Association between sociodemographic, psychosocial, lifestyle factors, and self-reported health among migrant laborers in China.

BACKGROUND: There were 245 million migrants in China in 2013, the majority of whom migrated from rural to urban areas. Thus, the purpose of this study was to investigate the association between sociodemographic, psychosocial, and lifestyle factors, and self-reported health (SRH) in Chinese migrant laborers. METHODS: This study was conducted based on data from the China Labor-force Dynamics Survey 2012. SRH was measured in a single item, although there were other risk factors from three different groups: sociodemographic, psychosocial, and lifestyle factors. The associations between these risk factors and SRH were tested using multilevel logistic regression analyses including interaction tests. RESULTS: All three groups of factors were explored simultaneously. These factors included age, working hours, marital status, illness, and hospitalization, which were associated with poor SRH, as well as earnings, number of friends, relations with neighbors, trust level, education, and alcohol consumption, which were associated with good SRH. However, there was minimal association found between the two factors of medical insurance and nationality, and SRH. CONCLUSION: Our investigation indicated that there are many factors associated with SRH. In particular, this study undertook a comprehensive investigation of the associations between sociodemographic, psychosocial, lifestyle factors, and SRH in China, the results of which could better inform medical researchers and governments from a Chinese perspective.

Comparison of three data mining models for predicting diabetes or prediabetes by risk factors.

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.