EUVIMEDEUVIMED entdecken
KohortenstudieOpen Access

Predicting Long COVID in the National COVID Cohort Collaborative Using Super Learner: Cohort Study

Zachary Butzin-Dozier iD, Yunwen Ji iD, Haodong Li iD, Jeremy Coyle iD, Junming Shi iD, Rachael V Phillips iD, Andrew N Mertens iD, Romain Pirracchio iD, Mark J van der Laan iD, Rena C Patel iD, John M Colford iD, Alan E Hubbard iD und 1 weitere

JMIR Public Health and Surveillance · 15.08.2024 · 10 · e53322

DOI: 10.2196/53322 ↗

Kurz gefasst

Kohortenstudie in der Zeitschrift JMIR Public Health and Surveillance, online erschienen am 15.08.2024. Verfasst von Zachary Butzin-Dozier und 12 weiteren Autor:innen. Beteiligte Einrichtung: Division of Biostatistics, University of California Berkeley School of Public Health, Berkeley, CA, United States. Hauptthemen laut MEDLINE: COVID-19, Post-Acute COVID-19 Syndrome. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIMH NIH HHS, NCATS NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Postacute sequelae of COVID-19 (PASC), also known as long COVID, is a broad grouping of a range of long-term symptoms following acute COVID-19. These symptoms can occur across a range of biological systems, leading to challenges in determining risk factors for PASC and the causal etiology of this disorder. An understanding of characteristics that are predictive of future PASC is valuable, as this can inform the identification of high-risk individuals and future preventative efforts. However, current knowledge regarding PASC risk factors is limited.

Objective

Using a sample of 55,257 patients (at a ratio of 1 patient with PASC to 4 matched controls) from the National COVID Cohort Collaborative, as part of the National Institutes of Health Long COVID Computational Challenge, we sought to predict individual risk of PASC diagnosis from a curated set of clinically informed covariates. The National COVID Cohort Collaborative includes electronic health records for more than 22 million patients from 84 sites across the United States.

Methods

We predicted individual PASC status, given covariate information, using Super Learner (an ensemble machine learning algorithm also known as stacking) to learn the optimal combination of gradient boosting and random forest algorithms to maximize the area under the receiver operator curve. We evaluated variable importance (Shapley values) based on 3 levels: individual features, temporal windows, and clinical domains. We externally validated these findings using a holdout set of randomly selected study sites.

Results

We were able to predict individual PASC diagnoses accurately (area under the curve 0.874). The individual features of the length of observation period, number of health care interactions during acute COVID-19, and viral lower respiratory infection were the most predictive of subsequent PASC diagnosis. Temporally, we found that baseline characteristics were the most predictive of future PASC diagnosis, compared with characteristics immediately before, during, or after acute COVID-19. We found that the clinical domains of health care use, demographics or anthropometry, and respiratory factors were the most predictive of PASC diagnosis.

Conclusions

The methods outlined here provide an open-source, applied example of using Super Learner to predict PASC status using electronic health record data, which can be replicated across a variety of settings. Across individual predictors and clinical domains, we consistently found that factors related to health care use were the strongest predictors of PASC diagnosis. This indicates that any observational studies using PASC diagnosis as a primary outcome must rigorously account for heterogeneous health care use. Our temporal findings support the hypothesis that clinicians may be able to accurately assess the risk of PASC in patients before acute COVID-19 diagnosis, which could improve early interventions and preventive care. Our findings also highlight the importance of respiratory characteristics in PASC risk assessment. International Registered Report Identifier (IRRID) RR2-10.1101/2023.07.27.23293272

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

COVID-19Post-Acute COVID-19 SyndromeHumansCohort StudiesFemaleMaleUnited StatesMiddle AgedAgedAdultRisk FactorsMachine Learning

Stichwörter der Autor:innen

COVID-19SARS-CoV-2Super Learnerchroniccovariatecovariatesensembleinfectiouslong COVIDlong termmachine learningpredictpredictionpredictionspredictive

Autor:innen und Institutionen

  • Division of Biostatistics, University of California Berkeley School of Public Health, Berkeley, CA, United States.
  • Department of Anesthesia and Perioperative Care, University of California San Francisco, San Francisco, CA, United States.
  • Department of Infectious Diseases, University of Alabama at Birmingham School of Medicine, Birmingham, AL, United States.
  • Members are listed at the end of the manuscript, .

ORCID-Profile: Zachary Butzin-Dozier, Yunwen Ji, Haodong Li, Jeremy Coyle, Junming Shi, Rachael V Phillips, Andrew N Mertens, Romain Pirracchio, Mark J van der Laan, Rena C Patel, John M Colford, Alan E Hubbard

Förderung

  • NIMH NIH HHS
  • NCATS NIH HHS

Zitieren

APA

Butzin-Dozier, Z., Ji, Y., Li, H., Coyle, J., Shi, J., Phillips, R. V., Mertens, A. N., Pirracchio, R., van der Laan, M. J., Patel, R. C., Colford, J. M., Hubbard, A. E., & National COVID Cohort Collaborative (N3C) Consortium (2024). Predicting Long COVID in the National COVID Cohort Collaborative Using Super Learner: Cohort Study. JMIR Public Health and Surveillance, 10, e53322. https://doi.org/10.2196/53322

Vancouver

Butzin-Dozier Z, Ji Y, Li H, Coyle J, Shi J, Phillips RV, et al. Predicting Long COVID in the National COVID Cohort Collaborative Using Super Learner: Cohort Study. JMIR Public Health and Surveillance. 2024;10:e53322. doi:10.2196/53322

BibTeX
@article{ButzinDozier2024,
  author = {Butzin-Dozier, Zachary and Ji, Yunwen and Li, Haodong and Coyle, Jeremy and Shi, Junming and Phillips, Rachael V and Mertens, Andrew N and Pirracchio, Romain and van der Laan, Mark J and Patel, Rena C and Colford, John M and Hubbard, Alan E and National COVID Cohort Collaborative (N3C) Consortium, National COVID Cohort Collaborative (N3C) Consortium},
  title = {Predicting Long COVID in the National COVID Cohort Collaborative Using Super Learner: Cohort Study},
  journal = {JMIR Public Health and Surveillance},
  year = {2024},
  volume = {10},
  pages = {e53322},
  doi = {10.2196/53322}
}
Kostenlos starten →