Background: Late-life depression is a critical public health concern, particularly among older adults with chronic multimorbidity. Existing studies often focus on single-disease associations, neglecting the complex interplay of coexisting conditions. Understanding how multimorbidity patterns contribute to depression risk and identifying high-risk subgroups through integrated statistical and machine learning approaches remain underexplored, limiting targeted prevention strategies. Methods: Using data from the China Health and Retirement Longitudinal Study (CHARLS), latent class analysis (LCA) was employed to cluster multimorbidity patterns. Associations between these patterns and depression were analyzed using multivariable logistic regression, while predictive performance and interaction effects were evaluated via an XGBoost machine learning model. Results: Four distinct multimorbidity patterns were identified: cardio-metabolic, digestive–joint, respiratory, and cardiovascular–digestive pattern. All clusters showed significant independent associations with depression, with the cardiovascular–digestive pattern exhibiting the strongest association (OR = 4.56). However, the digestive–joint pattern demonstrated the highest predictive effects for depression. Sociodemographic factors—low income, limited education, female gender, and rural residence—emerged as robust predictors, amplifying depression risk in older adults with multimorbidity. Conclusions: This study bridges epidemiological insights with predictive analytics to inform depression risk stratification. We recommend routine depression screening for all individuals with cardiovascular–digestive diseases and prioritize screening for women with digestive–joint diseases. Additionally, low-income and rural-dwelling older adults with chronic conditions warrant heightened clinical vigilance. These findings provide a framework for integrating multimorbidity profiling into depression prevention protocols, addressing both biological and socioeconomic determinants.

Considering the remarkable population aging in China, more researchers pay attention to the health condition of elderly people. However, limited to the large amount of miscellaneous health examination data, a systematic method to quantify and evaluate the health condition of elderly people is still lacking. In this study, a Z ‐score‐based improved Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS) method was introduced by considering the omission of the positive or negative ideal solution of the original data. Then, the health conditions of elderly people were quantified and evaluated according to 1672 elderly health examination reports. Meanwhile, the influence factors that impact elderly people’s health conditions were also discussed. The analysis results demonstrated a positive impact of social development on elderly people’s health conditions. Oppositely, the influence of age and sex might be slight. This study could contribute to the characterization of the health condition of elderly people residing in Harbin, as well as its influence factors.