Vesicular stomatitis forecasting based on Google Trends

Effect of the COVID-19 Mitigation Measure on Dental Care Needs in 17 Countries: A Regression Discontinuity Analysis

Objectives

The effect of COVID-19 mitigation measures on different oral health care needs is unclear. This study aimed to estimate the effect of COVID-19 mitigation measures on different types of oral health care utilization needs and explore the heterogeneity of such effects in different countries by using real-time Internet search data.

Methods

Data were obtained from Google Trends and other public databases. The monthly relative search volume (RSV) of the search topics "toothache," "gingivitis," "dentures," "orthodontics," and "mouth ulcer" from January 2004 to June 2021 was collected for analysis. The RSV value of each topics before and after COVID-19 was the primary outcome, which was estimated by regression discontinuity analysis (RD). The effect bandwidth time after the COVID-19 outbreak was estimated by the data-driven optimal mean square error bandwidth method. Effect heterogeneity of COVID-19 on dental care was also evaluated in different dental care categories and in countries with different human development index (HDI) rankings, dentist densities, and population age structures.

Results

A total of 17,850 monthly RSV from 17 countries were used for analysis. The RD results indicated that advanced dental care was significantly decreased (OR: 0.63, 95% CI: 0.47-0.85) after the COVID-19 outbreak, while emergency dental care toothache was significantly increased (OR: 1.54, 95% CI: 0.99-2.37) 4 months after the COVID-19 outbreak. Compared to the countries with low HDI and low dentist density, the effect was much more evident in countries with high HDI and high dentist density.

Conclusions

COVID-19 mitigation measures have different effects on people with various dental care needs worldwide. Dental care services should be defined into essential care and advanced care according to specific socioeconomic status in different countries. Targeted health strategies should be conducted to satisfy different dental care needs in countries.

Forecasting the future number of pertussis cases using data from Google Trends

Background

Alternative methods could be used to enhance the monitoring and forecasting of re-emerging conditions such as pertussis. Here, whether data on the volume of Internet searching on pertussis could complement traditional modeling based solely on reported case numbers was assessed.

Methods

SARIMA models were fitted to describe reported weekly pertussis case numbers over a four-year period in Germany. Pertussis-related Google Trends data (GTD) was added as an external regressor. Predictions were made by the models, both with and without GTD, and compared with values within the validation dataset over a one-year and for a two-weeks period.

Results

Predictions of the traditional model using solely reported case numbers resulted in an RMSE (residual mean squared error) of 192.65 and 207.8, a mean absolute percentage error (MAPE) of 58.59 and 72.1, and a mean absolute error (MAE) 169.53 and 190.53 for the one-year and for the two-weeks period, respectively. The GTD expanded model achieved better forecasting accuracy (RMSE: 144.22 and 201.78), a MAPE 43.86, and 68.54 and a MAE of 124.46 and 178.96. Corrected Akaike Information Criteria also favored the GTD expanded model (1750.98 vs. 1746.73). The difference between the predictive performances was significant when using a two-sided Diebold-Mariano test (DM value: 6.86, p < 0.001) for the one-year period.

Conclusion

Internet-based surveillance data enhanced the predictive ability of a traditionally based model and should be considered as a method to enhance future disease modeling.

•

Pertussis-related Google Trends Data (GTD) showed a weak but significant correlation with the reported weekly number of pertussis cases.

•

We fitted a SARIMA models to estimate reported weekly pertussis case numbers

•

The GTD-expanded models achieved significantly better predictive accuracy than the traditional model over a one-year-period.

•

Corrected Akaike Information Criteria also favored the GTD-Expanded SARIMA model.

•

The use of GTD should be considered as a method to enhance pertussis forecasting.

EagleEye: A Worldwide Disease-Related Topic Extraction System Using a Deep Learning Based Ranking Algorithm and Internet-Sourced Data

Due to the prevalence of globalization and the surge in people’s traffic, diseases are spreading more rapidly than ever and the risks of sporadic contamination are becoming higher than before. Disease warnings continue to rely on censored data, but these warning systems have failed to cope with the speed of disease proliferation. Due to the risks associated with the problem, there have been many studies on disease outbreak surveillance systems, but existing systems have limitations in monitoring disease-related topics and internationalization. With the advent of online news, social media and search engines, social and web data contain rich unexplored data that can be leveraged to provide accurate, timely disease activities and risks. In this study, we develop an infectious disease surveillance system for extracting information related to emerging diseases from a variety of Internet-sourced data. We also propose an effective deep learning-based data filtering and ranking algorithm. This system provides nation-specific disease outbreak information, disease-related topic ranking, a number of reports per district and disease through various visualization techniques such as a map, graph, chart, correlation and coefficient, and word cloud. Our system provides an automated web-based service, and it is free for all users and live in operation.

The impact of monthly campaigns and other high-profile media coverage on public interest in 13 malignancies: a Google Trends analysis

It is estimated that more than 600,000 people will die of cancer in the United States in 2020. Annual cancer diagnoses throughout the country are expected to rise in the coming years, which may further strain the American healthcare system. As such, it is vital that public health campaigns intended to reduce cancer morbidity and mortality are successful. Monthly cancer awareness campaigns have been used in the past to raise awareness and funding for various malignancies. One notable example is the 'Pink October' campaign to raise awareness for breast cancer. There has been limited study, however, on the effectiveness of cancer awareness campaigns for other cancers such as colorectal cancer, prostate cancer and cervical cancer. High-profile media coverage of celebrity cancer diagnoses and/or cancer-related deaths is another method by which knowledge of common cancers is dispersed to the public. In this study, we evaluate the impact of monthly cancer awareness campaigns as well as celebrity cancer diagnoses and/or deaths on Internet search traffic regarding various malignancies. We used the Google Trends database to evaluate public interest in 13 different cancers (and their respective cancer screening methods, when applicable) from January 2010 to June 2020. Public interest in 6 of 13 cancers (cervical cancer, colorectal cancer, skin cancer, ovarian cancer, breast cancer and lung cancer) was significantly higher in their respective awareness months when compared to the rest of the year. Furthermore, peak public interest for 9 of 13 cancers was associated with a media-event such as a monthly awareness campaign or celebrity diagnoses and/or death. Our findings illustrate the important role that the media plays in facilitating public interest in common cancers and their screening methods. Cancer awareness months can serve as an effective tool to increase Internet search traffic regarding a given malignancy. In the future, public health agencies can attempt to utilise increased search traffic to better educate the public, raise funds and improve enrolment in cancer screening programmes that reduce cancer morbidity and mortality.

Forecasting tuberculosis using diabetes-related google trends data

Online activity-based data can be used to aid infectious disease forecasting. Our aim was to exploit the converging nature of the tuberculosis (TB) and diabetes epidemics to forecast TB case numbers. Thus, we extended TB prediction models based on traditional data with diabetes-related Google searches. We obtained data on the weekly case numbers of TB in Germany from June 8^th, 2014, to May 5^th, 2019. Internet search data were obtained from a Google Trends (GTD) search for 'diabetes' to the corresponding interval. A seasonal autoregressive moving average (SARIMA) model (0,1,1) (1,0,0) [52] was selected to describe the weekly TB case numbers with and without GTD as an external regressor. We cross-validated the SARIMA models to obtain the root mean squared errors (RMSE). We repeated this procedure with autoregressive feed-forward neural network (NNAR) models using 5-fold cross-validation. To simulate a data-poor surveillance setting, we also tested traditional and GTD-extended models against a hold-out dataset using a decreased 52-week-long period with missing values for training. Cross-validation resulted in an RMSE of 20.83 for the traditional model and 18.56 for the GTD-extended model. Cross-validation of the NNAR models showed a mean RMSE of 19.49 for the traditional model and 18.99 for the GTD-extended model. When we tested the models trained on a decreased dataset with missing values, the GTD-extended models achieved significantly better prediction than the traditional models (p < 0.001). The GTD-extended models outperformed the traditional models in all assessed model evaluation parameters. Using online activity-based data regarding diabetes can improve TB forecasting, but further validation is warranted.

