Sleep app can predict flu and COVID-19 outbreaks a week early, UK study finds
Key Points
- UKHSA and Sleep Cycle published a study on Thursday (3 September) testing app cough data as an illness indicator
- Overnight coughing recorded by the app closely matched respiratory illness reported through NHS 111
- Rises in coughing appeared around a week before increases in flu and COVID-19 cases
- The signal updates daily and avoids delays from healthcare-seeking behaviour and lab turnaround
- UKHSA said the data could complement, not replace, existing surveillance systems
Coughing recorded by the Sleep Cycle smartphone app rose around a week before flu and COVID-19 cases climbed in England, according to a study published by the UK Health Security Agency (UKHSA) on Thursday (3 September).
The UKHSA and Sleep Cycle, an AI sleep technology company, published the results of a research study on medRxiv evaluating whether cough data collected passively through the app could give early indications of rising respiratory illness in England.
The study found that the cough data provided a robust and regionally consistent indicator of community respiratory illness, while also giving early signals for influenza and COVID-19 activity.
Cough levels recorded through the app closely tracked the levels of respiratory illness reported through NHS 111, with rises in coughing often appearing around one week before increases in flu and COVID-19 cases.
The UKHSA said existing surveillance systems rely on people seeking care through the NHS, which public awareness, service availability and demographic or socioeconomic differences can all influence. Reporting and laboratory processing times also delay those systems.
Sleep Cycle generates its cough signal automatically during normal sleep using privacy-preserved, passively collected data, and updates it daily to give a near real-time view of respiratory illness activity.
The app uses AI-powered sound analysis to help people understand and improve their sleep, and the study drew on that same microphone data to count coughs overnight.
The UKHSA said that used alongside established surveillance systems, passive sleep monitoring could provide a fuller picture of respiratory surveillance data and help public health experts understand seasonal trends sooner.
“These findings suggest that combining established surveillance approaches with novel digital health signals could contribute to an earlier, richer and more resilient understanding of population respiratory health,” said Steven Riley, Chief Data Officer at the UKHSA.
“No single surveillance system provides a complete picture of respiratory disease activity, but this shows that passive nocturnal cough monitoring can complement other surveillance systems to provide a timely population-level signal of upcoming disease trends, without being affected by healthcare-seeking behaviour, laboratory turnaround times, backfilling and reporting delays,” he added.
The study demonstrates that passively collected nightly cough data captures meaningful changes in community respiratory illness, said Emil Carlsson, Research Scientist and Co-lead Author of the study.
“Equally important, it shows that consumer-generated health data can be transformed into epidemiologically meaningful surveillance signals using rigorous scientific methods while maintaining strong privacy protections,” he added.
The study also validates a completely new category of health data, said Mikael Kågebäck, Chief Technology Officer and Acting Chief Executive Officer at Sleep Cycle.
“For the first time, we’ve demonstrated that passively generated smartphone data can produce robust population-level health intelligence at national scale, while also providing earlier signals for influenza and COVID-19 activity,” he added.
Kågebäck said the results create opportunities to strengthen public health surveillance and allow researchers, healthcare organisations and industry partners to build new services for situational awareness and operational decision support.
