Zusammenfassung
Schlafbezogene Atmungsstörungen wie Schlafapnoe und Hypopnoe sind potenziell ernste Störungen und können die Ursache für eine Vielzahl von körperlichen und geistigen Gesundheitsproblemen sein und zudem die Lebensqualität reduzieren. Daher sind Schlafstudien unerlässlich zur Identifizierung und Behandlung dieser Schlafstörungen. Diese Studie zielt darauf ab, Erregungsregionen, die durch nicht-apnoeischen und nicht-hypopnoeischen Schlaf in Polysomnographie-Signalen verursacht werden, mithilfe von Ensemble-Techniken zu erkennen. Der in dieser Studie verwendete Datensatz bezieht sich auf Polysomnographie-Messkanäle von 100 Patienten, die in der Physionet Challenge-Datenbank von 2018 bereitgestellt wurden. Die Daten wurden in kleine Epochen mit 50 % Überlappung aufgeteilt. Aus jeder Epoche wurden mehrere unterschiedliche Merkmale im Zeit- und Frequenzbereich extrahiert. Der Wilcoxon-Rangsummentest und der genetische Algorithmus-Optimierungsalgorithmus wurden verwendet, um einen Satz von Merkmalen mit den meisten diskriminierenden Informationen zu finden. Eine Technik zur Datenvermehrung wurde verwendet, um das Problem der unausgeglichenen Daten anzugehen. Für die endgültige Klassifikation wurden lineare Diskriminanzanalyse, logistische Regression, bagged tree aus der Bagging-Technik und LightGBM aus der Boosting-Methode angewendet. Basierend auf den Physionet Challenge-Indizes, der Fläche unter der Receiver-Operating-Characteristic-Kurve (AUROC) und der Fläche unter der Precision-Recall-Kurve (AUPRC), verglichen wir die Leistung der Klassifikatoren auf diesem Datensatz. Die höchste Leistung bei 20 Testpersonen betrug 0,497 für AUPRC und 0,878 für AUROC.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Literatur
M.K. Pavlova, V. Latreille, Sleep disorders. Am. J. Med. 132(3), 292–299 (2019)
W. Wen, Sleep quality detection based on EEG signals using transfer support vector machine algorithm, Front. Neurosci. 15 (2021)
H. Ragnarsdóttir, B. Marinósson, E. Finnsson, E. Gunnlaugsson, J.S. Ágústsson, H. Helgadóttir, Automatic detection of target regions of respiratory effort-related arousals using recurrent neural networks, in 2018 Computing in Cardiology Conference (CinC), (2018), vol. 45: IEEE, pp. 1–4
M. Diykh, Y. Li, Complex networks approach for EEG signal sleep stages classification. Expert Syst. Appl. 63, 241–248 (2016)
E. Scoring, EEG arousals: Scoring rules and examples: A preliminary report from the sleep disorders atlas task force of the American sleep disorders association. Sleep 15(2), 174–184 (1992)
R.K. Malhotra, A.Y. Avidan, Sleep stages and scoring technique. Atlas Sleep Med., 77–99 (2013)
T. Penzel, S. Canisius, Polysomnography, in Sleep Apnea, vol. 35: (Karger Publishers, 2006), pp. 51–60
D. Álvarez-Estévez, V. Moret-Bonillo, Identification of electroencephalographic arousals in multichannel sleep recordings. IEEE Trans. Biomed. Eng. 58(1), 54–63 (2010)
S. Mariani, S.M. Purcell, S. Redline, Automated processing of big data in sleep medicine, in Signal Processing and Machine Learning for Biomedical Big Data, (CRC Press, 2018), pp. 443–463
R. Heinzer et al., Prevalence of sleep-disordered breathing in the general population: The HypnoLaus study. Lancet Respir. Med. 3(4), 310–318 (2015)
S. Cho, J. Lee, H. Park, K. Lee, Detection of arousals in patients with respiratory sleep disorders using a single channel EEG, in 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference, (2006) IEEE, pp. 2733–2735
D. Chylinski et al., Validation of an automatic arousal detection algorithm for whole-night sleep EEG recordings. Clocks & sleep 2(3), 258–272 (2020)
