Machine learning analysis of cross-sectional baseline data from the China Longitudinal Aging Society Survey – Harvard China Health Partnership Harvard China Health Collaboration Project


objective

This study aimed to investigate the causal effects of physical disability and number of comorbid chronic diseases on depressive symptoms in a Chinese elderly population.

Method

Cross-sectional baseline data were obtained from the China Longitudinal Ageing Society Survey, a stratified multistage probability sampling survey covering 28 of China’s 31 provinces conducted in 2014. The survey included 7496 subjects aged 60 years or older who answered questions on depressive symptoms and other independent variables of interest. The causal effects of physical disability and number of comorbid chronic diseases on depressive symptoms were analyzed using machine learning conditional mean treatment effect methods. Adjustments for the causal effect model were made for age, sex, place of residence, marital status, education level, ethnicity, wealth quintile, and other factors.

result

Physical disability and number of comorbid chronic conditions were causally related to depressive symptoms: subjects with one or more functional disabilities increased the odds of depressive symptoms by 22% (95% CI 19% to 24%). Subjects with one chronic condition and subjects with two or more chronic conditions increased the odds of depressive symptoms by 13% (95% CI 10% to 15%) and 20% (95% CI 18% to 22%), respectively.

Conclusion

This study provides evidence that the presence of one or more functional limitations influences the manifestation of depressive symptoms in older adults. Our findings are valuable for developing programs to identify older adults with physical disabilities and comorbid chronic diseases and provide early intervention.



Source link