Partner Relationships, Hopelessness, and Health Status Strongly Predict Maternal Well-Being During the COVID-19 Pandemic: A Machine Learning Approach (preprint)

ABSTRACT

No recent studies have explicitly focused on predicting the well-being of pregnant women during the novel coronavirus disease (COVID-19) pandemic. This study used data from an extensive online survey in Japan to examine predictors of the subjective well-being of pregnant women during the COVID-19 pandemic. We developed and validated a machine learning model using data from 400 pregnant women obtained in 2020 to identify three factors that predict subjective well-being. The results confirmed that the model could predict pregnant women's subjective well-being with 84% accuracy. The variables that contributed significantly to this prediction were "partner help," "hopelessness," and "health status." The machine learning model was built again using these three factors, trained and validated using data from 400 pregnant women in 2020, and predicted using data from 1,791 pregnant women in 2021, with an accuracy of 88%. These were also significant risk factors for subjective well-being in regression analysis adjusted for maternal age, region, parity, education level, and presence of mental illness. This model would help identify pregnant women with low subjective well-being during the COVID-19 pandemic, and appropriate interventions can then be initiated.