BackgroundThe COVID-19 pandemic has seen a large surge in case numbers over several waves, and has critically strained the health care system, with a significant number of cases requiring hospitalization and ICU admission. This study used a decision tree modeling approach to identify the most important predictors of severe outcomes among COVID-19 patients.MethodsWe identified a retrospective population-based cohort (n = 140,182) of adults who tested positive for COVID-19 between 5th March 2020 and 31st May 2021. Demographic information, symptoms and co-morbidities were extracted from a communicable disease and outbreak management information system and electronic medical records. Decision tree modeling involving conditional inference tree and random forest models were used to analyze and identify the key factors(s) associated with severe outcomes (hospitalization, ICU admission and death) following COVID-19 infection.ResultsIn the study cohort, nearly 6.37% were hospitalized, 1.39% were admitted to ICU and 1.57% died due to COVID-19. Older age (>71Y) and breathing difficulties were the top two factors associated with a poor prognosis, predicting about 50% of severe outcomes in both models. Neurological conditions, diabetes, cardiovascular disease, hypertension, and renal disease were the top five pre-existing conditions that altogether predicted 29% of outcomes. 79% of the cases with poor prognosis were predicted based on the combination of variables. Age stratified models revealed that among younger adults (18–40 Y), obesity was among the top risk factors associated with adverse outcomes.ConclusionDecision tree modeling has identified key factors associated with a significant proportion of severe outcomes in COVID-19. Knowledge about these variables will aid in identifying high-risk groups and allocating health care resources.

Background: Description of risk factors of severe acute COVID-19 outcomes with the consideration of vaccination status in the era of the Omicron variant of concern are limited. Objectives: To examine the association of age, sex, underlying medical conditions, and COVID-19 vaccination with hospitalization, intensive-care unit (ICU) admission, or death due to the disease, using data from a period when Omicron was the dominant strain. Methods: A population-based case-control study based on administrative health data, that included confirmed COVID-19 patients during January (2022) in Alberta, Canada. Patients who were non-residents, without the provincial healthcare insurance coverage, or <=18 years of age were excluded. Patients with any severe outcome were the cases; and those without any hospitalization, ICU admission, or death were controls. Adjusted odds ratios, of the explanatory factors of a severe outcome, were estimated using a logistic regression model. Results: There were 90,989 COVID-19 patients included in the analysis; 2% had severe outcomes and 98% were included in the control group. Overall, more COVID patients were found in the younger age-groups (72.0% <=49 years old), females (56.5%), with no underlying conditions (59.5%), and fully vaccinated patients (90.4%). However, the adjusted odds ratios were highest in the 70-79 age group (28.32; 95% CI 20.6-38.9) or among >=80 years old (29.8; 21.6-41.0), males (1.4; 1.3-1.6); unvaccinated (16.1; 13.8-18.8), or patients with >=3 underlying conditions (13.1; 10.9-15.8). Conclusion: Higher risk of severe acute COVID-19 outcomes were associated with older age, the male sex, and increased number of underlying medical conditions. Unvaccination or undervaccination remained as the greatest modifiable risk factor in prevention of severe COVID outcomes. These findings help inform medical decisions and allocation of scarce healthcare resources.