Early detection of potential depression among elderly people is conducive for timely preventive intervention and clinical care to improve quality of life. Therefore, depression prediction considering sequential progression patterns in elderly needs to be further explored. We selected 1,538 elderly people from Chinese Longitudinal Healthy Longevity Study (CLHLS) wave 3-7 survey. Long short-term memory (LSTM) and six machine learning (ML) models were used to predict different depression risk factors and the depression risks in the elderly population in the next two years. Receiver operating curve (ROC) and decision curve analysis (DCA) were used to evaluate the prediction accuracy of the reference model and ML models. The area under the ROC curve (AUC) values of logistic regression with lasso regularisation (AUC=0.629, p-value=0.020) was the highest among ML models. DCA results showed that the net benefit of six ML models was similar (threshold: 0.00-0.10), the net benefit of lasso regression was the largest (threshold: 0.10-0.17 and 0.22-0.25), and the net benefit of DNN was the largest (threshold: 0.17-0.22 and 0.25-0.40). In two ML models, activities of daily living (ADL)/ instrumental ADL (IADL), self-rated health, marital status, arthritis, and number of cohabiting were the most important predictors for elderly with depression. The retrospective waves used in the LSTM model need to be further increased. The decision support system based on the proposed LSTM+ML model may be very valuable for doctors, nurses and community medical providers for early diagnosis and intervention.

Background: Previous studies have demonstrated the effect of socioeconomic status on the health status of the elderly. Nevertheless, the specific dimensions of the effect and the mechanism await further investigation. In this study, socioeconomic status was divided into three dimensions and we used social participation as the mediation variable to investigate the specific path of effect. Methods: Using the 2018 Waves of Chinese Longitudinal Healthy Longevity Survey (CLHLS) dataset, a total of 10,197 effective samples of the elderly over 65 years old were screened out. Socioeconomic status included income, education level, and main occupation before retirement. The physical health and mental health of the elderly was measured by the Instrumental Activities of Daily Living Scale and the Minimum Mental State Examination, respectively. The social participation of the elderly was the mediation variable, including group exercise, organized social activities and interacting with friends. Omnibus mediation effect analysis was adopted to examine the mediation effect and mediation analysis was completed using the SPSS PROCESS program. Results: First, the results showed that when the income gap between the elderly reached a certain level, there was a significant difference in health status. Significant differences existed in health status amongst with different education levels. There was no sufficient evidence to show that occupation has a significant effect on the physical health. But when the dependent variable was mental health, the effect was significant. Second, group exercise mediated 64.11% (a_ib = 0.24, 95% CI [0.17,0.3]) and up to 20.44% (a_ib = 0.12, 95% CI [0.07,0.17]) of the disparity in physical and mental health due to income gap, respectively. And it could mediate the effect up to 56.30% (a_ib = 0.62, 95% CI [0.52,0.73]) and 17.87% (a_ib = 0.50, 95% CI [0.4,0.61]) of education on physical and mental health status, respectively. The proportion of relative mediation effect of occupation was up to 28.74% (a_ib = 0.19, 95% CI [0.13,0.25]) on mental health. Interacting with friends mediated only on the path that the education affected the health status of the elderly. The proportion was up to 33.72% (a_ib = 0.29, 95% CI [0.16,0.44]). The relative mediation effect of organized social activities on the health gap caused by income or education level gap was significant at some levels. The proportion was up to 21.20% (a_ib = 0.33, 95% CI [0.26,0.4]). Conclusion: The SES of the elderly including relatively large income gap, different education levels and occupational categories could indeed have a significant effect on health status of the elderly, and the reason why this effect existed could be partly explained by the mediation effect of social participation. Policymakers should pay more attention to the social participation of the elderly.

This study aimed to explore the impact of social participation (SP) on physical functioning and depression among empty-nest elderly taking part in the fourth wave of the China Health and Retirement Longitudinal Survey (CHARLS, 2018). The instrumental variable (IV) method and propensity score matching (PSM) method were used to analyse the impact of SP. The two-stage regression results of the IV method showed that SP has a significant negative impact on the physical functioning scores of empty-nest elderly (β = −3.539, p < 0.001) and non-empty-nest elderly (β = −4.703, p < 0.001), and SP has a significant negative impact on the depression scores of empty-nest elderly (β = −2.404, p < 0.001) and non-empty-nest elderly (β = −1.957, p < 0.001). The results of the PSM method were basically consistent with the IV method. Compared with non-empty-nest elderly, SP had more positive effects on the depression of empty-nest elderly (Wald χ² = 6.62, p = 0.010). Providing a friendly and supportive environment for the SP of empty-nest elderly was an important measure to promote healthy ageing. Targeted SP may be one of the greatest opportunities to improve the mental health of empty-nest elderly.

