Automatic Screening of Sleep Apnea Patients Based on the SpO₂ Signal

Abstract

This paper presents a methodology to automatically screen for sleep apnea based on the detection of apnea and hypopnea events in the blood oxygen saturation (SpO) signal. It starts by detecting all desaturations in the SpO signal. From these desaturations, a total of 143 time-domain features are extracted. After feature selection, the six most discriminative features are used to construct classifiers to predict if desaturations are caused by respiratory events. From these, a random forest classifier yielded the best classification performance. The number of desaturations, classified as caused by respiratory events per hour of recording can then be used as an estimate of the apnea-hypopnea index (AHI), and to predict if a patient suffers from sleep apnea-hypopnea syndrome (SAHS) or not. All classifiers were developed based on a subset of 500 subjects of the Sleep Heart Health Study (SHHS) and tested on three different datasets, containing 8052 subjects in total. An averaged desaturation classification accuracy of 82.8 % was achieved over the different test sets. Subjects having SAHS with an AHI larger than 15 can be detected with an average accuracy of 87.6 %. The achieved SAHS screening outperforms SpO methods from the literature on the SHHS test dataset. Moreover, the robustness of the method was shown when tested on different independent test sets. These results show that an algorithm based on simple features of SpO desaturations can outperform more elaborate methods in the detection of apneic events and the screening of SAHS patients.

A review of approaches for analysing obstructive sleep apnoea‐related patterns in pulse oximetry data

“…These can be further extended to deeper thresholds (5%, 6%, 7%, etc. ) and presented graphically as the cumulative frequency of the desaturations ≥ integer desaturation thresholds (depth–incidence plot; Fig. F) …”

“…The desaturation area is a manifestation of both desaturation depth and duration, and quantifies the area between the baseline and the SpO 2 trace during a desaturation, and therefore quantifies an overall hypoxaemic burden associated with events.…”

“…The re‐saturation part of the event can be interrogated in more detail to calculate the time taken to restore SpO 2 values to 3% or 4% above the desaturation minima, or back to baseline …”

“…OSA patients are expected to have a greater variance in SpO 2 values (whereas healthy individuals are expected to have relatively consistent values) …”

“…SpO 2 distribution can also be quantified with other statistics such as median, interquartile range and range between the 2.5th and 97.5th centiles of the distribution …”