Heterogeneity in public health service utilization and its relationship with social integration among older adult migrants in China: a latent class analysis.

Background: The older adult migrant population in China is on the rise, which presents challenges for the national public health service system. However, the heterogeneity of public health service utilization and its relationship with social integration among the older adult migrant population remains unclear. This study aims to explore the heterogeneity the public health service utilization and how it relates to their social integration. Methods: A total of 6,178 older adult migrants from the China Migrants Dynamic Survey (CMDS) in 2017 were included in this study. Exploratory factor analysis was used to categorize social integration into four dimensions. Latent class analysis (LCA) was used to identify different sub-groups of public health service utilization. ANOVA and multivariate logistic regression were used to determine the characteristics of different sub-groups. Results: Three potential classes of public health service utilization were identified: low utilization of basic public health services class (N = 3,264,52.756%), medium utilization of basic public health services class (N = 1,743,28.172%), and high utilization of basic public health services class (N = 1,180,19.072%). Gender, education, extent of mobility, and move alone or not, flow time were all predictors of the class of public health service utilization. There were significant differences in social integration across potential categories (p<0.0001). Conclusion: The utilization of public health services of the older adult migrants is affected by many aspects. Social integration deserves attention as a significant influencing factor in the utilization of public health services. The government should pay attention to the characteristics of the older adult migrants and formulate relevant policies in a targeted manner in order to improve the utilization of public health services of the older adult migrants.

Profiles of physical frailty, social frailty, and cognitive impairment among older adults in rural areas of China: a latent profile analysis.

Background: As China rapidly ages, it has now become a deeply aging society with the largest number of older individuals in the world. The issue is particularly severe in rural areas. With the aging population growing and the older population expanding, health problems are becoming more prevalent among older individuals, particularly frailty and cognitive impairments. This study aimed to identify the profiles of physical frailty, social frailty, and cognitive impairment among older adults and explore the influencing factors. Methods: In this cross-sectional study, participants were recruited from six villages in four cities in Shandong Province, China from July to October 2023 through cluster random sampling. Latent profile analysis was used to determine the profiles of physical frailty, social frailty, and cognitive impairment. Chi-square tests and Mann-Whitney U tests were used for univariate analysis, while binary logistic regression was used to analyze the related factors. Results: Seven hundred and sixty-nine older adult care in rural areas showed two profiles: the "high cognitive function and low frailty" group (73.7%, n = 567) and the "low cognitive function and high frailty" group (26.3%, n = 202). A binary logistic regression found that older people were more likely to be aged 80 or older (OR = 2.253, p = 0.029), have a low income level (OR = 1.051, p = 0.007), have one or two (OR = 2.287, p = 0.004), or more than three chronic diseases (OR = 3.092, p = 0.002), and report moderate (OR = 3.406, p = 0.024) or poor health status (OR = 9.085, p < 0.001) in the "low cognitive function and high frailty" group. Meanwhile, older adults who have completed high school (OR = 0.428, p = 0.005) or junior college and above (OR = 0.208, p = 0.009), and engage in adequate physical activity (OR = 0.319, p < 0.001) were more likely to be in the "high cognitive function and low frailty" group. Conclusion: In the future, medical professors should increasingly prioritize promptly identifying and intervening in cognitive decline and frailty status in older individuals without delay.

Sign language recognition based on dual-path background erasure convolutional neural network.

Sign language is an important way to provide expression information to people with hearing and speaking disabilities. Therefore, sign language recognition has always been a very important research topic. However, many sign language recognition systems currently require complex deep models and rely on expensive sensors, which limits the application scenarios of sign language recognition. To address this issue, based on computer vision, this study proposed a lightweight, dual-path background erasing deep convolutional neural network (DPCNN) model for sign language recognition. The DPCNN consists of two paths. One path is used to learn the overall features, while the other path learns the background features. The background features are gradually subtracted from the overall features to obtain an effective representation of hand features. Then, these features are flatten into a one-dimensional layer, and pass through a fully connected layer with an output unit of 128. Finally, use a fully connected layer with an output unit of 24 as the output layer. Based on the ASL Finger Spelling dataset, the total accuracy and Macro-F1 scores of the proposed method is 99.52% and 0.997, respectively. More importantly, the proposed method can be applied to small terminals, thereby improving the application scenarios of sign language recognition. Through experimental comparison, the dual path background erasure network model proposed in this paper has better generalization ability.