Dengue Baidu Search Index data can improve the prediction of local dengue epidemic: A case study in Guangzhou, China

Internet-based Surveillance Systems and Infectious Diseases Prediction: An Updated Review of the Last 10 Years and Lessons from the COVID-19 Pandemic

The last decade has seen major advances and growth in internet-based surveillance for infectious diseases through advanced computational capacity, growing adoption of smart devices, increased availability of Artificial Intelligence (AI), alongside environmental pressures including climate and land use change contributing to increased threat and spread of pandemics and emerging infectious diseases. With the increasing burden of infectious diseases and the COVID-19 pandemic, the need for developing novel technologies and integrating internet-based data approaches to improving infectious disease surveillance is greater than ever. In this systematic review, we searched the scientific literature for research on internet-based or digital surveillance for influenza, dengue fever and COVID-19 from 2013 to 2023. We have provided an overview of recent internet-based surveillance research for emerging infectious diseases (EID), describing changes in the digital landscape, with recommendations for future research directed at public health policymakers, healthcare providers, and government health departments to enhance traditional surveillance for detecting, monitoring, reporting, and responding to influenza, dengue, and COVID-19.

Anti-social behaviour and economic decision-making: Panel experimental evidence in the wake of COVID-19

We systematically examine the acute impact of exposure to a public health crisis on anti-social behaviour and economic decision-making using unique experimental panel data from China, collected just before the outbreak of COVID-19 and immediately after the first wave was overcome. Exploiting plausibly exogenous geographical variation in virus exposure coupled with a dataset of longitudinal experiments, we show that participants who were more intensely exposed to the virus outbreak became more anti-social than those with lower exposure, while other aspects of economic and social preferences remain largely stable. The finding is robust to multiple hypothesis testing and a similar, yet less pronounced pattern emerges when using alternative measures of virus exposure, reflecting societal concern and sentiment, constructed using social media data. The anti-social response is particularly pronounced for individuals who experienced an increase in depression or negative affect, which highlights the important role of psychological health as a potential mechanism through which the virus outbreak affected behaviour.

Predicting COVID-19 using lioness optimization algorithm and graph convolution network

In this paper, a graph convolution network prediction model based on the lioness optimization algorithm (LsOA-GCN) is proposed to predict the cumulative number of confirmed COVID-19 cases in 17 regions of Hubei Province from March 23 to March 29, 2020, according to the transmission characteristics of COVID-19. On the one hand, Spearman correlation analysis with delay days and LsOA are used to capture the dynamic changes of feature information to obtain the temporal features. On the other hand, the graph convolutional network is used to capture the topological structure of the city network, so as to obtain spatial information and finally realize the prediction task. Then, we evaluate this model through performance evaluation indicators and statistical test methods and compare the results of LsOA-GCN with 10 representative prediction methods in the current epidemic prediction study. The experimental results show that the LsOA-GCN prediction model is significantly better than other prediction methods in all indicators and can successfully capture spatio-temporal information from feature data, thereby achieving accurate prediction of epidemic trends in different regions of Hubei Province.

Predicting pulmonary tuberculosis incidence in China using Baidu search index: an ARIMAX model approach

BACKGROUND

Existing researches have established a correlation between internet search data and the epidemics of numerous infectious diseases. This study aims to develop a prediction model to explore the relationship between the Pulmonary Tuberculosis (PTB) epidemic trend in China and the Baidu search index.

METHODS

Collect the number of new cases of PTB in China from January 2011 to August 2022. Use Spearman rank correlation and interaction analysis to identify Baidu keywords related to PTB and construct a PTB comprehensive search index. Evaluate the predictive performance of autoregressive integrated moving average (ARIMA) and ARIMA with explanatory variable (ARIMAX) models for the number of PTB cases.

RESULTS

Incidence of PTB had shown a fluctuating downward trend. The Spearman rank correlation coefficient between the PTB comprehensive search index and its incidence was 0.834 (P < 0.001). The ARIMA model had an AIC value of 2804.41, and the MAPE value was 13.19%. The ARIMAX model incorporating the Baidu index demonstrated an AIC value of 2761.58 and a MAPE value of 5.33%.

CONCLUSIONS

The ARIMAX model is superior to ARIMA in terms of fitting and predicting accuracy. Additionally, the use of Baidu Index has proven to be effective in predicting cases of PTB.

Internet search data with spatiotemporal analysis in infectious disease surveillance: Challenges and perspectives

With the rapid development of the internet, the application of internet search data has been seen as a novel data source to offer timely infectious disease surveillance intelligence. Moreover, the advancements in internet search data, which include rich information at both space and time scales, enable investigators to sufficiently consider the spatiotemporal uncertainty, which can benefit researchers to better monitor infectious diseases and epidemics. In the present study, we present the necessary groundwork and critical appraisal of the use of internet search data and spatiotemporal analysis approaches in infectious disease surveillance by updating the current stage of knowledge on them. The study also provides future directions for researchers to investigate the combination of internet search data with the spatiotemporal analysis in infectious disease surveillance. Internet search data demonstrate a promising potential to offer timely epidemic intelligence, which can be seen as the prerequisite for improving infectious disease surveillance.

Online public attention toward allergic rhinitis in Wuhan, China: Infodemiology study using Baidu index and meteorological data

Background

With the popularization of the Internet and medical knowledge, more and more people are learning about allergic rhinitis (AR) on the Internet.

Objective

This study aims to analyze the epidemiological characteristics and online public attention to AR in Wuhan, China, utilizing the most popular search engine in mainland China and meteorological data of Wuhan.

Methods

To study the Internet attention and epidemiological characteristics of AR in Wuhan, the search volume (SV) of "Allergic Rhinitis" in Mandarin and AR-related search terms from 1 January 2014 through 31 December 2021 were recorded. For user interest, the search and demand data were collected and analyzed.

Results

The yearly average Baidu SV of AR in both Wuhan and China increased year by year but began to decline gradually after the COVID-19 pandemic. Baidu SV of AR in Wuhan exhibited significant seasonal variation, with the first peak was from March to May and the second peak occurring between September and October. Correlation analysis revealed a moderate positive correlation between the monthly average SV of "Allergic Rhinitis" and "Mites" and "Mites + Pollen Allergy" in Wuhan, a weak positive correlation between the monthly average SV of "Allergic Rhinitis" and "Pollen Allergy," and a positive correlation between monthly SV of "Allergic Rhinitis" and the meteorological index of pollen allergy (MIPA).

Conclusion

The attention given to the topic on the internet, as measured by the search volume, was reflective of the situation in Wuhan, China. It has the potential to predict the epidemiological characteristics of AR and help medical professionals more effectively plan seasonal AR health education.

Collaboration between meteorology and public health: Predicting the dengue epidemic in Guangzhou, China, by meteorological parameters

Background

Dengue has become an increasing public health threat around the world, and climate conditions have been identified as important factors affecting the transmission of dengue, so this study was aimed to establish a prediction model of dengue epidemic by meteorological methods.

Methods

The dengue case information and meteorological data were collected from Guangdong Provincial Center for Disease Prevention and Control and Guangdong Meteorological Bureau, respectively. We used spatio-temporal analysis to characterize dengue epidemics. Spearman correlation analysis was used to analyze the correlation between lagged meteorological factors and dengue fever cases and determine the maximum lagged correlation coefficient of different meteorological factors. Then, Generalized Additive Models were used to analyze the non-linear influence of lagged meteorological factors on local dengue cases and to predict the number of local dengue cases under different weather conditions.

Results

We described the temporal and spatial distribution characteristics of dengue fever cases and found that sporadic single or a small number of imported cases had a very slight influence on the dengue epidemic around. We further created a forecast model based on the comprehensive consideration of influence of lagged 42-day meteorological factors on local dengue cases, and the results showed that the forecast model has a forecast effect of 98.8%, which was verified by the actual incidence of dengue from 2005 to 2016 in Guangzhou.

Conclusion

A forecast model for dengue epidemic was established with good forecast effects and may have a potential application in global dengue endemic areas after modification according to local meteorological conditions. High attention should be paid on sites with concentrated patients for the control of a dengue epidemic.

Data-driven methods for dengue prediction and surveillance using real-world and Big Data: A systematic review

Background

Traditionally, dengue surveillance is based on case reporting to a central health agency. However, the delay between a case and its notification can limit the system responsiveness. Machine learning methods have been developed to reduce the reporting delays and to predict outbreaks, based on non-traditional and non-clinical data sources. The aim of this systematic review was to identify studies that used real-world data, Big Data and/or machine learning methods to monitor and predict dengue-related outcomes.

Methodology/Principal findings

We performed a search in PubMed, Scopus, Web of Science and grey literature between January 1, 2000 and August 31, 2020. The review (ID: CRD42020172472) focused on data-driven studies. Reviews, randomized control trials and descriptive studies were not included. Among the 119 studies included, 67% were published between 2016 and 2020, and 39% used at least one novel data stream. The aim of the included studies was to predict a dengue-related outcome (55%), assess the validity of data sources for dengue surveillance (23%), or both (22%). Most studies (60%) used a machine learning approach. Studies on dengue prediction compared different prediction models, or identified significant predictors among several covariates in a model. The most significant predictors were rainfall (43%), temperature (41%), and humidity (25%). The two models with the highest performances were Neural Networks and Decision Trees (52%), followed by Support Vector Machine (17%). We cannot rule out a selection bias in our study because of our two main limitations: we did not include preprints and could not obtain the opinion of other international experts.

Conclusions/Significance

Combining real-world data and Big Data with machine learning methods is a promising approach to improve dengue prediction and monitoring. Future studies should focus on how to better integrate all available data sources and methods to improve the response and dengue management by stakeholders.

Dengue is one of the most important arbovirus infections in the world and its public health, societal and economic burden is increasing. Although the majority of dengue cases are asymptomatic or mild, severe disease forms can lead to death. For this reason, early diagnosis and monitoring of dengue are crucial to decrease mortality. However, most endemic regions still rely on traditional monitoring methods, despite the growing availability of novel data sources and data-driven methods based on real-world data, Big Data, and machine learning algorithms. In this systematic review, we identified and analyzed studies that used these novel approaches for dengue monitoring and/or prediction. We found that novel data streams, such as Internet search engines and social media platforms, and machine learning methods can be successfully used to improve dengue management, but are still vastly ignored in real life. These approaches should be combined with traditional methods to help stakeholders better prepare for each outbreak and improve early responsiveness.

Online Public Attention of COVID-19 Vaccination in Mainland China

With the approval of the vaccine in mainland China, concerns over its safety and efficacy emerged. Since the Chinese vaccine has been promoted by the Chinese government for months and got emergency approval from the World Health Organization. The Chinese vaccination program is yet to be identified from the perspective of local populations. The COVID-19 vaccine-related keywords for the period from January 2019 to April 2021 were examined and queried from the Baidu search index. The searching popularity, searching trend, demographic distributions and users’ demand were analyzed. The first vaccine enquiry emerged on 25th January 2020, and 17 vaccination keywords were retrieved and with a total BSI value of 13,708,853. The average monthly searching trend growth is 21.05% (p < 0.05) and was led by people aged 20–29 (39.22%) years old. Over 54.93% of the demand term search were pandemic relevant, and the summed vaccine demand ratio was 44.79%. With the rising search population in COVID-19 vaccination, education programs and materials should be designed for teens and people above the 40 s. Also, vaccine-related birth safety should be alerted and further investigated.

Using internet-based query and climate data to predict climate-sensitive infectious disease risks: a systematic review of epidemiological evidence

The use of internet-based query data offers a novel approach to improve disease surveillance and provides timely disease information. This paper systematically reviewed the literature on infectious disease predictions using internet-based query data and climate factors, discussed the current research progress and challenges, and provided some recommendations for future studies. We searched the relevant articles in the PubMed, Scopus, and Web of Science databases between January 2000 and December 2019. We initially included studies that used internet-based query data to predict infectious disease epidemics, then we further filtered and appraised the studies that used both internet-based query data and climate factors. In total, 129 relevant papers were included in the review. The results showed that most studies used a simple descriptive approach (n=80; 62%) to detect epidemics of influenza (including influenza-like illness (ILI)) (n=88; 68%) and dengue (n=9; 7%). Most studies (n=61; 47%) purely used internet search metrics to predict the epidemics of infectious diseases, while only 3 out of the 129 papers included both climate variables and internet-based query data. Our research shows that including internet-based query data and climate variables could better predict climate-sensitive infectious disease epidemics; however, this method has not been widely used to date. Moreover, previous studies did not sufficiently consider the spatiotemporal uncertainty of infectious diseases. Our review suggests that further research should use both internet-based query and climate data to develop predictive models for climate-sensitive infectious diseases based on spatiotemporal models.

The impacts of precipitation patterns on dengue epidemics in Guangzhou city

Some studies have demonstrated that precipitation is an important risk factor of dengue epidemics. However, current studies mostly focused on a single precipitation variable, and few studies focused on the impact of precipitation patterns on dengue epidemics. This study aims to explore optimal precipitation patterns for dengue epidemics. Weekly dengue case counts and meteorological data from 2006 to 2018 in Guangzhou of China were collected. A generalized additive model with Poisson distribution was used to investigate the association between precipitation patterns and dengue. Precipitation patterns were defined as the combinations of three weekly precipitation variables: accumulative precipitation (Pre_A), the number of days with light or moderate precipitation (Pre_LMD), and the coefficient of precipitation variation (Pre_CV). We explored to identify optimal precipitation patterns for dengue epidemics. With a lead time of 10 weeks, minimum temperature, relative humidity, Pre_A, and Pre_LMD were positively associated with dengue, while Pre_CV was negatively associated with dengue. A precipitation pattern with Pre_A of 20.67-55.50 mm per week, Pre_LMD of 3-4 days per week, and Pre_CV less than 1.41 per week might be an optimal precipitation pattern for dengue epidemics in Guangzhou. The finding may be used for climate-smart early warning and decision-making of dengue prevention and control.

Dengue models based on machine learning techniques: A systematic literature review

BACKGROUND

Dengue modeling is a research topic that has increased in recent years. Early prediction and decision-making are key factors to control dengue. This Systematic Literature Review (SLR) analyzes three modeling approaches of dengue: diagnostic, epidemic, intervention. These approaches require models of prediction, prescription and optimization. This SLR establishes the state-of-the-art in dengue modeling, using machine learning, in the last years.

METHODS

Several databases were selected to search the articles. The selection was made based on Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology. Sixty-four articles were obtained and analyzed to describe their strengths and limitations. Finally, challenges and opportunities for research on machine-learning for dengue modeling were identified.

RESULTS

Logistic regression was the most used modeling approach for the diagnosis of dengue (59.1%). The analysis of the epidemic approach showed that linear regression (17.4%) is the most used technique within the spatial analysis. Finally, the most used intervention modeling is General Linear Model with 70%.

CONCLUSIONS

We conclude that cause-effect models may improve diagnosis and understanding of dengue. Models that manage uncertainty can also be helpful, because of low data-quality in healthcare. Finally, decentralization of data, using federated learning, may decrease computational costs and allow model building without compromising data security.

Early warning systems (EWSs) for chikungunya, dengue, malaria, yellow fever, and Zika outbreaks: What is the evidence? A scoping review

BACKGROUND

Early warning systems (EWSs) are of increasing importance in the context of outbreak-prone diseases such as chikungunya, dengue, malaria, yellow fever, and Zika. A scoping review has been undertaken for all 5 diseases to summarize existing evidence of EWS tools in terms of their structural and statistical designs, feasibility of integration and implementation into national surveillance programs, and the users' perspective of their applications.

