Predicting the Risk Factors Associated With Severe Outcomes Among COVID-19 Patients–Decision Tree Modeling Approach

Abstract

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.