Automated prediction of the apnea-hypopnea index using a wireless patch sensor

Abstract

Polysomnography (PSG) is the gold standard that manually quantifies the apnea-hypopnea index (AHI) to assess the severity of sleep apnea syndrome (SAS). This study presents an algorithm that automatically estimates the AHI value using a disposable HealthPatch(TM) sensor. Volunteers (n=53, AHI: 0.1-85.8) participated in an overnight PSG study with patch sensors attached to their chest at three specified locations and data were wirelessly acquired. Features were computed for 150-second epochs of patch sensor data using analyses of heart rate variability, respiratory signals, posture and movements. Linear Support Vector Machine classifier was trained to detect the presence/absence of apnea/hypopnea events for each epoch. The number of epochs identified with events was subsequently mapped to AHI values using quadratic regression analysis. The classifier and regression models were optimized to minimize the mean-square error of AHI based on leave-one-out cross-validation. Comparison of predicted and reference AHI values resulted in linear correlation coefficients of 0.87, 0.88 and 0.92 for the three locations, respectively. The predicted AHI values were subsequently used to classify the control-to-mild apnea group (AHI<;15) and moderate-to-severe apnea (AHI≥15) with an accuracy (95% confidence intervals) of 89.4% (77.4-95.4%), 85.0% (70.9-92.9%), and 82.9% (67.3-91.9%) for the three locations, respectively. Overnight physiological monitoring using a wireless patch sensor provides an accurate estimate of AHI.