Background: Chronic disease knowledge is an important prerequisite for an individual to implement behavioural changes towards the prevention and control of chronic diseases (CDs). Limited information is available about the relationship between different levels of health services and CD knowledge among rural residents with CDs. This research explores the distribution characteristics of CD knowledge and its determinants among chronically ill adults in rural China according to the aspects of patients and health service providers. Methods: A cross-sectional study was undertaken to estimate distribution characteristics of CD knowledge and collect data of socio-demographic characteristics, healthcare institutions attendances, duration of illness, and family history of CDs. Participants were 1060 rural adults with hypertension or type II diabetes. Correct responses to 12 questions were summed into a total knowledge score, and participants were divided into an adequate health knowledge group (score ≥ 6) or an inadequate health knowledge group (score < 5). Logistic regression was used determine the predictors of adequate CD health knowledge. Results: The mean age of participants was 61.34 years (SD = 10 years). Out of a possible 12, the median score on the CD knowledge questionnaire was 3.0. About 25% of participants were classified as having adequate CD knowledge. Those who had a family history and/or long duration of CDs were more likely to have adequate health knowledge. Participants who received CD health information and self-care instructions from their physicians had 2.67 and 13.34 times greater odds of possessing adequate health knowledge than those who received no information, respectively. Adequate CD knowledge was strongly associated with regular check-ups, especially for those who attended township hospitals (OR = 40.17). Conclusions: Having regular check-ups at a fixed healthcare institution and receiving health information from physicians are important measures for increasing CD knowledge among rural adults with CDs. Township hospitals are the most effective settings for health education. It is important to develop an effective community-based prevention and control mechanism for CDs. This requires township hospitals to take a leading role in improving CD knowledge among chronically ill patients, and enhancing implementation of health education in rural China.

Objectives In this study, we aim to evaluate the effect of urban and rural resident medical insurance scheme (URRMI) on the utilisation of medical services by urban and rural residents in the four pilot provinces. Setting and participants The sample used in this study is 13 305 individuals, including 2620 in the treatment group and 10 685 in the control group, from the 2011 and 2015 surveys of China Health and Retirement Longitudinal Study. Outcome measures Propensity score matching and difference-in-differences regression approach (PSM-DID) is used in the study. First, we match the baseline data by using kernel matching. Then, the average treatment effect of the four outcome variables are analysed by using the DID model. Finally, the robustness of the PSM-DID estimation is tested by simple model and radius matching. Results Kernel matching have improved the overall balance after matching. The URRMI policy has significantly reduced the need-but-not outpatient care and significantly increased outpatient care cost and inpatient care cost for rural residents, with DID value of −0.271, 0.090 and 0.256, respectively. After robustness test, the DID competing results of four outcome variables are consistent. Conclusions URRMI has a limited effect on the utilisation of medical and health services by all residents, but the effect on rural residents is obvious. The government should establish a unified or income-matching payment standard to prevent, control the use of medical insurance funds and increase its efforts to implement URRMI integration in more regions to improve overall fundraising levels.

Background: A healthcare system refers to a typical network production system. Network data envelopment analysis (DEA) show an advantage than traditional DEA in measure the efficiency of healthcare systems. This paper utilized network data envelopment analysis to evaluate the overall and two substage efficiencies of China’s healthcare system in each of its province after the implementation of the healthcare reform. Tobit regression was performed to analyze the factors that affect the overall efficiency of healthcare systems in the provinces of China. Methods: Network DEA were obtained on MaxDEA 7.0 software, and the results of Tobit regression analysis were obtained on StataSE 15 software. The data for this study were acquired from the China health statistics yearbook (2009–2018) and official websites of databases of Chinese national bureau. Results: Tobit regression reveals that regions and government health expenditure effect the efficiency of the healthcare system in a positive way: the number of high education enrollment per 100,000 inhabitants, the number of public hospital, and social health expenditure effect the efficiency of healthcare system were negative. Conclusion: Some provincial overall efficiency has fluctuating increased, while other provincial has fluctuating decreased, and the average overall efficiency scores were fluctuations increase.