In reference to Prediction of Oxygen Desaturation by Using Sound Data From a Noncontact Device: A Proof‐of‐Concept Study

Abstract

We read with interest the report of the study by Kim et al., which focused on predicting oxygen desaturation using sleep breathing sounds with a non-contact device. 1 However, we wanted to share our criticisms of this proof-of-concept study and our suggestions for improving the accuracy of the oxygen desaturation index (ODI) estimation to shed light on future studies.The authors stated that the ODI could be estimated by evaluating the patients' sleep breathing sounds, body mass index, and age. However, it is known that gender, sleeping position, smoking history, and basal arterial oxygen saturation values also affect the ODI value. 2 In addition, differences in upper airway anatomy should have been considered in such a study. Because the upper airway is made up of pharyngeal muscles that are essential for speech and breathing. Factors that cause variations in upper airway anatomy, such as racial differences, change the activity of the pharyngeal muscles that create sleep breathing sounds and may affect the results of studies on this subject. Due to craniofacial differences, the frequency of obstructive sleep apnea may be different among patients with equivalent body mass indexes. 3 On the other hand, the authors did not consider the patients' sleep staging during the study and evaluated only sleep breathing sounds. However, sleep staging is necessary to evaluate sleep and sleep disorders. This is because various physiological changes occur during different sleep stages. Macro sleep stages changes during NREM, REM, or wakefulness cause changes in pharyngeal muscle tone, breathing pattern, and body movements. 4 All these activities are associated with the emergence of different sleep breathing sounds. In addition, increased upper airway resistance during REM sleep causes a decrease in lung volumes and ventilation-perfusion mismatch. This causes oxygen desaturation and may affect ODI results. 2 Another criticism is that the position of the patients was not taken into account. The supine sleeping position causes a significant reduction in the lung volumes and leads to more oxygen desaturation than the lateral decubitus and prone positions. This can affect the ODI results. In addition, the acoustic characteristics of snoring may change with different body positions, and sleep breathing sounds may vary from night to night, even for the same patient. 5 Consequently, a combination of oxygen desaturation and other parameters is more appropriate to increase the diagnostic capability of a sleep monitor. This way, a precise assessment of symptomatic respiratory events can be performed.

Is Polysomnography Both Reliable and Accessible to Predict Respiratory Events?

“…Because the O 2 saturation levels and gas exchange measurements detected by PSG change according to the body's movements and the sleep stages. 2 On the other hand, patient selection for PSG is highly biased, and PSG can alone predict only 25% of high-risk patients. 3 Because there is very little data on respiratory parameters in children, the interpretation of PSG results has not yet been standardized in pediatric age groups.…”