METHODS

Data were extracted from Cochrane Database of Systematic Reviews (CDSR), Google Scholar, Latin American and Caribbean Health Sciences Literature (LILACS), PubMed, Web of Science, and WHO Library Database (WHOLIS) databases until August 2019. Included were studies reporting on (a) experiences with existing EWS, including implemented tools; and (b) the development or implementation of EWS in a particular setting. No restrictions were applied regarding year of publication, language or geographical area.

FINDINGS

Through the first screening, 11,710 documents for dengue, 2,757 for Zika, 2,706 for chikungunya, 24,611 for malaria, and 4,963 for yellow fever were identified. After applying the selection criteria, a total of 37 studies were included in this review. Key findings were the following: (1) a large number of studies showed the quality performance of their prediction models but except for dengue outbreaks, only few presented statistical prediction validity of EWS; (2) while entomological, epidemiological, and social media alarm indicators are potentially useful for outbreak warning, almost all studies focus primarily or exclusively on meteorological indicators, which tends to limit the prediction capacity; (3) no assessment of the integration of the EWS into a routine surveillance system could be found, and only few studies addressed the users' perspective of the tool; (4) almost all EWS tools require highly skilled users with advanced statistics; and (5) spatial prediction remains a limitation with no tool currently able to map high transmission areas at small spatial level.

CONCLUSIONS

In view of the escalating infectious diseases as global threats, gaps and challenges are significantly present within the EWS applications. While some advanced EWS showed high prediction abilities, the scarcity of tool assessments in terms of integration into existing national surveillance systems as well as of the feasibility of transforming model outputs into local vector control or action plans tends to limit in most cases the support of countries in controlling disease outbreaks.

Exploiting Real-time Search Engine Queries for Earthquake Detection: A Summary of Results

Online search engine has been widely regarded as the most convenient approach for information acquisition. Indeed, the intensive information-seeking behaviors of search engine users make it possible to exploit search engine queries as effective “crowd sensors” for event monitoring. While some researchers have investigated the feasibility of using search engine queries for coarse-grained event analysis, the capability of search engine queries for real-time event detection has been largely neglected. To this end, in this article, we introduce a large-scale and systematic study on exploiting real-time search engine queries for outbreak event detection, with a focus on earthquake rapid reporting. In particular, we propose a realistic system of real-time earthquake detection through monitoring millions of queries related to earthquakes from a dominant online search engine in China. Specifically, we first investigate a large set of queries for selecting the representative queries that are highly correlated with the outbreak of earthquakes. Then, based on the real-time streams of selected queries, we design a novel machine learning–enhanced two-stage burst detection approach for detecting earthquake events. Meanwhile, the location of an earthquake epicenter can be accurately estimated based on the spatial-temporal distribution of search engine queries. Finally, through the extensive comparison with earthquake catalogs from China Earthquake Networks Center, 2015, the detection precision of our system can achieve 87.9%, and the accuracy of location estimation (province level) is 95.7%. In particular, 50% of successfully detected results can be found within 62 s after earthquake, and 50% of successful locations can be found within 25.5 km of seismic epicenter. Our system also found more than 23.3% extra earthquakes that were felt by people but not publicly released, 12.1% earthquake-like special outbreaks, and meanwhile, revealed many interesting findings, such as the typical query patterns of earthquake rumor and regular memorial events. Based on these results, our system can timely feed back information to the search engine users according to various cases and accelerate the information release of felt earthquakes.

Using Search Trends to Analyze Web-Based Interest in Lower Urinary Tract Symptoms-Related Inquiries, Diagnoses, and Treatments in Mainland China: Infodemiology Study of Baidu Index Data

Background

Lower urinary tract symptoms (LUTS) are one of the most commonly described urination disorders worldwide. Previous investigations have focused predominantly on the prospective identification of cases that meet the researchers’ criteria; thus, the genuine demands regarding LUTS from patients and related issues may be neglected.

Objective

We aimed to examine web-based search trends and behaviors related to LUTS on a national and regional scale by using the dominant, major search engine in mainland China.

Methods

Baidu Index was queried by using LUTS-related terms for the period of January 2011 to September 2020. The search volume for each term was recorded to analyze search trends and demographic distributions. For user interest, user demand graph data and trend data were collected and analyzed.

Results

Of the 13 LUTS domains, 11 domains are available in the Baidu Index database. The Baidu search index for each LUTS domain varied from 37.78% to 1.47%. The search trends for urinary frequency (2011-2018: annual percent change APC=7.82%; P<.001), incomplete emptying (2011-2014: APC=17.74%; P<.001), nocturia (2011-2018: APC=11.54%; P<.001), dysuria (2017-2020: APC=20.77%; P<.001), and incontinence (2011-2016: APC=13.39%; P<.001) exhibited fluctuations over time. The search index trends for weak stream (2011-2017: APC=−4.68%; P<.001; 2017-2020: APC=9.32%; P=.23), split stream (2011-2013: APC=9.50%; P=.44; 2013-2020: APC=2.05%; P=.71), urgency (2011-2018: APC=−2.63%; P=.03; 2018-2020: APC=8.58%; P=.19), and nocturnal enuresis (2011-2018: APC=−3.20%; P=.001; 2018-2020: APC=−4.21%; P=.04) remained relatively stable and consistent. The age distribution of the population for all LUTS-related inquiries showed that individuals aged 20 to 40 years made 73.86% (49,218,123/66,635,247) of the total search inquiries. Further, individuals aged 40 to 49 years made 12.29% (8,193,922/66,635,247) of the total search inquiries for all LUTS-related terms. People from the east part of China made 67.79% (45,172,031/66,635,247) of the total search queries. Additionally, most of the searches for LUTS-related terms were related to those for urinary diseases to varying degrees.

Conclusions

Web-based interest in LUTS-related terms fluctuated wildly and was reflected timely by Baidu Index in mainland China. The web-based search popularity of each LUTS-related term varied significantly and differed based on personal interests, the population’s concerns, regional variations, and gender. These data can be used by care providers to track the prevalence of LUTS and the population’s interests, guide the establishment of disease-specific health care policies, and optimize physician-patient health care sessions.

Predicting seasonal influenza using supermarket retail records

Increased availability of epidemiological data, novel digital data streams, and the rise of powerful machine learning approaches have generated a surge of research activity on real-time epidemic forecast systems. In this paper, we propose the use of a novel data source, namely retail market data to improve seasonal influenza forecasting. Specifically, we consider supermarket retail data as a proxy signal for influenza, through the identification of sentinel baskets, i.e., products bought together by a population of selected customers. We develop a nowcasting and forecasting framework that provides estimates for influenza incidence in Italy up to 4 weeks ahead. We make use of the Support Vector Regression (SVR) model to produce the predictions of seasonal flu incidence. Our predictions outperform both a baseline autoregressive model and a second baseline based on product purchases. The results show quantitatively the value of incorporating retail market data in forecasting models, acting as a proxy that can be used for the real-time analysis of epidemics.

Estimation of Asthma Symptom Onset Using Internet Search Queries: Lag-Time Series Analysis

Background

Asthma affects over 330 million people worldwide. Timing of an asthma event is extremely important and lack of identification of asthma increases the risk of death. A major challenge for health systems is the length of time between symptom onset and care seeking, which could result in delayed treatment initiation and worsening of symptoms.

Objective

This study evaluates the utility of the internet search query data for the identification of the onset of asthma symptoms.

Methods

Pearson correlation coefficients between the time series of hospital admissions and Google searches were computed at lag times from 4 weeks before hospital admission to 4 weeks after hospital admission. An autoregressive integrated moving average (ARIMAX) model with an autoregressive process at lags of 1 and 2 and Google searches at weeks –1 and –2 as exogenous variables were conducted to validate our correlation results.

Results

Google search volume for asthma had the highest correlation at 2 weeks before hospital admission. The ARIMAX model using an autoregressive process showed that the relative searches from Google about asthma were significant at lags 1 (P<.001) and 2 (P=.04).

Conclusions

Our findings demonstrate that internet search queries may provide a real-time signal for asthma events and may be useful to measure the timing of symptom onset.

Turn to the Internet First? Using Online Medical Behavioral Data to Forecast COVID-19 Epidemic Trend

The surveillance and forecast of newly confirmed cases are important to mobilize medical resources and facilitate policymaking during a public health emergency. Digital surveillance using data available online has increasingly become a trend with the advancement of the Internet. In this study, we assessed the predictive value of multiple online medical behavioral data, including online medical consultation (OMC), online medical appointment (OMA), and online medical search (OMS) for the regional outbreak of coronavirus disease 2019 in Shenzhen, China during January 1, 2020 to March 5, 2020. Multivariate vector autoregression models were used for the prediction. The results identified a novel predictor, OMC, which can forecast the disease trend up to 2 days ahead of the official reports of confirmed cases from the local health department. OMS data had relatively weaker predictive power than OMC in our model, and OMA data failed to predict the confirmed cases. This study highlights the importance of OMC data and has implication in providing evidence-based guidelines for local authorities to evaluate risks and allocate resources during the pandemic.

Public Emotions and Rumors Spread During the COVID-19 Epidemic in China: Web-Based Correlation Study

BACKGROUND

Various online rumors have led to inappropriate behaviors among the public in response to the COVID-19 epidemic in China. These rumors adversely affect people's physical and mental health. Therefore, a better understanding of the relationship between public emotions and rumors during the epidemic may help generate useful strategies for guiding public emotions and dispelling rumors.

OBJECTIVE

This study aimed to explore whether public emotions are related to the dissemination of online rumors in the context of COVID-19.

METHODS

We used the web-crawling tool Scrapy to gather data published by People's Daily on Sina Weibo, a popular social media platform in China, after January 8, 2020. Netizens' comments under each Weibo post were collected. Nearly 1 million comments thus collected were divided into 5 categories: happiness, sadness, anger, fear, and neutral, based on the underlying emotional information identified and extracted from the comments by using a manual identification process. Data on rumors spread online were collected through Tencent's Jiaozhen platform. Time-lagged cross-correlation analyses were performed to examine the relationship between public emotions and rumors.

RESULTS

Our results indicated that the angrier the public felt, the more rumors there would likely be (r=0.48, P<.001). Similar results were observed for the relationship between fear and rumors (r=0.51, P<.001) and between sadness and rumors (r=0.47, P<.001). Furthermore, we found a positive correlation between happiness and rumors, with happiness lagging the emergence of rumors by 1 day (r=0.56, P<.001). In addition, our data showed a significant positive correlation between fear and fearful rumors (r=0.34, P=.02).

CONCLUSIONS

Our findings confirm that public emotions are related to the rumors spread online in the context of COVID-19 in China. Moreover, these findings provide several suggestions, such as the use of web-based monitoring methods, for relevant authorities and policy makers to guide public emotions and behavior during this public health emergency.

Online Public Attention During the Early Days of the COVID-19 Pandemic: Infoveillance Study Based on Baidu Index

BACKGROUND

The COVID-19 pandemic has become a global public health event, attracting worldwide attention. As a tool to monitor public awareness, internet search engines have been widely used in public health emergencies.

OBJECTIVE

This study aims to use online search data (Baidu Index) to monitor the public's attention and verify internet search engines' function in public attention monitoring of public health emergencies.

METHODS

We collected the Baidu Index and the case monitoring data from January 20, 2020, to April 20, 2020. We combined the Baidu Index of keywords related to COVID-19 to describe the public attention's temporal trend and spatial distribution, and conducted the time lag cross-correlation analysis.

RESULTS

The Baidu Index temporal trend indicated that the changes of the Baidu Index had a clear correspondence with the development time node of the pandemic. The Baidu Index spatial distribution showed that in the regions of central and eastern China, with denser populations, larger internet user bases, and higher economic development levels, the public was more concerned about COVID-19. In addition, the Baidu Index was significantly correlated with six case indicators of new confirmed cases, new death cases, new cured discharge cases, cumulative confirmed cases, cumulative death cases, and cumulative cured discharge cases. Moreover, the Baidu Index was 0-4 days earlier than new confirmed and new death cases, and about 20 days earlier than new cured and discharged cases while 3-5 days later than the change of cumulative cases.

CONCLUSIONS

The national public's demand for epidemic information is urgent regardless of whether it is located in the hardest hit area. The public was more sensitive to the daily new case data that represents the progress of the epidemic, but the public's attention to the epidemic situation in other areas may lag behind. We could set the Baidu Index as the sentinel and the database in the online infoveillance system for infectious disease and public health emergencies. According to the monitoring data, the government needs to prevent and control the possible outbreak in advance and communicate the risks to the public so as to ensure the physical and psychological health of the public in the epidemic.

An Extensive Search Trends-Based Analysis of Public Attention on Social Media in the Early Outbreak of COVID-19 in China

Background

A novel coronavirus (COVID-19) caused pneumonia broke out at the end of 2019 in Wuhan, China. Many cases were subsequently reported in other cities, which has aroused strong reverberations on the Internet and social media around the world.

Objective

The aim of this study was to investigate the reaction of global Internet users to the outbreak of COVID-19 by evaluating the possibility of using Internet monitoring as an instrument in handling communicable diseases and responding to public health emergencies.

Methods

The disease-related data were retrieved from China's National Health Commission (CNHC) and World Health Organization (WHO) from January 10 to February 29, 2020. Daily Google Trends (GT) and daily Baidu Attention Index (BAI) for the keyword "Coronavirus" were collected from their official websites. Rumors which occurred in the course of this outbreak were mined from Chinese National Platform to Refute Rumors (CNPRR) and Tencent Platform to Refute Rumors (TPRR). Kendall's Tau-B rank test was applied to check the bivariate correlation among the two indexes mentioned above, epidemic trends, and rumors.

Results

After the outbreak of COVID-19, both daily BAI and daily GT increased rapidly and remained at a high level, this process lasted about 10 days. When major events occurred, daily BAI, daily GT, and the number of rumors simultaneously reached new peaks. Our study indicates that these indexes and rumors are statistically related to disease-related indicators. Information symmetry was also found to help significantly eliminate the false news and to prevent rumors from spreading across social media through the epidemic outbreak.

Conclusion

Compared to traditional methods, Internet monitoring could be particularly efficient and economical in the prevention and control of epidemic and rumors by reflecting public attention and attitude, especially in the early period of an outbreak.

The Application of Internet-Based Sources for Public Health Surveillance (Infoveillance): Systematic Review

Background

Public health surveillance is based on the continuous and systematic collection, analysis, and interpretation of data. This informs the development of early warning systems to monitor epidemics and documents the impact of intervention measures. The introduction of digital data sources, and specifically sources available on the internet, has impacted the field of public health surveillance. New opportunities enabled by the underlying availability and scale of internet-based sources (IBSs) have paved the way for novel approaches for disease surveillance, exploration of health communities, and the study of epidemic dynamics. This field and approach is also known as infodemiology or infoveillance.

Objective

This review aimed to assess research findings regarding the application of IBSs for public health surveillance (infodemiology or infoveillance). To achieve this, we have presented a comprehensive systematic literature review with a focus on these sources and their limitations, the diseases targeted, and commonly applied methods.

Methods

A systematic literature review was conducted targeting publications between 2012 and 2018 that leveraged IBSs for public health surveillance, outbreak forecasting, disease characterization, diagnosis prediction, content analysis, and health-topic identification. The search results were filtered according to previously defined inclusion and exclusion criteria.

Results

Spanning a total of 162 publications, we determined infectious diseases to be the preferred case study (108/162, 66.7%). Of the eight categories of IBSs (search queries, social media, news, discussion forums, websites, web encyclopedia, and online obituaries), search queries and social media were applied in 95.1% (154/162) of the reviewed publications. We also identified limitations in representativeness and biased user age groups, as well as high susceptibility to media events by search queries, social media, and web encyclopedias.

Conclusions

IBSs are a valuable proxy to study illnesses affecting the general population; however, it is important to characterize which diseases are best suited for the available sources; the literature shows that the level of engagement among online platforms can be a potential indicator. There is a necessity to understand the population’s online behavior; in addition, the exploration of health information dissemination and its content is significantly unexplored. With this information, we can understand how the population communicates about illnesses online and, in the process, benefit public health.

Social Media- and Internet-Based Disease Surveillance for Public Health

Disease surveillance systems are a cornerstone of public health tracking and prevention. This review addresses the use, promise, perils, and ethics of social media- and Internet-based data collection for public health surveillance. Our review highlights untapped opportunities for integrating digital surveillance in public health and current applications that could be improved through better integration, validation, and clarity on rules surrounding ethical considerations. Promising developments include hybrid systems that couple traditional surveillance data with data from search queries, social media posts, and crowdsourcing. In the future, it will be important to identify opportunities for public and private partnerships, train public health experts in data science, reduce biases related to digital data (gathered from Internet use, wearable devices, etc.), and address privacy. We are on the precipice of an unprecedented opportunity to track, predict, and prevent global disease burdens in the population using digital data.

Syndromic surveillance using web data: a systematic review

During the recent years, a lot of debate is taken place about the evolution of Smart Healthcare systems. Particularly, how these systems can help people improve human conditions of health, by taking advantages of the new Information and Communication Technologies (ICT), regarding early prediction and efficient treatment. The purpose of this study is to provide a systematic review of the current literature available that focuses on information systems on syndromic surveillance using web data. All published items concern articles, books, reviews, reports, conference announcements, and dissertations. We used a variation of PRISMA Statements methodology to conduct a systematic review. The review identifies the relevant published papers from the year 2004 to 2018, systematically includes and explores them to extract similarities, gaps, and conclusions on the research that has been done so far. The results presented concern the year, the examined disease, the web data source, the geographic location/country, and the data analysis method used. The results show that influenza is the most examined infectious disease. The internet tools most used are Twitter and Google. Regarding the geographical areas explored in the published papers, the most examined country is the United States, since many scientists come from this country. There is a significant growth of articles since 2009. There are also various statistical methods used to correlate the data retrieved from the internet to the data from national authorities. The conclusion of all researches is that the Web can be a useful tool for the detection of serious epidemics and for a creation of a syndromic surveillance system using the Web, since we can predict epidemics from web data before they are officially detected in population. With the advance of ICT, Smart Healthcare can benefit from the monitoring of epidemics and the early prediction of such a system, improving national or international health strategies and policy decision. This can be achieved through the provision of new technology tools to enhance health monitoring systems toward the new innovations of Smart Health or eHealth, even with the emerging technologies of Internet of Things. The challenges and impacts of an electronic system based on internet data include the social, medical, and technological disciplines. These can be further extended to Smart Healthcare, as the data streaming can provide with real-time information, awareness on epidemics and alerts for both patients or medical scientists. Finally, these new systems can help improve the standards of human life.

Using big data to predict pertussis infections in Jinan city, China: a time series analysis

This study aims to use big data (climate data, internet query data and school calendar patterns (SCP)) to improve pertussis surveillance and prediction, and develop an early warning model for pertussis epidemics. We collected weekly pertussis notifications, SCP, climate and internet search query data (Baidu index (BI)) in Jinan, China between 2013 and 2017. Time series decomposition and temporal risk assessment were used for examining the epidemic features in pertussis infections. A seasonal autoregressive integrated moving average (SARIMA) model and regression tree model were developed to predict pertussis occurrence using identified predictors. Our study demonstrates clear seasonal patterns in pertussis epidemics, and pertussis activity was most significantly associated with BI at 2-week lag (r_BI = 0.73, p < 0.05), temperature at 1-week lag (r_temp = 0.19, p < 0.05) and rainfall at 2-week lag (r_rainfall = 0.27, p < 0.05). No obvious relationship between pertussis peaks and school attendance was found in the study. Pertussis cases were more likely to be temporally concentrated throughout the epidemics during the study period. SARIMA models with 2-week-lagged BI and 1-week-lagged temperature had better predictive performance (β_{search query} = 0.06, p = 0.02; β_temp = 0.16, p = 0.03) with large correlation coefficients (r = 0.67, p < 0.01) and low root mean squared error (RMSE) value (r = 3.59). The regression tree model identified threshold values of potential predictors (search query, climate and SCP) for pertussis epidemics. Our results showed that internet query in conjunction with social and climatic data can predict pertussis epidemics, which is a foundation of using such data to develop early warning systems.

A dengue fever predicting model based on Baidu search index data and climate data in South China

With the acceleration of global urbanization and climate change, dengue fever is spreading worldwide. Different levels of dengue fever have also occurred in China, especially in southern China, causing enormous economic losses. Unfortunately, there is no effective treatment for dengue, and the most popular dengue vaccine does not exhibit good curative effects. Therefore, we developed a Generalized Additive Mixed Model (GAMM) that gathered climate factors (mean temperature, relative humidity and precipitation) and Baidu search data during 2011-2015 in Guangzhou city to improve the accuracy of dengue fever prediction. Firstly, the time series dengue fever data were decomposed into seasonal, trend and remainder components by the seasonal-trend decomposition procedure based on loess (STL). Secondly, the time lag of variables was determined in cross-correlation analysis and the order of autocorrelation was estimated using autocorrelation (ACF) and partial autocorrelation functions (PACF). Finally, the GAMM was built and evaluated by comparing it with Generalized Additive Mode (GAM). Experimental results indicated that the GAMM (R2: 0.95 and RMSE: 34.1) has a superior prediction capability than GAM (R2: 0.86 and RMSE: 121.9). The study could help the government agencies and hospitals respond early to dengue fever outbreak.

The Relationship Between the Actual Level of Air Pollution and Residents' Concern about Air Pollution: Evidence from Shanghai, China

This study explored the relationship between the actual level of air pollution and residents’ concern about air pollution. The actual air pollution level was measured by the air quality index (AQI) reported by environmental monitoring stations, while residents’ concern about air pollution was reflected by the Baidu index using the Internet search engine keywords “Shanghai air quality”. On the basis of the daily data of 2068 days for the city of Shanghai in China over the period between 2 December 2013 and 31 July 2019, a vector autoregression (VAR) model was built for empirical analysis. Estimation results provided three interesting findings. (1) Local residents perceived the deprivation of air quality and expressed their concern on air pollution quickly, within the day on which the air quality index rose. (2) A decline in air quality in another major city, such as Beijing, also raised the concern of Shanghai residents about local air quality. (3) A rise in Shanghai residents’ concern had a beneficial impact on air quality improvement. This study implied that people really cared much about local air quality, and it was beneficial to inform more residents about the situation of local air quality and the risks associated with air pollution.

Association of sociodemographic factors and internet query data with pertussis infections in Shandong, China

This study explored how internet queries vary in facilitating monitoring of pertussis, and the effects of sociodemographic characteristics on such variation by city in Shandong province, China. We collected weekly pertussis notifications, Baidu Index (BI) data and yearly sociodemographic data at the city level between 1 January 2009 and 31 December 2017. Spearman's correlation was performed for temporal risk indices, generalised linear models and regression tree models were developed to identify the hierarchical effects and the threshold between sociodemographic factors and internet query data with pertussis surveillance. The BI was correlated with pertussis notifications, with a strongly spatial variation among cities in temporal risk indices (composite temporal risk metric (CTRM) range: 0.59–1.24). The percentage of urban population (relative risk (RR): 1.05, 95% confidence interval (CI) 1.03–1.07), the proportion of highly educated population (RR: 1.27, 95% CI 1.16–1.39) and the internet access rate (RR: 1.04, 95% CI 1.02–1.05) were correlated with CTRM. Higher RRs in the three identified sociodemographic factors were associated with higher stratified CTRM. The percentage of highly educated population was the most important determinant in the BI with pertussis surveillance. The findings may lead to spatially-specific criteria to inform development of an early warning system of pertussis infections using internet query data.

The prediction of petition based on Big Data

Purpose

The development of Big Data and online searching engine provides a good opportunity for studying petition in China. This study has constructed a set of indices for predicting petitions in China by using online searching engines and further explored the predicting role of economic, environment and public life risk perception in various petitions.

Design/methodology/approach

Based on the study of Xue and Liu (2017), this research first re-classified offline petition by human and cluster analysis in terms of social risk perception and built online searching indices of the two sets of petition by using data from “Google Trend” and “Baidu Index.” Second, it analyzed the predicting effect of social risk perception on online searching indices of petition by using Granger causality analysis. Finally, this study integrated the results and selected significant paths from social risk perception to the two sets of petition.

Findings

The study found that the re-classification made by human was more appropriate than the categories made by cluster analysis in terms of social risk perception. For the two sets of petition, the correlations between offline petition and Baidu Index of petition were both more significant than that of Google index. Moreover, economic and finance and resource and environment risk perception had a significant predicting effect on more than one kind of online searching indices of petition.

Originality/value

The results have demonstrated the important role of economic issues in China on predicting petitions of the economic kind, as well as other kinds. They have also reflected the dominant social contradictions and their relationship in modern China.

Evaluating the effects of control interventions and estimating the inapparent infections for dengue outbreak in Hangzhou, China

Background

The number of dengue fever (DF) cases and the number of dengue outbreaks have increased in recent years in Zhejiang Province, China. An unexpected dengue outbreak was reported in Hangzhou in 2017 and caused more than one thousand dengue cases. This study was undertaken to evaluate the effectiveness of the actual control measures, estimate the proportion of inapparent infections during this outbreak and simulate epidemic development based on different levels of control measures taking inapparent infections into consideration.

Methods

The epidemic data of dengue cases in Hangzhou, Zhejiang Province, in 2017 and the number of the people exposed to the outbreaks were obtained from the China Information Network System of Disease Prevention and Control. The epidemic without intervention measures was used to estimate the unknown parameters. A susceptible-exposed-infectious/inapparent-recovered (SEIAR) model was used to estimate the effectiveness of the control interventions. The inapparent infections were also evaluated at the same time.

Results

In total, 1137 indigenous dengue cases were reported in Hangzhou in 2017. The number of indigenous dengue cases was estimated by the SEIAR model. This number was predicted to reach 6090 by the end of November 2, 2017, if no control measures were implemented. The total number of reported cases was reduced by 81.33% in contrast to the estimated incidence without intervention. The number of average daily inapparent cases was 10.18 times higher than the number of symptomatic cases. The earlier and more rigorously the vector control interventions were implemented, the more effective they were. The results showed that implementing vector control continuously for more than twenty days was more effective than every few days of implementation. Case isolation is not sufficient enough for epidemic control and only reduced the incidence by 38.10% in contrast to the estimated incidence without intervention, even if case isolation began seven days after the onset of the first case.

Conclusions

The practical control interventions in the outbreaks that occurred in Hangzhou City were highly effective. The proportion of inapparent infections was large, and it played an important role in transmitting the disease during this epidemic. Early, continuous and high efficacy vector control interventions are necessary to limit the development of a dengue epidemic. Timely diagnosis and case reporting are important in the intervention at an early stage of the epidemic.

Avian Influenza A (H7N9) and related Internet search query data in China

The use of Internet-based systems for infectious disease surveillance has been increasingly explored in recent years. However, few studies have used Internet search query or social media data to monitor spatial and temporal trends of avian influenza in China. This study investigated the potential of using search query and social media data in detecting and monitoring avian influenza A (H7N9) cases in humans in China. We collected weekly data on laboratory-confirmed H7N9 cases in humans, as well as H7N9-related Baidu Search Index (BSI) and Weibo Posting Index (WPI) data in China from 2013 to 2017, to explore the spatial and temporal trends of H7N9 cases and H7N9-related Internet search queries. Our findings showed a positive relationship of H7N9 cases with BSI and WPI search queries spatially and temporally. The outbreak threshold time and peak time of H7N9-related BSI and WPI searches preceded H7N9 cases in most years. Seasonal autoregressive integrated moving average (SARIMA) models with BSI (β = 0.008, p < 0.001) and WPI (β = 0.002, p = 0.036) were used to predict the number of H7N9 cases. Regression tree model analysis showed that the average H7N9 cases increased by over 2.4-fold (26.8/11) when BSI for H7N9 was >  = 11524. Both BSI and WPI data could be used as indicators to develop an early warning system for H7N9 outbreaks in the future.

Study of the Effects of Air Pollutants on Human Health Based on Baidu Indices of Disease Symptoms and Air Quality Monitoring Data in Beijing, China

There is an increasing body of evidence showing the impact of air pollutants on human health such as on the respiratory, and cardio- and cerebrovascular systems. In China, as people begin to pay more attention to air quality, recent research focused on the quantitative assessment of the effects of air pollutants on human health. To assess the health effects of air pollutants and to construct an indicator placing emphasis on health impact, a generalized additive model was selected to assess the health burden caused by air pollution. We obtained Baidu indices (an evaluation indicator launched by Baidu Corporation to reflect the search popularity of keywords from its search engine) to assess daily query frequencies of 25 keywords considered associated with air pollution-related diseases. Moreover, we also calculated the daily concentrations of major air pollutants (including PM10, PM2.5, SO₂, O₃, NO₂, and CO) and the daily air quality index (AQI) values, and three meteorological factors: daily mean wind level, daily mean air temperature, and daily mean relative humidity. These data cover the area of Beijing from 1 March 2015 to 30 April 2017. Through the analysis, we produced the relative risks (RRs) of the six main air pollutants for respiratory, and cardio- and cerebrovascular diseases. The results showed that O₃ and NO₂ have the highest health impact, followed by PM10 and PM2.5. The effects of any pollutant on cardiovascular diseases was consistently higher than on respiratory diseases. Furthermore, we evaluated the currently used AQI in China and proposed an RR-based index (health AQI, HAQI) that is intended for better indicating the effects of air pollutants on respiratory, and cardio- and cerebrovascular diseases than AQI. A higher Pearson correlation coefficient between HAQI and RRTotal than that between AQI and RRTotal endorsed our efforts.

Inter-annual variation in seasonal dengue epidemics driven by multiple interacting factors in Guangzhou, China

Vector-borne diseases display wide inter-annual variation in seasonal epidemic size due to their complex dependence on temporally variable environmental conditions and other factors. In 2014, Guangzhou, China experienced its worst dengue epidemic on record, with incidence exceeding the historical average by two orders of magnitude. To disentangle contributions from multiple factors to inter-annual variation in epidemic size, we fitted a semi-mechanistic model to time series data from 2005-2015 and performed a series of factorial simulation experiments in which seasonal epidemics were simulated under all combinations of year-specific patterns of four time-varying factors: imported cases, mosquito density, temperature, and residual variation in local conditions not explicitly represented in the model. Our results indicate that while epidemics in most years were limited by unfavorable conditions with respect to one or more factors, the epidemic in 2014 was made possible by the combination of favorable conditions for all factors considered in our analysis.

The application of meteorological data and search index data in improving the prediction of HFMD: A study of two cities in Guangdong Province, China

Hand, foot and mouth disease (HFMD) is a public health issue in China, and its incidence in Guangdong Province is higher than the national average. Previous studies have found climatic factors have an influential role in the transmission of HFMD. Internet search technology has been shown to predict some infectious disease epidemics and is a potential resource in tracking epidemics in countries where the use of Internet search index data is prevalent. This study aims to improve the prediction of HFMD in two Chinese cities, Shantou and Shenzhen in Guangdong Province, applying both meteorological data and Baidu search indices to create a HFMD forecasting model. To this end, the relationship between meteorological factors and HFMD was found to be linear in both cities, while the relationship between search engine data and HFMD was not consistent. The results of our study suggest that using both Internet search and meteorological data can improve the prediction of HFMD incidence. Using comparative analysis of both cities, we posit that improved quality search indices enhance prediction of HFMD.

Association Between Cancer Incidence and Mortality in Web-Based Data in China: Infodemiology Study

Background

Cancer poses a serious threat to the health of Chinese people, resulting in a major challenge for public health work. Today, people can obtain relevant information from not only medical workers in hospitals, but also the internet in any place in real-time. Search behaviors can reflect a population’s awareness of cancer from a completely new perspective, which could be driven by the underlying cancer epidemiology. However, such Web-retrieved data are not yet well validated or understood.

Objective

This study aimed to explore whether a correlation exists between the incidence and mortality of cancers and normalized internet search volumes on the big data platform, Baidu. We also assessed whether the distribution of people who searched for specific types of cancer differed by gender. Finally, we determined whether there were regional disparities among people who searched the Web for cancer-related information.

Methods

Standard Boolean operators were used to choose search terms for each type of cancer. Spearman’s correlation analysis was used to explore correlations among monthly search index values for each cancer type and their monthly incidence and mortality rates. We conducted cointegration analysis between search index data and incidence rates to examine whether a stable equilibrium existed between them. We also conducted cointegration analysis between search index data and mortality data.

Results

The monthly Baidu index was significantly correlated with cancer incidence rates for 26 of 28 cancers in China (lung cancer: r=.80, P<.001; liver cancer: r=.28, P=.016; stomach cancer: r=.50, P<.001; esophageal cancer: r=.50, P<.001; colorectal cancer: r=.81, P<.001; pancreatic cancer: r=.86, P<.001; breast cancer: r=.56, P<.001; brain and nervous system cancer: r=.63, P<.001; leukemia: r=.75, P<.001; Non-Hodgkin lymphoma: r=.88, P<.001; Hodgkin lymphoma: r=.91, P<.001; cervical cancer: r=.64, P<.001; prostate cancer: r=.67, P<.001; bladder cancer: r=.62, P<.001; gallbladder and biliary tract cancer: r=.88, P<.001; lip and oral cavity cancer: r=.88, P<.001; ovarian cancer: r=.58, P<.001; larynx cancer: r=.82, P<.001; kidney cancer: r=.73, P<.001; squamous cell carcinoma: r=.94, P<.001; multiple myeloma: r=.84, P<.001; thyroid cancer: r=.77, P<.001; malignant skin melanoma: r=.55, P<.001; mesothelioma: r=.79, P<.001; testicular cancer: r=.57, P<.001; basal cell carcinoma: r=.83, P<.001). The monthly Baidu index was significantly correlated with cancer mortality rates for 24 of 27 cancers. In terms of the whole population, the number of women who searched for cancer-related information has slowly risen over time. People aged 30-39 years were most likely to use search engines to retrieve cancer-related knowledge. East China had the highest Web search volumes for cancer.

Conclusions

Search behaviors indeed reflect public awareness of cancer from a different angle. Research on internet search behaviors could present an innovative and timely way to monitor and estimate cancer incidence and mortality rates, especially for cancers not included in national registries.

An ensemble forecast model of dengue in Guangzhou, China using climate and social media surveillance data

BACKGROUND

China experienced an unprecedented outbreak of dengue in 2014, and the number of dengue cases reached the highest level over the past 25 years. There is a significant delay in the release of official case count data, and our ability to timely track the timing and magnitude of local outbreaks of dengue remains limited.

MATERIAL AND METHODS

We developed an ensemble penalized regression algorithm (EPRA) for initializing near-real time forecasts of the dengue epidemic trajectory by integrating different penalties (LASSO, Ridge, Elastic Net, SCAD and MCP) with the techniques of iteratively sampling and model averaging. Multiple streams of near-real time data including dengue-related Baidu searches, Sina Weibo posts, and climatic conditions with historical dengue incidence were used. We compared the predictive power of the EPRA with the alternates, penalized regression models using single penalties, to retrospectively forecast weekly dengue incidence and detect outbreak occurrence defined using different cutoffs, during the periods of 2011-2016 in Guangzhou, south China.

RESULTS

The EPRA showed the best or at least comparable performance for 1-, 2-week ahead out-of-sample and leave-one-out cross validation forecasts. The findings indicate that skillful near-real time forecasts of dengue and confidence in those predictions can be made. For detecting dengue outbreaks, the EPRA predicted periods of high incidence of dengue more accurately than the alternates.

CONCLUSION

This study developed a statistically rigorous approach for near-real time forecast of dengue in China. The EPRA provides skillful forecasts and can be used as timely and complementary ways to assess dengue dynamics, which will help to design interventions to mitigate dengue transmission.

Using internet search data to predict new HIV diagnoses in China: a modelling study

OBJECTIVES

Internet data are important sources of abundant information regarding HIV epidemics and risk factors. A number of case studies found an association between internet searches and outbreaks of infectious diseases, including HIV. In this research, we examined the feasibility of using search query data to predict the number of new HIV diagnoses in China.

DESIGN

We identified a set of search queries that are associated with new HIV diagnoses in China. We developed statistical models (negative binomial generalised linear model and its Bayesian variants) to estimate the number of new HIV diagnoses by using data of search queries (Baidu) and official statistics (for the entire country and for Guangdong province) for 7 years (2010 to 2016).

RESULTS

Search query data were positively associated with the number of new HIV diagnoses in China and in Guangdong province. Experiments demonstrated that incorporating search query data could improve the prediction performance in nowcasting and forecasting tasks.

CONCLUSIONS

Baidu data can be used to predict the number of new HIV diagnoses in China up to the province level. This study demonstrates the feasibility of using search query data to predict new HIV diagnoses. Results could potentially facilitate timely evidence-based decision making and complement conventional programmes for HIV prevention.

Global Research on Syndromic Surveillance from 1993 to 2017: Bibliometric Analysis and Visualization

Syndromic Surveillance aims at analyzing medical data to detect clusters of illness or forecast disease outbreaks. Although the research in this field is flourishing in terms of publications, an insight of the global research output has been overlooked. This paper aims at analyzing the global scientific output of the research from 1993 to 2017. To this end, the paper uses bibliometric analysis and visualization to achieve its goal. Particularly, a data processing framework was proposed based on citation datasets collected from Scopus and Clarivate Analytics’ Web of Science Core Collection (WoSCC). The bibliometric method and Citespace were used to analyze the institutions, countries, and research areas as well as the current hotspots and trends. The preprocessed dataset includes 14,680 citation records. The analysis uncovered USA, England, Canada, France and Australia as the top five most productive countries publishing about Syndromic Surveillance. On the other hand, at the Pinnacle of academic institutions are the US Centers for Disease Control and Prevention (CDC). The reference co-citation analysis uncovered the common research venues and further analysis of the keyword cooccurrence revealed the most trending topics. The findings of this research will help in enriching the field with a comprehensive view of the status and future trends of the research on Syndromic Surveillance.

Forecasting influenza epidemics by integrating internet search queries and traditional surveillance data with the support vector machine regression model in Liaoning, from 2011 to 2015

Background

Influenza epidemics pose significant social and economic challenges in China. Internet search query data have been identified as a valuable source for the detection of emerging influenza epidemics. However, the selection of the search queries and the adoption of prediction methods are crucial challenges when it comes to improving predictions. The purpose of this study was to explore the application of the Support Vector Machine (SVM) regression model in merging search engine query data and traditional influenza data.

Methods

The official monthly reported number of influenza cases in Liaoning province in China was acquired from the China National Scientific Data Center for Public Health from January 2011 to December 2015. Based on Baidu Index, a publicly available search engine database, search queries potentially related to influenza over the corresponding period were identified. An SVM regression model was built to be used for predictions, and the choice of three parameters (C, γ, ε) in the SVM regression model was determined by leave-one-out cross-validation (LOOCV) during the model construction process. The model’s performance was evaluated by the evaluation metrics including Root Mean Square Error, Root Mean Square Percentage Error and Mean Absolute Percentage Error.

