A Pilot Study of Detecting Individual Sleep Apnea Events Using Noncontact Radar Technology, Pulse Oximetry, and Machine Learning

Abstract

The gold standard for assessing sleep apnea, polysomnography, is resource intensive and inconvenient. Thus, several simpler alternatives have been proposed. However, validations of these alternatives have focused primarily on estimating the apnea-hypopnea index (apnea events per hour of sleep), which means information, clearly important from a physiological point of view such as apnea type, apnea duration, and temporal distribution of events, is lost. The purpose of the present study was to investigate if this information could also be provided with the combination of radar technology and pulse oximetry by classifying sleep apnea events on a second-by-second basis. Fourteen patients referred to home sleep apnea testing by their medical doctor were enrolled in the study (6 controls and 8 patients with sleep apnea; 4 mild, 2 moderate, and 2 severe) and monitored by Somnofy (radar-based sleep monitor) in parallel with respiratory polygraphy. A neural network was trained on data from Somnofy and pulse oximetry against the polygraphy scorings using leave-one-subject-out cross-validation. Cohen’s kappa for second-by-second classifications of no event/event was 0.81, or almost perfect agreement. For classifying no event/hypopnea/apnea and no event/hypopnea/obstructive apnea/central apnea/mixed apnea, Cohen’s kappa was 0.43 (moderate agreement) and 0.36 (fair agreement), respectively. The Bland-Altman 95% limits of agreement for the respiratory event index (apnea events per hour of recording) were -8.25 and 7.47, and all participants were correctly classified in terms of sleep apnea severity. Furthermore, the results showed that the combination of radar and pulse oximetry could be more accurate than the two technologies separately. Overall, the results indicate that radar technology and pulse oximetry could reliably provide information on a second-by-second basis for no event/event which could be valuable for management of sleep apnea. To be clinically useful, a larger study is necessary to validate the algorithm on a general population.

Machine Learning in RADAR-based Physiological Signals Sensing: A Scoping Review of the Models, Datasets and Metrics

“…In one case, model training is carried out on a simulated pattern, while testing on people with a real disorder [146]. The remaining six papers consider subjects with a history of sleep disorders in their studies [111], [114], [121], [126], [137], [138]. Only two papers also assess the degree of severity of obstructive sleep disorders by estimating the Apnea Hypopnea Index (AHI), defined as the number of apneas and hypopneas divided by total sleep time [114], or the Respiratory Event Index (REI), defined as apnea or hypopnea events per hour of recording [138].…”

Noncontact Longitudinal Respiratory Rate Measurements in Healthy Adults Using Radar-Based Sleep Monitor (Somnofy): Validation Study

“…Radar technology has been extensively studied for measuring RR [26][27][28][29] and even for detecting apnea [26,[30][31][32]. However, most studies have measured RR only during optimized conditions where the participant is asked to sit or lie still [26] or during natural movements or sleep, but only for short periods [28,29].…”