Burden and risk factors of depression in seniors from 1990 to 2021: a multi-database study based on EMR mining methods

Abstract

Depression in seniors is a growing public health concern worldwide. Despite the rising prevalence of depression in this demographic, comprehensive data on its burden and trends over an extended period remain limited. This study aims to assess the trends in the burden of depression among seniors from 1990 to 2021, utilizing the Global Burden of Diseases, Injuries, and Risk Factors Study (GBD) database, and to further explore the risk factors using China Health and Retirement Longitudinal Study (CHARLS) database and National Health and Nutrition Examination Survey (NHANES) database. We utilized data from the GBD 2021, reporting incidence and disability-adjusted life years (DALYs) per 100,000 population, average annual percentage change (AAPC), and risk factors at global, and regional levels. Trends were analyzed by age, sex, and social development index. Joinpoint regression identified significant changes in global trends. We established an interpretable machine learning (ML) model with high efficiency and robustness that identifies depression based on CHARLS (2015, 2018, &2020) and NHANES (2013-2020.3). We chose a best-performing eXtreme Gradient Boosting (XGB) with Genetic Algorithm (GA) for identification, and used SHapley Additive exPlanation (SHAP) to illustrate the potential risk factors. From 1990 to 2021, the overall global incidence of depression among seniors remained broadly stable (AAPC 0.01, 95% CI -0.07 to 0.08), although marked changes emerged in specific regions and population subgroups. The incidence of depressive disorders increased globally for males (AAPC 0.06 [95% CI -0.02 to 0.15]) while it decreased for females (AAPC -0.01 [95% CI -0.09 to 0.07]). Regional analysis showed the highest incidence rates in low-SDI countries, while middle-SDI countries experienced the most significant increases in the burden of depression (AAPC 0.25 [95% CI 0.17 to 0.34]). Risk factor analysis using machine learning models identified key predictors of depression in elderly populations in both China and the United States. The burden of depression among seniors has significantly shifted globally, with marked regional and demographic variations. These findings underscore the urgent need for targeted interventions, policy modifications, and early screening programs to address the rising burden of depression in this vulnerable age group. The use of advanced machine learning models provides valuable insights into the risk factors, facilitating the development of more effective and tailored intervention strategies.

Fig. 1. Joinpoint regression analysis of depressive disorders among adults aged 60 years and older, 1990–2021.

The figure shows prevalence, incidence, and DALYs (per 100,000 population). Red dots indicate significant joinpoints, black dots represent observed values, purple lines denote fitted regression trends, and dashed vertical lines mark joinpoint years. APC values are annotated.

Fig. 2. Global distribution and temporal trends of depressive disorders, 1990–2021.

The maps display the incidence and DALYs of depressive disorders in 2021 (per 100,000 population), as well as the AAPC in incidence and DALYs from 1990 to 2021. Color gradients represent burden levels or AAPC values across regions.

Fig. 3. Relative contribution of risk factors to depressive disorder DALYs in 1990 and 2021.

Concentric ring plots show the proportion of DALYs attributable to selected risk factors globally, in the United States, and in China. Inner to outer rings represent China, the United States, and global estimates, respectively. Risk factors include intimate partner violence, childhood sexual abuse, bullying victimization, behavioral risks, and combined categories.

Fig. 4. SHAP analysis of predictors of depressive disorders in CHARLS and NHANES datasets.

The figure presents SHAP summary and decision plots derived from machine-learning models. Colors indicate feature values (red = high, blue = low), and horizontal positions represent the contribution of each feature to model outputs.