Identifying Predictors of Psychological Distress During COVID-19: A Machine Learning Approach

Frontiers in Psychology

article

Tracy A. Prout¹  Sigal Zilcha-Mano²  Katie Aafjes-van Doorn³  Vera Békés³  Isabelle Christman-Cohen¹  Kathryn Whistler¹  Thomas Kui¹  Mariagrazia Di Giuseppe⁴ 

[1] School-Clinical Child Psychology Program, Ferkauf Graduate School of Psychology, Yeshiva University, United States;Department of Psychology, University of Haifa;Clinical Psychology Program, Ferkauf Graduate School of Psychology, Yeshiva University, United States;Department of Surgical, Medical and Molecular Pathology and of Critical Care Medicine, University of Pisa

关键词: COVID-19 pandemic;    emotion regulation;    somatization;    machine learning;    anxiety;    depression;    post-traumatic stress;    defense mechanisms;   

DOI  :  10.3389/fpsyg.2020.586202

学科分类：社会科学、人文和艺术（综合）

来源: Frontiers

【 摘 要 】

Scientific understanding about the psychological impact of the COVID-19 global pandemic is in its nascent stage. Prior research suggests that demographic factors, such as gender and age, are associated with greater distress during a global health crisis. Less is known about how emotion regulation impacts levels of distress during a pandemic. The present study aimed to identify predictors of psychological distress during the COVID-19 pandemic. Participants ( N = 2,787) provided demographics, history of adverse childhood experiences, current coping strategies (use of implicit and explicit emotion regulation), and current psychological distress. The overall prevalence of clinical levels of anxiety, depression, and post-traumatic stress was higher than the prevalence outside a pandemic and was higher than rates reported among healthcare workers and survivors of severe acute respiratory syndrome. Younger participants (<45 years), women, and non-binary individuals reported higher prevalence of symptoms across all measures of distress. A random forest machine learning algorithm was used to identify the strongest predictors of distress. Regression trees were developed to identify individuals at greater risk for anxiety, depression, and post-traumatic stress. Somatization and less reliance on adaptive defense mechanisms were associated with greater distress. These findings highlight the importance of assessing individuals’ physical experiences of psychological distress and emotion regulation strategies to help mental health providers tailor assessments and treatment during a global health crisis.

【 授权许可】

CC BY