Prediction of generalized anxiety levels during the Covid-19 pandemic: A machine learning-based modeling approach

Faisal Mashel Albagmi; Aisha Alansari; Deema Saad Al Shawan; Heba Yaagoub AlNujaidi; Sunday O Olatunji

doi:10.1016/j.imu.2022.100854

Prediction of generalized anxiety levels during the Covid-19 pandemic: A machine learning-based modeling approach

Inform Med Unlocked. 2022:28:100854. doi: 10.1016/j.imu.2022.100854. Epub 2022 Jan 19.

Authors

Faisal Mashel Albagmi¹, Aisha Alansari², Deema Saad Al Shawan³, Heba Yaagoub AlNujaidi³, Sunday O Olatunji²

Affiliations

¹ College of Applied Medical Science, Imam Abdulrahman Bin Faisal University, Dammam, Saudi Arabia.
² College of Computer Science and Information Technology, Imam Abdulrahman Bin Faisal University, Dammam, Saudi Arabia.
³ College of Public Health, Imam Abdulrahman Bin Faisal University, Dammam, Saudi Arabia.

Abstract

The rapid spread of the Covid-19 outbreak led many countries to enforce precautionary measures such as complete lockdowns. These lifestyle-altering measures caused a significant increase in anxiety levels globally. For that reason, decision-makers are in dire need of methods to prevent potential public mental crises. Machine learning has shown its effectiveness in the early prediction of several diseases. Therefore, this study aims to classify two-class and three-class anxiety problems early by utilizing a dataset collected during the Covid-19 pandemic in Saudi Arabia. The data was collected from 3017 participants from all regions of the Kingdom via an online survey containing questions to identify factors influencing anxiety levels, followed by questions from the GAD-7, a screening tool for Generalized Anxiety Disorders. The prediction models were built using the Support Vector Machine classifier for its robust outcomes in medical-related data and the J48 Decision Tree for its interpretability and comprehensibility. Experimental results demonstrated promising results for the early classification of two-class and three-class anxiety problems. As for comparing Support Vector Machine and J48, the Support Vector Machine classifier outperformed the J48 Decision Tree by attaining a classification accuracy of 100%, precision of 1.0, recall of 1.0, and f-measure of 1.0 using 10 features.

Keywords: Anxiety; COVID-19; Machine learning; Pandemic; Saudi Arabia.