Contactless Sleep Apnea Detection on Smartphones

Abstract

We present a contactless solution for detecting sleep apnea events on smartphones. To achieve this, we introduce a novel system that monitors the minute chest and abdomen movements caused by breathing on smartphones. Our system works with the phone away from the subject and can simultaneously identify and track the fine-grained breathing movements from multiple subjects. We do this by transforming the phone into an active sonar system that emits frequency-modulated sound signals and listens to their reflections; our design monitors the minute changes to these reflections to extract the chest movements. Results from a home bedroom environment shows that our design operates efficiently at distances of up to a meter and works even with the subject under a blanket.Building on the above system, we develop algorithms that identify various sleep apnea events including obstructive apnea, central apnea, and hypopnea from the sonar reflections. We deploy our system at the UW Medicine Sleep Center at Harborview and perform a clinical study with 37 patients for a total of 296 hours. Our study demonstrates that the number of respiratory events identified by our system is highly correlated with the ground truth and has a correlation coefficient of 0.9957, 0.9860, and 0.9533 for central apnea, obstructive apnea and hypopnea respectively. Furthermore, the average error in computing of rate of apnea and hypopnea events is as low as 1.9 events/hr.

Extracting Multi-Person Respiration from Entangled RF Signals

“…Studies using Doppler Radio [30], FMCW [2,14,47], millimeter waves [43,9], and WiFi signals [42,20] all demonstrate accurate monitoring of a single person's breathing. Respiration monitoring using radio signal is also closely related to monitoring breathing using acoustic signals, which tends to use FMCW techniques and demonstrates good accuracy for a single person [25,40]. Further, some recent papers demonstrate that the breathing signal extracted from RF can be used to infer additional health metrics [46,33].…”

“…The only past studies, that we know of, that report breathing results for users in the same bed are [42] and [25]. The former requires the users to lie in a specific position and have significantly different breathing rates.…”

Single-Frequency Ultrasound-Based Respiration Rate Estimation with Smartphones

“…Most off-the-shelf smartphones can generate sound up to 22 kHz using their built-in speakers [20, 21]. The smartphone is placed in front of the tester.…”

“…Instead of specially deployed wireless transceivers, some researchers proposed using smartphones to detect vital signs, which is easier to access in daily life. Some works used built-in inertial sensors in smartphones to monitor vital signs [16–19], while others leveraged ultrasonic signals to conduct respiration detection and sleep monitoring [20, 21]; they utilized built-in speakers and microphones in smartphones to play and record ultrasound signals and extract useful information such as respiration patterns from them [22]. In our paper, we will also use ultrasound as the media to detect the respiration rate.…”

The Past Is Prologue: The Future of Sleep Medicine

“…26,27 A comprehensive telemedicine pathway could exist for sleep-disordered breathing. The initial visit and follow-ups could be completed by simultaneous video-based telemedicine with either the sleep specialist or a member of the sleep team; the diagnosis would be accomplished through physician supervision of contactless monitoring of breathing patterns in the patient's own home over multiple nights; and PAP compliance and adjustment would be assessed and facilitated by industry-provided cloud computing solutions and simultaneous telemedicine visits.…”