A.H. Khandoker, J. Gubbi, M. Palaniswami, Automated scoring of obstructive sleep apnea and hypopnea events using short-term electrocardiogram recordings. IEEE Trans. Inf. Technol. Biomed. 13(6), 1057–1067 (2009)
R. Lazazzera et al., Detection and classification of sleep apnea and hypopnea using PPG and SpO $ _2 $ signals. IEEE Trans. Biomed. Eng. 68(5), 1496–1506 (2020)
T. Sugi, F. Kawana, M. Nakamura, Automatic EEG arousal detection for sleep apnea syndrome. Biomed. Signal Proc. Control 4(4), 329–337 (2009)
M.M. Ghassemi et al., You snooze, you win: the physionet/computing in cardiology challenge 2018,“ in 2018 Computing in Cardiology Conference (CinC), (2018), vol. 45: IEEE, pp. 1–4
V. Tsara, A. Amfilochiou, M. Papagrigorakis, D. Georgopoulos, E. Liolios, Guidelines for diagnosis and treatment of sleep-related breathing disorders in adults and children. Definition and classification of sleep related breathing disorders in adults: Different types and indications for sleep studies (part 1). Hippokratia 13(3), 187–191 (2009)
E. J. Olson, W. R. Moore, T. I. Morgenthaler, P. C. Gay, B. A. Staats, Obstructive sleep apnea-hypopnea syndrome, in Mayo Clinic Proceedings, vol. 78, no. 12: Elsevier, 2003, pp. 1545–1552
J.F.M. Jiménez, M.R. González, L.J. Findley, Sleepy drivers have a high frequency of traffic accidents related to respiratory effort-related arousals. Archivos de bronconeumologia 39(4), 153–158 (2003)
M. Howe-Patterson, B. Pourbabaee, F. Benard, Automated detection of sleep arousals from polysomnography data using a dense convolutional neural network, in 2018 Computing in Cardiology Conference (CinC), (2018), vol. 45: IEEE, pp. 1–4
R. He et al., Identification of arousals with deep neural networks (DNNs) using different physiological signals, in 2018 Computing in Cardiology Conference (CinC) (2018), vol. 45: IEEE, pp. 1–4
A. Patane, S. Ghiasi, E. P. Scilingo, M. Kwiatkowska, Automated recognition of sleep arousal using multimodal and personalized deep ensembles of neural networks, in 2018 Computing in Cardiology Conference (CinC), (2018), vol. 45: IEEE, pp. 1–4
P. Warrick and M. N. Homsi, ”Sleep arousal detection from polysomnography using the scattering transform and recurrent neural networks,“ in 2018 Computing in Cardiology Conference (CinC), 2018, vol. 45: IEEE, pp. 1–4
H. Li, Q. Cao, Y. Zhong, Y. Pan, Sleep arousal detection using end-to-end deep learning method based on multi-physiological signals, in 2018 Computing in Cardiology Conference (CinC), (2018), vol. 45: IEEE, pp. 1–4
B. Varga, M. Görög, P. Hajas, Using auxiliary loss to improve sleep arousal detection with neural network, in 2018 Computing in Cardiology Conference (CinC), (2018), vol. 45: IEEE, pp. 1–4
N. Sadr, P. de Chazal, Automatic scoring of non-apnoea arousals using the polysomnogram, in 2018 Computing in Cardiology Conference (CinC), (2018), vol. 45: IEEE, pp. 1–4
K.E. Bloch, Polysomnography: A systematic review. Technol. Health Care 5(4), 285–305 (1997)
V.R. Badrakalimuthu, R. Swamiraju, H. de Waal, EEG in psychiatric practice: To do or not to do? Adv. Psychiatr. Treat. 17(2), 114–121 (2011)
C.L. Drake, K.M. Mason, S.M. Bowyer, T. Roth, G.L. Barkley, N. Tepley, Vertex sharp waves during sleep localized by 2DII. Cortex 1, 8 (2002)
M. Schönauer, D. Pöhlchen, Sleep spindles. Curr. Biol. 28(19), R1129–R1130 (2018)
S. Tong and N. V. Thankor, Quantitative EEG Analysis Methods and Clinical Applications. Artech House, 2009
M. Sharma, D. Goyal, P. Achuth, U.R. Acharya, An accurate sleep stages classification system using a new class of optimally time-frequency localized three-band wavelet filter bank. Comput. Biol. Med. 98, 58–75 (2018)
