The Identification of Risk Factors Associated with COVID-19 in a Large Inpatient Cohort Using Machine Learning Approaches

Document Type

Article

Abstract

Coronavirus disease 2019 (COVID-19) has become a global pandemic that significantly challenged healthcare systems worldwide, with over 4 million deaths among 18.6 million identified cases as of June 2021. Understanding the current COVID-19 cases and determining clinical solutions is of paramount importance. In this chapter, we describe an exploratory study of identifying risk factors associated with COVID-19 inpatient care. Based on a set of COVID-19 inpatient medical health records in a US hospital system, we used both unsupervised and supervised machine learning methods to explore risk factors associated with hospitalized COVID-19 patients. We found that the most important features related to the COVID-19 disease include (1) influenza vaccines, (2) pneumococcal vaccines, and (3) weight-related variables (i.e., weight, height, and BMI). As such, we provide a use case that machine learning methods are valuable for predicting COVID-19 inpatient risk factors, and the results are promising to guide further research in this area.

Digital Object Identifier (DOI)

https://doi.org/10.1016/B978-0-12-821318-6.00017-7

APA Citation

Wu, D., Ren, Y., He, L., & Johnson, J. (2022). The identification of risk factors associated with COVID-19 in a large inpatient cohort using machine learning approaches. Elsevier EBooks, 1, 189–199.https://doi.org/10.1016/B978-0-12-821318-6.00017-7

Rights

© Copyright 2025 IEEE - All rights reserved, including rights for text and data mining and training of artificial intelligence and similar technologies.

Share

COinS