Supervised Machine Learning Approach to Identify Early Predictors of Poor Outcome in Patients with COVID-19 Presenting to a Large Quaternary Care Hospital in New York City.

Autor: Zucker J; Division of Infectious Diseases, Columbia University Irving Medical Center, New York, NY 10032, USA., Gomez-Simmonds A; Division of Infectious Diseases, Columbia University Irving Medical Center, New York, NY 10032, USA., Purpura LJ; Division of Infectious Diseases, Columbia University Irving Medical Center, New York, NY 10032, USA., Shoucri S; Division of Infectious Diseases, Columbia University Irving Medical Center, New York, NY 10032, USA., LaSota E; Tulane University School of Medicine, Tulane Medical Center, New Orleans, LA 70112, USA., Morley NE; Columbia University Vagelos College of Physicians and Surgeons, Columbia University Irving Medical Center, New York, NY 10032, USA., Sovic BW; Division of Infectious Diseases, Columbia University Irving Medical Center, New York, NY 10032, USA., Castellon MA; Division of Infectious Diseases, Columbia University Irving Medical Center, New York, NY 10032, USA., Theodore DA; Division of Infectious Diseases, Columbia University Irving Medical Center, New York, NY 10032, USA., Bartram LL; Division of Infectious Diseases, Icahn School of Medicine at Mount Sinai, New York, NY 10029, USA., Miko BA; Division of Infectious Diseases, Columbia University Irving Medical Center, New York, NY 10032, USA., Scherer ML; Division of Infectious Diseases, Columbia University Irving Medical Center, New York, NY 10032, USA., Meyers KA; Aaron Diamond AIDS Research Center, Vagelos College of Physicians and Surgeons, New York, NY 10032, USA., Turner WC; General Internal Medicine, Columbia University Irving Medical Center, New York, NY 10032, USA., Kelly M; General Internal Medicine, Columbia University Irving Medical Center, New York, NY 10032, USA., Pavlicova M; Mailman School of Public Health, Columbia University Irving Medical Center, New York, NY 10032, USA., Basaraba CN; Mailman School of Public Health, Columbia University Irving Medical Center, New York, NY 10032, USA., Baldwin MR; Division of Pulmonology, Columbia University Irving Medical Center, New York, NY 10032, USA., Brodie D; Division of Pulmonology, Columbia University Irving Medical Center, New York, NY 10032, USA., Burkart KM; Division of Pulmonology, Columbia University Irving Medical Center, New York, NY 10032, USA., Bathon J; Division of Rheumatology, Columbia University Irving Medical Center, New York, NY 10032, USA., Uhlemann AC; Division of Infectious Diseases, Columbia University Irving Medical Center, New York, NY 10032, USA., Yin MT; Division of Infectious Diseases, Columbia University Irving Medical Center, New York, NY 10032, USA., Castor D; Division of Infectious Diseases, Columbia University Irving Medical Center, New York, NY 10032, USA., Sobieszczyk ME; Division of Infectious Diseases, Columbia University Irving Medical Center, New York, NY 10032, USA.
Jazyk: angličtina
Zdroj: Journal of clinical medicine [J Clin Med] 2021 Aug 11; Vol. 10 (16). Date of Electronic Publication: 2021 Aug 11.
DOI: 10.3390/jcm10163523
Abstrakt: Background: The progression of clinical manifestations in patients with coronavirus disease 2019 (COVID-19) highlights the need to account for symptom duration at the time of hospital presentation in decision-making algorithms.
Methods: We performed a nested case-control analysis of 4103 adult patients with COVID-19 and at least 28 days of follow-up who presented to a New York City medical center. Multivariable logistic regression and classification and regression tree (CART) analysis were used to identify predictors of poor outcome.
Results: Patients presenting to the hospital earlier in their disease course were older, had more comorbidities, and a greater proportion decompensated (<4 days, 41%; 4-8 days, 31%; >8 days, 26%). The first recorded oxygen delivery method was the most important predictor of decompensation overall in CART analysis. In patients with symptoms for <4, 4-8, and >8 days, requiring at least non-rebreather, age ≥ 63 years, and neutrophil/lymphocyte ratio ≥ 5.1; requiring at least non-rebreather, IL-6 ≥ 24.7 pg/mL, and D-dimer ≥ 2.4 µg/mL; and IL-6 ≥ 64.3 pg/mL, requiring non-rebreather, and CRP ≥ 152.5 mg/mL in predictive models were independently associated with poor outcome, respectively.
Conclusion: Symptom duration in tandem with initial clinical and laboratory markers can be used to identify patients with COVID-19 at increased risk for poor outcomes.
Databáze: MEDLINE
Externí odkaz: