Carnegie Mellon, Sleep Cycle Will Explore Sleep Data To Detect Outbreaks Collaboration Will Investigate How Respiratory Signals Can Support Epidemiological Modeling and Forecasting
Aaron AupperleeFriday, February 20, 2026Print this page.
Sleep Cycle, an AI sleep technology company, and the Delphi Group at Carnegie Mellon University have announced a five-year research collaboration. The collaboration focuses on understanding how privacy-preserved data and sleep-based signals, such as nighttime cough patterns, may complement and enhance traditional respiratory disease surveillance systems and early detection of both seasonal and emerging disease outbreaks.
Through the collaboration, Sleep Cycle will provide the Delphi Group with deidentified research data related to coughing and breathing to support epidemiological modeling and forecasting research. The study will analyze trends derived from anonymized, differentially private data from Sleep Cycle's Cough Radar, a public visualization tool that shows aggregated trends in nightly coughing intensity across regions. Researchers will explore whether these signals can provide earlier visibility into respiratory disease activity, including viruses such as influenza, RSV and SARS-CoV-2.
This study marks the first time CMU's Delphi Group — a leading epidemiologic research group coordinated by School of Computer Science Professor Roni Rosenfeld — will systematically assess sleep app data as a potential input for national epidemiological monitoring and research in conjunction with other health indicators available on its Delphi Epidata platform.
"This research will evaluate the utility of Sleep Cycle-derived cough and breathing signals for epidemiological surveillance applications," said Rosenfeld, faculty in CMU's School of Computer Science and the principal investigator of the Delphi Group. "Our goal is to rigorously assess where these indicators can add value alongside existing public health data streams. Bolstered monitoring could lead to earlier detection of seasonal and emerging respiratory disease outbreaks, allowing health officials to react faster and safeguard the public health."
Sleep Cycle's data science and respiratory-signal research, including its proprietary audio-based cough-detection technology, have demonstrated that nighttime cough behavior can correlate with real-world viral activity. The collaboration with the Delphi Group provides an opportunity to evaluate those findings within a leading epidemiology research institute in the U.S. and marks another important step forward in Sleep Cycle's evolution from a consumer sleep app to a contributor in population-level health research, helping surface patterns in nocturnal breathing and nighttime physiology that may inform public health decision-making.
"Sleep and breathing-related signals offer a consistent, passive window into population-level trends," said Dr. Mikael Kågebäck, head of science at Sleep Cycle. "We're pleased to support Delphi's long-term research efforts by contributing privacy-preserved indicators that may help advance epidemiological modeling and forecasting with the support of Sleep Cycle sleep data library, including three billion nights across 180 countries."
This collaboration supports both parties' commitment to advancing scientific understanding and the responsible use of digital health data for public benefit.
By contributing anonymized trends from the world's largest sleep library, Sleep Cycle advances its mission to use the power of sleep, breath and recovery to support healthier individuals and more informed societies.
Learn more on the Sleep Cycle website.
Aaron Aupperlee | 412-268-9068 | aaupperlee@cmu.edu