A research group led by Prof. LIU Zhiyong from the School of Medicine and Health Management at Tongji Medical College, Huazhong University of Science and Technology (HUST), has published their results in npj Digital Medicine that used machine learning to identify key predictors of depressive symptoms in middle-aged and older adults across multiple countries. The article, titled “Determinants of depressive symptoms in multinational middle-aged and older adults,” appeared in August 2025 issue of the periodical.

The study employed six ensemble-learning algorithms and SHapley Additive exPlanations (SHAP) to analyze a multinational cohort database, creating an interpretable prediction model for depression. It specifically addressed variations linked to income and gender, highlighting the significant roles that socio-economic status, health behaviors, and physiological factors play in shaping mental health outcomes.

These findings provide valuable insights for designing more equitable and targeted depression-prevention strategies on a global scale.

LU Can, a master’s degree student at School of Medicine and Health Management, and Wan Shenwei, a doctoral candidate at School of Agricultural Economics and Rural Development of Renmin University of China, served as co-first authors. Prof. LIU was the corresponding author.