Background: This study intends to identify the best model for predicting the incidence of hand, foot and mouth disease (HFMD) in Ningbo by comparing Autoregressive Integrated Moving Average (ARIMA) and Long Short-Term Memory Neural Network (LSTM) models combined and uncombined with exogenous meteorological variables. Methods: The data of daily HFMD incidence in Ningbo from January 2014 to November 2017 were set as the training set, and the data of December 2017 were set as the test set. ARIMA and LSTM models combined and uncombined with exogenous meteorological variables were adopted to fit the daily incidence of HFMD by using the data of the training set. The forecasting performances of the four fitted models were verified by using the data of the test set. Root mean square error (RMSE) was selected as the main measure to evaluate the performance of the models. Results: The RMSE for multivariate LSTM, univariate LSTM, ARIMA and ARIMAX (Autoregressive Integrated Moving Average Model with Exogenous Input Variables) was 10.78, 11.20, 12.43 and 14.73, respectively. The LSTM model with exogenous meteorological variables has the best performance among the four models and meteorological variables can increase the prediction accuracy of LSTM model. For the ARIMA model, exogenous meteorological variables did not increase the prediction accuracy but became the interference factor of the model. Conclusions: Multivariate LSTM is the best among the four models to fit the daily incidence of HFMD in Ningbo. It can provide a scientific method to build the HFMD early warning system and the methodology can also be applied to other communicable diseases.

Background The COVID-19 pandemic has underscored the importance of behaviours such as social distancing in controlling pandemics. Currently, the epidemic is under control in China and production has resumed in various industries. This study investigates the behavioural compliance and related factors for COVID-19 prevention among employees returning to the workplace and provide strategic recommendations for improving individual-level preventive behaviour to prevent a new outbreak. Methods A cross-sectional study design was used. Data were gathered from returning employees in China using an online questionnaire survey, from March to May, 2020. The questionnaire covered participants’ COVID-19-related knowledge, compliance with recommended preventive behaviours, and levels of depression and anxiety. Univariate and multi-factor methods were used to analyse the data and identify factors influencing behaviour compliance. Results Of the 1300 participants completing the full survey, more than half were male (71.92%) and 61% were aged between 31 and 50 years. Six hundred and ninety-eight (53.7%) participants showed high compliance, while 602 (46.3%) showed low compliance. In models adjusted for demographic and socio-economic factors, high education level (odds ratio [OR] = 0.23, 95% confidence interval [CI]: 0.07–0.70), office staff (OR = 0.51, 95% CI: 0.33–0.78), higher knowledge of COVID-19 (OR = 0.74, 95% CI: 0.67–0.81), and quarantining (OR = 0.74, 95% CI: 0.57–0.96) predicted better compliance with preventive behaviours (P <  0.05), while high anxiety levels (OR = 1.55, 95% CI: 1.10–2.18) predicted lower compliance with preventive behaviours (P <  0.05). Conclusion For employees returning to work during the post-COVID-19-epidemic period, compliance with recommended preventive behaviours requires improvement. Consequently, comprehensive intervention measures, including the provision of health education and psychological counselling, as well as the continuance of a strict isolation policy, could enhance such compliance.

It is very important to have a comprehensive understanding of the health status of a country’s population, which helps to develop corresponding public health policies. Correct inference of the underlying cause-of-death for citizens is essential to achieve a comprehensive understanding of the health status of a country’s population. Traditionally, this relies mainly on manual methods based on medical staff’s experiences, which require a lot of resources and is not very efficient. In this work, we present our efforts to construct an automatic method to perform inferences of the underlying causes-of-death for citizens. A sink algorithm is introduced, which could perform automatic inference of the underlying cause-of-death for citizens. The results show that our sink algorithm could generate a reasonable output and outperforms other stat-of-the-art algorithms. We believe it would be very useful to greatly enhance the efficiency of correct inferences of the underlying causes-of-death for citizens.

BackgroundVisual impairments related to non-correctable vision loss, including blindness and low vision, have been consistently shown to lower a person's health-related quality of life. This study assessed the reliability, validity, and discrimination of the Quality of Life Scale for Children with Visual Impairments (QOLS-CVI) in China.MethodsThe Pediatric Quality of Life Inventory™ 4.0 and World Health Organization Quality of Life-Disability Scale for physical disability were selected to define conceptual frameworks and item libraries based on relevant existing studies. According to two rounds of expert consultations and group discussions, some items were modified, and the draft scale was developed. Two item selection processes based on classical test theory and item response theory were used to conduct a preliminary survey and a formal survey in special schools in Shanxi and Hebei Provinces. Finally, the reliability and validity of the quality of life scale for visually impaired children in China were verified.ResultsThe final QOLS-CVI consisted of 38 items, 10 subdomains, and 6 domains. Reliability was verified by Cronbach's alpha coefficient, split-half reliability, and test-retest reliability (Cronbach's alpha for the full scale, 0.841; split-half reliability, 0.629; and test–retest reliability, 0.888). The validity results showed that the multidimensional scale met expectations: exploratory factor analysis and confirmatory factor analysis indicated good fitting models for children with visual impairments.ConclusionsThe QOLS-CVI was determined to be reliable and valid and to have strong feasibility and effectiveness. This scale can be used as an evaluation tool to study the QOL and social-participation ability of children with visual impairments.

Background The emergence of the new coronavirus disease (COVID-19) as a global pandemic has had an impact on the lifestyle of people worldwide. Government measures aimed at containing the spread of the virus have been successful in many places, leading to a relaxation of these measures. To prevent the return of an outbreak in these places, people returning to the workforce are expected to follow proper health behaviours. Therefore, this study investigated COVID-19 related knowledge, attitudes, and behaviours of employees who are returning to work during the COVID-19 prevention and control period as well as their compliance with recommended COVID-19 preventive behaviours. Methods A cross-sectional study design was used. Data were gathered using an online questionnaire survey from March to May 2020 among 1,300 returning employees in China. Questionnaire items concerned participants’ COVID-19-related knowledge, compliance with recommended preventive behaviours, and levels of depression and anxiety. Univariate and multi-factor methods were used to analyse the data and identify factors influencing behaviour compliance. Results Six hundred and ninety-eight (53.7%) participants showed high compliance, and 602 (46.3%) showed low compliance. High education level (odds ratio [OR] = 5.598, 95% confidence interval [CI]: 1.846–16.976), white-collar occupation (OR = 1.992, 95% CI: 1.331–2.983), high knowledge of COVID-19 (OR = 1.704, 95% CI: 1.303–2.229), no anxiety (OR = 0.646, 95% CI: 0.463–0.901), and quarantining (OR = 1.320, 95% CI: 1.039–1.676) predicted better compliance with preventive behaviours (p < 0.05). Conclusion Factors such as educational background, occupation, isolation, COVID-19 knowledge level, and psychological anxiety have an impact on the health behaviour of employees returning to work. For employees returning to work during the post-COVID-19-epidemic period, compliance with recommended health behaviours requires improvement. The provision of health education and psychological counselling and the continuance of a strict isolation policy could enhance such compliance.