Detecting COVID-19 infection hotspots in England using large-scale self-reported data from a mobile application : a prospective, observational study
- Submitting institution
-
King's College London
- Unit of assessment
- 12 - Engineering
- Output identifier
- 142644400
- Type
- D - Journal article
- DOI
-
10.1016/S2468-2667(20)30269-3
- Title of journal
- The Lancet Public Health
- Article number
- -
- First page
- E21
- Volume
- 6
- Issue
- 1
- ISSN
- 2468-2667
- Open access status
- Compliant
- Month of publication
- December
- Year of publication
- 2020
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- Yes
- Number of additional authors
-
20
- Research group(s)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This work describes the novel application of machine learning and modelling techniques to self-reported data from a mobile application in order to estimate Covid-19 incidence, prevalence, and the effective reproduction number, R. The study finds this new approach tracks the pandemic as accurately as traditional approaches based on population testing, whilst being more cost-effective, quicker to detect changes in the pandemic’s trajectory, and allowing predictions to be more geographically granular. Daily reports generated using this method are sent directly to the UK’s Joint Biosecurity Centre and incorporated in the UK Government’s pandemic response planning (http://covid-assets.joinzoe.com/latest/covid_symptom_study_report.pdf).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -