Deep learning based classification for healthcare data analysis system

This paper presents a deep learning based mechanism to analyze the healthcare data to detect the possible anomalies and classify the data into different so that we can know the nature of health problem. An implementation of deep convolutional neural network (DCNN) to classify the image patterns data extracted from electrocardiograph (ECG) is discussed in detail. A dedicated convolutional neural network will be trained using different data samples taken from various patients termed as training data. On later stage, the algorithm is tested using test data samples and it is observed that the proposed algorithm does perform efficient, stable and superior classification performance for the detection of normal beats (N-Type), ventricular ectopic beats (V-Type) and super ventricular ectopic beats (SV-Type). The experimental analysis shows the recognition accuracy and loss value. Subsequently, sensitivity and specificity of the algorithm is measured to show the effectiveness of the proposed solution.

[1]  Roshan Joy Martis,et al.  DIAGNOSIS OF MULTICLASS TACHYCARDIA BEATS USING RECURRENCE QUANTIFICATION ANALYSIS AND ENSEMBLE CLASSIFIERS , 2016 .

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

[3]  Fahim Sufi,et al.  Diagnosis of Cardiovascular Abnormalities From Compressed ECG: A Data Mining-Based Approach , 2009, IEEE Transactions on Information Technology in Biomedicine.

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

[5]  Joseph E. Marine,et al.  Epidemiology of arrhythmias and conduction disorders in older adults. , 2012, Clinics in geriatric medicine.

[6]  U. Rajendra Acharya,et al.  Automated characterization of arrhythmias using nonlinear features from tachycardia ECG beats , 2016, 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

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

[8]  Luca Maria Gambardella,et al.  Convolutional Neural Network Committees for Handwritten Character Classification , 2011, 2011 International Conference on Document Analysis and Recognition.

[9]  Patrice Y. Simard,et al.  Best practices for convolutional neural networks applied to visual document analysis , 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..

[10]  Elif Derya Übeyli Usage of eigenvector methods in implementation of automated diagnostic systems for ECG beats , 2008, Digit. Signal Process..

[11]  U. RajendraAcharya Advances in cardiac signal processing , 2007 .

[12]  Fei Wang,et al.  Deep learning for healthcare: review, opportunities and challenges , 2018, Briefings Bioinform..

[13]  David G. Stork,et al.  Pattern classification, 2nd Edition , 2000 .

[14]  Naif Alajlan,et al.  Deep learning approach for active classification of electrocardiogram signals , 2016, Inf. Sci..

[15]  G. Bortolan,et al.  Sequential analysis for automatic detection of atrial fibrillation and flutter , 2001, Computers in Cardiology 2001. Vol.28 (Cat. No.01CH37287).