Automated Prediction of the Apnea-Hypopnea Index from Nocturnal Oximetry Recordings

Abstract

Nocturnal polysomnography (PSG) is the gold-standard for sleep apnea-hypopnea syndrome (SAHS) diagnosis. It provides the value of the apnea-hypopnea index (AHI), which is used to evaluate SAHS severity. However, PSG is costly, complex, and time-consuming. We present a novel approach for automatic estimation of the AHI from nocturnal oxygen saturation (SaO(2)) recordings and the results of an assessment study designed to characterize its performance. A set of 240 SaO(2) signals was available for the assessment study. The data were divided into training (96 signals) and test (144 signals) sets for model optimization and validation, respectively. Fourteen time-domain and frequency-domain features were used to quantify the effect of SAHS on SaO(2) recordings. Regression analysis was performed to estimate the functional relationship between the extracted features and the AHI. Multiple linear regression (MLR) and multilayer perceptron (MLP) neural networks were evaluated. The MLP algorithm achieved the highest performance with an intraclass correlation coefficient (ICC) of 0.91. The proposed MLP-based method could be used as an accurate and cost-effective procedure for SAHS diagnosis in the absence of PSG.

Multi-class adaboost to detect Sleep Apnea-Hypopnea Syndrome severity from oximetry recordings obtained at home

“…It reached 95.2% Se, 86.0% Sp, and 88.7% Acc after a hold-out cross-validation strategy. Marcos et al followed a different approach by training a multi-layer perceptron neural network to estimate AHI [10] [16].…”

“…These drawbacks have led to the search for alternatives focused on simplifying SAHS diagnosis. In this regard, overnight pulse oximetry has been commonly investigated as single-channel diagnostic alternative for SAHS [7]- [10]. Pulse oximetry is a standard for monitoring and recording the SpO2 signal [11], which is able to reflect blood oxygen desaturations caused by apneic events.…”

“…Pulse oximetry is a standard for monitoring and recording the SpO2 signal [11], which is able to reflect blood oxygen desaturations caused by apneic events. A few works have analyzed the diagnostic ability of conventional clinical parameters obtained from SpO2, such as oxygen desaturation index (ODI) or delta index [8], [12] whereas other studies have focused on automated methodologies based on signal processing and pattern recognition techniques [9], [10], [13]. However, SpO2 signals are commonly acquired during in-hospital PSG and, consequently, there exists a lack of evaluation of these methodologies when using unattended at-home recordings.…”

“…A set of features from different analytical approaches (statistical, spectral and non-linear), already used to characterize SAHS in in-lab SpO2 signals [9], [10], was extracted from 320 at-home recordings. Moreover, an automatic feature selection stage, based on the fast correlation-based filter (FCBF) method [14], was implemented.…”

Pulse Rate Variability Analysis to Enhance Oximetry as at-Home Alternative for Sleep Apnea Diagnosing

“…The eight features extracted from NPO (SpO 2 and PRV) are subsequently used as the only source of information to train a multi-layer perceptron (MLP) artificial neural network with ability to automatically estimate AHI. We chose MLP in view of its success in previous studies focused on automatic AHI estimation [12,13]. The diagnostic performance of this estimated AHI is compared with ODI 3 to assess whether the use of PRV information can improve the ability of oximetry to detect SAHS and its severity.…”