Predicting psychological resilience in older adults during the COVID-19 pandemic: a machine learning approach.

BACKGROUND AND OBJECTIVES: This study predicted psychological resilience among older adults during the COVID-19 pandemic based on a comprehensive, theory-informed set of factors at the individual, interpersonal, and community levels.

RESEARCH DESIGN AND METHODS: The study sample consisted of 3,364 individuals who completed the 2016 and 2020 Leave-Behind Questionnaire from the Health and Retirement Study. A longitudinal design was used, with pre-pandemic predictors measured in 2016 and resilience measured in 2020. Three machine learning algorithms (LASSO, Ridge, and Random Forest) were trained with five-fold cross-validation. SHAP values were used to interpret feature importance.

RESULTS: LASSO had the best model fit (RMSE = 0.873; R2 = 0.195). Twenty-four features emerged as important predictors. Psychological dispositions and resources, including four Big Five personality traits, optimism, purpose in life, life satisfaction, and religiosity, were strong predictors of resilience. Pre-pandemic social participation, social support, and neighborhood cohesion were also positively associated with resilience. Several indicators of technology adaptation, particularly learning a new device, and socio-behavioral adaptation during the pandemic were additional positive predictors of resilience. In contrast, older subjective age was linked to lower resilience. Several non-linear and interaction effects were identified.

DISCUSSION AND IMPLICATIONS: Study findings underscore the complex, multifactorial nature of resilience and demonstrate the value of theory-informed data science approach in advancing our understanding of resilience. Addressing digital inequities and fostering supportive social relationships and community participation are potential targets for population-based strategies as we face increasing threats from disasters.