Providing early indication of regional anomalies in COVID-19 case counts in England using search engine queries

Elad Yom-Tov,Ingemar J Cox,Michael Edelstein,Vasileios Lampos,Thomas Inns

doi:10.1038/s41598-022-06340-2

Abstract

Prior work has shown the utility of using Internet searches to track the incidence of different respiratory illnesses. Similarly, people who suffer from COVID-19 may query for their symptoms prior to accessing the medical system (or in lieu of it). To assist in the UK government’s response to the COVID-19 pandemic we analyzed searches for relevant symptoms on the Bing web search engine from users in England to identify areas of the country where unexpected rises in relevant symptom searches occurred. These were reported weekly to the UK Health Security Agency to assist in their monitoring of the pandemic. Our analysis shows that searches for “fever” and “cough” were the most correlated with future case counts during the initial stages of the pandemic, with searches preceding case counts by up to 21 days. Unexpected rises in search patterns were predictive of anomalous rises in future case counts within a week, reaching an Area Under Curve of 0.82 during the initial phase of the pandemic, and later reducing due to changes in symptom presentation. Thus, analysis of regional searches for symptoms can provide an early indicator (of more than one week) of increases in COVID-19 case counts.

Highlights

Prior work has shown the utility of using Internet searches to track the incidence of different respiratory illnesses
In early March 2020, the UK’s Health Security Agency (UKHSA; formerly Public Health England), University College London (UCL) and Microsoft began investigating the possibility of using Bing web search data to detect areas where disease incidence might be increasing faster than expected, so as to assist UKHSA in the early detection of local clusters and better planning of their response
Our results below show that symptom searches were correlated with case counts, and that our approach allowed the prediction of regional anomalies approximately 7–10 days before they were identified using case counts during the first stages of the pandemic

Summary

Introduction

Prior work has shown the utility of using Internet searches to track the incidence of different respiratory illnesses. To assist in the UK government’s response to the COVID-19 pandemic we analyzed searches for relevant symptoms on the Bing web search engine from users in England to identify areas of the country where unexpected rises in relevant symptom searches occurred. These were reported weekly to the UK Health Security Agency to assist in their monitoring of the pandemic. The added value of these data relies on the fact that most people with, for example, ILI will not seek healthcare but will search about the condition or mention it in social media postings[8] Such behaviour could be compounded by fear of attending medical facilities in the midst of a pandemic. We focused on the regional level because much of the response to the pandemic was coordinated at this level, and because detecting local clusters while they may still be undetected by national level surveillance and before they have spread further is an efficient approach to outbreak management

Objectives

Methods

Results

Conclusion