Towards Identifying and Reducing the Bias of Disease Information Extracted from Search Engine Data

Abstract

The estimation of disease prevalence in online search engine data (e.g., Google Flu Trends (GFT)) has received a considerable amount of scholarly and public attention in recent years. While the utility of search engine data for disease surveillance has been demonstrated, the scientific community still seeks ways to identify and reduce biases that are embedded in search engine data. The primary goal of this study is to explore new ways of improving the accuracy of disease prevalence estimations by combining traditional disease data with search engine data. A novel method, Biased Sentinel Hospital-based Area Disease Estimation (B-SHADE), is introduced to reduce search engine data bias from a geographical perspective. To monitor search trends on Hand, Foot and Mouth Disease (HFMD) in Guangdong Province, China, we tested our approach by selecting 11 keywords from the Baidu index platform, a Chinese big data analyst similar to GFT. The correlation between the number of real cases and the composite index was 0.8. After decomposing the composite index at the city level, we found that only 10 cities presented a correlation of close to 0.8 or higher. These cities were found to be more stable with respect to search volume, and they were selected as sample cities in order to estimate the search volume of the entire province. After the estimation, the correlation improved from 0.8 to 0.864. After fitting the revised search volume with historical cases, the mean absolute error was 11.19% lower than it was when the original search volume and historical cases were combined. To our knowledge, this is the first study to reduce search engine data bias levels through the use of rigorous spatial sampling strategies.

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

“…The success of GFT motivated several studies aiming to assess current flu activity based on secondary data such as Internet search queries and electronic health records [ 29 – 35 ]. Several studies have been conducted on HFMD prediction using Baidu search queries [ 36 – 38 ]. In these research works, Baidu search queries are incorporated into forecasting methods, and the HFMD prediction is either at provincial or national level.…”

Modeling and Inference for Infectious Disease Dynamics: A Likelihood-Based Approach

“…It has been pointed out that failing to separate these sources entails dangers, both in the context of population dynamics in general (Nadeem et al, 2016) and of infectious disease dynamics in particular (see, e.g., Fujiwara, 2009; Gibbons et al, 2014). Moreover, measurement models have been receiving more attention motivated by the access to massive datasets related to infectious diseases in recent times (Huang et al, 2016). Here, we focus on two variations on the models of Section 3.2 for noisy parameters in measurement models that seem to have been so far unexplored: dependent environmental noise and diagnosis error.…”

Tracking and predicting hand, foot, and mouth disease (HFMD) epidemics in China by Baidu queries

“…Interestingly, these words use generic nouns but not ILI symptoms. Huang et al [22] used the same method to choose key words for the prediction of HFMD epidemics from Baidu queries, but extended the number of key words to 11. Hulth et al [14] detected an influenza outbreak in Sweden by counting 20 types of web queries that contained 'influenza' or symptoms of ILI (in Swedish).…”

“…Previous predictive studies, which adopted methods such as dynamic modeling [3], autologistic regression [4], gray system GM (1,1) [5,6], and neural networks [7], did not report errors in the predicted value; therefore the predictive value of these different models cannot be compared using MAPE. Huang et al [22] used MAPE to describe the difference of fitted results and the real HFMD data. But what we care about is the divergence between the predictive value and the actual case number.…”

“…A recent study by Huang et al [22] has estimated HFMD prevalence in Guangdong province, China, with Baidu search data. Taking into consideration spatial inconsistency between disease cases and internet queries in different areas, which might create a bias for epidemic prediction using search engine data, Huang et al evaluated Baidu search data with the biased sentinel hospital-based area disease estimation (B-SHADE) model [24] by sampling those subspaces with a high correlation coefficient between HFMD cases and Baidu queries [22]. However, whether a revision of the Baidu index is necessary for HFMD prediction with big internet datasets is still not clear.…”