Key result
The proposed 1-D CNN model with ADASYN sampling achieved 100% accuracy on a balanced dataset and 99.98% accuracy on an imbalanced dataset for classifying heart murmurs.
Why the study?
Pathological cardiac murmurs indicate heart disorders, but automated classification models struggle with consistent recognition when datasets are imbalanced and feature extraction is difficult.
A 1-D CNN combined with the ADASYN sampling approach accurately classifies heart murmurs from PCG signals, demonstrating high performance even in highly imbalanced and noisy datasets.
May inform AI-assisted murmur detection research; leaves open clinical validation and generalizability.
Ubiquitous Perturbations in cardiac auscultation properties, cardiovascular diseases (CVDs) are widely recognized. In the auscultation procedure, the appearance of pathological cardiac murmurs is linked to heart disorders. A noble automated detection system using 1-D Convolutional Neural Network (CNN) for the detection of pathological heart murmurs is proposed in this study, which removes the difficult task of extracting and selecting features. It directly acts on the phonocardiogram (PCG) signals. The fundamental purpose of this research is to develop a classification model for consistent recognition of cardiac murmurs when the data-set is imbalanced. In view of this, the proposed study for the imbalanced data-set incorporates the Adaptive Synthetic (ADASYN) approach to generate synthetic data for the minority class. The outcome analysis illustrates the positive result in the identification of heart murmurs on both balanced and imbalanced data-sets. Therefore, the developed deep learning model will learn better from the minority class and classify heart murmurs accurately.
No takes yet. Share an insight, caveat, or question.
Vakamullu et al. (2022) studied Heart murmurs (n=258). 1-D Convolutional Neural Network (CNN) with ADASYN vs. Multi-layer perceptron (MLP) was evaluated on Classification accuracy. The proposed 1-D CNN model with ADASYN sampling achieved 100% accuracy on a balanced dataset and 99.98% accuracy on an imbalanced dataset for classifying heart murmurs.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: