The purpose of this study was to compare the performance of logistic regression, artificial neural networks (ANNs) and decision tree models for predicting diabetes or prediabetes using common risk factors. Participants came from two communities in Guangzhou, China; 735 patients confirmed to have diabetes or prediabetes and 752 normal controls were recruited. A standard questionnaire was administered to obtain information on demographic characteristics, family diabetes history, anthropometric measurements and lifestyle risk factors. Then we developed three predictive models using 12 input variables and one output variable from the questionnaire information; we evaluated the three models in terms of their accuracy, sensitivity and specificity. The logistic regression model achieved a classification accuracy of 76.13% with a sensitivity of 79.59% and a specificity of 72.74%. The ANN model reached a classification accuracy of 73.23% with a sensitivity of 82.18% and a specificity of 64.49%; and the decision tree (C5.0) achieved a classification accuracy of 77.87% with a sensitivity of 80.68% and specificity of 75.13%. The decision tree model (C5.0) had the best classification accuracy, followed by the logistic regression model, and the ANN gave the lowest accuracy.
Background Healthcare workers are often exposed to stressful working conditions at work which affect their quality of life. The study investigated the relationship between psychosocial risk factors, stress, burnout, and quality of life among primary healthcare workers in general medical practice in Qingyuan and Chaozhou cities in Guangdong province. Method The cross-sectional study was conducted in 108 primary health facilities including 36 community health centers (CHCs) across two developing cities in Guangdong province. A total of 873 healthcare workers completed the questionnaires. Quality of life was evaluated using The World Health Organization Quality of Life Questionnaire (WHOQOL-BREF) and psychological risk factors were evaluated by the Copenhagen Psychosocial Questionnaire (COPSOQ). General quality of life and the quality of life domains were transformed into a score range from minimum 0 to 100 maximum. Higher scores indicated better quality of life and vice versa. Significant associations were verified using multiple regression analysis. Results Poor quality of life was observed in 74.6% of healthcare workers surveyed. General poor quality of life was significantly higher among workers who reported higher burnout (Beta = − 0.331, p < 0.001). In addition, workers with high levels of burnout, unmarried workers and female workers had a higher possibility of physical health. A greater risk of poor psychological health was observed among workers with high burnout, poor sense of community and those with lower educational levels. Workers who lacked social support, those with fewer possibilities for development had increased probability of poor quality of life in the social domain. Poor quality of life in the environmental domain was observed among workers who were dissatisfied with their jobs and workers with low salaries. Conclusions Primary healthcare workers in developing cities in China have a highly demanding and strained working environment and poor quality of life. Reducing job stress and improving work conditions may ultimately improve the well-being of primary healthcare workers.
Background Depression is regarded as a major public health concern in our society. While living arrangements as a structural factor of social support may contribute to older adults’ depression. Our study aims to investigate the association between living arrangements and depressive symptoms among older adults in the whole China, and to explore whether such influences differ by genders. Methods Data were obtained from the 2015 China Health and Retirement Longitudinal Study. The sample was comprised of 6001 individuals aged ≥60 years. Depressive symptoms were measured by the 10-item Short-Form Center for Epidemiological Studies Depression. Independent variables were divided into 4 groups, considering living with/without a spouse and living with/without a child. The multivariate logistic regression was used to estimate the relationship between living arrangements and depressive symptoms in four models. Results Compared with living only with a spouse, people living with a spouse and child, or living alone were more likely to have depressive symptoms (odds ratio = 1.23 95% CI 1.06–1.42 and 1.40 95% CI 1.03–1.92, respectively). Women were more associated with depressive symptoms (odds ratio = 2.13), but there were no significant associations between living arrangements and depressive symptoms among women. Men living with a spouse and a child had stronger positively depressive symptoms (odds ratio = 1.37). Conclusions Older adults living alone, or living with both a child and spouse were more likely to have depressive symptoms. It is important to provide more social services for those older adult, particularly for men living with a spouse and child. Electronic supplementary material The online version of this article (10.1186/s12889-019-7350-8) contains supplementary material, which is available to authorized users.
Hyperuricemia (HU) is a risk factor for different kinds of chronic noncommunicable diseases, and eating away from home (EAFH) may play an important role in their development, which has been ignored greatly so far. This study aimed to investigate the association between EAFH and HU in different models. A cross-sectional study involving 8,322 participants of the China Health and Nutrition Survey (CHNS) was conducted. Logistic regression models were used to analyze the data. We found that participants who consumed more away-from-home food had a higher risk for HU, and the adjusted odds ratio (aOR) and 95% confidence interval (CI) (for each increment in grades of EAFH) were 1.11 (1.02, 1.20) in a multiadjusted model (adjusted for age, gender, province, net individual income, body mass index, smoking, leisure-time physical activities, energy intake, and sleep duration). As for stratified analyses, the aOR (95% CI) of EAFH was 1.12 (1.01, 1.24) for men and 1.06 (0.92, 1.21) for women. Similar results can be found in the middle-aged and obese population, with aOR (95% CI) of EAFH as 1.17 (1.05, 1.30) and 1.15 (1.03, 1.29), respectively. In conclusion, EAFH is positively associated with the prevalence of HU.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.