A Study of Breathing Sound-based Classification of Patients With Breathing Disorders
Study Details
Study Description
Brief Summary
Sleep-disordered breathing can damage the cardiovascular system, and may also lead to dysregulation of the autonomic nervous system, endocrine disorders, and hemodynamic changes, causing multi-system and multi-organ damage. Screening for potential central-type patients among patients with respiratory disorders can help provide scientific diagnosis and treatment decisions, thus achieving precise treatment. Currently, research on the identification of sleep-disordered breathing phenotypes is in its infancy. Sleep-disordered breathing phenotypes, such as obstructive and central respiratory events, vary widely among individuals. Compared to indirect methods such as RIP and SpO2, changes in breathing sounds and snoring during sleep can more directly reflect airway obstruction. Different types of sleep-disordered breathing exhibit different characteristics in terms of snoring. Patients with obstructive sleep apnea experience narrowing or blockage of the airway due to relaxation of the throat muscles during sleep, which leads to breathing pauses and hypopnea events, resulting in decreased blood oxygen levels, arousal, and snoring. Central sleep apnea is caused by problems with the brainstem or respiratory control center, leading to breathing pauses. Snoring is usually not very prominent in patients with central sleep apnea. This study aims to screen for potential central-type patients by analyzing upper airway sounds of patients with sleep-disordered breathing, in order to achieve precise treatment.
| Condition or Disease | Intervention/Treatment | Phase |
|---|---|---|
|
Detailed Description
Snoring is a common manifestation of sleep breathing disorders, and through the analysis of a patient's snoring, potential patients with central sleep apnea can be screened from patients with sleep breathing disorders.
First, a microphone is used to record the patient's airway sound throughout the night. Sleep and wakefulness are separated from the airway sound throughout the night, and only the patient's sleep periods are analyzed. Breath-holding positions are determined in 30-second frames, and in snoring event detection, if the sound stops and lasts for more than 10 seconds, it may be a respiratory arrest event. Finally, the detected respiratory arrest events are differentiated into sleep breathing disorder phenotypes. Snoring can be described based on physiological information features such as sound frequency, volume, and duration. Respiratory information features of breath-holding events are selected and fused to classify the type of breathing disorder.
Generally, obstructive sleep apnea is caused by partial or complete blockage of the airway. During sleep, the throat and soft tissue relax and may block the airway, resulting in breathing pauses. This type of breathing pause often accompanies snoring, as the vibration sound is produced by the air being forced through the blocked airway. The snoring of obstructive sleep apnea is usually loud, high frequency, and there are brief pauses in breathing. Central sleep apnea is caused by a disruption in the brain's control of breathing. The snoring of this type of breathing pause is usually softer, lower frequency, and there are no brief pauses in breathing.
Study Design
Arms and Interventions
| Arm | Intervention/Treatment |
|---|---|
| Group 1 Patients suspected of having obstructive apnea |
Diagnostic Test: polysomnography
Polysomnography is mainly used to diagnose sleep breathing disorders, including sleep apnea syndrome, snoring, upper airway resistance syndrome, and also used for the auxiliary diagnosis of other sleep disorders, such as: narcolepsy, restless legs syndrome, insomnia classification, etc.
|
Outcome Measures
Primary Outcome Measures
- The accuracy of the binary classification of obstructive apnea and central apnea [3 days]
Based on the binary classification of events, obstructive apnea is the negative class and central apnea is the positive class. Accuracy is the ratio of the predicted correct positive plus negative class to the total event.
- The recall of the binary classification of obstructive apnea and central apnea [3 days]
According to the binary classification of events, obstructive apnea is negative and central apnea is positive. Recall represents the proportion of all positive events in the dataset that the model correctly classifies as positive.
Secondary Outcome Measures
- The accuracy of the patient's apnea detection [3 days]
Apnea detection in 30-second segments. Segments with apnea are positive and segments without apnea are negative. Accuracy is the ratio of the predicted correct positive plus negative classes to the total fragment.
- The recall of the patient's apnea detection. [3 days]
30-second apnea detection. Segments with apnea are positive and those without apnea are negative. Recall indicates the ratio of the correctly classified positive fragments of the model to all positive fragments in the dataset.
Other Outcome Measures
- The patient's sleep efficiency [3 days]
The patient's sleep time was detected in 30-second segments. Sleep efficiency is the sum of detected slices of sleep time and the ratio of the patient's time in bed.
- The accuracy of hypoventilation detection in patients [3 days]
Hypoventilation of patients was detected in 30-second segments. Segments with hypoventilation are positive and segments without hypoventilation are negative. Accuracy is the ratio of the predicted correct positive plus negative classes to the total fragment.
- The recall of hypoventilation detection in patients [3 days]
Hypoventilation of patients was detected in 30-second segments. Segments with hypoventilation are positive and segments without hypoventilation are negative.Recall indicates the ratio of the correctly classified positive fragments of the model to all positive fragments in the dataset.
Eligibility Criteria
Criteria
Inclusion Criteria:
-
the age of the patient is 18-75 years old;
-
patients with confirmed PSG with AHI ≥ 5 times/hour, with or without daytime sleepiness, hypertension, and diabetes;
-
sleep-disordered breathing has not been treated;
-
informed consent of patients
Exclusion Criteria:
-
pregnancy;
-
have other diseases that are not suitable for participation in this study
Contacts and Locations
Locations
| Site | City | State | Country | Postal Code | |
|---|---|---|---|---|---|
| 1 | Department Of Respiratory Medicine,Huai'an First People's Hospital,Nanjing Medical University | Huai'an | Jiangsu | China | 223300 |
Sponsors and Collaborators
- Huai'an No.1 People's Hospital
- The First Affiliated Hospital with Nanjing Medical University
- Nanjing University of Science and Technology
Investigators
None specified.Study Documents (Full-Text)
None provided.More Information
Publications
None provided.- YX-2021-061-01