Phát hiện ngưng thở khi ngủ từ tín hiệu ecg và phương pháp phân loại dựa trên mô hình se resnext

HA NOI UNIVERSITY OF SCIENCE AND TECHNOLOGY SCHOOL OF ELECTRICAL & ELECTRONIC ENGINEERING MASTER THESIS A SLEEP APNEA DETECTION FROM ECG SIGNAL AND CLASSIFICATION METHOD BASED ON THE SE-ResNeXt MODEL DO THI THU PHUONG Phuong.DTT212478M@hust.edu.vn Advanced Program in Biomedical Engineering Instructor: PhD Tran Anh Vu Instructor’s signature School: Electronics and Telecommunications HA NOI, 7th 2023 HA NOI, 8th 2023 SOCIALIST REPUBLIC OF VIET NAM Independence- Freedom- Happiness VERIFICATION OF THE MASTER THESIS The full name of the author: Do Thi Thu Phuong Thesis topic: A sleep apnea detection from ECG signal and classification method based on the SE-ResNeXt model Majority: Biomedical Engineering The student code: 20212478M The instructor and the chairman of committee verify that the author has corrected and supplemented the thesis according to the minutes of the meeting committee with the following contents: Add content on why ECG signals are related to sleep apnea Add content to the ECG signal lead Use exactly words (detection => classification, project => thesis) Remove 2.6: Other classification methods content Ha Noi,…./…./2021 The Instructor CHAIRMAN OF THE COMMITTEE The Author MASTER THESIS A SLEEP APNEA DETECTION FROM ECG SIGNAL AND CLASSIFICATION METHOD BASED ON THE SE-ResNeXt MODEL Instructor Sign and write full name ACKNOWLEDGEMENT During my studies at Hanoi University of Science and Technology, I was equipped with in-depth knowledge, helping me grow in learning and scientific research I would like to thank my teachers, who taught me whole heartedly during my time at the university With deep respect and gratitude, I express my sincere thanks to PhD Tran Anh Vu, lecturer in the Electronic Technology and Biomedical Engineering Department, who is a instructor and has spent a lot of time guiding, instructing, and supporting me throughout the research and completion of this thesis During the research and completion of my thesis, I received encouragement, sharing, and help from family, friends, colleagues, and other close people I would like to express my deep gratitude Thank you for the support! ABSTRACT Sleep apnea (SA) is a serious sleep disorder that happens when a person’s breathing repeatedly stops and starts during sleep Thesis "A sleep apnea detection from ECG signal and classification method based on the SE-ResNeXt model" Once completed, accurate classification of sleep apnea episodes is a crucial step to develop effective therapies and management strategies for treatment In this work, the SA classification procedure is based on a single-lead electrocardiogram (ECG), which is one of the most physiologically relevant signals for SA I propose a new feature extraction technique, which utilized the detection of R peaks Particularly, we derive from the Teager Energy Operator (TEO) algorithm to detect R peaks and then obtain the RR intervals and amplitudes Afterward, the SE-ResNeXt 50 deep learning model is used as a classifier to detect sleep apnea This model is a variant of ResNet 50 and can learn how to use global information to selectively emphasize useful information and suppress less beneficial ones, as well as allow feature recalibration The dataset is taken from a published database and is initiated by 70 recordings of the PhysioNet ECG Sleep Apnea v1.0.0 dataset The performance of my classification method is 89,21% accuracy, 90,29% sensitivity, and 87,36% specificity, demonstrating the model’s validity when compared to other researches This is also proof that I can utilize the ECG signal to efficiently classify SA STUDENT Sign and write full name CONTENTS CHAPTER INTRODUCTION 1.1 Chapter description 1.2 The sleep apnea overview 1.3 Chapter conclusion CHAPTER 2: THEORETICAL BASIC 2.1 Chapter description 2.2 ECG signal 2.2.1 Definition 2.2.2 Objective 2.2.3 ECG test procedure 10 2.2.4 Types 11 2.2.5 The ECG wave 11 2.3 Teager energy operator 14 2.4 SE-ResNeXt 50 model 15 2.4.1 Squeeze-and-Excitation Blocks 15 2.4.2 Model and Computational Complexity 18 2.4.3 Implementation 19 2.5 Band-pass filter 20 2.6 Chapter conclusion 21 