Lingling Zhou

Application of a New Hybrid Model with Seasonal Auto-Regressive Integrated Moving Average (ARIMA) and Nonlinear Auto-Regressive Neural Network (NARNN) in Forecasting Incidence Cases of HFMD in Shenzhen, China

Background Outbreaks of hand-foot-mouth disease (HFMD) have been reported for many times in Asia during the last decades. This emerging disease has drawn worldwide attention and vigilance. Nowadays, the prevention and control of HFMD has become an imperative issue in China. Early detection and response will be helpful before it happening, using modern information technology during the epidemic. Method In this paper, a hybrid model combining seasonal auto-regressive integrated moving average (ARIMA) model and nonlinear auto-regressive neural network (NARNN) is proposed to predict the expected incidence cases from December 2012 to May 2013, using the retrospective observations obtained from China Information System for Disease Control and Prevention from January 2008 to November 2012. Results The best-fitted hybrid model was combined with seasonal ARIMA and NARNN with 15 hidden units and 5 delays. The hybrid model makes the good forecasting performance and estimates the expected incidence cases from December 2012 to May 2013, which are respectively −965.03, −1879.58, 4138.26, 1858.17, 4061.86 and 6163.16 with an obviously increasing trend. Conclusion The model proposed in this paper can predict the incidence trend of HFMD effectively, which could be helpful to policy makers. The usefulness of expected cases of HFMD perform not only in detecting outbreaks or providing probability statements, but also in providing decision makers with a probable trend of the variability of future observations that contains both historical and recent information.

A hybrid model for predicting the prevalence of schistosomiasis in humans of Qianjiang City, China.

Backgrounds/Objective Schistosomiasis is still a major public health problem in China, despite the fact that the government has implemented a series of strategies to prevent and control the spread of the parasitic disease. Advanced warning and reliable forecasting can help policymakers to adjust and implement strategies more effectively, which will lead to the control and elimination of schistosomiasis. Our aim is to explore the application of a hybrid forecasting model to track the trends of the prevalence of schistosomiasis in humans, which provides a methodological basis for predicting and detecting schistosomiasis infection in endemic areas. Methods A hybrid approach combining the autoregressive integrated moving average (ARIMA) model and the nonlinear autoregressive neural network (NARNN) model to forecast the prevalence of schistosomiasis in the future four years. Forecasting performance was compared between the hybrid ARIMA-NARNN model, and the single ARIMA or the single NARNN model. Results The modelling mean square error (MSE), mean absolute error (MAE) and mean absolute percentage error (MAPE) of the ARIMA-NARNN model was 0.1869×10−4, 0.0029, 0.0419 with a corresponding testing error of 0.9375×10−4, 0.0081, 0.9064, respectively. These error values generated with the hybrid model were all lower than those obtained from the single ARIMA or NARNN model. The forecasting values were 0.75%, 0.80%, 0.76% and 0.77% in the future four years, which demonstrated a no-downward trend. Conclusion The hybrid model has high quality prediction accuracy in the prevalence of schistosomiasis, which provides a methodological basis for future schistosomiasis monitoring and control strategies in the study area. It is worth attempting to utilize the hybrid detection scheme in other schistosomiasis-endemic areas including other infectious diseases.

Parkinson’s Disease and Risk of Fracture: A Meta-Analysis of Prospective Cohort Studies

Backgrounds/Objective Parkinson’s disease (PD) is the second most common neurodegenerative disease among the elderly population. However, epidemiological evidence on the relationship of PD with risk of fracture has not been systematically assessed. Therefore, we performed this meta-analysis of prospective studies to explore the association between PD and risk of fracture. Methods PubMed, Embase, Web of Science and Cochrane Library up to February 26, 2014 were searched to identify eligible studies. Random-effects model was used to pool the results. Results Six studies that totally involved 69,387 participants were included for analysis. Overall, PD patients had an increased risk of fracture compared with control subjects (pooled hazard ratio = 2.66, 95% confidence interval: 2.10–3.36). No publication bias was observed across studies and the subgroup as well as sensitivity analysis suggested that the general results were robust. Conclusion The present study suggested that PD is associated with an increased risk of fracture. However, given the limited number and moderate quality of included studies, well-designed prospective cohort studies are required to confirm the findings from this meta-analysis.

Household physical activity and cancer risk: a systematic review and dose-response meta-analysis of epidemiological studies

Controversial results of the association between household physical activity and cancer risk were reported among previous epidemiological studies. We conducted a meta-analysis to investigate the relationship of household physical activity and cancer risk quantitatively, especially in dose-response manner. PubMed, Embase, Web of science and the Cochrane Library were searched for cohort or case-control studies that examined the association between household physical activity and cancer risks. Random–effect models were conducted to estimate the summary relative risks (RRs), nonlinear or linear dose–response meta-analyses were performed to estimate the trend from the correlated log RR estimates across levels of household physical activity quantitatively. Totally, 30 studies including 41 comparisons met the inclusion criteria. Total cancer risks were reduced 16% among the people with highest household physical activity compared to those with lowest household physical activity (RR = 0.84, 95% CI = 0.76–0.93). The dose-response analyses indicated an inverse linear association between household physical activity and cancer risk. The relative risk was 0.98 (95% CI = 0.97–1.00) for per additional 10 MET-hours/week and it was 0.99 (95% CI = 0.98–0.99) for per 1 hour/week increase. These findings provide quantitative data supporting household physical activity is associated with decreased cancer risk in dose-response effect.

Using a Hybrid Model to Forecast the Prevalence of Schistosomiasis in Humans

Background: We previously proposed a hybrid model combining both the autoregressive integrated moving average (ARIMA) and the nonlinear autoregressive neural network (NARNN) models in forecasting schistosomiasis. Our purpose in the current study was to forecast the annual prevalence of human schistosomiasis in Yangxin County, using our ARIMA-NARNN model, thereby further certifying the reliability of our hybrid model. Methods: We used the ARIMA, NARNN and ARIMA-NARNN models to fit and forecast the annual prevalence of schistosomiasis. The modeling time range included was the annual prevalence from 1956 to 2008 while the testing time range included was from 2009 to 2012. The mean square error (MSE), mean absolute error (MAE) and mean absolute percentage error (MAPE) were used to measure the model performance. We reconstructed the hybrid model to forecast the annual prevalence from 2013 to 2016. Results: The modeling and testing errors generated by the ARIMA-NARNN model were lower than those obtained from either the single ARIMA or NARNN models. The predicted annual prevalence from 2013 to 2016 demonstrated an initial decreasing trend, followed by an increase. Conclusions: The ARIMA-NARNN model can be well applied to analyze surveillance data for early warning systems for the control and elimination of schistosomiasis.