Statistical Modeling for COVID-19 Related Depression: Prediction, Classification, and Intervention

Abstract

The globe has been in a chaos state since a corona-virus (SARSCoV2) first appeared in December 2019. It was helpful to utilize an isolation strategy with quarantine to slow down the spread of disease. As a result, individuals stayed indoors instead of engaging in their regular daily activities outside. The goal of this study is to examine the connections and potential mediatory pathways between mental health issues, how people perceive their illnesses, and disorders of anxiety and depression. This aim of this study is to use various machine learning approaches to predict, classify, and detect depression risk factors in two districs of Khyber Pukhtunkhwa (KPK), Pakistan. In this paper, machine learning methods i.e., Random Forest and LASSO have been used for feature selection. Random Forest (RF), Support Vector Machine (SVM), k-Nearest Neighbor (k-NN), Least Absolute Shrinkage Selection Operation (LASSO), and Random Projection ensembles (RP) have been used to assess the performance of the LASSO and Random Forest by identifying important features. The results show that LASSO has performed better than the other methods. Additionally, the clustering technique is also utilized to detect different hot spots in the population by considering the data as an unsupervised issue.