CHAPTER 3: DATASET AND PROPOSED METHODS 22 3.1 Chapter description 22 3.2 Experimental dataset 22 3.3 The proposed methods 23 3.4 3.3.1 Pre-processing 23 3.3.2 Feature extraction 24 3.3.1 Classification 26 3.3.2 Performance matrics 26 Chapter conclusion 27 CHAPTER 4: RESULT AND DISCUSSION 28 4.1 Result 28 4.2 Discussion 28 4.3 Conclusion 29 REFERENCES 30 SUMMARY OF THE MASTER'S THESIS 34 a) Reason of choosing the topic 34 b) Purpose, Research Object, Scope of Research 34 c) Content Summary and Author’s Contribution 35 d) Research method 36 e) Conclusion 36 LIST OF FIGURES Figure 1.2-1: Obstructive sleep apnea 12 Figure 2.2-1: An example of ECG signal Figure 2.2-2: The ECG test procedure 15 Figure 2.2-3: The ECG wave 12 Figure 2.2-4: The normal ECG signal 19 Figure 2.2-5: The angina ECG signal 13 Figure 2.2-6: The serious heart attack 1319 Figure 2.2-7: The atrial fibrillation ECG signal 14 Figure 2.4-1: A Squeeze-and-Excitation block 16 Figure 2.4-2: The schema of the original Inception module (left) and the SEInception module (right) 17 Figure 2.4-3: The schema of the original Residual module (left) and the SE-ResNet module (right) 18 Figure 2.4-4: (Left) ResNet-50 (Middle) SE-ResNet-50 (Right) SE-ResNeXt-50 model 26 Figure 2.5-1: Unrestricted signal (upper diagram) 27 LIST OF TABLES Table 4.1-1: Result table 46 CHAPTER INTRODUCTION 1.1 Chapter description Chapter presents the clinical basics of the sleep apnea The first chapter of the thesis will focus on clarifying the definition, symptoms, causes and risks of patients with the sleep apnea Then from the clinical facility will use ECG signal combined with Machine Learning (ML) application in disease classification This is an effective, optimal solution and offers many treatment opportunities for patients with the sleep apnea 1.2 The sleep apnea overview A repeated interruption or sleep disorder called sleep apnea (SA) is characterized by the collapse of the upper airway, which could result in the atic reduction of respiration airflow The word “apnea” comes from the Greek word for “breathless” SA events can occur hundreds of times as you sleep, and if they so repeatedly overtime, they can lead to a variety of health issues [1] Sleep apnea occurs more often in men than in women Sleep apnea can occur at any age including infants, children, especially those over 50 and people who are overweight Sleep apnea is uncommon but widespread Experts estimate it affects about 5% to 10% of people worldwide The American Academy of Sleep Medicine (AASM) defines SA patients as individuals who have an apnea-hypopnea index (AHI) of or higher [2] Nearly 90% of SA patients not receive timely diagnosis and treatment Besides, people with obesity and overweight are more likely to suffer from SA [3] The resulting lack of oxygen activates a survival reflex that wakes you up just enough to resume breathing While that reflex keeps you alive, it also interrupts your sleep cycle That prevents restful sleep and can have other effects, including putting stress on your heart that can have potentially deadly consequences The symptoms of obstructive and central sleep apneas overlap, sometimes making it difficult to determine which type you have The most common symptoms of obstructive and central sleep apneas include: loud snoring, episodes in which you stop breathing during sleep which would be reported by another person, gasping for air during sleep, awakening with a dry mouth, morning headache, difficulty staying asleep, known as insomnia, excessive daytime sleepiness, known as hypersomnia, difficulty paying attention while awake, irritability… The main causes of sleep apnea are: - Obstructive sleep apnea (OSA), which is the more common form that occurs when throat muscles relax and block the flow of air into the lungs These muscles support the soft palate, the triangular piece of tissue hanging from the soft palate called the uvula, the tonsils, the side walls of the throat and the tongue When the muscles relax, your airway narrows or closes as you breathe in You can't get enough air, which can lower the oxygen level in your blood Your brain senses that you can't breathe, and briefly wakes you so that you can reopen