A convolutional neural network-based decision support system for neonatal quiet sleep detection

Saadullah Farooq Abbasi; Qammer Hussain Abbasi; Faisal Saeed; Norah Saleh Alghamdi; Saadullah Farooq Abbasi; Qammer Hussain Abbasi; Faisal Saeed; Norah Saleh Alghamdi

doi:10.3934/mbe.2023759

Mathematical Biosciences and Engineering

2023, Volume 20, Issue 9: 17018-17036. doi: 10.3934/mbe.2023759

Previous Article Next Article

Research article

A convolutional neural network-based decision support system for neonatal quiet sleep detection

1.
Department of Biomedical Engineering, Riphah International University, Islamabad 44000, Pakistan
2.
James Watt School of Engineering, University of Glasgow, Glasgow, G4 0PE, United Kingdom
3.
DAAI Research Group, Department of Computing and Data Science, School of Computing and Digital Technology, Birmingham City University, Birmingham B4 7XG, UK
4.
Department of Computer Sciences, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi Arabia

Academic Editor: Andre Longtin

Received: 20 April 2023 Revised: 06 July 2023 Accepted: 11 August 2023 Published: 29 August 2023

Sleep plays an important role in neonatal brain and physical development, making its detection and characterization important for assessing early-stage development. In this study, we propose an automatic and computationally efficient algorithm to detect neonatal quiet sleep (QS) using a convolutional neural network (CNN). Our study used 38-hours of electroencephalography (EEG) recordings, collected from 19 neonates at Fudan Children's Hospital in Shanghai, China (Approval No. (2020) 22). To train and test the CNN, we extracted 12 prominent time and frequency domain features from 9 bipolar EEG channels. The CNN architecture comprised two convolutional layers with pooling and rectified linear unit (ReLU) activation. Additionally, a smoothing filter was applied to hold the sleep stage for 3 minutes. Through performance testing, our proposed method achieved impressive results, with 94.07% accuracy, 89.70% sensitivity, 94.40% specificity, 79.82% F1-score and a 0.74 kappa coefficient when compared to human expert annotations. A notable advantage of our approach is its computational efficiency, with the entire training and testing process requiring only 7.97 seconds. The proposed algorithm has been validated using leave one subject out (LOSO) validation, which demonstrates its consistent performance across a diverse range of neonates. Our findings highlight the potential of our algorithm for real-time neonatal sleep stage classification, offering a fast and cost-effective solution. This research opens avenues for further investigations in early-stage development monitoring and the assessment of neonatal health.
- neonatal sleep,
- convolutional neural network,
- electroencephalography,
- polysomnography,
- biomedical engineering
Citation: Saadullah Farooq Abbasi, Qammer Hussain Abbasi, Faisal Saeed, Norah Saleh Alghamdi. A convolutional neural network-based decision support system for neonatal quiet sleep detection[J]. Mathematical Biosciences and Engineering, 2023, 20(9): 17018-17036. doi: 10.3934/mbe.2023759

Related Papers:

Abstract

Sleep plays an important role in neonatal brain and physical development, making its detection and characterization important for assessing early-stage development. In this study, we propose an automatic and computationally efficient algorithm to detect neonatal quiet sleep (QS) using a convolutional neural network (CNN). Our study used 38-hours of electroencephalography (EEG) recordings, collected from 19 neonates at Fudan Children's Hospital in Shanghai, China (Approval No. (2020) 22). To train and test the CNN, we extracted 12 prominent time and frequency domain features from 9 bipolar EEG channels. The CNN architecture comprised two convolutional layers with pooling and rectified linear unit (ReLU) activation. Additionally, a smoothing filter was applied to hold the sleep stage for 3 minutes. Through performance testing, our proposed method achieved impressive results, with 94.07% accuracy, 89.70% sensitivity, 94.40% specificity, 79.82% F1-score and a 0.74 kappa coefficient when compared to human expert annotations. A notable advantage of our approach is its computational efficiency, with the entire training and testing process requiring only 7.97 seconds. The proposed algorithm has been validated using leave one subject out (LOSO) validation, which demonstrates its consistent performance across a diverse range of neonates. Our findings highlight the potential of our algorithm for real-time neonatal sleep stage classification, offering a fast and cost-effective solution. This research opens avenues for further investigations in early-stage development monitoring and the assessment of neonatal health.

References

[1]	A. R. Hassan, M. I. H. Bhuiyan, An automated method for sleep staging from EEG signals using normal inverse Gaussian parameters and adaptive boosting, Neurocomputing, 219 (2017), 76–87. https://doi.org/10.1016/j.neucom.2016.09.011 doi: 10.1016/j.neucom.2016.09.011
[2]	A. R. Hassan, M. I. H. Bhuiyan, A decision support system for automatic sleep staging from EEG signals using tunable Q-factor wavelet transform and spectral features, J. Neurosci. Methods, 271 (2016), 107–118. https://doi.org/10.1016/j.jneumeth.2016.07.012 doi: 10.1016/j.jneumeth.2016.07.012
[3]	A. Dereymaeker, K. Pillay, J. Vervisch, S. Van Huffel, G. Naulaers, K. Jansen, et al., An automated quiet sleep detection approach in preterm infants as a gateway to assess brain maturation, Int. J. Neural Syst., 27 (2017), 1750023. https://doi.org/10.1142/S012906571750023X doi: 10.1142/S012906571750023X
[4]	N. Koolen, L. Oberdorfer, Z. Rona, V. Giordano, T. Werther, K. Klebermass-Schrehof, et al., Automated classification of neonatal sleep states using EEG, Clin. Neurophysiol., 128 (2017), 1100–1108. https://doi.org/10.1016/j.clinph.2017.02.025 doi: 10.1016/j.clinph.2017.02.025
[5]	K. Pillay, A. Dereymaeker, K. Jansen, G. Naulaers, S. Van Huffel, M. De Vos, Automated EEG sleep staging in the term-age baby using a generative modelling approach, J. Neural Eng., 15 (2018), 036004. https://doi.org/10.1088/1741-2552/aaab73 doi: 10.1088/1741-2552/aaab73
[6]	J. Bronzino, Principles of Electroencephalography, CRC Press, 2015.
[7]	M. Andre, Pesquisas sobre formaço de professores: Contribuiçes delimitaço do campo, Convergncias e tenses no campo da formao e do trabalho docente: Didática, formaço de professores, trabalho docente, Tech. Rep., 2010.
[8]	A. Loomis, E. Harvey, G. Hobart, Cerebral states during sleep, as studied by human brain potentials, J. Exp. Psychol., 21 (1937), 127. https://doi.org/10.1037/h0057431 doi: 10.1037/h0057431
[9]	T. Lajnef, S. Chaibi, P. Ruby, P. E. Aguera, J. B. Eichenlaub, M. Samet, et al., Learning machines and sleeping brains: Automatic sleep stage classification using decision-tree multi-class support vector machines, J. Neurosci. Methods, 250 (2015), 94–105. https://doi.org/10.1016/j.jneumeth.2015.01.022 doi: 10.1016/j.jneumeth.2015.01.022
[10]	M. Xiao, H. Yan, J. Song, Y. Yang, X. Yang, Sleep stages classification based on heart rate variability and random forest, Biomed. Signal Process. Control, 8 (2013), 624–633. https://doi.org/10.1016/j.bspc.2013.06.001 doi: 10.1016/j.bspc.2013.06.001
[11]	P. Fonseca, N. den Teuling, X. Long, R. M. Aarts, Cardiorespiratory sleep stage detection using conditional random fields, IEEE J. Biomed. Health Inf., 21 (2017), 956–966. https://doi.org/10.1109/JBHI.2016.2550104 doi: 10.1109/JBHI.2016.2550104
[12]	S. Gudmundsson, T. P. Runarsson, S. Sigurdsson, Automatic sleep staging using support vector machines with posterior probability estimates, in International Conference on Computational Intelligence for Modelling, Control and Automation and International Conference on Intelligent Agents, Web Technologies and Internet Commerce (CIMCA-IAWTIC'06), IEEE, (2005), 366–372.
[13]	H. Dong, A. Supratak, W. Pan, C. Wu, P. M. Matthews, Y. Guo, et al., Mixed neural network approach for temporal sleep stage classification, IEEE Trans. Neural Syst. Rehabil. Eng., 26 (2017), 324–333. https://doi.org/10.1109/TNSRE.2017.2733220 doi: 10.1109/TNSRE.2017.2733220
[14]	J. Zhang, R. Yao, W. Ge, J. Gao, Orthogonal convolutional neural networks for automatic sleep stage classification based on single-channel EEG, Comput. Methods Programs Biomed., 183 (2020), 105089. https://doi.org/10.1016/j.cmpb.2019.105089 doi: 10.1016/j.cmpb.2019.105089
[15]	F. Andreotti, H. Phan, N. Cooray, C. Lo, M. T. Hu, M. De Vos, Multichannel sleep stage classification and transfer learning using convolutional neural networks, in 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), IEEE, (2018), 171–174. https://doi.org/10.1109/EMBC.2018.8512214
[16]	J. Zhang, Y. Wu, A new method for automatic sleep stage classification, IEEE Trans. Biomed. Circuits Syst., 11 (2017), 1097–1110. https://doi.org/10.1109/TBCAS.2017.2719631 doi: 10.1109/TBCAS.2017.2719631
[17]	A. Sors, S. Bonnet, S. Mirek, L. Vercueil, J. F. Payen, A convolutional neural network for sleep stage scoring from raw single-channel EEG, Biomed. Signal Process. Control, 42 (2018), 107–114. https://doi.org/10.1016/j.bspc.2017.12.001 doi: 10.1016/j.bspc.2017.12.001
[18]	T. F. Anders, R. N. Emde, A. H. Parmelee, A Manual of Standardized Terminology, Techniques and Criteria for Scoring of States of Sleep and Wakefulness in Newborn Infants, UCLA Brain Information Service/BRI Publications Office, NINDS Neurological Information Network, 1971.
[19]	J. W. Britton, L. C. Frey, J. L. Hopp, P. Korb, M. Z. Koubeissi, W. E. Lievens, et al., Electroencephalography (EEG): An introductory text and atlas of normal and abnormal findings in adults, children, and infants, Am. Epilepsy Soc., (2016), 20–41.
[20]	R. J. Ellingson, Development of sleep spindle bursts during the first year of life, Sleep, 5 (1982), 39–46. https://doi.org/10.1093/sleep/5.1.39 doi: 10.1093/sleep/5.1.39
[21]	J. Werth, L. Atallah, P. Andriessen, X. Long, E. Zwartkruis-Pelgrim, R. M. Aarts, Unobtrusive sleep state measurements in preterm infants–A review, Sleep Med. Rev., 32 (2017), 109–122. https://doi.org/10.1016/j.smrv.2016.03.005 doi: 10.1016/j.smrv.2016.03.005
[22]	B. Chakravarthi, S. C. Ng, M. R. Ezilarasan, M. F. Leung, EEG-based emotion recognition using hybrid CNN and LSTM classification, Front. Comput. Neurosci., 16 (2022), 1019776. https://doi.org/10.3389/fncom.2022.1019776 doi: 10.3389/fncom.2022.1019776
[23]	J. P. Turnbull, K. A. Loparo, M. W. Johnson, M. S. Scher, Automated detection of tracé alternant during sleep in healthy full-term neonates using discrete wavelet transform, Clin. Neurophysiol., 112 (2001), 1893–1900. https://doi.org/10.1016/S1388-2457(01)00641-1 doi: 10.1016/S1388-2457(01)00641-1
[24]	A. Piryatinska, G. Terdik, W. A. Woyczynski, K. A. Loparo, M. S. Scher, A. Zlotnik, Automated detection of neonate EEG sleep stages, Comput. Methods Programs Biomed., 95 (2009), 31–46. https://doi.org/10.1016/j.cmpb.2009.01.006 doi: 10.1016/j.cmpb.2009.01.006
[25]	A. H. Ansari, O. De. Wel, M. Lavanga, A. Caicedo, A. Dereymaeker, K. Jansen, et al., Quiet sleep detection in preterm infants using deep convolutional neural networks, J. Neural Eng., 15 (2018), 066006. https://doi.org/10.1088/1741-2552/aadc1f doi: 10.1088/1741-2552/aadc1f
[26]	O. De Wel, M. Lavanga, A. Caicedo, K. Jansen, G. Naulaers, S. Van Huffel, Decomposition of a multiscale entropy tensor for sleep stage identification in preterm infants, Entropy, 21 (2019), 936. https://doi.org/10.3390/e21100936 doi: 10.3390/e21100936
[27]	L. Fraiwan, K. Lweesy, Neonatal sleep state identification using deep learning autoencoders, in IEEE 13th International Colloquium on Signal Processing & its Applications (CSPA), IEEE, (2017), 228–231. https://doi.org/10.1109/CSPA.2017.8064956
[28]	L. Fraiwan, M. Alkhodari, Neonatal sleep stage identification using long short-term memory learning system, Med. Biol. Eng. Comput., 58 (2020), 1383–1391. https://doi.org/10.1007/s11517-020-02169-x doi: 10.1007/s11517-020-02169-x
[29]	S. F. Abbasi, J. Ahmad, A. Tahir, M. Awais, C. Chen, M. Irfan, et al., EEG-Based neonatal sleep-wake classification using multilayer perceptron neural network, IEEE Access, 8 (2020), 183025–183034. https://doi.org/10.1109/ACCESS.2020.3028182 doi: 10.1109/ACCESS.2020.3028182
[30]	M. Awais, C. Chen, X. Long, B. Yin, A. Nawaz, S. F. Abbasi, et al., Novel framework: face feature selection algorithm for neonatal facial and related attributes recognition, IEEE Access, 8 (2020), 59100–59113. https://doi.org/10.1109/ACCESS.2020.2982865 doi: 10.1109/ACCESS.2020.2982865
[31]	M. Awais, X. Long, B. Yin, C. Chen, S. Akbarzadeh, S. F. Abbasi, et al., Can pre-trained convolutional neural networks be directly used as a feature extractor for video-based neonatal sleep and wake classification, BMC Res. Notes, 13 (2020), 1–6. https://doi.org/10.1186/s13104-020-05343-4 doi: 10.1186/s13104-019-4871-2
[32]	M. Awais, X. Long, B. Yin, S. F. Abbasi, S. Akbarzadeh, C. Lu, et al., A hybrid DCNN-SVM model for classifying neonatal sleep and wake states based on facial expressions in video, IEEE J. Biomed. Health. Inf., 25 (2021), 1441–1449. https://doi.org/10.1109/JBHI.2021.3073632 doi: 10.1109/JBHI.2021.3073632
[33]	S. F. Abbasi, M. Awais, X. Zhao, W. Chen, Automatic denoising and artifact removal from neonatal EEG, in the Third International Conference on Biological Information and Biomedical Engineering, VDE, (2019), 1–5.
[34]	S. F. Abbasi, H. Jamil, W. Chen, EEG-based neonatal sleep stage classification using ensemble learning, CMC-Comput. Mater. Continua, 70 (2022), 4619–4633. https://doi.org/10.32604/cmc.2022.020318 doi: 10.32604/cmc.2022.020318
[35]	P. J. Cherian, R. M. Swarte, G. H. Visser, Technical standards for recording and interpretation of neonatal electroencephalogram in clinical practice, Ann. Indian Acad. Neurol., 12 (2009), 58.
[36]	S. Janjarasjitt, M. S. Scher, K. A. Loparo, Nonlinear dynamical analysis of the neonatal EEG time series: the relationship between sleep state and complexity, Clin. Neurophysiol., 119 (2008), 1812–1823. https://doi.org/10.1016/j.clinph.2008.03.024 doi: 10.1016/j.clinph.2008.03.024
[37]	D. Zhang, H. Ding, Y. Liu, C. Zhou, H. Ding, D. Ye, Neurodevelopment in newborns: a sample entropy analysis of electroencephalogram, Physiol. Meas., 30 (2009), 491. https://doi.org/10.1088/0967-3334/30/5/006 doi: 10.1088/0967-3334/30/5/006

Reader Comments

Your name:*

Email:*
© 2023 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)