Tracheal Sound Analysis Using a Deep Neural Network to Detect Sleep Apnea

Abstract

Study Objectives: Portable devices for home sleep apnea testing are often limited by their inability to discriminate sleep/wake status, possibly resulting in underestimations. Tracheal sound (TS), which can be visualized as a spectrogram, carries information about apnea/hypopnea and sleep/wake status. We hypothesized that image analysis of all-night TS recordings by a deep neural network (DNN) would be capable of detecting breathing events and classifying sleep/wake status. The aim of this study is to develop a DNN-based system for sleep apnea testing and validate it using a large sampling of polysomnography (PSG) data. Methods: PSG examinations for the evaluation of sleep-disordered breathing (SDB) were performed for 1,852 patients: 1,548 PSG records were used to develop the system, and the remaining 304 records were used for validation. TS spectrogram images were obtained every 60 seconds and labeled with the PSG scoring results (breathing event and sleep/wake status), then introduced to DNN learning. Two different DNNs were trained for breathing status and sleep/wake status, respectively. Results: A DNN with convolutional layers showed the best performance for discriminating breathing status. The same DNN structure was trained for sleep/wake discrimination. In the validation study, the DNN analysis was capable of discriminating the sleep/wake status with reasonable accuracy. The diagnostic sensitivity, specificity, and area under the receiver operating characteristic curves for diagnosis of SDB with apnea-hypopnea index of > 5, 15, and 30 were 0.98, 0.76, and 0.99; 0.97, 0.90, and 0.99; and 0.92, 0.94, and 0.98, respectively. Conclusions: The developed system using the TS DNN analysis has a good performance for SDB testing.

The Importance of Respiratory Rate Monitoring: From Healthcare to Sport and Exercise

“…Hence, tracheal sound sensors meet the oronasal flow evaluation criteria for apnea detection required by the American Academy of Sleep Medicine, and can thus be used as alternatives to temperature sensors [79,80]. Furthermore, these sensors can provide additional useful information on snoring sounds and sleep/wake status discrimination [78,81].…”

“…Acoustic sensors can also be used in home settings when the aim is not to perform a diagnostic test for sleep apnea identification but to monitor the patient on a routine basis. To this end, sleep apnea can be detected with a mobile phone built-in microphone [81,82]. Other available techniques for apnea monitoring include the use of camera sensors for the recording of surveillance videos that can be post-processed to retrieve apnea episodes [83,84].…”

“…Besides, fR and its variability change across wakefulness and different sleep stages [300,301], which is relevant when interpreting nocturnal fR values. Sleep stages are usually identified with electroencephalography, but approaches based on breathing sound processing have also been proposed [81]. Another strategy to gain insight into the factors behind the changes in fR is the The framework is composed of ten steps that are numbered and listed on the left-hand side of the figure.…”

Joint Apnea and Body Position Analysis for Home Sleep Studies Using a Wireless Audio and Motion Sensor

“…Accordingly, the quantitative prediction of hypopneas was almost impossible in this setup; however, we include them in the qualitative analysis presented in sections 2.6. and 3.4. Those also did not allow us to use more sophisticated methods, like recurrent deep learning techniques, like it was presented by Nakano et al [45]. The device do not allow to distinguish central and obstructive apneas, as there is no EEG and direct respiratory effort information; however, we will work on it, as in our opinion, audio contact sensor with actigraphy together might be used to analyze respiratory effort indirectly.…”

Snoring is a pathogenic symptom: A need for its objective assessment

“…For example, a monitor used in one study, which detects the tracheal sound and analyzes it, using the deep neural network approach, can predict an Apnea-Hypopnea Index ≥5 with high sensitivity and specificity. 6 This type of device will process the combined objective information of both the frequency and intensity of snoring for a night or two, and give cut-off values, over which each component should be pathogenic. One day in the future, these devices will give an objective diagnosis based on snoring, even for older people who live alone.…”