your airway This awakening is usually so brief that you don't remember it You might snort, choke or gasp This pattern can repeat itself to 30 times or more each hour, all night This makes it hard to reach the deep, restful phases of sleep Figure 1.2-1: Obstructive sleep apnea - - Central sleep apnea (CSA), which occurs when the brain doesn't send proper signals to the muscles that control breathing Central sleep apnea is a disorder in which you breathing repeatedly stops and starts during sleep This condition is different from obstructive sleep apnea, in which you can't breathe normally because of upper airway obstruction Central sleep apnea is less common than obstructive sleep apnea Central sleep apnea can result from other conditions, such as heart failure and stroke Another possible cause is sleeping at a high altitude Treatments for central sleep apnea might involve treating existing conditions, using a device to assist breathing or using supplemental oxygen Treatment-emergent central sleep apnea, also known as complex sleep apnea, which happens when someone has OSA diagnosed with a sleep study that converts to CSA when receiving therapy for OSA pass filter, and then the TEO algorithm is used to determine the peak R The next step is to determine the interval and the amplitude of the R peaks Cubic interpolation is used to generate 900 values for each feature After pre-processing the data and extracting features, I proceed to classify the signal based on the SE-ResNeXt 50 model Figure 3.2-1: Sleep apnea classification scheme 3.3 The proposed methods 3.3.1 Pre-processing The recorded ECG signals are frequently distorted by noise and artifacts Their frequencies, generated by the power lines’ interference are in the range of 50 to 60 Hz The noises generated by the muscle contractions and the electrodes placed on the body’s skin are in the range of 40 to 48 Hz [37] The ECG signals are severely hindered by them In order to increase peak detection and decrease noise and artifacts from the electrical (device) components, I employed the ECG band-pass filter with a frequency range of to 40 Hz The phase response and signal attenuation are best balanced by the band-pass filter, which allows signals within a selected range of frequencies to be heard or decoded while preventing signals at undesirable frequencies The signals before and after they have been through the band-pass filter are depicted in Figure 3.3-1 and 3.32, respectively 23 Figure 3.3-1: The original signal on lead V2 ECG Figure 3.3-2: The component falls within to Hz frequency range of the ECG signal 3.3.2 Feature extraction Abnormal characteristics of the ECG signal are extracted and input to a machine learning classifier in order to detect abnormal ECG segments in patients with SA In the study [38], it was shown that the QRS complex was found using a novel technique that was based on the TEO in the ECG signal The study’s major conclusions show that this method is highly accurate and reliable at spotting the QRS complex The suggested approach performs better than more complex methods like neural networks The outcomes demonstrate that the suggested approach is straightforward, efficient, precise, and suited for real-world use Therefore, I used the TEO algorithm to detect R peaks in ECG signals in my study and then fed them into a CNN model to classify the disease a R peaks detection 24 The TEO algorithm [38] was first used to locate the R peaks; the amplitudes of the R peaks were then retrieved; and finally, the positions of the R peaks were used to estimate the RR intervals The TEO has a wide range of uses, particularly useful for processing speech transmission The TEO can be driven by a second-order differential equation [39] The total energy of oscillation, which is the sum of the kinetic and potential energies, can be calculated using the equation below:   E = k  + m   (3.1)  where k is the spring constant and m is the mass of the oscillating body A periodic harmonic formula can be produced using the formula in (1): x(t) = Acos(  󰇜 (3.2) Where  is the phase shift,  is the oscillation frequency, A is the oscillation amplitude, and x(t) denotes the position of the oscillating