Staffordshire University logo
STORE - Staffordshire Online Repository

Evaluation of COVID-19 pandemic on components of social and mental health using machine learning, analysing United States data in 2020

Sadegh-Zadeh, Seyed-Ali, Bahrami, Mahboobe, Najafi, Amirreza, Asgari-Ahi, Meisam, Campion, Russell and Hajiyavand, Amir M. (2022) Evaluation of COVID-19 pandemic on components of social and mental health using machine learning, analysing United States data in 2020. Frontiers in Psychiatry, 13. ISSN 1664-0640

fpsyt-13-933439.pdf - Publisher's typeset copy
Available under License Creative Commons Attribution 4.0 International (CC BY 4.0) .

Download (19MB) | Preview

Abstract or description

Background: COVID-19 was named a global pandemic by the World Health Organization in March 2020. Governments across the world issued various restrictions such as staying at home. These restrictions significantly influenced mental health worldwide. This study aims to document the prevalence of mental health problems and their relationship with the quality and quantity of social relationships affected by the pandemic during the United States national lockdown.

Methods: Sample data was employed from the COVID-19 Impact Survey on April 20–26, 2020, May 4–10, 2020, and May 30–June 8, 2020 from United States Dataset. A total number of 8790, 8975, and 7506 adults participated in this study for April, May and June, respectively. Participants’ mental health evaluations were compared clinically by looking at the quantity and quality of their social ties before and during the pandemic using machine learning techniques. To predict relationships between COVID-19 mental health and demographic and social factors, we employed random forest, support vector machine, Naive Bayes, and logistic regression.

Results: The result for each contributing feature has been analyzed separately in detail. On the other hand, the influence of each feature was studied to evaluate the impact of COVID-19 on mental health. The overall result of our research indicates that people who had previously been diagnosed with any type of mental illness were most affected by the new constraints during the pandemic. These people were among the most vulnerable due to the imposed changes in lifestyle.

Conclusion: This study estimates the occurrence of mental illness among adults with and without a history of mental disease during the COVID-19 preventative limitations. With the persistence of quarantine limitations, the prevalence of psychiatric issues grew. In the third survey, which was done under quarantine or house restrictions, mental health problems and acute stress reactions were substantially greater than in the prior two surveys. The findings of the study reveal that more focused messaging and support are needed for those with a history of mental illness throughout the implementation of restrictions.

Item Type: Article
Uncontrolled Keywords: mental health, COVID-19 pandemic, social behaviours, psychiatry issues, machine learning, statistic analysis, prediction model
Faculty: School of Digital, Technologies and Arts > Computer Science, AI and Robotics
Depositing User: Ali SADEGH ZADEH
Date Deposited: 02 Sep 2022 09:37
Last Modified: 02 Sep 2022 09:37

Actions (login required)

View Item View Item

DisabledGo Staffordshire University is a recognised   Investor in People. Sustain Staffs
Legal | Freedom of Information | Site Map | Job Vacancies
Staffordshire University, College Road, Stoke-on-Trent, Staffordshire ST4 2DE t: +44 (0)1782 294000