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

2025-07-08

AI Summary

This study systematically compares convolutional neural networks (CNNs) and zero-shot audio Transformers (BEATs) for automated heart murmur classification from phonocardiogram (PCG) signals, introducing— for the first time—a personalized cardiac-cycle normalization preprocessing strategy. We evaluate two CNN architectures and two BEATs variants under two input paradigms: fixed-length windows and cycle-normalized segments. Results show that CNNs achieve an AUROC of 79.5% on fixed-length inputs, significantly outperforming BEATs; although cycle normalization improves some BEATs performance, it remains inferior to domain-specialized CNNs. The key contribution lies in empirically demonstrating that physiological rhythm–aware preprocessing exerts a decisive influence on PCG modeling efficacy. This work provides evidence-based guidance for co-optimizing model selection and signal preprocessing in clinical deployment, establishing a methodological foundation for translating PCG analysis into real-world cardiac screening applications.

Technology Category

• Machine Learning: Multimodal Learning
• Cognitive Modeling & Cognitive Systems: Affective Computing
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

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.

Problem

• Compare CNN and transformer models for PCG classification
• Evaluate heart cycle normalization impact on model performance
• Provide guidelines for clinical architecture selection balancing accuracy and efficiency

Innovation

• Heart cycle normalization for PCG classification
• Comparison of CNNs and transformers in diagnostics
• Custom normalization method for cardiac rhythms