body with respect to time The necessary harmonic energy to produce signals can be computed using equations (3.1) and (3.2):  E = m    (3.3) The following is a simplified form of TEO: c[x(t)] = 󰇟    󰇛 󰇜󰇠 – x(t)     󰇛 󰇜 c[x(t)] = [x’(t)]² - x(t)x’’(t) (3.4) (3.5) Substituting nT for t we will get the following equation: c[x(t)] = x²[n] – x[n-1]x[n+1] (3.6) where c[x(t)] is the energy operator for continuous time t, x(t) is the tth signal component, hx′(t)i and hx′′(t)i are the first and second derivatives of x(t), respectively, T is the sample period, and n is the sample size [39] The TEO pattern is intermittent and nonlinear due to the heartbeats’ dynamic nature TEO captures the intermittent properties nonlinearly because it is a nonlinear operator itself The process of peak detection includes the following step: Signal[n], baseline < signal[n] n = 2, 3, 4,… (3.7) Not select: signal[n] < baseline 25 ECG signals are detected at baseline (0), where R peaks are found in an ECG signal by searching for the maximum peak within 50 samples (length of window = (RR interval)) of the recognized location of the candidate R peak in the previous step (Equation (3.7)) The TEO algorithm’s detection of the R peaks on the filtered signal and the matching raw signal are shown in Figure 3.3-3 accordingly Figure 3.3-3: The diagram block show steps of E peaks detection 3.3.1 Classification After preprocessing the data and extracting features, I proceed to classify the signal Then, I use the SE-ResNeXt 50 model with the following specific setup parameters: The number of epochs is 100, the batch size is 256, the cross entropy loss is 1e3, and the AdamW optimization algorithm is used 3.3.2 Performance matrics In this study, I use accuracy, sensitivity, and specificity as measures to assess the performance of the machine learning classifier Accuracy: It is defined as the ratio of number of correctly classified samples to that of total samples Accuracy =      (3.8) Sensitivity: Sensitivity of a class is defined as the ratio of correctly classified samples to total number of samples actually belonging to that class Hence, the sensitivity is the measure of how well the model can correctly identify true values Sensitivity =    (3.9) Specificity: Specificity is used to measure the proportion of negatives that are correctly identified It is defined as the ratio of true negatives predicted to total number of samples which belong to negative class 26 Specificity =    (3.10) where TP: True Positive, TN: True Negative, FP: False Positive, FN : False Negative Hence, these metrics form a complete set of evaluating the performance of the model 3.4 Chapter conclusion Chapter has outlined the method of classifying sleep apnea by ECG signal Besides, the summary diagram described in detail every step I took As a result, the sleep apnea is classified with high accuracy, providing many opportunities for the medical use of ML 27 CHAPTER 4: RESULT AND DISCUSSION 4.1 Result In this work, there are two main contributions Firstly, in the pre-processing of ECG signals, I add noise filtering, peak detection, and feature extraction procedures After that, I use the TEO algorithm to detect R peaks and then calculate amplitudes and RR intervals The activation function is optimized based on the TEO algorithm, which greatly improves the accuracy of the classification result Secondly, I utilize the SE-ResNeXt 50 model in classification, which has not applied in SA classification before The classification results clearly showed higher accuracy and sensitivity Table 4.1-1 shows the comparison between the results of this paper and those of similar performs better than current researches for the same purpose Study [34] [41] [42] [43] [33] [32] Year 2019 2022 2019 2021 2019 2018 My research Model LeNet-5 ZFNet GRU Scalogram LeNet-LSTM Wise feature selection Hidden Markov model SE-ResNeXt 50 Comparison Accuracy Sensitivity 87.6 % 83.10 % 88.13 % 84.26 % 86.22 % 90.00 % 80.67 % 74.04 % Specificity 90.30 % 92.27 % 83.82 % 84.13 % 82.12 % 88.41 % 72.29 % 84.70 % 88.90 % 82.10 % 89.21 % 90.29 % 87.36 % Table 4.1-1: Result table 4.2 Discussion In this study, it included steps to detect sleep apnea: - The