Performance of a commercial smart watch compared to polysomnography reference for overnight continuous oximetry measurement and sleep apnea evaluation.

STUDY OBJECTIVES:To evaluate the accuracy and precision of continuous overnight oxygen saturation (SpO2) measurement by a commercial wrist device (WD) incorporating high-grade sensors, and investigate WD estimation of sleep-disordered breathing by quantifying overnight oxygen desaturation index (ODI) compared to polysomnography (PSG) ODI and apnea-hypopnea index (AHI) with and without sleep questionnaire data, to assess WD ability to detect obstructive sleep apnea (OSA) and determine its severity. METHODS:Participants completed sleep questionnaires, had a WD (Samsung Galaxy Watch 4) placed on their wrist, and underwent attending, in-lab overnight PSG (Nihon Kohden) with pulse oximetry probe secured either to a finger or ear lobe. PSG data was scored by a single experienced registered PSG technologist. Statistical analysis included demographic characteristics, continuous SpO2 measurement WD vs PSG root mean square error (RMSE) with Bland Altman plot and linear regression associations. Predictive models for PSG ODI and AHI severity were built using logistic regression with probability cutoffs determined via receiver operating curve (ROC) characteristics. RESULTS:The 51 participants analyzed had median age of 49 (range 22-78) years, 66.7% were male, with median body mass index (BMI) 28.1 (range 20.1, 47.3) kg/m2 with race/ethnicity distribution of 49.0% Caucasian, 25.5% Hispanic, 9.8% African-American, 9.8% Asian, and 5.9% Middle Eastern. WD vs PSG continuous SpO2 measurement in percentage points demonstrated bias of 0.91 (CI95 0.38, 1.45), standard deviation 2.37 (CI95 2.36, 2.38), and RMSE 2.54 (CI95 2.34, 2.73). WD area under the curve (AUC) ROC characteristics for predicting PSG were 0.882 ODI>15/h, 0.894 AHI>30/h, 0.800 AHI>15/h, and 0.803 AHI>5/h. WD plus select sleep questionnaire AUCs for predicting PSG were 0.943 AHI>30/h, 0.868 AHI>15/h, and 0.863 AHI>5/h. CONCLUSIONS:The WD conducted reliable overnight continuous SpO2 monitoring with RMSE <3% vs PSG. Predictive models of PSG AHI based on WD measurements alone, or plus sleep questionnaires, demonstrated excellent to outstanding discrimination for OSA identification and severity. Longitudinal WD use should be evaluated promptly based on WD potential to improve accessibility and accuracy of OSA testing, as well as support treatment follow-up.