i-Sense flu (also known as Flu Detector) uses Google search data to estimate influenza-like illness (flu) rates in England. Daily flu rate estimates reflect on data from the past 7 days. Models are trained using GP consultation data (aggregate, anonymised) obtained from the Royal College of General Practitioners (RCGP). This website is supported by the EPSRC IRC project i-sense (Early-Warning Sensing Systems for Infectious Diseases) and a Google Research Sponsorship. Our estimates are included in the weekly syndromic surveillance reports published by UK Health Security Agency (UKHSA).

Note: All estimates on this website should be considered as experimental (see the website's disclaimer below).

i-Sense Flu's source code is available at github (GNU GPL v3)

Research team

The research team behind i-Sense Flu is based at the Computer Science Department of University College London.

Vasileios Lampos
Associate Professor
Aarzoo Dhiman
Research Fellow
David Guzman
Lead Software Engineer
Ingemar J. Cox
Professor in Information Retrieval
Michael Morris
PhD Student
Past Members:
Simon Moura
Jens K. Geyti
Bin Zou

Relevant publications

Vasileios Lampos, Andrew Miller, Steve Crossan and Christian Stefansen. Advances in nowcasting influenza-like illness rates using search query logs. Scientific Reports, vol. 5 (12760), 2015. doi:10.1038/srep12760.

Vasileios Lampos, Bin Zou and Ingemar J. Cox. Enhancing feature selection using word embeddings: The case of flu surveillance. Proc. of the 2017 World Wide Web Conference, pp. 695-704, 2017.

Vasileios Lampos. Flu Detector: Estimating influenza-like illness rates from online user-generated content. Technical Report, Computing Research Repository, 2016. arXiv:1612.03494.

Moritz Wagner, Vasileios Lampos, Ingemar J. Cox and Richard Pebody. The added value of online user-generated content in traditional methods for influenza surveillance. Scientific Reports, vol. 8 (13963), 2018. doi:10.1038/s41598-018-32029-6.

Vasileios Lampos, Elad Yom-Tov, Richard Pebody and Ingemar J. Cox. Assessing the impact of a health intervention via user-generated Internet content. Data Mining and Knowledge Discovery, vol. 29 (5), pp. 1434-1457, 2015. doi:10.1007/s10618-015-0427-9.

Moritz Wagner, Vasileios Lampos, Elad Yom-Tov, Richard Pebody, Ingemar J. Cox. Estimating the Population Impact of a New Pediatric Influenza Vaccination Program in England Using Social Media Content. Journal of Medical Internet Research, vol. 19 (12), 2017. doi:10.2196/jmir.8184.

Bin Zou, Vasileios Lampos and Ingemar J. Cox. Multi-Task Learning Improves Disease Models from Web Search. Proc. of the 2018 World Wide Web Conference, pp. 87-96, 2018.

Bin Zou, Vasileios Lampos and Ingemar J. Cox. Transfer Learning for Unsupervised Influenza-like Illness Models from Online Search Data. Proc. of the 2019 World Wide Web Conference, pp. 2505-2516, 2019.

Vincent Primault, Vasileios Lampos, Ingemar J. Cox and Emiliano De Cristofaro. Privacy-Preserving Crowd-Sourcing of Web Searches with Private Data Donor. Proc. of the 2019 World Wide Web Conference, pp. 1487-1497, 2019.

Michael Morris, Peter Hayes, Ingemar J. Cox, Vasileios Lampos. Estimating the Uncertainty of Neural Network Forecasts for Influenza Prevalence Using Web Search Activity. arXiv, 2105.12433, 2021.

Disclaimer

The information contained in this web site serves as a demonstration of research currently under way at University College London (UCL) and is provided 'as is' without warranty of any kind. Any reliance you place on this information is strictly at your own risk. Flu Detector is a demonstration of a research product and is used for research purposes only. We make no claim for its medical usability. UCL is not responsible for any use of this data. Through this web site you are able to link to other web sites which are not under our control. Therefore, the inclusion of any links does not necessarily imply a recommendation or endorses the view expressed within them. Access to this web site may be suspended temporarily and without any notice in circumstances of system failure or maintenance or for reasons beyond our control. We reserve the right to remove or alter the content of this web site at any time and without prior notice.