De los pulsos al fenotipo: Endotipificación de la apnea del sueño para poligrafía mediante la autoproxmia derivada de...

Understanding the underlying cause of obstructive sleep apnea (OSA) in the individual patient, referred to as pathophysiological endotyping, is essential for personalized care. The current classification of these traits from routine sleep recordings relies on manually scored arousals from sleep. Automating this process could widen the applicability of endotyping.

Can analyzing autonomic variability, derived from finger oximeter photoplethysmography (PPG), accurately classify sleep apnea pathophysiological endotypes with results comparable to the established electroencephalography (EEG)-based method?

Eighty-seven patients referred for suspected OSA underwent ambulatory polysomnography. Pulse wave amplitude (PWA), pulse rate (PR), pulse propagation time (PPT), and blood oxygen saturation (SpO₂) were extracted from PPG. A logistic mixed-effect model was developed to predict the presence of EEG-based arousals using these PPG-derived parameters following respiratory events. The automatically predicted PPG-based arousals were then incorporated into an established model (Phenotyping Using Polysomnography, PUP) to determine OSA endotypic traits from the airflow and PPG signal. The agreement between endotypes with PPG-based and EEG-based arousals was assessed using intra-class correlation (ICC).

PPG responses to respiratory events were more pronounced in the presence of arousal (all p < 0.001). The model using PPG metrics to predict cortical arousal demonstrated moderate performance (sensitivity 0.71, specificity 0.59). Endotypic traits derived by PPG-derived arousals showed strong agreement, compared to the EEG-derived reference (ICC_LG1 = 0.95 with 95% CI [0.88-0.98], ICC_Vactive = 0.96 [0.81 - 0.99], ICC_Vpassive = 0.99 [0.99-0.99], ICC_Vmin = 0.99 [0.99 - 0.99], ICC_ArTh = 0.85 [0.48 - 0.96], ICC_Vcomp = 0.80 [0.60 - 0.91]).

Using pulse wave features instead of manually scored EEG-based arousals in respiratory modelling allows for accurately determining OSA endotypes. This approach might enable physiological endotyping in non-EEG-based sleep studies, expanding the accessibility of personalized OSA management.