Development of a Sleep Apnea Detection Algorithm Using Long Short-Term Memory and Heart Rate Variability

2019 ◽  
Author(s):  
Ayako Iwasaki ◽  
Chikao Nakayama ◽  
Koichi Fujiwara ◽  
Yukiyoshi Sumi ◽  
Masahiro Matsuo ◽  
...  
Keyword(s):  
Heart Rate ◽  
Heart Rate Variability ◽  
Sleep Apnea ◽  
Short Term Memory ◽  
Detection Algorithm ◽  
Short Term ◽  
Term Memory ◽  
Apnea Detection ◽  
Long Short Term Memory

Automated sleep apnea detection in snoring signal using long short-term memory neural networks

2022 ◽  
Vol 71 ◽  
pp. 103238
Author(s):  
Siyi Cheng ◽  
Chao Wang ◽  
Keqiang Yue ◽  
Ruixue Li ◽  
Fanlin Shen ◽  
...  
Keyword(s):  
Neural Networks ◽  
Sleep Apnea ◽  
Short Term Memory ◽  
Short Term ◽  
Term Memory ◽  
Apnea Detection ◽  
Long Short Term Memory

scholarly journals Deep Recurrent Neural Networks for Automatic Detection of Sleep Apnea from Single Channel Respiration Signals

Sensors ◽  
2020 ◽  
Vol 20 (18) ◽  
pp. 5037
Author(s):  
Hisham ElMoaqet ◽  
Mohammad Eid ◽  
Martin Glos ◽  
Mutaz Ryalat ◽  
Thomas Penzel
Keyword(s):  
Feature Extraction ◽  
Sleep Apnea ◽  
Short Term Memory ◽  
Single Channel ◽  
Automated Detection ◽  
Detection Methods ◽  
Short Term ◽  
Term Memory ◽  
Deep Recurrent Neural Network ◽  
Long Short Term Memory

Sleep apnea is a common sleep disorder that causes repeated breathing interruption during sleep. The performance of automated apnea detection methods based on respiratory signals depend on the signals considered and feature extraction methods. Moreover, feature engineering techniques are highly dependent on the experts’ experience and their prior knowledge about different physiological signals and conditions of the subjects. To overcome these problems, a novel deep recurrent neural network (RNN) framework is developed for automated feature extraction and detection of apnea events from single respiratory channel inputs. Long short-term memory (LSTM) and bidirectional long short-term memory (BiLSTM) are investigated to develop the proposed deep RNN model. The proposed framework is evaluated over three respiration signals: Oronasal thermal airflow (FlowTh), nasal pressure (NPRE), and abdominal respiratory inductance plethysmography (ABD). To demonstrate our results, we use polysomnography (PSG) data of 17 patients with obstructive, central, and mixed apnea events. Our results indicate the effectiveness of the proposed framework in automatic extraction for temporal features and automated detection of apneic events over the different respiratory signals considered in this study. Using a deep BiLSTM-based detection model, the NPRE signal achieved the highest overall detection results with true positive rate (sensitivity) = 90.3%, true negative rate (specificity) = 83.7%, and area under receiver operator characteristic curve = 92.4%. The present results contribute a new deep learning approach for automated detection of sleep apnea events from single channel respiration signals that can potentially serve as a helpful and alternative tool for the traditional PSG method.

scholarly journals Automatic Detection for Multi-Labeled Cardiac Arrhythmia Based on Frame Blocking Preprocessing and Residual Networks

2021 ◽  
Vol 8 ◽  
Author(s):  
Zicong Li ◽  
Henggui Zhang
Keyword(s):  
Cardiac Arrhythmias ◽  
Short Term Memory ◽  
Area Under The Curve ◽  
Detection Algorithm ◽  
Memory Model ◽  
Binary Classifier ◽  
Short Term ◽  
Term Memory ◽  
Cardiac Functions ◽  
Long Short Term Memory

Introduction: Electrocardiograms (ECG) provide information about the electrical activity of the heart, which is useful for diagnosing abnormal cardiac functions such as arrhythmias. Recently, several algorithms based on advanced structures of neural networks have been proposed for auto-detecting cardiac arrhythmias, but their performance still needs to be further improved. This study aimed to develop an auto-detection algorithm, which extracts valid features from 12-lead ECG for classifying multiple types of cardiac states.Method: The proposed algorithm consists of the following components: (i) a preprocessing component that utilizes the frame blocking method to split an ECG recording into frames with a uniform length for all considered ECG recordings; and (ii) a binary classifier based on ResNet, which is combined with the attention-based bidirectional long-short term memory model.Result: The developed algorithm was trained and tested on ECG data of nine types of cardiac states, fulfilling a task of multi-label classification. It achieved an averaged F1-score and area under the curve at 0.908 and 0.974, respectively.Conclusion: The frame blocking and bidirectional long-short term memory model represented an improved algorithm compared with others in the literature for auto-detecting and classifying multi-types of cardiac abnormalities.

scholarly journals Real-Time System Prediction for Heart Rate Using Deep Learning and Stream Processing Platforms

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Abdullah Alharbi ◽  
Wael Alosaimi ◽  
Radhya Sahal ◽  
Hager Saleh
Keyword(s):  
Heart Rate ◽  
Time Series ◽  
Real Time ◽  
Short Term Memory ◽  
Stream Processing ◽  
Care Providers ◽  
Short Term ◽  
Term Memory ◽  
Risk Of Death ◽  
Long Short Term Memory

Low heart rate causes a risk of death, heart disease, and cardiovascular diseases. Therefore, monitoring the heart rate is critical because of the heart’s function to discover its irregularity to detect the health problems early. Rapid technological advancement (e.g., artificial intelligence and stream processing technologies) allows healthcare sectors to consolidate and analyze massive health-based data to discover risks by making more accurate predictions. Therefore, this work proposes a real-time prediction system for heart rate, which helps the medical care providers and patients avoid heart rate risk in real time. The proposed system consists of two phases, namely, an offline phase and an online phase. The offline phase targets developing the model using different forecasting techniques to find the lowest root mean square error. The heart rate time-series dataset is extracted from Medical Information Mart for Intensive Care (MIMIC-II). Recurrent neural network (RNN), long short-term memory (LSTM), gated recurrent units (GRU), and bidirectional long short-term memory (BI-LSTM) are applied to heart rate time series. For the online phase, Apache Kafka and Apache Spark have been used to predict the heart rate in advance based on the best developed model. According to the experimental results, the GRU with three layers has recorded the best performance. Consequently, GRU with three layers has been used to predict heart rate 5 minutes in advance.

Sign in / Sign up

Export Citation Format

Share Document