Developing mortality surveillance systems using Google trend: A pilot study

Yeh, Fu-Chun; Yeh, Chien-Hung

doi:10.1016/j.physa.2019.121125

Cited by 6 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our previous findings revealed that both high-weight and annual periodic patterns contribute to the prediction of death-related queries for the continent's economy 11 . However, whether or not similar models and/or features fit well to an island economy remained unclear.…”

Section: Introductionmentioning

confidence: 99%

Query-based-learning mortality-related decoders for the developed island economy

Yeh

Wang

Yeh

2022

Sci Rep

Self Cite

View full text Add to dashboard Cite

Search volumes from Google Trends over clear-defined temporal and spatial scales were reported beneficial in predicting influenza or disease outbreak. Recent studies showed Wiener Model shares merits of interpretability, implementation, and adaptation to nonlinear fluctuation in terms of real-time decoding. Previous work reported Google Trends effectively predicts death-related trends for the continent economy, yet whether it applies to the island economy is unclear. To this end, a framework of the mortality-related model for a developed island economy Taiwan was built based on potential death causes from Google Trends, aiming to provide new insights into death-related online search behavior at a population level. Our results showed estimated trends based on the Wiener model significantly correlated to actual trends, outperformed those with multiple linear regression and seasonal autoregressive integrated moving average. Meanwhile, apart from that involved all possible features, two other sets of feature selecting strategies were proposed to optimize pre-trained models, either by weights or waveform periodicity of features, resulting in estimated death-related dynamics along with spectrums of risk factors. In general, high-weight features were beneficial to both “die” and “death”, whereas features that possessed clear periodic patterns contributed more to “death”. Of note, normalization before modeling improved decoding performances.

show abstract

Section: Introductionmentioning

confidence: 99%

Query-based-learning mortality-related decoders for the developed island economy

Yeh

Wang

Yeh

2022

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…Real-time data sources are the only fitting mean to address the high-speed alterations in COVID-19-imposed issues in the public health context. Google Trends (GT) has already been proven as a powerful pubic surveillance tool for epidemiological studies (Nuti et al 2014b; Yeh and Yeh 2019). It is also stated that the more broad target audience of a common disease gets, the more reliable results of GT data records get (Cervellin et al 2017).…”

Section: Introductionmentioning

confidence: 99%

The association between COVID-19-imposed lockdowns and online searches for toothache using Google Trends

Sofi‐Mahmudi¹,

Shamsoddin²,

Ghasemi

et al. 2020

Preprint

View full text Add to dashboard Cite

Objective To assess the association between the lockdowns due to COVID-19 and global online searches for toothache using Google Trends (GT). Methods We investigated GT online searches for the search terms toothache and tooth pain, within the past five years. The time frame for data gathering was considered as the initiation and end dates of national/regional lockdowns in each country. Relative search volumes (RSVs) for online Google Search queries in 2019 was considered as the control. We analysed data after normalising based on the Internet penetration rate. We used one-way ANOVA to identify statistical difference for RSVs between 2020 and 2016-2019 for each country. A linear regression model was used to assess whether there is a correlation between RSVs in 2020 and gross domestic production, COVID-19 deaths, dentists' density, YLDs of oral conditions, Internet access, lockdown duration, Education Index, and dental expenditure per capita. Results The results of worldwide RSVs for toothache and tooth pain also showed significantly higher values in 2020 compared to the previous four years. Of 23 included countries in our study, 16 showed significantly increased RSVs during the lockdown period compared to the same periods in the past four years. There was a statistically significant relationship between difference of RSVs means in 2020 and in 2016-2019 combined with percent of urban residency (B=-1.82; 95% CI: (-3.38, -0.26); p=0.026) and dental expenditure per capita (B=-0.42; 95% CI: (-0.80, -0.05); p=0.031) (R2=0.66). Conclusion Generally, the interest in toothache and tooth pain has significantly increased in 2020 compared to the last four years. This could implicitly reinforce the importance of dental care, as urgent medical care worldwide. Governments' expenditure on oral healthcare and the rate of urban residency, could be mentioned as important factors to direct general populations' online care-seeking behaviour with regard to dental pain.

show abstract

Box-office forecasting in Korea using search trend data: a modified generalized Bass diffusion model

Kang

2021

Electron Commer Res

View full text Add to dashboard Cite

Developing mortality surveillance systems using Google trend: A pilot study

Cited by 6 publications

References 10 publications

Query-based-learning mortality-related decoders for the developed island economy

Query-based-learning mortality-related decoders for the developed island economy

The association between COVID-19-imposed lockdowns and online searches for toothache using Google Trends

Box-office forecasting in Korea using search trend data: a modified generalized Bass diffusion model

Contact Info

Product

Resources

About