Analysis of the interests of Google users on toothache information

Abstract

Background: The knowledge on health interests of a given population of Internet users might contribute to the increase of evidence on community's dental needs, and consequently, to the improvement of public health planning. The frequency of searches for specific issues on Google can be analyzed by the application of Google Trends.

Aim: In this study, we aimed to characterize the interests on toothache information of Google users from the United States, United Kingdom, Australia and Brazil.

Methods: The monthly variation of relative search volume (RSV) and the lists of main toothache-related queries were determined from January 2004 through April 2016 using Google Trends. Autoregressive Integrated Moving Average (ARIMA) forecasting models were developed to determine predictive RSV values for toothache for additional 12 months. Autocorrelation plots and general additive model (GAM) were applied to determine trends and seasonality in RSV curves. Through linear regression models, we assessed the association between the variation of annual means of RSV values and national statistics for toothache in the U.S. and U.K. Subsequently, the distribution of main queries according to the identification of endodontic pain, type of searching information, and the interest in self-management of toothache was evaluated for the four countries.

Results: The autocorrelation plots showed patterns of non-stationary time series. The monthly variation influenced the data of the U.S. and U.K., with the higher RSV values found respectively in January/July and December. Also, the interest on toothache in the U.K. increases in the second semester and in the fourth quarter, especially in December. Additionally, an annual variation affected significantly all time series, with the increment of RSV means over the years, varying from 265% in the U.S. to 745% in Brazil. In parallel, the increments in RSV values were also observed in all predictive curves. The annual variation of observed and fitted RSV values was directly associated with the increase of toothache visits in the U.S. and urgent dental treatments in the U.K. Moreover, the queries typed on Google were markedly linked to searches on endodontic pain information, especially in Brazil, where the residents usually searched for relief and/or self-management of pain.

Conclusions: Therefore, these findings indicate an increasing interest of Google users on toothache-related topics, regardless of country and season. The Internet activity can be used by policy makers as a complementary source of data for the development and implementation of strategies to control and prevent toothache complications.

Fig 1. Flowchart summarizing the development of query strategies to assess the RSV toothache values in the U.S., U.K., Australia and Brazil.

Fig 2. Autocorrelation and partial autocorrelation plots for the monthly variation of RSV toothache values.

(A) U.S., (B) U.K., (C) Australia, and (D) Brazil.

Fig 3. Seasonality of the interests of Google users on toothache.

It was estimated by fitting a generalized additive model (GAM) to the detrended Google Trends data (lag-1 difference). Note that the scales vary from negative to positive values, since they represent the variation of values of the RSV of a month minus the RSV of the previous month. For instance, the detrended value of December 2004 is represented by the difference of its RSV in relation to the RSV of November 2004. GAM values using monthly RSV as a predictive variable for Google data are represented in the heat map.

Fig 4. Predictive charts demonstrate the variation of RSV toothache values in the U.S., U.K., Australia and Brazil from January 2004 through April 2017.

Note that RSVs presented after April 2016 (black line) represent 12-month predictive values. Observe the increase of the interest of Google users on toothache in all countries.