pre-processing step: Use a finite impulse response band-pass filter for the ECG signal The feature extraction step: + Apply TEO algorithm detects R peaks + Calculate the amplitude and interval between the R peaks The classification step: Use SE-ResNext 50 model to classify SA As a result, the network can learn how to use global information to selectively accentuate informative qualities and suppress less useful ones This permits feature recalibration This model has proven to be useful, especially with 1D data and ECG signals [40] 28 4.3 Conclusion In this paper, I propose a modified method to classify SA using ECG signals I add a filter to the PhysioNet dataset to eliminate noise Then I use TEO algorithm to detect R peaks of the ECG The signal amplitudes and RR intervals are caculated for the feature extraction After that, the SE-ResNeXt 50 model is used for SA disease classification This algorithm obtained an 89.21% average accuracy, 90.29% sensitivity, and 87.36% specificity In addition, the TEO algorithm has developed quickly in recent years, which is employed in the preprocessing of the data to locate R peaks This method outperforms more complex methods like neural networks and is exceedingly reliable and accurate The findings demonstrate that the suggested approach is straightforward, efficient, precise, and suitable for use in the modern era This is the basis for the demonstration of the SA classification performance of my algorithm using ECG signals After completing the thesis, as the result shows above, the accuracy of my method is quite high It opens up a bright future for me to develop the plan I made before In the future, I am going to apply other methods that can process ECG signals to diagnose patients who get the sleep apnea with the most reliable and highest accuracy I will improve the pre-processing step like use another filter to combine normalization as well as transfer spectrum images Besides, I can also improve the feature extraction step with another algorithm Moreover, I will choose better machine learning methods to detect SA I hope that in recent days, my thesis can be applied possibly in hospitals to support doctors so that the patient can be assured of the result of the diagnosis they receive 29 REFERENCES [1] Matthew L.H and Steven D.B Obstructive sleep apnea In National Library of Medicine: National Center for Biotechnology Information, pp 2-5 (2011) [2] Mannario M.R., Filippo F.D., Pirro M Obstructive sleep apnea syndrome, Eur In J Intern Med 23 (7), pp 586-593 (2012) [3] Young T., Evans L., Finn L., Palta M Estimation of the clinically diagnosed proportion of sleep apnea syndrome In Middle-aged men and women, Sleep 20 (9), pp 705-706 (1997) [4] Ali S.Q., Khalid S., Brahim B A Novel Technique to Diagnose Sleep Apnea In Suspected Patients Using Their ECG Data, IEEE Access, 7, pp 35184–35194 (2019) [5] Li Y., Pan W., Li K., Jiang Q., Liu G Sliding trend fuzzy approximate entropy as a novel descriptor of heart rate variability In obstructive sleep apnea, IEEE J Biomed Health Inf 23 (1), pp 175–183 (2019) [6] Lavie P., Herer P., Hoffstein V Obstructive sleep apnea syndrome as a risk factor for hypertension In Population study, Br Med J 320 (7233), pp 479–482 (2000) [7] Peker Y., Kraiczi H., Hedner J., Lăoth S., Johansson A., Bende M An independent association between obstructive sleep apnea and coronary artery disease In Eur Respir J 14 (1), pp 179–184 (1999) [8] Yoshihisa A and Takeishi Y Sleep disordered breathing and cardiovas cular diseases In J Atheroscler Thromb 26 (4), pp 315–327 (2019) [9] Mark E.D and Kyoung B.I Obstructive sleep apnea and stroke In Chest, 136(6), pp 1668–1677 (2009) [10] Baek J.W., Kim Y.N., Kim D.E., Lee, J.H Computer-aided detection with a portable electrocardiographic recorder and acceleration sensors for monitoring obstructive sleep apnea In Sensors and Transducers, 167(3), pp 80–87 (2014) [11] Rundo J.V and Downey R Chapter 25 - Polysomnography In K H Levin, & P Chauvel (Eds.), Handbook of Clinical Neurology, pp 381–392 (2019) [12] Syeda Q.A., Sohail K., Samir B.B A Novel Technique to Diagnose Sleep Apnea in Suspected Patients Using Their ECG Data In IEEE Access, 7, pp 35184 –35194 (2019) [13] Manish S., Shreyansh Ag., U R.A Application of an optimal class of antisymmetric wavelet filter banks for obstructive sleep apnea diagnosis using ECG signals In Computers: Biology and Medicine, pp 100:100–113, (2018) 30 [14] Pombo N., Silva B.M.C., Pinho A.M., Garcia N Classifier Precision Analysis for Sleep Apnea Detection Using ECG Signals In IEEE Access, 8, pp 200477– 200485 (2020) [15] Bozkurt F., Ucar M.K., Bozkurt M.R., Bilgin C Detection of Abnormal Respiratory Events with Single Channel ECG and Hybrid Machine Learning Model In Patients with Obstructive Sleep Apnea Irbm, 41(5), pp 241–251 (2020) [16] Vega P.R., Gang L., Wan-Young C Sleep apnea classification using ECG signal wavelet-PCA features In National library of medicine, pp 2-10 (2014) [17] Inez B and Wiersema J.R Resting electroencephalogram in attention deficit hyperactivity disorder Developmental course and diagnostic value Author links open overlay panel In Psychiatry Research 216(3), pp 391- 397 (2014) [18] Simranjit K., Sukhwinder S., Priti A., Damanjeet K., Manoj B Phase Space Reconstruction of EEG signals for classification of ADHD and control adults In Clinical EEG and Neuroscience (2020) [19] Pham T.V.H., Nguyen A.T., Tran A.V Ensemble learning in detecting ADHD children by utilizing the non-linear features of EEG signal In: N.D Vo, O.J Lee, K.H N Bui, H G Lim, H.J Jeon, P.M Nguyen, B.Q Tuyen, J.T Kim, J.J Jung, T.A Vo (eds.): Proceedings of the 2nd International Conference on Human-centered Artificial Intelligence (Computing Human 2021) (2021) [20] Duda M., Ma R., Haber N., Wall D.P Use of machine learning for behavioral distinction of autism and ADHD In Translational Psychiatry, vol (2016) [21] Alchalabi A.E., Shirmohammadi S., Eddin A.N., Elsharnouby M Detecting ADHD patients by an EEG-based serious game In IEEE Transactions on Instrumentation and Measurement (2018) [22] Nguyen D.C et al Short time cardio-vascular pulses estimation for dengue fever screening via continuous-wave Doppler radar using empirical mode decomposition and continuous wavelet transform Biomedical Signal Processing and Control, Vol 65 (2021) 102361 [23] Wessel J.R Testing Multiple Psychological Processes for Common Neural Mechanisms Using EEG and Independent Component Analysis In Brain Topography, vol 31, pp 90-100 (2016) [24] Katoab K., Takahashia K., Mizuguchiac N., Ushiba J Online detection of amplitude modulation of motor-related EEG desynchronization using a lock-in amplifier: Comparison with a fast Fourier transform, a continuous wavelet transform, and an autoregressive algorithm In Journal of Neuroscience Method, vol 293, pp 289-298 (2018) 31 [25] Armin A., Alireza K., Mohammad R.M., Ali M.N Detecting ADHD Childrenusing the Attention Continuity as Nonlinear Feature of EEG In Frontiers Biomed Technol, pp 28-33 (2016) [26] Mohammad R.M et al EEG classification of ADHD and normal children using non-linear features and neural network In Biomedical Engineering Letters, vol 6, pp 66-73 (2016) [27] Tran A.V et al Classify arrhythmia by using 2D spectral images and deep neural network Indonesian Journal of Electrical Engineering and Computer Science Vol 25, No 2, pp 931-940 (2022) [28] Bozkurt F., Ucar M.K., Bozkurt M.R., Bilgin C Detection of Abnormal Respiratory Events with Single Channel ECG and Hybrid Machine Learning Model in Patients with Obstructive Sleep Apnea Irbm, 41(5), pp 241–251 (2020) [29] Erdenebayar U., Kim Y.J., Park J.U., Joo E.Y., Lee, K.J Deep learning approaches for automatic detection of sleep apnea events from an electrocardiogram In Computer Methods Programs Biomed, pp 105001 (2019) [30] Nguyen H.D., Wilkins B.A., Cheng Q., Benjamin B.A An online sleep apnea detection method based on recurrence quantification analysis In IEEE J Biomed Health Inform, 18(4), pp 1285–1293 (2014) [31] Tao W., Changhua L., Guohao S., Feng H Sleep apnea detection from a singlelead ECG signal with automatic feature-extraction through a modified lenet-5 convolutional neural network In PeerJ Hefei University of Technology, Hefei, Anhui, China pp (2019) [32] Penzel T., Moody G.B., Mark R.G., Goldberger A.L., Peter J.H Apnea-ECG Database In Physionet (2000) https://physionet.org/content/apnea-ecg/1.0.0/ [33] Norio I An Efficient Teager Energy Operator-Based Automated QRS Complex Detection In Jounal of healthcare engineering (2018) [34] Holambe R.S and Deshpande M.S Nonlinear measurement and modeling using Teager energy operator In Advances in Non-Linear Modeling for Speech Processing Springer Briefs in Electrical and Computer Engineering, pp 45–59 (2012) [35] Jie H., Li S and Gang S Squeeze and excitation networks In Proceedings of the IEEE conference on computer vision and pattern, pp 7132-7141 (2018) [36] Dongqi W., Qinghua M., Dongming C., Hupo Z., Lisheng X Automatic detection of arrhythmia based on multiresolution representation of ECG signal In Sensors, pp 1579 (2020) 32 [37] Tao W., Changhua L., Guohao S., Feng H Sleep apnea detection from a singlelead ecg signal with automatic feature-extraction through a modified lenet-5 convolutional neural network PeerJ, pp 7731 (2019) [38] Mahsa B and Mohamad F Sleep apnea detection from single-lead ecg: a comprehensive analysis of machine learning and deep learning algorithms IEEE Transactions on Instrumentation and Measurement, pp 1–11 (2022) [39] Sinam A.S and Swanirbhar M A novel approach osa detection using single-lead ECG scalogram based on deep neural network Journal of Mechanics in Medicine and Biology, pp 1950026 (2019) [40] Bahrami M and Forouzanfar M Detection of sleep apnea from single-lead ECG: Comparison of deep learning algorithms In IEEE International Symposium on Medical Measurements and Applications (MeMeA), pp 1-5 (2021) [41] Andr´e P., Nuno P., Bruno M.C.S., Kouamana B., Nuno G Towards an accurate sleep apnea detection based on ECG signal: The quintessential of a wise feature selection In Applied Soft Computing, vol 83, pp 105568 (2019) [42] Li K., Pan W., Li Y., Jiang Q., Liu G A method to detect sleep apnea based on deep neural network and hidden Markov model using single-lead ECG signal In Neurocomputing, vol 294, pp 94-101 (2018) 33 SUMMARY OF THE MASTER'S THESIS Topic: A sleep apnea detection from ECG signal and classification method based on the SE-ResNeXt model Author: Do Thi Thu Phuong – 2021B Instructor: PhD Tran Anh Vu Keyword: Sleep apnea, Classfication, SE-ResNeXt, ECG signal Summary content: a) Reason of choosing the topic The sleep apnea is a sleep disorder that causes the sufferer to have episodes of complete shortness of breath, repeated at least 10 times during each sleep If these diseases are not detected and treated at the right time, they can lead to many serious health problems Therefore, accurate classification of sleep apnea is an important step in developing effective therapies The electrocardiogram (ECG) signal used to classify the sleep apnea, because it is a signal directly related to breathing b) Purpose, Research Object, Scope of Research Purpose The purpose of the thesis is to propose a method to classify apnea based on an ECG signal, improve the accuracy compared to previous studies and use a suitable filter to remove noise from the signal as well as combine with the Teager Energy Operator (TEO) algorithm to detect the amplitude and distance of R peaks in the ECG signal, then the SE-ResNeXt deep learning model is used as a classification for the sleep apnea Research results have shown that with the proposed method, using ECG signals has the ability to classify the sleep apnea accurately and effectively, which is the basis for expanding the application of artificial intelligence into medical care and opening up many opportunities in the detection and treatment of human diseases Research Object Based on the identified research objectives and implementation process, the research objects of the thesis are determined to include the following groups: - - A group of objects related to sleep apnea, including the basic theory of sleep apnea, the causes and effects of sleep apnea and methods of classification of sleep apnea during sleep being applied in practice A group of objects related to the classification of sleep apnea by machine learning methods, including pre-processing techniques such as using a signal filter, feature extraction by the TEO algorithm and SE-ResNeXt model for the classification of sleep apnea with high accuracy Scope of research 34 Due to limited research time and dataset, I focused on solving scientific problems essential to achieving my purposes Specifically, the content of the thesis is limited to the following scope: - - Theory of the sleep apnea: The thesis only presents an overview of the causes and effects of sleep apnea when not treated promptly, highlighting the advantages and disadvantages of traditional classification methods This content summarizes the important bases for the proposal to use artificial intelligence to classify sleep apnea designed in the thesis Theory of classification of sleep apnea by artificial intelligence: the thesis systematizes the general knowledge about the basis and principle of the method, including pre-processing, feature extraction algorithms and classification methods by ECG signals c) Content Summary and Author’s Contribution Content Summary My Research includes chapters: Chapter 1: Introduction This chapter presented an overview of sleep apnea and went in depth to clarify the risks as well as adverse effects on patients if not detected and treated promptly In addition, this chapter outlines studies using ML that have been used to classify disease I also gave an overview of the new methods to be used in my thesis in conjunction with ECG signal Chapter 2: Theoretical basic This chapter explained the basic content of the ECG signal and the methods used in classifying sleep apnea In addition, this chapter answered the question of why I should be used ECG signal to classify the disease Chapter 3: Dataset and proposed methods This chapter has outlined the method of classifying sleep apnea by ECG signals Besides, the summary diagram described in detail every step I took As a result, the sleep apnea is classified with high accuracy, providing many opportunities for the medical use of ML Chapter 4: Result and discussion 35 This chapter describes the new methods that have been applied to the classification of sleep apnea that I have studied As a result, the proposed methods are optimized with high accuracy in my thesis Author’s Contribution In this subject, there are two main contributions Firstly, in the pre-processing of ECG signals, I add noise filtering, peak detection, and feature extraction procedures After that, I use the TEO algorithm to detect R peaks and then calculate amplitudes and RR intervals The activation function is optimized based on the TEO algorithm, which greatly improves the accuracy of the classification result Secondly, I utilize the SE-ResNeXt 50 model in classification, which has not applied in SA classification before The classification results clearly showed higher accuracy and sensitivity d) Research method During the research, sI used many different research methods to achieve the set goals It included steps to detect sleep apnea: - The pre-processing step: Use a finite impulse response band-pass filter for the ECG signal The feature extraction step: + Apply TEO algorithm detects R peaks + Calculate the amplitude and interval between the R peaks - The classification step: Use SE-ResNext 50 model to classify SA e) Conclusion In this paper, I propose a modified method to classify SA using ECG signals I add a filter to the PhysioNet dataset to eliminate noise Then I use TEO algorithm to detect R peaks of the ECG The signal amplitudes and RR intervals are caculated for the feature extraction After that, the SE-ResNeXt 50 model is used for SA disease classification This algorithm obtained an 89.21% average accuracy, 90.29% sensitivity, and 87.36% specificity This is the basis for the demonstration of the SA classification performance of my algorithm using ECG signals After completing the thesis, as the result shows above, the accuracy of my method is quite high It opens up a bright future for me to develop the plan I made before In the future, I am going to apply other methods that can process ECG signals to diagnose patients who get the sleep apnea with the most reliable and highest 36 accuracy I hope that in recent days, my thesis can be applied possibly in hospitals to support doctors so that the patient can be assured of the result of the diagnosis they receive 37