Automated detection of cardiovascular disease by electrocardiogram signal analysis: a deep learning system

Project Title

Automated detection of cardiovascular disease by electrocardiogram signal analysis: a deep learning system

Project Area of Specialization Artificial IntelligenceProject Summary

Automated electrocardiogram (ECG) diagnosis could be a useful aid for clinical use. We applied a deep learning method to build a system for automated detection and classification of ECG signals. We first trained a convolutional neural network (CNN) to detect cardiovascular disease in ECG signals using a training data set of 259,789 ECG signals collected from the cardiac function rooms of a tertiary care hospital. The CNN classification was validated using an independent test data set of 18,018 ECG signals. The labels used covered >90% of clinical diagnoses. The system grouped ECGs into 18 classifications-17 different types of abnormalities and normal ECG. The overall accuracy of the model was tested and found to be close to 95%; the accuracy for diagnosis of normal rhythm/atrial fibrillation was 99.15%. The proposed CNN model could help reduce misdiagnosis and missed diagnosis in primary care settings and also improve efficiency and save manpower cost for large general hospitals.

Project Objectives

The Project Objectives are as follows:

To help clinicians.

To Help cardiologists to diagnose the heart disease.

For Detecting atrioventricular block.

For Detecting ventricular tachycardia.

Project Implementation Method

Python 3.5 on the Keras library (TensorFlow background) will be used to implement the proposed deep CNN model, which will be trained and evaluated using graphics processing unit (NVIDIA Tesla P100) computing in an Ubuntu 16.04 environment. The training for cardiovascular disease detection will be fully supervised. It back-propagated the gradients from the fully-connected layer through to the convolutional layers. As a loss function, we will minimize the binary cross-entropy to optimize the model parameters. The gradient descent with the Adam update rule was utilized.

Benefits of the Project

The AI-aided ECG diagnosis system that we will develop appears to be sufficiently reliable for clinical use.

It could help reduce misdiagnosis and missed diagnosis in the primary care setting and also save manpower costs for large general hospitals.

Automated electrocardiogram (ECG) diagnosis could be a useful aid for clinical use.

Classification of normal and CAD ECG segments.

For achieving accurate result for recognition of 18-classes of heart rhythms.

Different from other ECG analysis algorithms reported earlier, our system will considers 18 classifications.

Technical Details of Final Deliverable

Computerized recognition of ECG abnormalities is

routinely used by cardiologists classifying long-term ECG

records. Feature extraction methods include wave shape

functions , Hermite functions , wavelet-based features , and statistical features . Methodologies to classify these extracted features include support vector machines , k-th nearest-neighbor rules, decision trees , artificial neural networks and linear discriminants .Automated ECG recognition systems will rely on a pattern-matching framework that represents the ECG signal as a sequence of  stochastic patterns.Deep learning is a new machine learning technique that is becoming the mainstream for pattern recognition.

Accuracy of our system will be of 94.95% and 95.11%  for two and five seconds ECG segments respectively.

With the development of optimization methods for processing

of the large amounts of data being accumulated, the sensitivity

and specificity of automated ECG diagnosis will improve.

Final Deliverable of the Project HW/SW integrated systemCore Industry ITOther Industries Medical Core Technology Internet of Things (IoT)Other Technologies Augmented & Virtual RealitySustainable Development Goals Good Health and Well-Being for PeopleRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	80000
Printing and Binding	Miscellaneous	2	5000	10000
ECG Heart Machine	Equipment	1	40000	40000
Vector Machine	Equipment	1	19000	19000
accuracy sensor	Equipment	2	5500	11000