This research, presented by Xu et. al, performed a multidata base study that used artificial intelligence XGBoost and SHAP to examine the prevalence of depressive symptoms in older populations nationally and across the globe. The researchers engaged in EMR mining methods pulling data from the Global Burden of Disease (GBD 2021), the China Health and Retirement Longitudinal Study (CHARLS) and the National Health and Nutrition Examination Survey (NHANES) in the United States. Not only that, XGBoost was programmed to function as a tree based machine learning while SHapley Additive exPlanations (SHAP) allowed for an idea of how much each variable actually influenced depression outcomes. The overall average annual percent change of new depression cases found in seniors across the years 1990-2021 was not significant (AAPC = 0.01). However, certain trends such as the increased incidence of depression in males compared to females, AAPC is 0.06 and 0.01 respectively, or the fact that males made up 63% of new depression cases were noted. Xu et. al acknowledged the incidence of COVID-19 as an important disruptor of the data but also the fact that patients living with depression are becoming more prevalent than those simply experiencing it’s symptoms.