Assessing the Mental Health Impact of COVID-19 on the US Population: A Large-Scale Survey Analysis Using SMOTE
Open Access
- 17 May 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 298-303
Abstract
The coronavirus (COVID-19) outbreak, recognized as one of the deadliest health crises in recent history, swiftly affected over 200 countries. The pandemic has posed complex challenges, specifically affected not only the rising number of cases but also deeply influenced individual mental health. This research explores the significant mental health implications of the COVID-19 pandemic on the US population, analyzed through a large-scale survey of 25,136 participants across various ages, economic backgrounds, and chronic disease status. We categorized mental health status into three risk levels: low, moderate, and high, based on the key features influencing stress levels. Notably, our findings reveal that the age group 25-54 years exhibited higher anxiety levels compared to other age groups. The implementation of Extreme Gradient Boosting (XGBoost) with Synthetic Minority Over-sampling (SMOTE) Technique for balancing data yielded impressive accuracy rates: 94.55% for high risk, 90.73% for moderate risk, and 77.77% for low risk, respectively. These results significantly outperformed the Random Forest (RF) model in both imbalanced and SMOTE balanced datasets. Furthermore, the study identified high obesity and chronic diseases, such as bronchitis, as factors exacerbating stress levels. This research contributes valuable insights to the mental health condition prediction during COVID-19 pandemic by underlining the importance of targeted interventions for high-risk groups.Keywords
Funding Information
- National Science and Technology Council (MOST 111-2628-E-038 -001 -MY2)
This publication has 8 references indexed in Scilit:
- Investigating the mental health of university students during the COVID-19 pandemic in a UK university: a machine learning approach using feature permutation importanceBrain Informatics, 2023
- Machine learning approaches for predicting suicidal behaviors among university students in Bangladesh during the COVID-19 pandemic: A cross-sectional studyMedicine, 2023
- Mental Health in Tech: Analysis of Workplace Risk Factors and Impact of COVID-19SN Computer Science, 2023
- A machine learning analysis of COVID-19 mental health dataScientific Reports, 2022
- COVID-19 Vaccination and Mental Health: A Difference-In-Difference Analysis of the Understanding America StudyAmerican Journal of Preventive Medicine, 2021
- Mental Health of COVID-19 Patients—A Cross-Sectional Survey in Saudi ArabiaInternational Journal of Environmental Research and Public Health, 2021
- Learning the Mental Health Impact of COVID-19 in the United States With Explainable Artificial Intelligence: Observational StudyJMIR Mental Health, 2021
- Loneliness in the UK during the COVID-19 pandemic: Cross-sectional results from the COVID-19 Psychological Wellbeing StudyPLOS ONE, 2020