Using Baidu index to nowcast hand-foot-mouth disease in China: a meta learning approach

Zhao, Yang; Xu, Qinneng; Chen, Yupeng; Tsui, Kwok Leung

doi:10.1186/s12879-018-3285-4

Cited by 27 publications

(26 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to infections, yet another variable that would affect the significance is the overlaps of Baidu Maps and Baidu search user communities in different cities. Considering the coverage of Baidu users throughout the Chinese population, we follow the previous work 17,18 to set this issue aside. Please see also Figure 6 for the visualization of the correlations.…”

Section: Resultsmentioning

confidence: 99%

Understanding the Collective Responses of Populations to the COVID-19 Pandemic in Mainland China

Xiong

Liu

Huang

et al. 2020

Preprint

View full text Add to dashboard Cite

Timely information acquisition and stay-at-home measures have been considered as two effective steps that every person could take to help contain the coronavirus (COVID-19) pandemic. From the perspectives of information and mobility, this work aims at evaluating to what degree the massive population has responded to the emergencies of the COVID-19 pandemic in China. Using the real-time and historical data collected from the Baidu Maps and Baidu search engines, we confirm the strong correlation between the local pandemic situation in every major Chinese city and the population inflows from Wuhan between 1 January and 23 January 2020. We further evidence that, in cities under more critical situations, people are likely to engage COVID-19-related searches more frequently, while they are not likely to escape from the cities. Finally, the correlation analysis using search and mobility data shows that well-informed individuals are likely to travel less, even while the overall travel demands are low compared to the historical records. Partial correlation analysis has been conducted to test the significance of these observations with respect to other controlling factors.

show abstract

Section: Resultsmentioning

confidence: 99%

Understanding the Collective Responses of Populations to the COVID-19 Pandemic in Mainland China

Xiong

Liu

Huang

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…In Zhejiang Province of China, the prevalence of Norwalk virus has been determined through Internet monitoring (Baidu Index), and an appropriate model has been established to predict potential Norwalk virus infection 19 . Similarly, some methods of using Baidu Search Index(BSI) data have also been carried out in HIV/AIDS; hand, foot and mouth disease; and dengue 17,20,21 .…”

mentioning

confidence: 99%

Search trends and prediction of human brucellosis using Baidu index data from 2011 to 2018 in China

Zhao

Yang

et al. 2020

Sci Rep

View full text Add to dashboard Cite

Reporting on brucellosis, a relatively rare infectious disease caused by Brucella, is often delayed or incomplete in traditional disease surveillance systems in china. internet search engine data related to brucellosis can provide an economical and efficient complement to a conventional surveillance system because people tend to seek brucellosis-related health information from Baidu, the largest search engine in china. in this study, brucellosis incidence data reported by the cDc of china and Baidu index data were gathered to evaluate the relationship between them. We applied an autoregressive integrated moving average (ARiMA) model and an ARiMA model with Baidu search index data as the external variable (ARiMAX) to predict the incidence of brucellosis. the two models based on brucellosis incidence data were then compared, and the ARiMAX model performed better in all the measurements we applied. our results illustrate that Baidu index data can enhance the traditional surveillance system to monitor and predict brucellosis epidemics in china.

show abstract

“…For example, the ‘FluSight’ challenge 25 of the US evaluates the proposed models on future incidence prediction, peak intensity prediction, peak week prediction and onset week prediction, because these error indicators are directly related to the development of control measures by the public health department. Previous HFMD prediction 12 – 14 , 26 – 29 didn’t use similar indicators. In our study, we evaluated our models on future point prediction, peak intensity prediction and peak month prediction, and these error indicators may facilitate deep learning models to be more widely used in the practice of epidemic prediction.…”

Section: Discussionmentioning

confidence: 99%

Using deep learning to predict the hand-foot-and-mouth disease of enterovirus A71 subtype in Beijing from 2011 to 2018

Wang¹,

Cao²,

Zeng³

et al. 2020

Sci Rep

View full text Add to dashboard Cite

Hand-foot-and-month disease (HFMD), especially the enterovirus A71 (EV-A71) subtype, is a major health problem in Beijing, China. Previous studies mainly used regressive models to forecast the prevalence of HFMD, ignoring its intrinsic age groups. This study aims to predict HFMD of EV-A71 subtype in three age groups (0-3, 3-6 and > 6 years old) from 2011 to 2018 using residualconvolutional-recurrent neural network (CNNRNN-Res), convolutional-recurrent neural network (CNNRNN) and recurrent neural network (RNN). They were compared with auto-regressio, global auto-regression and vector auto-regression on both short-term and long-term prediction. Results showed that CNNRNN-Res and RNN had higher accuracies on point forecast tasks, as well as robust performances in long-term prediction. Three deep learning models also had better skills in peak intensity forecast, and CNNRNN-Res achieved the best results in the peak month forecast. We also found that three age groups had consistent outbreak trends and similar patterns of prediction errors. These results highlight the superior performance of deep learning models in HFMD prediction and can assist the decision-makers to refine the HFMD control measures according to age groups. HFMD is a mild gastrointestinal disease, mainly caused by EV-A, EV-B and EV-C species, while the EV-A71 subtype is prone to more serious complications 1. Spatial and temporal patterns of HFMD incidence are strongly correlated with climatic factors 2-4 , e.g. high-level humidity and middle-level temperatures. Social factors also affect the spread of HFMD, e.g. contact amongst children in school 5. Under the influences of multi-type pathogenic viruses, complex climatic and social factors, HFMD presents a periodic outbreak in the Asia-Pacific region 1,5. In China, the incidence and mortality of HFMD have been leading the type C infectious diseases since its severe outbreak in 2008 and the situation is getting worse. Beijing city, the capital of China, is also vastly threatened by HFMD 6. Studies have explored the predominant virus 6,7 , weather factors 8,9 and space-time patterns 10 of HFMD in Beijing. Vaccines that prevent EV71-associated HFMD have been developed, but HFMD wouldn't be eliminated because of many other pathogens. Therefore, forecasting the prevalence of HFMD in Beijing is still essential for public health. Many previous studies used regressive models to predict the incidence of HFMD 11-16. In addition to the HFMD incidence data, search index, temperature records, air quality and other exogenous variables were applied to fit the regressive models. Although these methods had achieved acceptable prediction accuracies, there are still some limitations. First, these works only focused on the total number of cases. They ignored the intrinsic age groups in children. In fact, children aged 0 to 6 are the most susceptible to HFMD, while children over the age of 6 have stronger immunities to HFMD. So, under the effect of epidemic transmission dynamics and immunity, there are connections among inc...

show abstract

Using Baidu index to nowcast hand-foot-mouth disease in China: a meta learning approach

Cited by 27 publications

References 59 publications

Understanding the Collective Responses of Populations to the COVID-19 Pandemic in Mainland China

Understanding the Collective Responses of Populations to the COVID-19 Pandemic in Mainland China

Search trends and prediction of human brucellosis using Baidu index data from 2011 to 2018 in China

Using deep learning to predict the hand-foot-and-mouth disease of enterovirus A71 subtype in Beijing from 2011 to 2018

Contact Info

Product

Resources

About