A single-center validation of the effectiveness of
photoplethysmography-based smart device for screening obstructive sleep
apnea
Abstract
Background: Obstructive sleep apnea (OSA), the most common upper-airway
disease, is closely associated with cardiovascular risk. However, the
early screening of OSA is challenging, relying on polysomnography (PSG)
or home sleep apnea test (HSAT) in hospitals. Photoplethysmography (PPG)
has been developed as a novel technology for OSA screening, but the
validation of PPG-based smart devices is limited as compared to that for
PSG or HSAT. Objective: This study aimed to investigate the feasibility
and validity of PPG-based smart devices in the screening of OSA.
Methods: A total of 119 consecutive outpatients were recruited from the
Chinese PLA General Hospital and assessed for a whole-night sleep using
a smartwatch, PSG, or HSAT. Results: 17/119 patients were excluded from
the study due to the poor quality of PPG signals. Among the remaining,
83 patients were diagnosed with OSA. Compared to HSAT devices, the
accuracy, sensitivity, and specificity of PPG-based smart devices in
predicting moderate-to-severe OSA patients (apnea-hypopnea index,
AHI≥15) were 87.9%, 89.7%, and 86.0%, respectively. Compared to PSG,
the accuracy, sensitivity, and specificity in predicting sleep apnea in
patients (AHI≥5) were 81.1%, 76.5%, and 100%, respectively. Moreover,
for moderate-to-severe OSA patients (AHI≥15), the predictive ability of
PPG-based smart devices in OSA did no differ significantly as compared
to HSAT (P=0.75) or PSG (P=0.52). Conclusions: The PPG-based smart
devices performed adequately in detecting OSA; nevertheless, validation
in a large-scale population is imperative.