Endotyping Sleep Apnea One Breath at a Time: An Automated Approach for Separating Obstructive from Central Sleep-disordered Breathing.

Determining whether an individual has obstructive or central sleep apnea is fundamental to selecting the appropriate treatment. Here we derive an automated breath-by-breath probability of obstruction, as a surrogate of gold-standard upper airway resistance, using hallmarks of upper airway obstruction visible on clinical sleep studies. From five nocturnal polysomnography signals (airflow, thoracic and abdominal effort, oxygen saturation, and snore), nine features were extracted and weighted to derive the breath-by-breath probability of obstruction (P). A development and initial test set of 29 subjects (development = 6, test = 23) (New York, NY) and a second test set of 39 subjects (Solingen, Germany), both with esophageal manometry, were used to develop P and validate it against gold-standard upper airway resistance. A separate dataset of 114 subjects with 2 consecutive nocturnal polysomnographies (New York, NY) without esophageal manometry was used to assess the night-to-night variability of P. A total of 1,962,229 breaths were analyzed. On a breath-by-breath level, P was strongly correlated with normalized upper airway resistance in both test sets (set 1: cubic adjusted [adj.]  = 0.87,  < 0.001, area under the receiver operating characteristic curve = 0.74; set 2: cubic adj.  = 0.83,  < 0.001, area under the receiver operating characteristic curve = 0.7). On a subject level, median P was associated with the median normalized upper airway resistance (set 1: linear adj.  = 0.59,  < 0.001; set 2: linear adj.  = 0.45,  < 0.001). Median P exhibited low night-to-night variability [intraclass correlation(2, 1) = 0.93]. Using nearly 2 million breaths from 182 subjects, we show that breath-by-breath probability of obstruction can reliably predict the overall burden of obstructed breaths in individual subjects and can aid in determining the type of sleep apnea.