Screening of Obstructive Sleep Apnea with Empirical Mode Decomposition of Pulse Oximetry

TL;DR

This paper introduces a novel automatic detection method for obstructive sleep apnea using empirical mode decomposition of pulse oximetry signals, achieving high sensitivity and specificity for screening the syndrome.

Contribution

The paper presents a new recognition approach based on empirical mode decomposition to detect oxygen desaturations, improving screening accuracy over standard methods.

Findings

High sensitivity (0.838) in detection

High specificity (0.855) in detection

Outperforms standard desaturation detection methods

Abstract

Detection of desaturations on the pulse oximetry signal is of great importance for the diagnosis of sleep apneas. Using the counting of desaturations, an index can be built to help in the diagnosis of severe cases of obstructive sleep apnea-hypopnea syndrome. It is important to have automatic detection methods that allows the screening for this syndrome, reducing the need of the expensive polysomnography based studies. In this paper a novel recognition method based on the empirical mode decomposition of the pulse oximetry signal is proposed. The desaturations produce a very specific wave pattern that is extracted in the modes of the decomposition. Using this information, a detector based on properly selected thresholds and a set of simple rules is built. The oxygen desaturation index constructed from these detections produces a detector for obstructive sleep apnea-hypopnea syndrome with high sensitivity ($0.838$) and specificity ($0.855$) and yields better results than standard desaturation detection approaches.