Scholarlink

Background: <p>Cardiovascular diseases remain one of the primary causes of death worldwide, thus generating an ever-continuing market demand for authentic and non-invasive diagnostic tools. The current research focuses on the automatic classification of heart sound signal recordings (phonocardiograms, PCGs) with deep learning models to facilitate detection of cardiac abnormalities.</p> Methods: <p>Three deep learning approaches were compared in a common experimental framework: a baseline Convolutional Neural Network (CNN), an Attention Augmented CNN (Attention-CNN), and Audio Spectrogram Transformer (AST). Experiments were performed on the PhysioNet/CinC Challenge 2016 data set using Mel-spectrogram representations. The performance of all the architectures was evaluated using a 5-fold cross-validation protocol with Area Under the Receiver Operating Characteristic Curve (AUC), Accuracy, and F1 metrics. Training used the Adam optimizer with binary cross-entropy loss, and record-level predictions were obtained by aggregating segment-level probabilities for each recording.</p> Results: <p>Attention-CNN got the best results with an AUC of 0.9711 and an F1-score of 0.7679, beating the baseline CNN (AUC = 0.9636) and AST (AUC = 0.9243). The use of channel attention resulted in better feature discrimination and fewer false positive predictions. While AST demonstrated the ability to capture global contextual features through self-attention, its performance was constrained by computational resources and limited training period.</p> Conclusion: <p>The findings suggest that Attention-CNN is a preferable balanced relationship between performance and computational requirements for PCG-based heart sound classification. However, the study has limitations in terms of data size and availability of computational resources, especially for transformer models. Future work will continue with larger scale training and validation to further test model generalizability in clinical and telemedicine practice.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

From convolutions to transformers: a comparative analysis of deep learning models for heart sound classification

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年8月4日

查看全文
  • Bollapalli Althaph,
  • Devyani Sah,
  • Lasya Reddy,
  • Venkatannagari Sireesha,
  • Yeddula Samyuktha,
  • Nagendra Panini Challa

摘要

Background:

Cardiovascular diseases remain one of the primary causes of death worldwide, thus generating an ever-continuing market demand for authentic and non-invasive diagnostic tools. The current research focuses on the automatic classification of heart sound signal recordings (phonocardiograms, PCGs) with deep learning models to facilitate detection of cardiac abnormalities.

Methods:

Three deep learning approaches were compared in a common experimental framework: a baseline Convolutional Neural Network (CNN), an Attention Augmented CNN (Attention-CNN), and Audio Spectrogram Transformer (AST). Experiments were performed on the PhysioNet/CinC Challenge 2016 data set using Mel-spectrogram representations. The performance of all the architectures was evaluated using a 5-fold cross-validation protocol with Area Under the Receiver Operating Characteristic Curve (AUC), Accuracy, and F1 metrics. Training used the Adam optimizer with binary cross-entropy loss, and record-level predictions were obtained by aggregating segment-level probabilities for each recording.

Results:

Attention-CNN got the best results with an AUC of 0.9711 and an F1-score of 0.7679, beating the baseline CNN (AUC = 0.9636) and AST (AUC = 0.9243). The use of channel attention resulted in better feature discrimination and fewer false positive predictions. While AST demonstrated the ability to capture global contextual features through self-attention, its performance was constrained by computational resources and limited training period.

Conclusion:

The findings suggest that Attention-CNN is a preferable balanced relationship between performance and computational requirements for PCG-based heart sound classification. However, the study has limitations in terms of data size and availability of computational resources, especially for transformer models. Future work will continue with larger scale training and validation to further test model generalizability in clinical and telemedicine practice.