- Book Chapter
2
- 10.1007/978-981-19-6004-8_49
Advanced Approach for Heart Disease Diagnosis with Grey Wolf Optimization and Deep Learning Techniques
- Dec 03, 2022
- Dimple Santoshi + 2 more +2
Electrocardiography (ECG) has gained popularity in recognizing abnormally quick and slow heart rates. Previously, clinical data was used for heart disease diagnosis. Advance technology led to improvement in deep learning (DL) and optimization algorithms that use image data to classify and predict heart diseases. DL eliminates data pre-processing as in machine learning (ML), to scan and search features that correlate and combine them to enable faster learning. DL requires huge data to perform accurately. DL is expensive concerning hardware requirements and training which increases the overall cost. Hence, grey wolf optimization (GWO) can provide competitive results of improved local optima. This paper presents an advanced approach of index matching to perform analysis in two categories by merging clinical data with ECG for classifying and diagnosing heart diseases. Best features are selected by GWO on merging 12-lead Physikalisch-Technische Bundesanstalt (PTB-XL) ECG data and clinical data. Evaluations using deep neural networks on the merged data set are performed. In comparison, the results show that convolutional neural networks (CNNs) using Visual Geometry Group (VGG-16) outperform all other algorithms. Performance is evaluated with various parameters like accuracy, recall, precision, and area under the receiver operator characteristic curve (AUC). Deep learning-based algorithms have a promising future in ECG analysis regarding quantitative exactness and quality.
Read more