A convolutional neural network based approach to QRS detection

In this paper we present a QRS detection algorithm based on pattern recognition as well as a new approach to ECG baseline wander removal and signal normalization. Each point of the zero-centred and normalized ECG signal is a QRS candidate, while a 1-D CNN classifier serves as a decision rule. Positive outputs from the CNN are clustered to form final QRS detections. The data is obtained from the 44 non-pacemaker recordings of the MIT-BIH arrhythmia database. Classifier was trained on 22 recordings and the remaining ones are used for performance evaluation. Our method achieves a sensitivity of 99.81% and 99.93% positive predictive value, which is comparable with most state-of-the-art solutions. This approach opens new possibilities for improvements in heartbeat classification as well as P and T wave detection problems.

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

[2]  W.J. Tompkins,et al.  Neural-network-based adaptive matched filtering for QRS detection , 1992, IEEE Transactions on Biomedical Engineering.

[3]  P. Melillo,et al.  Nonlinear Heart Rate Variability features for real-life stress detection. Case study: students under stress due to university examination , 2011, Biomedical engineering online.

[4]  Goran Krstačić,et al.  Optimizing the detection of characteristic waves in ECG based on exploration of processing steps combinations , 2017 .

[5]  Israel C Christie,et al.  PhysioScripts: An extensible, open source platform for the processing of physiological data , 2013, Behavior research methods.

[6]  Jian Li,et al.  Heartbeat classification using projected and dynamic features of ECG signal , 2017, Biomed. Signal Process. Control..

[7]  Amr Mohamed,et al.  Efficient ECG Compression and QRS Detection for E-Health Applications , 2017, Scientific Reports.

[8]  Dimitri Palaz,et al.  Estimating phoneme class conditional probabilities from raw speech signal using convolutional neural networks , 2013, INTERSPEECH.

[9]  Hangsik Shin,et al.  Simple and Robust Realtime QRS Detection Algorithm Based on Spatiotemporal Characteristic of the QRS Complex , 2016, PloS one.

[10]  A. Moss,et al.  QT Interval: How to Measure It and What Is “Normal” , 2006, Journal of cardiovascular electrophysiology.

[11]  Mohamed Elgendi,et al.  Fast QRS Detection with an Optimized Knowledge-Based Method: Evaluation on 11 Standard ECG Databases , 2013, PloS one.

[12]  Yike Guo,et al.  Automatic Sleep Stage Scoring with Single-Channel EEG Using Convolutional Neural Networks , 2016, ArXiv.

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

[14]  H V Pipberger,et al.  Skin-electrode impedance problems in electrocardiography. , 1968, American heart journal.

[15]  K. Chan,et al.  Characteristic wave detection in ECG signal using morphological transform , 2005, BMC cardiovascular disorders.

[16]  Enzo Pasquale Scilingo,et al.  Recognizing Emotions Induced by Affective Sounds through Heart Rate Variability , 2015, IEEE Transactions on Affective Computing.

[17]  George B. Moody,et al.  Derivation of Respiratory Signals from Multi-lead ECGs , 2008 .

[18]  H. T. Nagle,et al.  A comparison of the noise sensitivity of nine QRS detection algorithms , 1990, IEEE Transactions on Biomedical Engineering.

[19]  Jean-Marc Vesin,et al.  Extraction of QRS fiducial points from the ECG using adaptive mathematical morphology , 2016, Digit. Signal Process..

[20]  D. Cysarz,et al.  Comparison of Respiratory Rates Derived from Heart Rate Variability, ECG Amplitude, and Nasal/Oral Airflow , 2008, Annals of Biomedical Engineering.

[21]  Lionel Tarassenko,et al.  Data fusion for estimating respiratory rate from a single-lead ECG , 2013, Biomed. Signal Process. Control..

[22]  Hee Don Seo,et al.  A New QRS Detection Method Using Wavelets and Artificial Neural Networks , 2011, Journal of Medical Systems.

[23]  Derek Abbott,et al.  Revisiting QRS Detection Methodologies for Portable, Wearable, Battery-Operated, and Wireless ECG Systems , 2014, PloS one.

[24]  Md. Mamun Ibne Reaz,et al.  NN-based R-peak detection in QRS complex of ECG signal , 2008 .

[25]  Philip de Chazal,et al.  Automatic classification of heartbeats using ECG morphology and heartbeat interval features , 2004, IEEE Transactions on Biomedical Engineering.

[26]  Francisco Sandoval Hernández,et al.  A New QRS Detector Based on Neural Network , 1997, IWANN.

[27]  Fethi Bereksi-Reguig,et al.  Automatic Classification of Heartbeats Using Wavelet Neural Network , 2012, Journal of Medical Systems.

[28]  Roger C. Barr,et al.  Skin-electrode impedance and its effect on recording cardiac potentials , 1966 .

[29]  Moncef Gabbouj,et al.  Real-Time Patient-Specific ECG Classification by 1-D Convolutional Neural Networks , 2016, IEEE Transactions on Biomedical Engineering.

[30]  G.B. Moody,et al.  The impact of the MIT-BIH Arrhythmia Database , 2001, IEEE Engineering in Medicine and Biology Magazine.

[31]  W. Cleveland.  LOWESS: A Program for Smoothing Scatterplots by Robust Locally Weighted Regression , 1981 .