The impact of cancer campaigns in Brazil: a Google Trends analysis

It is estimated that more than 600,000 new cases of cancer will be reported in Brazil during the 2018-2019 biennium, especially with regard to prostate, breast, lung and colorectal cancers. Due to the high prevalence, incidence and mortality rates of these diseases, cancer campaigns such as 'Pink October' and 'Blue November' were strongly promoted in the past decade throughout the country to raise awareness of breast and prostate cancer, respectively. Nevertheless, whether the implementation of these campaigns has been proven efficient is still unknown. In the present study, we analysed the effectiveness of these campaigns on eliciting population online interest for cancer information. The Google Trends database was evaluated for the relative Internet search popularity for the terms 'breast cancer' and 'prostate cancer' from 2014 to 2019. Aside from some regional differences, we found that there was a high demand for 'breast cancer' and, to a lesser extent, 'prostate cancer' searches in a seasonal fashion (during October and November, respectively). Despite the worldwide high incidence of lung and colorectal cancers, searches including these keywords did not show increases in any specific period of the year, demonstrating the efficiency of the 'Pink October' and 'Blue November' campaigns in engaging the interest of the Brazilian population on the subject. These results allow us to infer that campaigns are effective in mobilising the attention of the Brazilian population with regard to breast and prostate cancers, but the practical aspects in reducing incidence and mortality should still be discussed.

Google Trends Predicts Present and Future Plague Cases During the Plague Outbreak in Madagascar: Infodemiological Study

Background

Plague is a highly infectious zoonotic disease caused by the bacillus Yersinia pestis. Three major forms of the disease are known: bubonic, septicemic, and pneumonic plague. Though highly related to the past, plague still represents a global public health concern. Cases of plague continue to be reported worldwide. In recent months, pneumonic plague cases have been reported in Madagascar. However, despite such a long-standing and rich history, it is rather difficult to get a comprehensive overview of the general situation. Within the framework of electronic health (eHealth), in which people increasingly search the internet looking for health-related material, new information and communication technologies could enable researchers to get a wealth of data, which could complement traditional surveillance of infectious diseases.

Objective

In this study, we aimed to assess public reaction regarding the recent plague outbreak in Madagascar by quantitatively characterizing the public’s interest.

Methods

We captured public interest using Google Trends (GT) and correlated it to epidemiological real-world data in terms of incidence rate and spread pattern.

Results

Statistically significant positive correlations were found between GT search data and confirmed (R²=0.549), suspected (R²=0.265), and probable (R²=0.518) cases. From a geospatial standpoint, plague-related GT queries were concentrated in Toamasina (100%), Toliara (68%), and Antananarivo (65%). Concerning the forecasting models, the 1-day lag model was selected as the best regression model.

Conclusions

An earlier digital Web search reaction could potentially contribute to better management of outbreaks, for example, by designing ad hoc interventions that could contain the infection both locally and at the international level, reducing its spread.

Can Google Trends data improve forecasting of Lyme disease incidence?

BACKGROUND

Online activity-based epidemiological surveillance and forecasting is getting more and more attention. To date, Google search volumes have not been assessed for forecasting of tick-borne diseases. Thus, we performed an analysis of forecasting of the Lyme disease incidence based on the traditional data extended with Google Trends.

METHODS

Data on the weekly incidence of Lyme disease in Germany from 16 June 2013 to 27 May 2018 were obtained from the database of the Robert Koch Institute. Data of Internet searches were obtained from Google Trends searching "Borreliose" in Germany for the "last 5 years" as a timespan category. Data were split into the training (from 16 June 2013 to 11 June 2017) and validation (from 12 June 2017, to 27 May 2018) data sets. A seasonal autoregressive moving average model, SARIMA (0,1,1) (0,1,1) [52] model was selected to describe the time series of the weekly Lyme incidence. After this, we added the Google Trends data as an external regressor and identified the SARIMA (0,1,1) (0,1,1) [52] model as optimal. We made predictions for the validation interval using these two models and compared predictions with the values of the validation data set.

RESULTS

Forecasting for the validation timespan resulted in similar values for the models. Comparing the forecasted values with the reported ones resulted in an residual mean squared error (RMSE) of 0.3763; the mean absolute percentage error (MAPE) was 8.233 for the model without Google searches with an RMSE of 0.3732; and the MAPE was 8.17495 for the Google Trends values-expanded model. The difference between the predictive performances was insignificant (Diebold-Mariano Test, p-value = 0.4152).

CONCLUSION

Google Trends data are a good correlate of the reported incidence of Lyme disease in Germany, but it failed to significantly improve the forecasting accuracy in models based on traditional data.