Track: Online syndromic surveillance to track outbreaks

Research impact

• Our influenza surveillance tool has been adopted by Public Health England to include in their weekly and annual influenza surveillance reports
• Our methods have been applied to other problems, including detecting outbreaks at mass gatherings, estimating effectiveness of an influenza vaccine for children, and estimating the virulence of influenza 

Go local: the key to COVID-19 lockdown release (2020)

The piece, published as a pre-print on arXiv, draws on geospatial data highlighting local variation in mobility across the country, as well as case rate data, which shows potential hotspots of COVID-19 infection.

Tracking COVID-19 using online search data (2020)

i-sense researchers from University College London, led by Dr Vasileios Lampos, in collaboration with Public Health England, Microsoft Research, and Harvard Medical School are looking at ways of tracking COVID-19 using online search data to better understand the true extent of community spread.

i-sense flu.png

i-sense flu – Tracking flu in real-time (2019)

A recent feature on real-time tracking of influenza in Nature Outlook discusses how scientists are using social media and online search data to monitor potential outbreaks. The piece draws on expertise across the field, including i-sense computer scientist, Dr Vasileios Lampos (@lampos), and i-sense collaborator Dr Richard Pebody from Public Health England (PHE).

Can Google help to assess the impact of heatwaves on the health of the population? (2018)

Research from Public Health England and members of i-sense at UCL, published in Environmental Research, suggests that monitoring online search terms related to the health impact of heatwaves could help contribute to public health surveillance systems in the UK and have potential benefits for countries that lack established public health surveillance systems.

The power of web data: Assessing the impact of health interventions (2015)

i-sense, UCL, Public Health England (PHE) and Microsoft researchers have proven the effectiveness of an England-wide flu vaccination programme by analysing tweets and Bing search queries. The study, led by UCL and i-sense researcher Vasileios Lampos, demonstrates how data generated by Internet users can be successfully used to assess the impact of health interventions, in this case the pilot Live Attenuated Influenza Vaccine (LAIV) campaign.

Google Flu Trends revisited: Improving influenza modelling from search query logs (2014)

In July 2014, i-sense joined up with Google to contribute to the earlier global detection of influenza outbreaks. Since then, researchers from i-sense, UCL, Google and Harvard University have been developing influenza modeling techniques from search query data, in order to support a more accurate picture of influenza-like illness (ILI) in the UK. They were able to significantly improve on the original Google models and make more accurate flu estimates, during peak flu seasons in the US (from 2008 to 2013).

Google press release image.jpg

i-sense collaborate with Google to track flu outbreaks (2014)

UCL and i-sense have joined forces with Google to contribute to the earlier global detection of influenza outbreaks. The Google Flu Trends service uses flu‐related search queries to map flu activity in near real‐time. These trends can be used to complement other influenza surveillance systems such as sentinel networks.i‐sense will work with Google to develop their models for estimating flu. This would support a more accurate picture of influenza‐like illnesses in the UK.

Relevant publications 

2019

Primault, V., Lampos, V., Cox, I. J., and De Cristofaro, E. 'Privacy-preserving crowd-sourcing of web searches with private data donor.' Proc. of the 28th International Web Conference (WWW ’19), pp. 1487–1497 (2019); DOI: 10.1145/3308558.3313474

Zou, B., Lampos, V., and Cox, I. J. 'Transfer Learning for Unsupervised Influenza-like Illness Models from Online Search Data' WWW '19 The World Wide Web Conference (2019); DOI: 10.1145/3308558.3313477

2018

Flekova, L., Lampos, V., and Ingemar J. Cox, I. J. 'Changes in psycholinguistic attributes of social media users before, during, and after self reported influenza symptoms.' Proc. of the 2018 EMNLP Workshop SMM4H: The 3rd Social Media Mning for Health Applications Workshop & Shared Task, pp. 17–21 (2018); DOI: 10.18653/v1/W18-5905

Zou, B., Lampos, V., and Cox, I. J. 'Multi-task learning improves disease models from web search' WWW '18 Proceedings of the 2018 World Wide Web (2018); DOI: 10.1145/3178876.3186050

Wagner, M., Lampos, V., Cox., I. J., and Pebody, R. 'The added value of online user-generated content in traditional methods for influenza surveillance.' Scientific Reports (2018); DOI: 10.1038/s41598-018-32029-6

Green, H. K., Edeghere, O., Elliot, A. J., Cox, I. J., Morbey, Pebody, P., Bones, A., McKendry, R. A., Smith, G. E. ‘Google search patterns monitoring the daily health impact of heatwaves in England: how do the findings compare to established syndromic surveillance systems from 2013 to 2017?’ Environmental Research (2018); DOI: 10.1016/j.envres.2018.04.002

2017

Wagner, M., Lampos, V., Yom-Tov, E., Pebody, R., Cox, I. J. 'Estimating the Population Impact of a New Pediatric Influenza Vaccination Program in England Using Social Media Content' J Med Internet Res 19(12):e416 (2017); DOI: 10.2196/jmir.8184

Lampos, V., Zou, B., Cox, I.J. 'Enhancing Feature Selection Using Word Embeddings: The Case of Flu Surveillance' WWW '17 Proceedings of the 26th International Conference on World Wide Web (2017); DOI: 10.1145/3038912.3052622

2016

Lampos V., Aletras N., Geyti J.K., Zou B., Cox I.J. 'Inferring the Socioeconomic Status of Social Media Users Based on Behaviour and Language.' Advances in Information Retrieval. ECIR 2016. Lecture Notes in Computer Science, vol 9626. Springer, Cham (2016); DOI: 10.1007/978-3-319-30671-1_54

Zou, B., Lampos, V., Gorton, R. & Cox, I.J. 'On Infectious Intestinal Disease Surveillance using Social Media Content' Proceedings of the 6th International Conference on Digital Health (2016); PDF.

2015

Lampos, V., Yom-Tov, E., Pebody, R. & Cox, I.J. 'Assessing the impact of a health intervention via user-generated Internet content' Data Mining and Knowledge Discovery 5, 1434-1457 (2015); DOI: 10.1007/s10618-015-0427-9.

Yom-Tov, E., Cox, I.J., Lampos, V. & Hayward, A.C. 'Estimating the secondary attack rate and serial interval of influenza-like illnesses using social media' Influenza and other respiratory viruses 9, 191-199 (2015); DOI: 10.1111/irv.12321.

Zhang, C., Zhou, S., Miller, J.C., Cox, I.J. & Chain, B.M. 'Optimizing Hybrid Spreading in Metapopulations' Scientific Reports 5, 9924 (2015); DOI: 10.1038/srep09924.

Yom-Tov, E., Borsa, D., Hayward, A.C., McKendry, R.A. & Cox, I.J. 'Automatic Identification of Web-Based Risk Markers for Health Events' Journal of Medical Internet Research 17(1):e29, (2015); DOI: 10.2196/jmir.4082

2014

Yom-Tov, E., Borsa, D., Cox, I.J. & McKendry, R.A. 'Detecting Disease Outbreaks in Mass Gatherings Using Internet Data' J. Med. Internet Res. 16(6):e154, (2014); DOI: 10.2196/jmir.3156.