Stroke prediction from electrocardiograms by deep neural network

The brain is an energy-consuming organ that heavily relies on the heart for energy supply. Heart abnormalities detected by electrocardiogram (ECG) might provide diagnostic indicators for brain dysfunctions such as stroke. Diagnosis of brain diseases by ECG requires proficient domain knowledge, which is both time and labor consuming. Deep learning is capable of constructing a nonlinear correlation between ECG and stroke without prior expert knowledge. Here, we propose a data-driven classifier-Dense convolutional neural Network (DenseNet) for stroke prediction based on 12-leads ECG data. With our finely-tuned model, we obtain the training accuracy of 99.99% and the prediction accuracy of 85.82%. To our knowledge, this is the first report studying the correlation between stroke and ECG with the aid of deep learning. The results indicate that ECG is a valuable complementary technique for stroke diagnostics.

[1]  Bo Zhou,et al.  A Weakly Supervised Adaptive DenseNet for Classifying Thoracic Diseases and Identifying Abnormalities , 2018, ArXiv.

[2]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[3]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  L Edenbrandt,et al.  A confident decision support system for interpreting electrocardiograms. , 1999, Clinical physiology.

[5]  G. Lip,et al.  Usefulness of P Wave Duration in Embolic Stroke of Undetermined Source , 2020, Journal of clinical medicine.

[6]  U. Rajendra Acharya,et al.  Automated detection of arrhythmias using different intervals of tachycardia ECG segments with convolutional neural network , 2017, Inf. Sci..

[7]  Philip de Chazal,et al.  A Patient-Adapting Heartbeat Classifier Using ECG Morphology and Heartbeat Interval Features , 2006, IEEE Transactions on Biomedical Engineering.

[8]  Herbert F. Jelinek,et al.  ECG Biometric with Abnormal Cardiac Conditions in Remote Monitoring System , 2014, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[9]  U. Rajendra Acharya,et al.  Application of deep convolutional neural network for automated detection of myocardial infarction using ECG signals , 2017, Inf. Sci..

[10]  C. McKevitt,et al.  Socioeconomic status and stroke , 2006, The Lancet Neurology.

[11]  C. Chiou,et al.  Cardiac arrhythmia diagnosis method using linear discriminant analysis on ECG signals , 2009 .

[12]  Jonathan Rubin,et al.  Cardiac arrhythmia detection using deep learning: A review. , 2019, Journal of electrocardiology.

[13]  Tara N. Sainath,et al.  Deep convolutional neural networks for LVCSR , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[14]  Dellagi Sofiene,et al.  Full training convolutional neural network for ECG signals classification , 2019, TECHNOLOGIES AND MATERIALS FOR RENEWABLE ENERGY, ENVIRONMENT AND SUSTAINABILITY: TMREES19Gr.

[15]  Pasin Israsena,et al.  EEG-Based Emotion Recognition Using Deep Learning Network with Principal Component Based Covariate Shift Adaptation , 2014, TheScientificWorldJournal.

[16]  Marimuthu Palaniswami,et al.  Support Vector Machines for Automated Recognition of Obstructive Sleep Apnea Syndrome From ECG Recordings , 2009, IEEE Transactions on Information Technology in Biomedicine.

[17]  Jinsul Kim,et al.  An Automated ECG Beat Classification System Using Convolutional Neural Networks , 2016, 2016 6th International Conference on IT Convergence and Security (ICITCS).

[18]  Yixiang Huang,et al.  Multi-domain modeling of atrial fibrillation detection with twin attentional convolutional long short-term memory neural networks , 2020, Knowl. Based Syst..

[19]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[21]  Jiayu Dong,et al.  Dynamic Facial Expression Recognition Based on Convolutional Neural Networks with Dense Connections , 2018, 2018 24th International Conference on Pattern Recognition (ICPR).

[22]  Yuanzhi Li,et al.  An Alternative View: When Does SGD Escape Local Minima? , 2018, ICML.

[23]  D. Goldstein,et al.  The Electrocardiogram in Stroke: Relationship to Pathophysiological Type and Comparison with Prior Tracings , 1979, Stroke.

[24]  Seyyed Mahdi Zia Ziabari,et al.  Electrocardiogram Changes as an Independent Predictive Factor of Mortality in Patients with Acute Ischemic Stroke; a Cohort Study , 2019, Archives of academic emergency medicine.

[25]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Yoram Singer,et al.  Adaptive Subgradient Methods for Online Learning and Stochastic Optimization , 2011, J. Mach. Learn. Res..

[27]  Parshuram N Aarotale,et al.  Relationship between Ischemic Stroke and Pulse Rate Variability as a Surrogate of Heart Rate Variability , 2019, Brain sciences.

[28]  Hyeon-Min Shim,et al.  Multi-channel electromyography pattern classification using deep belief networks for enhanced user experience , 2015, Journal of Central South University.

[29]  Maarten De Vos,et al.  Comparing feature-based classifiers and convolutional neural networks to detect arrhythmia from short segments of ECG , 2017, 2017 Computing in Cardiology (CinC).

[30]  Matthias Hein,et al.  Variants of RMSProp and Adagrad with Logarithmic Regret Bounds , 2017, ICML.

[31]  Giovanni Calcagnini,et al.  P-wave Variability and Atrial Fibrillation , 2016, Scientific Reports.