Results

In total, 17 search queries related to influenza were generated through the initial query selection approach and were adopted to construct the SVM regression model, including nine queries in the same month, three queries at a lag of one month, one query at a lag of two months and four queries at a lag of three months. The SVM model performed well when with the parameters (C = 2, γ = 0.005, ɛ = 0.0001), based on the ensemble data integrating the influenza surveillance data and Baidu search query data.

Conclusions

The results demonstrated the feasibility of using internet search engine query data as the complementary data source for influenza surveillance and the efficiency of SVM regression model in tracking the influenza epidemics in Liaoning.

Weather variables and the El Niño Southern Oscillation may drive the epidemics of dengue in Guangdong Province, China

OBJECTIVE

To investigate the periodicity of dengue and the relationship between weather variables, El Niño Southern Oscillation (ENSO) and dengue incidence in Guangdong Province, China.

METHODS

Guangdong monthly dengue incidence and weather data and El Niño index information for 1988 to 2015 were collected. Wavelet analysis was used to investigate the periodicity of dengue, and the coherence and time-lag phases between dengue and weather variables and ENSO. The Generalized Additive Model (GAM) approach was further employed to explore the dose-response relationship of those variables on dengue. Finally, random forest analysis was applied to measure the relative importance of the climate predictors.

RESULTS

Dengue in Guangdong has a dominant annual periodicity over the period 1988-2015. Mean minimum temperature, total precipitation, and mean relative humidity are positively related to dengue incidence for 2, 3, and 4months lag, respectively. ENSO in the previous 12months may have driven the dengue epidemics in 1995, 2002, 2006 and 2010 in Guangdong. GAM analysis indicates an approximate linear association for the temperature-dengue relationship, approximate logarithm curve for the humidity-dengue relationship, and an inverted U-shape association for the precipitation-dengue (the threshold of precipitation is 348mm per month) and ENSO-dengue relationships (the threshold of ENSO index is 0.6°C). The monthly mean minimum temperature in the previous two months was identified as the most important climate variable associated with dengue epidemics in Guangdong Province.

CONCLUSION

Our study suggests weather factors and ENSO are important predictors of dengue incidence. These findings provide useful evidence for early warning systems to help to respond to the global expansion of dengue fever.

Applicability of internet search index for asthma admission forecast using machine learning

OBJECTIVE

This study aimed to determine whether a search index could provide insight into trends in asthma admission in China. An Internet search index is a powerful tool to monitor and predict epidemic outbreaks. However, whether using an internet search index can significantly improve asthma admissions forecasts remains unknown. The long-term goal is to develop a surveillance system to help early detection and interventions for asthma and to avoid asthma health care resource shortages in advance.

METHODS

In this study, we used a search index combined with air pollution data, weather data, and historical admissions data to forecast asthma admissions using machine learning.

RESULTS

Results demonstrated that the best area under the curve in the test set that can be achieved is 0.832, using all predictors mentioned earlier.

CONCLUSION

A search index is a powerful predictor in asthma admissions forecast, and a recent search index can reflect current asthma admissions with a lag-effect to a certain extent. The addition of a real-time, easily accessible search index improves forecasting capabilities and demonstrates the predictive potential of search index.

Harnessing Big Data for Communicable Tropical and Sub-Tropical Disorders: Implications From a Systematic Review of the Literature

Aim

According to the World Health Organization (WHO), communicable tropical and sub-tropical diseases occur solely, or mainly in the tropics, thriving in hot, and humid conditions. Some of these disorders termed as neglected tropical diseases are particularly overlooked. Communicable tropical/sub-tropical diseases represent a diverse group of communicable disorders occurring in 149 countries, favored by tropical and sub-tropical conditions, affecting more than one billion people and imposing a dramatic societal and economic burden.

Methods

A systematic review of the extant scholarly literature was carried out, searching in PubMed/MEDLINE and Scopus. The search string used included proper keywords, like big data, nontraditional data sources, social media, social networks, infodemiology, infoveillance, novel data streams (NDS), digital epidemiology, digital behavior, Google Trends, Twitter, Facebook, YouTube, Instagram, Pinterest, Ebola, Zika, dengue, Chikungunya, Chagas, and the other neglected tropical diseases.

Results

47 original, observational studies were included in the current systematic review: 1 focused on Chikungunya, 6 on dengue, 19 on Ebola, 2 on Malaria, 1 on Mayaro virus, 2 on West Nile virus, and 16 on Zika. Fifteen were dedicated on developing and validating forecasting techniques for real-time monitoring of neglected tropical diseases, while the remaining studies investigated public reaction to infectious outbreaks. Most studies explored a single nontraditional data source, with Twitter being the most exploited tool (25 studies).

Conclusion

Even though some studies have shown the feasibility of utilizing NDS as an effective tool for predicting epidemic outbreaks and disseminating accurate, high-quality information concerning neglected tropical diseases, some gaps should be properly underlined. Out of the 47 articles included, only 7 were focusing on neglected tropical diseases, while all the other covered communicable tropical/sub-tropical diseases, and the main determinant of this unbalanced coverage seems to be the media impact and resonance. Furthermore, efforts in integrating diverse NDS should be made. As such, taking into account these limitations, further research in the field is needed.

Monitoring hand, foot and mouth disease by combining search engine query data and meteorological factors

Hand, foot and mouth disease (HFMD) has been recognized as a significant public health threat and poses a tremendous challenge to disease control departments. To date, the relationship between meteorological factors and HFMD has been documented, and public interest of disease has been proven to be trackable from the Internet. However, no study has explored the combination of these two factors in the monitoring of HFMD. Therefore, the main aim of this study was to develop an effective monitoring model of HFMD in Guangzhou, China by utilizing historical HFMD cases, Internet-based search engine query data and meteorological factors. To this end, a case study was conducted in Guangzhou, using a network-based generalized additive model (GAM) including all factors related to HFMD. Three other models were also constructed using some of the variables for comparison. The results suggested that the model showed the best estimating ability when considering all of the related factors.

Developing a dengue forecast model using machine learning: A case study in China

BACKGROUND

In China, dengue remains an important public health issue with expanded areas and increased incidence recently. Accurate and timely forecasts of dengue incidence in China are still lacking. We aimed to use the state-of-the-art machine learning algorithms to develop an accurate predictive model of dengue.

METHODOLOGY/PRINCIPAL FINDINGS

Weekly dengue cases, Baidu search queries and climate factors (mean temperature, relative humidity and rainfall) during 2011-2014 in Guangdong were gathered. A dengue search index was constructed for developing the predictive models in combination with climate factors. The observed year and week were also included in the models to control for the long-term trend and seasonality. Several machine learning algorithms, including the support vector regression (SVR) algorithm, step-down linear regression model, gradient boosted regression tree algorithm (GBM), negative binomial regression model (NBM), least absolute shrinkage and selection operator (LASSO) linear regression model and generalized additive model (GAM), were used as candidate models to predict dengue incidence. Performance and goodness of fit of the models were assessed using the root-mean-square error (RMSE) and R-squared measures. The residuals of the models were examined using the autocorrelation and partial autocorrelation function analyses to check the validity of the models. The models were further validated using dengue surveillance data from five other provinces. The epidemics during the last 12 weeks and the peak of the 2014 large outbreak were accurately forecasted by the SVR model selected by a cross-validation technique. Moreover, the SVR model had the consistently smallest prediction error rates for tracking the dynamics of dengue and forecasting the outbreaks in other areas in China.

CONCLUSION AND SIGNIFICANCE

The proposed SVR model achieved a superior performance in comparison with other forecasting techniques assessed in this study. The findings can help the government and community respond early to dengue epidemics.