Comparative Analysis of CNN and Transformer Architectures with Heart Cycle Normalization for Automated Phonocardiogram Classification

TL;DR

This study compares CNN and transformer models for phonocardiogram classification, introducing a heart cycle normalization method, and finds CNNs generally outperform transformers, with implications for clinical application and model efficiency.

Contribution

The paper introduces a novel heart cycle normalization approach and systematically compares CNN and transformer architectures for PCG classification.

Findings

CNN with fixed-length windowing achieves 79.5% AUROC

Heart cycle normalization impacts model performance significantly

CNNs outperform transformers in classification accuracy

Abstract

The automated classification of phonocardiogram (PCG) recordings represents a substantial advancement in cardiovascular diagnostics. This paper presents a systematic comparison of four distinct models for heart murmur detection: two specialized convolutional neural networks (CNNs) and two zero-shot universal audio transformers (BEATs), evaluated using fixed-length and heart cycle normalization approaches. Utilizing the PhysioNet2022 dataset, a custom heart cycle normalization method tailored to individual cardiac rhythms is introduced. The findings indicate the following AUROC values: the CNN model with fixed-length windowing achieves 79.5%, the CNN model with heart cycle normalization scores 75.4%, the BEATs transformer with fixed-length windowing achieves 65.7%, and the BEATs transformer with heart cycle normalization results in 70.1%. The findings indicate that physiological signal constraints, especially those introduced by different normalization strategies, have a substantial impact on model performance. The research provides evidence-based guidelines for architecture selection in clinical settings, emphasizing the need for a balance between accuracy and computational efficiency. Although specialized CNNs demonstrate superior performance overall, the zero-shot transformer models may offer promising efficiency advantages during development, such as faster training and evaluation cycles, despite their lower classification accuracy. These findings highlight the potential of automated classification systems to enhance cardiac diagnostics and improve patient care.