H. Rao et al., Feature selection based on artificial bee colony and gradient boosting decision tree. Appl. Soft Comput. 74, 634–642 (2019)
G. Ke et al., Lightgbm: A highly efficient gradient boosting decision tree. Adv. Neural Inf. Proces. Syst. 30, 3146–3154 (2017)
J. Brownlee, how to Develop a Light Gradient Boosted Machine (LightGBM) Ensemble, ed (2020)
M. Thoma, Wikimedia Commons, the free media repository, Roc-draft-xkcd-style.svg, Ed., ed (June 2018)
Draelos. Measuring Performance: AUPRC and Average Precision. https://glassboxmedicine.com/2019/03/02/measuring-performance-auprc/. Zugriff auf
A. A. Gharbali, J. M. Fonseca, S. Najdi, and T. Y. Rezaii, „Automatic eog and emg artifact removal method for sleep stage classification,“ in Doctoral Conference on Computing, Electrical and Industrial Systems, 2016: Springer, pp. 142–150
P. Shooshtari, G. Mohammadi, B. Molaee Ardekani, M. B. Shamsollahi, Removing ocular artifacts from EEG signals using adaptive filtering and ARMAX modeling, in Proceeding of World Academy of Science, Engineering and Technology, vol. 11, no. CONF, (2006) pp. 277–280
X. Jiang, G.-B. Bian, Z. Tian, Removal of artifacts from EEG signals: a review. Sensors 19(5), 987 (2019)
X. Li, S.H. Ling, S. Su, A hybrid feature selection and extraction methods for sleep apnea detection using bio-signals. Sensors 20(15), 4323 (2020)
C. Vidaurre, N. Krämer, B. Blankertz, A. Schlögl, Time domain parameters as a feature for EEG-based brain–computer interfaces. Neural Netw. 22(9), 1313–1319 (2009)
J.V. Liu, H.K. Yaggi, Characterization of Arousals in Polysomnography Using the Statistical Significance of Power Change, in 2018 IEEE Signal Processing in Medicine and Biology Symposium (SPMB) (2018): IEEE, pp. 1–6
B. Mandelbrot, How long is the coast of Britain? Statistical self-similarity and fractional dimension. Science 156(3775), 636–638 (1967)
E.B. Sadeghian, M.H. Moradi, Fractal dimension for detection of ERD/ERS patterns in asynchronous brain computer interface, in 2008 2nd International Conference on Bioinformatics and Biomedical Engineering, (2008): IEEE, pp. 560–563
C.-T. Shi, Signal pattern recognition based on fractal features and machine learning. Appl. Sci. 8(8), 1327 (2018)
A. Yilmaz, G. Unal, Multiscale Higuchi’s fractal dimension method. Nonlinear Dynamics 101(2), 1441–1455 (2020)
A. Adda, H. Benoudnine, Detrended fluctuation analysis of EEG recordings for epileptic seizure detection, in 2016 International Conference on Bio-engineering for Smart Technologies (BioSMART), (2016): IEEE, pp. 1–4
V. Bolón-Canedo, N. Sánchez-Maroño, A. Alonso-Betanzos, Feature Selection for High-Dimensional Data (Springer, 2015)
C.-j. Tian, J. Lv, X.-f. Xu, Evaluation of feature selection methods for mammographic breast cancer diagnosis in a unified framework. BioMed Res. Int. 2021, 1–9 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 Der/die Autor(en), exklusiv lizenziert an Springer Nature Switzerland AG
About this chapter
Cite this chapter
Jalili Shani, N.S., Moradi, M.H. (2024). Biomedizinische Signalverarbeitung für die automatisierte Erkennung von Schlafarousals, basierend auf Multi-Physiologischen Signalen mit Ensemble-Lernmethoden. In: Qaisar, S.M., Nisar, H., Subasi, A. (eds) Fortschritte in der nicht-invasiven biomedizinischen Signalverarbeitung mit ML. Springer Vieweg, Cham. https://doi.org/10.1007/978-3-031-52856-9_11
Download citation
DOI: https://doi.org/10.1007/978-3-031-52856-9_11
Published:
Publisher Name: Springer Vieweg, Cham
Print ISBN: 978-3-031-52855-2
Online ISBN: 978-3-031-52856-9
eBook Packages: Computer Science and Engineering (German Language)