Ensembled Transfer Learning and Multiple Kernel Learning for Phonocardiogram Based Atherosclerotic Coronary Artery Disease Detection

• Published in: IEEE journal of biomedical and health informatics Vol. 26; no. 6; pp. 2804 - 2813
• Main Authors: Pathak, Akanksha, Mandana, Kayapanda, Saha, Goutam
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.06.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accuracy; Arteries; Arteriosclerosis; Artificial neural networks; Atherosclerosis; Bioinformatics; Cardiovascular disease; Continuous wavelet transforms; Coronary artery; Coronary artery disease; Coronary Artery Disease - diagnostic imaging; Coronary vessels; Deep learning; Disease detection; Diseases; Heart; Heart diseases; Humans; Kernel; Kernels; Machine Learning; multiple kernel learning; Neural networks; Neural Networks, Computer; Optimization; Performance measurement; phonocardiogram; Phonocardiography; Redundancy; Transfer learning; Vein & artery diseases; VGG16
• DOI: 10.1109/JBHI.2022.3140277
• ISSN: 2168-2194; 2168-2208

Conventional machine learning has paved the way for a simple, affordable, non-invasive approach for Coronary artery disease (CAD) detection using phonocardiogram (PCG). It leaves a scope to explore improvement of performance metrics by fusion of learned representations from deep learning. In this study, we propose a novel, multiple kernel learning (MKL) for their fusion using deep embeddings transferred from pre-trained convolutional neural network (CNN). The proposed MKL, finds optimal kernel combination by maximizing the similarity with ideal kernel and minimizing the redundancy with other basis kernels. Experiments are performed on 960 PCG epochs collected from 40 CAD and 40 normal subjects. The transferred embeddings attain maximum subject-level accuracy of 89.25% with kappa of 0.7850. Later, their fusion with handcrafted features using the proposed MKL gives an accuracy of 91.19% and kappa 0.8238. The study shows the potential of development of high accuracy CAD detection system by using easy to acquire, non-invasive PCG signal.