Self-reported visual impairment and depression of middle-aged and older adults: The chain-mediating effects of internet use and social participation.

Background: Visual impairment (VI) is a strong predictor of depression in middle-aged and older adults. However, the underlying mechanisms and pathways have not been well characterized. The purpose of this study was to determine whether Internet use and social participation mediate the effects of self-reported VI on depression. Methods: The study used the fourth wave of cross-sectional data from the China Health and Retirement Longitudinal Study, including 19,766 Chinese adults. Depression was assessed according to the CES-D 10 International Scale. Logistic regression models were used to examine the relationship between self-reported VI and depression. While adjusting for relevant covariates, the PROCESS macro (model nos. 6 and 91) was used to assess the chain-mediating effects of Internet use and social participation. Results: A total of 17,433 respondents were included in this study. The CES-D 10 results showed that 7,327 middle-aged and older adults had depressive symptoms, of whom 39.5% were male and 10.2% were ≥75 years old. 32.1% of respondents self-reported VI. Regression analysis showed a positive association between VI and depression, while Internet use and social participation had a negative predictive effect on depression. In the mediation analysis, the social participation pathway contributed the most to the total effect, accounting for 52.69% of it. The proportion of Internet use is 37.72%. When these two mediators were considered together in the full model, they accounted for 9.58% of the total effect of VI on depression. Conclusion: Internet use and social participation were important mediators that mitigated the effects of VI on depression. Combined with previous evidence, online activities such as e-health and m-health can effectively promote disease monitoring and diagnosis, and various offline social participation activities can also play a role in regulating emotions. Therefore, Internet use and social participation factors may serve as relevant entry points for the development of intervention programs that may further improve the mental health of the visually impaired.

UFRC: A Unified Framework for Reliable COVID-19 Detection on Crowdsourced Cough Audio.

We suggested a unified system with core components of data augmentation, ImageNet-pretrained ResNet-50, cost-sensitive loss, deep ensemble learning, and uncertainty estimation to quickly and consistently detect COVID-19 using acoustic evidence. To increase the model's capacity to identify a minority class, data augmentation and cost-sensitive loss are incorporated (infected samples). In the COVID-19 detection challenge, ImageNet-pretrained ResNet-50 has been found to be effective. The unified framework also integrates deep ensemble learning and uncertainty estimation to integrate predictions from various base classifiers for generalisation and reliability. We ran a series of tests using the DiCOVA2021 challenge dataset to assess the efficacy of our proposed method, and the results show that our method has an AUC-ROC of 85.43 percent, making it a promising method for COVID-19 detection. The unified framework also demonstrates that audio may be used to quickly diagnose different respiratory disorders.