Leading Predictors of COVID-19-Related Poor Mental Health in Adult Asian Indians: An Application of Extreme Gradient Boosting and Shapley Additive Explanations

Abstract

During the COVID-19 pandemic, an increase in poor mental health among Asian Indians was observed in the United States. However, the leading predictors of poor mental health during the COVID-19 pandemic in Asian Indians remained unknown. A cross-sectional online survey was administered to self-identified Asian Indians aged 18 and older (N = 289). Survey collected information on demographic and socio-economic characteristics and the COVID-19 burden. Two novel machine learning techniques-eXtreme Gradient Boosting and Shapley Additive exPlanations (SHAP) were used to identify the leading predictors and explain their associations with poor mental health. A majority of the study participants were female (65.1%), below 50 years of age (73.3%), and had income ≥ $75,000 (81.0%). The six leading predictors of poor mental health among Asian Indians were sleep disturbance, age, general health, income, wearing a mask, and self-reported discrimination. SHAP plots indicated that higher age, wearing a mask, and maintaining social distancing all the time were negatively associated with poor mental health while having sleep disturbance and imputed income levels were positively associated with poor mental health. The model performance metrics indicated high accuracy (0.77), precision (0.78), F1 score (0.77), recall (0.77), and AUROC (0.87). Nearly one in two adults reported poor mental health, and one in five reported sleep disturbance. Findings from our study suggest a paradoxical relationship between income and poor mental health; further studies are needed to confirm our study findings. Sleep disturbance and perceived discrimination can be targeted through tailored intervention to reduce the risk of poor mental health in Asian Indians.

Identification of predictive patient characteristics for assessing the probability of COVID-19 in-hospital mortality

“…Data-driven investigation of COVID-19 mortality employing machine learning tools (such as XGBoost) and feature explanation methods (SHAP values) has been demonstrated before for the processing of clinical laboratory results [14][15][16], for predicting death outcomes [17][18][19], demonstrating links between socioeconomic disparities and COVID-19 spread [20], and showing the impact of COVID-19 on mental health in self-identified Asian Indians in the USA [21]. Several other articles using SHAP were reviewed recently by Bottino et al [22].…”

The relationships of preventive behaviors and psychological resilience with depression, anxiety, and stress among university students during the COVID-19 pandemic: A two-wave longitudinal study in Shandong Province, China

“…Depression severity was classified into five categories: normal (0-9), mild (10)(11)(12)(13), moderate (14-20), severe (21)(22)(23)(24)(25)(26)(27), and very severe (28+). Similarly, for anxiety, the categories were normal (0-7), mild (8)(9), moderate (10)(11)(12)(13)(14), severe (15)(16)(17)(18)(19), and very severe (20+). Stress scores were categorized as normal (0-14), mild (15)(16)(17)(18), moderate (19)(20)(21)(22)(23)(24)(25), severe (26)(27)(28)(29)(30)(31)(32)(33), or very severe (34+) (37).…”

“…Similarly, for anxiety, the categories were normal (0-7), mild (8)(9), moderate (10)(11)(12)(13)(14), severe (15)(16)(17)(18)(19), and very severe (20+). Stress scores were categorized as normal (0-14), mild (15)(16)(17)(18), moderate (19)(20)(21)(22)(23)(24)(25), severe (26)(27)(28)(29)(30)(31)(32)(33), or very severe (34+) (37). The scores obtained on these three subscales were dichotomized (38).…”

“…A study by Green et al with university students in Pakistan showed that higher levels of fear of COVID-19 were linked to greater adherence to COVID-19 preventive behaviors ( 17 ). However, Ikram et al showed that wearing a mask was a predictor of poor mental health among Asian Indians ( 18 ). In contrast, Abir et al found that Bangladeshis who did not wear masks and who did not comply with WHO precautions were more likely to report psychological ill health ( 19 ).…”

Identification of predictive patient characteristics for assessing the probability of COVID-19 in-hospital mortality

“…Data-driven investigation of COVID-19 mortality employing machine learning tools (such as XGBoost) and feature explanation methods (SHAP values) has been demonstrated before for the processing of clinical laboratory results [9][10][11], for predicting death outcomes [12][13][14], demonstrating links between socioeconomic disparities and COVID-19 spread [15], and showing the impact of COVID-19 on mental health in selfidentified Asian Indians in the USA [16]. Several other articles using SHAP were reviewed recently by Bottino et al [17].…”