Individual Factors Associated With COVID-19 Infection: A Machine Learning Study

Abstract

The fast, exponential increase of COVID-19 infections and their catastrophic effects on patients' health have required the development of tools that support health systems in the quick and efficient diagnosis and prognosis of this disease. In this context, the present study aims to identify the potential factors associated with COVID-19 infections, applying machine learning techniques, particularly random forest, chi-squared, xgboost, and rpart for feature selection; ROSE and SMOTE were used as resampling methods due to the existence of class imbalance. Similarly, machine and deep learning algorithms such as support vector machines, C4.5, random forest, rpart, and deep neural networks were explored during the train/test phase to select the best prediction model. The dataset used in this study contains clinical data, anthropometric measurements, and other health parameters related to smoking habits, alcohol consumption, quality of sleep, physical activity, and health status during confinement due to the pandemic associated with COVID-19. The results showed that the XGBoost model got the best features associated with COVID-19 infection, and random forest approximated the best predictive model with a balanced accuracy of 90.41% using SMOTE as a resampling technique. The model with the best performance provides a tool to help prevent contracting SARS-CoV-2 since the variables with the highest risk factor are detected, and some of them are, to a certain extent controllable.

An adaptive data-driven architecture for mental health care applications

“…Validity is further ensured through outlier detection and expert verification, forming the foundation for machine learning manipulations. Data manipulation: Critical for machine learning algorithms, data manipulation facilitates automated prediction and analysis ( Ramirez-del Real et al, 2022 ). This includes parameter tuning, feature selection, model selection, and evaluation for machine learning models.…”

“…Data manipulation: Critical for machine learning algorithms, data manipulation facilitates automated prediction and analysis ( Ramirez-del Real et al, 2022 ). This includes parameter tuning, feature selection, model selection, and evaluation for machine learning models.…”

Superspreading of SARS-CoV-2: a systematic review and meta-analysis of event attack rates and individual transmission patterns

“…Previous meta-analyses of individual-level superspreading included only a small number of papers (<26) that calculated overdispersion in transmission, missing the majority of published transmission trees and capturing data primarily from Asia [14,15]. Early investigations of individual-level characteristics related to superspreading were also limited by incomplete contact tracing [16,17] and a focus on clinical over demographic characteristics [16]. A more complete summary of superspreading is needed to understand the scale of transmission heterogeneity across settings and identify causes of individual heterogeneity.…”

A large-scale machine learning study of sociodemographic factors contributing to COVID-19 severity

“…Overall, we carefully devise several state-of-the-art feature selection methods, intending to start from a large number of sociodemographic factors and, in an unbiased way (without prior assumptions), determine the most important predictors directly from the data. While machine learning has been successfully applied to a number of COVID-19-related problems, such as disease diagnosis and prognosis (Alizadehsani et al, 2021; Mahdavi et al, 2021; Amini et al, 2022; Kamalov et al, 2022; Rajab et al, 2022; Ramírez-del Real et al, 2022; Yousefzadeh et al, 2022) it was to our knowledge less frequently applied in the ecological study design (a transverse comparison of geographical regions) as done here (Wang et al, 2021).…”