am 28.12.2022. Verfasst von Bing Xue und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science & Engineering, Washington University in St. Louis, St. Louis, Missouri, USA. Hauptthemen laut MEDLINE: Critical Illness, COVID-19. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 91 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Big Ideas 2020 COVID Grant, Healthcare Innovations Lab, BJC Healthcare and Washington University in St. Louis School of Medicine.
Abstract (Originalsprache)
Objective
Extracorporeal membrane oxygenation (ECMO) resource allocation tools are currently lacking. We developed machine learning (ML) models for predicting COVID-19 patients at risk of receiving ECMO to guide patient triage and resource allocation. Material and Methods We included COVID-19 patients admitted to intensive care units for >24 h from March 2020 to October 2021, divided into training and testing development and testing-only holdout cohorts. We developed ECMO deployment timely prediction model ForecastECMO using Gradient Boosting Tree (GBT), with pre-ECMO prediction horizons from 0 to 48 h, compared to PaO2/FiO2 ratio, Sequential Organ Failure Assessment score, PREdiction of Survival on ECMO Therapy score, logistic regression, and 30 pre-selected clinical variables GBT Clinical GBT models, with area under the receiver operator curve (AUROC) and precision recall curve (AUPRC) metrics.
Results
ECMO prevalence was 2.89% and 1.73% in development and holdout cohorts. ForecastECMO had the best performance in both cohorts. At the 18-h prediction horizon, a potentially clinically actionable pre-ECMO window, ForecastECMO, had the highest AUROC (0.94 and 0.95) and AUPRC (0.54 and 0.37) in development and holdout cohorts in identifying ECMO patients without data 18 h prior to ECMO. Discussion and Conclusions We developed a multi-horizon model, ForecastECMO, with high performance in identifying patients receiving ECMO at various prediction horizons. This model has potential to be used as early alert tool to guide ECMO resource allocation for COVID-19 patients. Future prospective multicenter validation would provide evidence for generalizability and real-world application of such models to improve patient outcomes.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Computer Science & Engineering, Washington University in St. Louis, St. Louis, Missouri, USA.
- Department of Pediatrics, Washington University in St. Louis, St. Louis, Missouri, USA.
- Department of Anesthesiology, Washington University in St. Louis, St. Louis, Missouri, USA.
- Institute of Informatics, Washington University in St. Louis, St. Louis, Missouri, USA.
- Department of Medicine, Washington University in St. Louis, St. Louis, Missouri, USA.
ORCID-Profile: Thomas Kannampallil, Philip Richard Orrin Payne, Ahmed Sameh Said
Förderung
- Big Ideas 2020 COVID Grant
- Healthcare Innovations Lab
- BJC Healthcare and Washington University in St. Louis School of Medicine
- Children’s Discovery Institute Faculty Development Award at Washington University in St. Louis
Zitieren
APA
Xue, B., Shah, N., Yang, H., Kannampallil, T., Payne, P. R. O., Lu, C., & Said, A. S. (2023). Multi-horizon predictive models for guiding extracorporeal resource allocation in critically ill COVID-19 patients. Journal of the American Medical Informatics Association, 30(4), 656-667. https://doi.org/10.1093/jamia/ocac256
Vancouver
Xue B, Shah N, Yang H, Kannampallil T, Payne PRO, Lu C, et al. Multi-horizon predictive models for guiding extracorporeal resource allocation in critically ill COVID-19 patients. Journal of the American Medical Informatics Association. 2023;30(4):656-667. doi:10.1093/jamia/ocac256
BibTeX
@article{Xue2023,
author = {Xue, Bing and Shah, Neel and Yang, Hanqing and Kannampallil, Thomas and Payne, Philip Richard Orrin and Lu, Chenyang and Said, Ahmed Sameh},
title = {Multi-horizon predictive models for guiding extracorporeal resource allocation in critically ill COVID-19 patients},
journal = {Journal of the American Medical Informatics Association},
year = {2023},
volume = {30},
number = {4},
pages = {656--667},
doi = {10.1093/jamia/ocac256}
}
EUVIMED