Combining Deep Learning with Traditional Machine Learning to Improve Phonocardiography Classification Accuracy

Abstract

Phonocardiography (PCG) is a widely used technique to detect and diagnose cardiovascular diseases. We have combined the advantages of traditional machine learning (ML) and deep learning (DL) techniques to build deep hybrid PCG classification models. We have shown that, though DL models usually outperform ML models in classifying PCG signals, optimal classification can be achieved if we combine these two architectures to build a single PCG classification model. A Convolutional Neural Network (CNN) is used along with 7 traditional machine learning methods including Logistic Regression (LR), Random Forest (RF), K-Nearest Neighbors (KNN), Decision Tree (DT), Naive Bayes (NB), Support Vector Machine (SVM), and AdaBoost (AB) to build hybrid PCG classification models. Our experimental results have shown that significant improvements in the classification accuracy can be achieved by using deep hybrid models compared to traditional machine learning models. We have also shown that some hybrid models performed better than the single deep learning model in classifying PCG signals. We have also compared the performance of the best hybrid model to 11 other PCG classification models and obtained better accuracy.