Dataset Information

Cascading detection model for prediction of apnea-hypopnea events based on nasal flow and arterial blood oxygen saturation.

ABSTRACT: PURPOSE:Sleep apnea and hypopnea syndrome (SAHS) seriously affects sleep quality. In recent years, much research has focused on the detection of SAHS using various physiological signals and algorithms. The purpose of this study is to find an efficient model for detection of apnea-hypopnea events based on nasal flow and SpO2 signals. METHODS:A 60-s detector and a 10-s detector were cascaded for precise detection of apnea-hypopnea (AH) events. Random forests were adopted for classification of data segments based on morphological features extracted from nasal flow and arterial blood oxygen saturation (SpO2). Then the segments' classification results were fed into an event detector to locate the start and end time of every AH event and predict the AH index (AHI). RESULTS:A retrospective study of 24 subjects' polysomnography recordings was conducted. According to segment analysis, the cascading detection model reached an accuracy of 88.3%. While Pearson's correlation coefficient between estimated AHI and reference AHI was 0.99, in the diagnosis of SAHS severity, the proposed method exhibited a performance with Cohen's kappa coefficient of 0.76. CONCLUSIONS:The cascading detection model is able to detect AH events and provide an estimate of AHI. The results indicate that it has the potential to be a useful tool for SAHS diagnosis.

SUBMITTER: Yu H

PROVIDER: S-EPMC7289775 | biostudies-literature | 2020 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Cascading detection model for prediction of apnea-hypopnea events based on nasal flow and arterial blood oxygen saturation.

Yu Hui H Deng Chenyang C Sun Jinglai J Chen Yanjin Y Cao Yuzhen Y

Sleep & breathing = Schlaf & Atmung 20190705 2

<h4>Purpose</h4>Sleep apnea and hypopnea syndrome (SAHS) seriously affects sleep quality. In recent years, much research has focused on the detection of SAHS using various physiological signals and algorithms. The purpose of this study is to find an efficient model for detection of apnea-hypopnea events based on nasal flow and SpO<sub>2</sub> signals.<h4>Methods</h4>A 60-s detector and a 10-s detector were cascaded for precise detection of apnea-hypopnea (AH) events. Random forests were adopted ...[more]

PMID: 31278530

Similar Datasets

Project description:ObjectivesThe aim of this study was to identify correlations between sleep apnea severity and tongue volume or posterior airway space measured via three-dimensional reconstruction of volumetric computerized tomography (CT) images in patients with obstructive sleep apnea (OSA) for use in predicting OSA severity and in surgical treatment. We also assessed associations between tongue volume and Mallampati score.MethodsSnoring/OSA male patients (n = 64) who underwent polysomnography, cephalometry, and CT scans were enrolled in this retrospective study. OSA was diagnosed when the apnea-hypopnea index (AHI) was greater than 5 (mild 5-14; moderate 15-29; severe>30). The patients were also categorized into the normal-mild group (n = 22) and the moderate-severe group (n = 42). Using volumetric CT images with the three-dimensional reconstruction technique, the volume of the tongue, posterior airway space volume, and intra-mandibular space were measured. The volumes, polysomnographic parameters, and physical examination findings were compared, and independent factors that are related to OSA were analysed.ResultsNo associations between tongue volume or posterior airway space and the AHI were observed. However, multivariate linear analyses showed that tongue volume had significantly negative association with lowest O2 saturation (r = 0.365, p = 0.027). High BMI was related to an increase in tongue volume. Modified Mallampati scores showed borderline significant positive correlations with absolute tongue volume (r = 0.251, p = 0.046) and standardized tongue volume (absolute tongue volume / intramandibular area; r = 0.266, p = 0.034). Between the normal-mild and moderate-severe groups, absolute tongue volumes were not different, although the standardized tongue volume in the moderate-severe group was significantly higher.ConclusionAbsolute tongue volume showed stronger associations with lowest O2 saturation during sleep than with the severity of AHI. We also found that high BMI was a relevant factor for an increase in absolute tongue volume and modified Mallampati grading was a useful physical examination to predict tongue size.

Dataset Information

Cascading detection model for prediction of apnea-hypopnea events based on nasal flow and arterial blood oxygen saturation.

Publications

Cascading detection model for prediction of apnea-hypopnea events based on nasal flow and arterial blood oxygen saturation.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets