Pre-determination of OSA degree using morphological features of the ECG signal

30 OSA patients were automatically classified using electrocardiogram (ECG) data.In total, 29,127 epochs identified as mild, moderate, and severe.Fifteen morphological features were extracted from these epochs.Success rates of 97.202.15% and 90.188.11% with the SBFS algorithm were obtained.ANN, NB, RF, DT, LOGR and SVM classifiers were used to obtain the best result. Obstructive sleep apnea (OSA) is a very common, but a difficult sleep disorder to diagnose. Recurrent obstructions form in the airway during sleep, such that OSA can threaten a breathing capacity of patients. Clinically, continuous positive airway pressure (CPAP) is the most specific and effective treatment for this. In addition, these patients must be separated according to its degree, with CPAP treatment applied as a result. In this study, 30 OSA patients from two different databases were automatically classified using electrocardiogram (ECG) data, identified as mild, moderate, and severe. One of the databases was original recordings which had 9 OSA patients with 8303 epochs and the other one was Physionet benchmark database which had 21 patients with 20,824 epochs. Fifteen morphological features could be identified when apnea was seen, both before and after it presented. Five data groups in total for first dataset and second dataset were prepared with these features and 10-fold cross validation was used to effectively determine the test data. Then, sequential backward feature selection (SBFS) algorithm was applied to understand the more effective features. The prepared data groups were evaluated with artificial neural networks (ANN) to obtain optimum classification performance. All processes were repeated for ten times and error deviation was calculated for the accuracy. Furthermore, different classifiers which are frequently used in the literature were tested with selected features. The degree of OSA was estimated from three epochs in pre-apnea data, yielding the success rates of 97.202.15% and 90.188.11% with the SBFS algorithm for the first and second datasets, respectively. Also, SVM classifier followed ANN system in the success rates of 96.233.48% and 88.758.52% for used datasets.

[1]  Jeffrey M. Hausdorff,et al.  Physionet: Components of a New Research Resource for Complex Physiologic Signals". Circu-lation Vol , 2000 .

[2]  David W. Aha,et al.  A Comparative Evaluation of Sequential Feature Selection Algorithms , 1995, AISTATS.

[3]  Xi Zhang,et al.  A severity measurement system for obstructive sleep apnea discrimination using a single ECG signal , 2013, 2013 IEEE International Conference on Automation Science and Engineering (CASE).

[4]  Xi Zhang,et al.  An Obstructive Sleep Apnea Detection Approach Using a Discriminative Hidden Markov Model From ECG Signals , 2016, IEEE Transactions on Biomedical Engineering.

[5]  Conor Heneghan,et al.  Automated processing of the single-lead electrocardiogram for the detection of obstructive sleep apnoea , 2003, IEEE Transactions on Biomedical Engineering.

[6]  Satish T. S. Bukkapatnam,et al.  Detection of sleep apnea events via tracking nonlinear dynamic cardio-respiratory coupling from electrocardiogram signals , 2013, 2013 6th International IEEE/EMBS Conference on Neural Engineering (NER).

[7]  Allan I Pack,et al.  Does untreated obstructive sleep apnea lead to death? A commentary on Young et al. Sleep 2008;31:1071-8 and Marshall et al. Sleep 2008;31:1079-85. , 2008, Sleep.

[8]  Necmettin Sezgin,et al.  Classification of sleep apnea by using wavelet transform and artificial neural networks , 2010, Expert Syst. Appl..

[9]  Iman Galal,et al.  Nocturnal heart rate variability analysis as a screening tool for obstructive sleep apnea syndrome , 2012 .

[10]  Madhuchhanda Mitra,et al.  Empirical mode decomposition based ECG enhancement and QRS detection , 2012, Comput. Biol. Medicine.

[11]  Hikmet Firat,et al.  Tissue Doppler atrial conduction times and electrocardiogram interlead P-wave durations with varying severity of obstructive sleep apnea. , 2011, Journal of electrocardiology.

[12]  Abdulnasir Hossen,et al.  The importance of the very low frequency power of heart rate variability in screening of patients with obstructive sleep Apnea , 2011, 2011 IEEE Symposium on Industrial Electronics and Applications.

[13]  Ian H. Witten,et al.  Weka: Practical machine learning tools and techniques with Java implementations , 1999 .

[14]  Wai-Chi Fang,et al.  Real-time obstructive sleep apnea detection based on ECG derived respiration signal , 2012, 2012 IEEE International Symposium on Circuits and Systems.

[15]  G. Castellanos-Dominguez,et al.  Detection of obstructive sleep apnea in ECG recordings using time-frequency distributions and dynamic features , 2009, 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[16]  Ahnaf Rashik Hassan,et al.  Computer-aided obstructive sleep apnea screening from single-lead electrocardiogram using statistical and spectral features and bootstrap aggregating , 2016 .

[17]  J. R. Landis,et al.  The measurement of observer agreement for categorical data. , 1977, Biometrics.

[18]  Bojan Cukic,et al.  A Statistical Framework for the Prediction of Fault-Proneness , 2007 .

[19]  Ahnaf Rashik Hassan,et al.  An expert system for automated identification of obstructive sleep apnea from single-lead ECG using random under sampling boosting , 2017, Neurocomputing.

[20]  Jeen-Shing Wang,et al.  Using Bootstrap AdaBoost with KNN for ECG-based automated obstructive sleep apnea detection , 2012, The 2012 International Joint Conference on Neural Networks (IJCNN).

[21]  Willis J. Tompkins,et al.  A Real-Time QRS Detection Algorithm , 1985, IEEE Transactions on Biomedical Engineering.

[22]  D. Dursunoglu,et al.  Effect of CPAP on QT interval dispersion in obstructive sleep apnea patients without hypertension. , 2007, Sleep medicine.

[23]  Min Soo Kim,et al.  Comparison of heart rate variability (HRV) and nasal pressure in obstructive sleep apnea (OSA) patients during sleep apnea , 2012 .

[24]  K. Gourgoulianis,et al.  Effects of adenotonsillectomy on R-R interval and brain natriuretic peptide levels in children with sleep apnea: a preliminary report. , 2011, Sleep medicine.

[25]  Ali Oto,et al.  P-wave duration and dispersion in patients with obstructive sleep apnea. , 2009, International journal of cardiology.

[26]  Mustafa Poyraz,et al.  An expert system for automated recognition of patients with obstructive sleep apnea using electrocardiogram recordings , 2011, Expert Syst. Appl..

[27]  Laiali Almazaydeh,et al.  SVM-Based Sleep Apnea Identification Using Optimal RR-Interval Features of the ECG Signal , 2013 .

[28]  Khaled M. Elleithy,et al.  Detection of obstructive sleep apnea through ECG signal features , 2012, 2012 IEEE International Conference on Electro/Information Technology.

[29]  Marimuthu Palaniswami,et al.  Automated recognition of patients with obstructive sleep apnoea using wavelet-based features of electrocardiogram recordings , 2009, Comput. Biol. Medicine.

[30]  Hartmut Dickhaus,et al.  Comparison of heart rhythm and morphological ECG features in recognition of sleep apnea from the ECG , 2003, Computers in Cardiology, 2003.

[31]  J. Shepard,et al.  Cardiac arrhythmias during normal sleep and in obstructive sleep apnea syndrome. , 1998, Sleep medicine reviews.

[32]  A. Ferikoglu,et al.  Sleep apnea diagnosis via single channel ECG feature selection , 2012, 2012 38th Annual Northeast Bioengineering Conference (NEBEC).

[33]  T. Rammohan,et al.  Detection of sleep apnea through ECG signal features , 2016, 2016 2nd International Conference on Advances in Electrical, Electronics, Information, Communication and Bio-Informatics (AEEICB).