EUVIMEDEUVIMED entdecken
Multizentrische StudieOpen Access

Multi-horizon predictive models for guiding extracorporeal resource allocation in critically ill COVID-19 patients

Bing Xue, Neel Shah, Hanqing Yang, Thomas Kannampallil iD, Philip Richard Orrin Payne iD, Chenyang Lu, Ahmed Sameh Said iD

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.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

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)

Critical IllnessCOVID-19HumansRetrospective StudiesOrgan Dysfunction ScoresIntensive Care Units

Stichwörter der Autor:innen

COVID-19ECMOearly alertmachine learningpredictionresource allocation

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}
}
Kostenlos starten →