Nonlinear Associations between Medical Expenditure, Perceived Medical Attitude, and Sociodemographics, and Older Adults’ Self-Rated Health in China: Applying the Extreme Gradient Boosting Model

Abstract

Background: although China’s total health expenditure has been dramatically increased so that the country can cope with its aging population, inequalities among individuals in terms of their medical expenditures (relative to their income level) have exacerbated health problems among older adults. This study aims to examine the nonlinear associations between each of medical expenditure, perceived medical attitude, and sociodemographics, and older adults’ self-rated health (SRH); it does so by using data from the 2018 China Family Panel Studies survey. Method: we used the extreme gradient boosting model to explore the nonlinear association between various factors and older adults’ SRH outcomes. We then conducted partial dependence plots to examine the threshold effects of each factor on older adults’ SRH. Results: older adults’ medical expenditure exceeded their overall income. Body mass index (BMI) and personal health expenditure play an essential role in predicting older adults’ SRH outcomes. We found older adult age, physical exercise status, and residential location to be robust predictors of SRH outcomes in older adults. Partial dependence plots of the results visualized the nonlinear association between variables and the threshold effects of factors on older adults’ SRH outcomes. Conclusions: findings from this study underscore the importance of medical expenditure, perceived medical attitudes, and BMI as important predictors of health benefits in older adults. The potential threshold effects of medical expenditure on older adults’ SRH outcomes provide a better understanding of the formation of appropriate medical policy interventions by balancing the government and personal medical expenditure to promote health benefits among older adults.

Relationships between the Physical Activity Intensity and the Medical Expenditure of Middle-Aged and Elderly People: Parsing from the CHARLS Database

“…Our results showed that drinking can reduce medical expenditures: the outpatient expenditure decreased by 11.5% (p = 0.044); inpatient expenditure decreased by 6.8% (p = 0.032); and total medical expenditure decreased by 17.1% (p = 0.040). This finding is consistent with the research conclusion of Song et al (2020) [36]. In addition, the outpatient expenditure, inpatient expenditure, and total medical expenditure of urban residents were all higher than rural residents, and the results were at the significance level of 1%.…”

“…Wang et al (2019) [33], Su et al (2020) [34], and Song et al (2020) [35], respectively, confirmed that physical activity was associated with lower medical expenditure in middle-aged and elderly patients with coronary heart disease, diabetes mellitus, and cardiovascular disease. In addition, Liang et al (2022) [36] used the extreme gradient-boosting model and found physical exercise status to be a robust predictor of self-rated health (SRH) outcomes in older adults, based on the data from the 2018 China Family Panel Studies survey. However, compared with the research in other countries, especially in Europe and the United States, the depth of relevant research and analysis methods in China still needs to be further explored.…”

The Mediation Effect of Perceived Attitudes toward Medical Service on the Association between Public Satisfaction with the Overall Medical Service and Self-Rated Health among the General Population in China: A Cross-Sectional Study

“…Future studies should pay special attention to examining specific health indicators once the data are available. Nonlinear associations between perceived attitudes toward medical services and health benefits are encouraged to explore findings among different population groups by conducting machine learning and deep learning approaches [ 56 , 90 ].…”

Machine Learning and Causal Approaches to Predict Readmissions and Its Economic Consequences Among Canadian Patients With Heart Disease: Retrospective Study

“…LGBM and XGB presented a relative advantage with regard to efficient computation and high accuracy on a wide range of data sets, including those with high dimensionality and categorical features [22][23][24][25]. Both methods required sequential decision tree generation via error combination or level-wise tree growth.…”