SC3: self-configuring classifier combination for obstructive sleep apnea
- 15 Downloads
Obstructive sleep apnea is considered to be one of the most prevalent sleep-related disorders that can affect the general population. However, the gold standard for the diagnosis, polysomnography, is an expensive and complicated process that is commonly unavailable to a large group of the population. Alternatively, automatic approaches have been developed to address this issue. One of the goals of this research is to perform the classification of the apnea events with the lowest possible number of sensors. Therefore, the blood oxygen saturation signal was employed in this work since it is correlated with the occurrence of apnea events and it can be measured from a single noninvasive sensor. The events detection was performed by a combination of classifiers. However, choosing the type of classifier to combine and select the most relevant features for each classifier is considered to be a well-known problem in the field of machine learning. A self-configuring classifier combination technique based on genetic algorithms was developed for multiple classifiers and features selection which was tested along with different databases and input sizes. The best performance for obstructive sleep apnea detection was achieved using maximum voting independent feature selection with 1 min time window having the best sensitivity of 82.48% similar database in the literature. This model was later tested on another database for cross-database accuracy. With an average accuracy of 91.33%, the system proved its capabilities for clinical diagnosis since the model was developed and validated with both subject and database independence.
KeywordsCombined classifiers Sleep apnea Genetic algorithm Machine learning
This research has been supported by the Portuguese Foundation for Science and Technology through Projeto Estratégico UID/EEA/50009/2019, ARDITI—Agência Regional para o Desenvolvimento da Investigação, Tecnologia e Inovação under the scope of the Project M1420-09-5369-FSE-000001-PhD Studentship and MITIExcell—Excelencia Internacional de IDT&I NAS TIC (Project Number M1420-01-01450FEDER0000002), provided by the Regional Government of Madeira.
Compliance with ethical standards
Conflict of interest
The authors declare that they have no conflict of interest.
- 2.Gastaut H, Tassinari C, Duron B (1965) Polygraphic study of the episodic diurnal and nocturnal (hypnic and respiratory) manifestations of the Pickwickian syndrome. Brain Res 2:167–186Google Scholar
- 4.Zhang J, Zhang Q, Wang Y, Qiu C (2013) A real-time auto-adjustable smart pillow system for sleep apnea detection and treatment. In: Proceedings of the 12th international conference on Information processing in sensor networks (IPSN), 2013, pp 179–190Google Scholar
- 13.Patil D, Wadhai VM, Gujar S, Surana K, Devkate P, Waghmare S (2012) APNEA detection on smart phone. Int J Comput Appl 59(7):15–19Google Scholar
- 18.Mostafa SS, Carvalho JP, Morgado-Dias F, Ravelo-García A (2017) Optimization of sleep apnea detection using SpO2 and ANN. In: 2017 XXVI international conference on information, communication and automation technologies (ICAT), 2017, pp 1–6Google Scholar
- 19.Mostafa SS et al (2017) SpO2 based sleep apnea detection using deep learning. In: 2017 IEEE 21st international conference on intelligent engineering systems (INES), pp 91–96Google Scholar
- 20.Elleithy K, Almazaydeh L, Faezipour M (2012) A neural network system for detection of obstructive sleep apnea through SpO2 signal features. Int J Adv Comput Sci Appl 3(5):7–11Google Scholar
- 22.Pathinarupothi RK et al (2017) Single sensor techniques for sleep apnea diagnosis using deep learning. In: 2017 IEEE international conference on healthcare informatics (ICHI), 2017, pp 524–529Google Scholar
- 23.Stanley H, Goldberger AL, Amaral LAN, Glass L, Hausdorff JM, Ivanov PC, Mark RG, Mietus JE, Moody GB, Peng C-K (2000) PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation 101(23):215–220Google Scholar
- 24.Penzel T, Moody G, Mark R, Goldberger A, Peter J (2000) The apnea-ECG database. Comput Cardiol 2000:255–258Google Scholar
- 29.Ravelo-Garcia AG, Navarro-Mesa JL, Murillo-Diaz MJ, Julia-Serda JG (2004) Application of RR series and oximetry to a statistical classifier for the detection of sleep apnoea/hypopnoea. Comput Cardiol 2004:305–308Google Scholar
- 30.Gupta M, Jin L, Homma N (2004) Static and dynamic neural networks: from fundamentals to advanced theory. Wiley, LondonGoogle Scholar
- 33.Santos AB, de A. Araújo A, Menotti D (2012) Combiner of classifiers using genetic algorithm for classification of remote sensed hyperspectral images. In: 2012 IEEE international geoscience and remote sensing symposium, 2012, pp 4146–4149Google Scholar
- 35.Mostafa SS, Mendonça F, Ravelo-García A, Morgado-Dias F (2018) Combination of deep and shallow networks for cyclic alternating patterns detection. In: 13th APCA international conference on automatic control and soft computing (CONTROLO), 2018, pp 98–103Google Scholar
- 36.Hartmanis J, Van Leeuwen J (2000) Multiple classifier systems: first international workshop proceedings, 2000Google Scholar
- 37.Cen L, Yu ZL, Kluge T, Ser W (2018) Automatic system for obstructive sleep apnea events detection using convolutional neural network. In: 2018 40th annual international conference of the IEEE engineering in medicine and biology society (EMBC), 2018, pp 3975–3978Google Scholar
- 39.St. Vincent’s University Hospital/University College Dublin Sleep Apnea Database. https://physionet.org/pn3/ucddb/