Real-time apnea-hypopnea event detection during sleep by convolutional neural networks

Choi, Sang Ho; Yoon, Heenam; Kim, Hyun‐Seok; Kim, Han Byul; Kwon, Hyun; Oh, Sung Min; Lee, Yu Jin; Park, Kwang Suk

doi:10.1016/j.compbiomed.2018.06.028

Cited by 87 publications

(68 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the detection of AH events may not be precise based on 60 s segment analysis because it can only determine whether there was AH in the segment, while, may make mistakes for the segments containing multiple AH events and lead to an error in AHI estimation. Therefore, some researchers [3,9] cut the signals into shorter segments for detection. However, it is difficult to extract effective features from a segment shorter than 10 s, because there will be no more than five complete breaths in one segment in most cases.…”

Section: Discussionmentioning

confidence: 99%

“…The annotation files consisted of onset time and duration of respiratory events provided by an experienced specialist. The cutoff values for AHI were commonly set to 5, 15, or 30 events/h [3,4,7,16,17]. There were data for two non-SAHS subjects, twelve mild-SAHS subjects, five moderate-SAHS subjects, and six severe-SAHS subjects in the database.…”

Section: Subjectsmentioning

confidence: 99%

“…However, many other diseases except SAHS also affect ECG. Hence, nasal flow (NF) [3][4][5][6], arterial blood oxygen saturation (SpO 2 ) [7], snoring [8], or a combination of these signals [9,10] have been adopted more recently. Gutierrez et al [4] used the overall features of NF for the diagnosis of SAHS severity.…”

Section: Introductionmentioning

confidence: 99%

“…Xie et al [10] utilized a combination of classifiers to achieve realtime detection of SAHS based on ECG and SpO 2 . All the above studies can be roughly divided into two categories: those that predict the AH index (AHI) based on the detection of AH events [2,3,5,7,[9][10][11], and those that predict AHI based on the overall signal features [1,4,6,8,12,13]. The latter approach cannot provide time information for each AH event, whereas most studies in the former [2,7,10,11] only involve a 60-s segment identification which may not be accurate for predicting the segments containing multiple AH events and may lead to errors in the estimation of AHI.…”

Section: Introductionmentioning

confidence: 99%

“…The latter approach cannot provide time information for each AH event, whereas most studies in the former [2,7,10,11] only involve a 60-s segment identification which may not be accurate for predicting the segments containing multiple AH events and may lead to errors in the estimation of AHI. On the other hand, the methods mentioned above include rule-based [5,7,9], SVM [2,10,11], and supervised neural network [3,11], which require a large number of hyperparameters to be set by experience. Therefore, we utilized random forests composed of classification and regression trees (CARTs) based on morphological features extracted from NF and SpO 2 for AH events detection.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

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

Deng

Sun

et al. 2019

Sleep Breath

View full text Add to dashboard Cite

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 SpO 2 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 (SpO 2). 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.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Subjectsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

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

Deng

Sun

et al. 2019

Sleep Breath

View full text Add to dashboard Cite

show abstract

Automatic diagnosis of sleep apnea from biomedical signals using artificial intelligence techniques: Methods, challenges, and future works

Moridian

Shoeibi

Khodatars

et al. 2022

WIREs Data Min & Knowl

View full text Add to dashboard Cite

Apnea is a sleep disorder that stops or reduces airflow for a short time during sleep. Sleep apnea may last for a few seconds and happen for many while sleeping. This reduction in breathing is associated with loud snoring, which may awaken the person with a feeling of suffocation. So far, a variety of methods have been introduced by researchers to diagnose sleep apnea, among which the polysomnography (PSG) method is known to be the best. Analysis of PSG signals is very complicated. Many studies have been conducted on the automatic diagnosis of sleep apnea from biological signals using artificial intelligence (AI), including machine learning (ML) and deep learning (DL) methods. This research reviews and investigates the studies on the diagnosis of sleep apnea using AI methods. First, computer aided diagnosis system (CADS) for sleep apnea using ML and DL techniques along with its parts including dataset, preprocessing, and ML and DL methods are introduced. This research also summarizes the important specifications of the studies on the diagnosis of sleep apnea using ML and DL methods in a table. In the following, a comprehensive discussion is made on the studies carried out in this field. The challenges in the diagnosis of sleep apnea using AI methods are of paramount importance for researchers. Accordingly, these obstacles are elaborately addressed. In another section, the most important future works for studies on sleep apnea detection from PSG signals and AI techniques are presented. Ultimately, the essential findings of this study are provided in the conclusion section. This article is categorized under: Technologies > Artificial Intelligence Application Areas > Data Mining Software Tools Algorithmic Development > Biological Data Mining

show abstract

Discussion

Villar

2023

Springer Theses

View full text Add to dashboard Cite

Real-time apnea-hypopnea event detection during sleep by convolutional neural networks

Cited by 87 publications

References 31 publications

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

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

Automatic diagnosis of sleep apnea from biomedical signals using artificial intelligence techniques: Methods, challenges, and future works

Discussion

Contact Info

Product

Resources

About