EEG Spectrograms to Determine Occurrence or Absence of Sleep Apnoea Using Deep Learning
Sleep and Vigilance - Trang 1-5 - 2024
Tóm tắt
Sleep apnoea has an increased mortality and morbidity. The diagnosis of the disease is cumbersome and very resource intensive. In a setup where the individual health is followed over a long period of time and records maintained, artificial intelligence-based model may help predict the presence of disease. With only two inputs, oximetry and one channel EEG, a model was devised based on EEG spectrograms which were put through VGG 19 and custom-made convolutional neural network (CNN). This was done on one full night polysomnographic data available from open data source. The model gave a prediction of almost 100%. An innovative method for screening of sleep apnoea is proposed using this model. The pilot work of building the model, preprocessing of EEG data, conversion to EEG spectrogram, using VGG 19 model and custom-made CNN model is discussed. Deep Learning models might be useful in screening out such disorders.
Tài liệu tham khảo
Yeboah J, Redline S, Johnson C, et al. Association between sleep apnea, snoring, incident cardiovascular events and all-cause mortality in an adult population: MESA. Atherosclerosis. 2011;219:963–8.
Laratta CR, Ayas NT, Povitz M, et al. Diagnosis and treatment of obstructive sleep apnea in adults. CMAJ. 2017;189:E1481–8.
Kapur VK, Auckley DH, Chowdhuri S, et al. Clinical practice guideline for diagnostic testing for adult obstructive sleep apnea: an American Academy of Sleep Medicine Clinical Practice Guideline. J Clin Sleep Med. 2017;13:479–504.
Pocobelli G, Akosile MA, Hansen RN, et al. Obstructive sleep apnea and risk of motor vehicle accident. Sleep Med. 2021;85:196–203.
Benjafield AV, Ayas NT, Eastwood PR, et al. Estimation of the global prevalence and burden of obstructive sleep apnoea: a literature-based analysis. Lancet Respir Med. 2019;7:687–98.
Screening high-risk employees for sleep apnea could save a corporation millions of dollars. American Academy of Sleep Medicine – Association for Sleep Clinicians and Researchers, https://aasm.org/screening-high-risk-employees-for-sleep-apnea-could-save-a-corporation-millions-of-dollars/ 2011, accessed 12 Sep 2021.
Faria A, Allen AH, Fox N, et al. The public health burden of obstructive sleep apnea. Sleep Sci. 2021;14:257–65.
Ichimaru Y, Moody GB. Development of the polysomnographic database on CD-ROM. Psychiatry Clin Neurosci. 1999;53:175–7.
PhysioBank, PhysioToolkit, and PhysioNet | Circulation, https://www.ahajournals.org/doi/full/10.1161/01.cir.101.23.e215 accessed 23 Sep 2021.
Álvarez D, Cerezo-Hernández A, Crespo A, et al. A machine learning-based test for adult sleep apnoea screening at home using oximetry and airflow. Sci Rep. 2020;10:5332.
Mehra R. Breast cancer histology images classification: training from scratch or transfer learning? ICT Express. 2018;4:247–54.
Labhane G, Pansare R, Maheshwari S, et al. Detection of pediatric pneumonia from chest x-ray images using cnn and transfer learning. In: 2020 3rd International Conference on Emerging Technologies in Computer Engineering: Machine Learning and Internet of Things (ICETCE). IEEE, 2020, pp. 85–92.
Carvalho T, De Rezende ER, Alves MT, et al. Exposing computer generated images by eye’s region classification via transfer learning of VGG19 CNN. In: 2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA). IEEE, 2017, pp. 866–870.
Choi JY, Yoo TK, Seo JG, et al. Multi-categorical deep learning neural network to classify retinal images: a pilot study employing small database. PLoS ONE. 2017;12: e0187336.
Understanding the VGG19 Architecture. OpenGenus IQ: Computing Expertise & Legacy, https://iq.opengenus.org/vgg19-architecture/ 2020, accessed 23 Sep 2021.
Team K. Keras documentation: VGG16 and VGG19, https://keras.io/api/applications/vgg/ accessed 23 Sep 2021.
Albawi S, Mohammed TA, Al-Zawi S. Understanding of a convolutional neural network. In: 2017 International Conference on Engineering and Technology (ICET). Antalya: IEEE, pp. 1–6.
Thornton BZ. Audio recognition using mel spectrograms and convolution neural networks. http://www.noiselab.ucsd.edu/ECE228_2019/Reports/Report38.pdf on 15 Sep 2023.
Siddiqui MM, Srivastava G, Saeed SH. Detection of sleep disorder breathing (SDB) using short time frequency analysis of PSD approach applied on EEG signal. Biomed Pharmacol J. 2016;9:357–63.
Budak U, Bajaj V, Akbulut Y, et al. An effective hybrid model for EEG-based drowsiness detection. IEEE Sens J. 2019;19:7624–31.
Ruffini G, Ibañez D, Castellano M, et al. Deep learning with EEG spectrograms in rapid eye movement behavior disorder. Front Neurol. 2019;10:806.
Chyad MH, Gharghan SK, Hamood HQ. A Survey on Detection and Prediction Methods for Sleep Apnea. IOP Conf Ser: Mater Sci Eng. 2020;745: 012102.
Taran S, Bajaj V. Drowsiness detection using adaptive hermite decomposition and extreme learning machine for electroencephalogram signals. IEEE Sens J. 2018;18:8855–62.
Prerau MJ, Brown RE, Bianchi MT, et al. Sleep neurophysiological dynamics through the lens of multitaper spectral analysis. Physiology. 2017;32:33.
Pogach MS, Punjabi NM, Thomas N, et al. Electrocardiogram-based sleep spectrogram measures of sleep stability and glucose disposal in sleep disordered breathing. Sleep. 2012;35:10.
Xiao J, Wang J, Cao S, et al. Application of a novel and improved VGG-19 network in the detection of workers wearing masks. J Phys: Conf Ser. 2020;1518: 012041.
Shaha M, Pawar M. Transfer learning for image classification. In: 2018 Second International Conference on Electronics, Communication and Aerospace Technology (ICECA). IEEE, 2018, pp. 656–660.
Screening for obstructive sleep apnoea in professional drivers | European Respiratory Society, https://breathe.ersjournals.com/content/16/1/29364 accessed 23 Sep 2021.