Scholarlink

Our research tackles the critical issue of congestive heart failure (CHF), a serious cardiovascular condition in which the heart’s ability to pump blood effectively is compromised, leading to fluid buildup. Existing diagnostic methods often struggle with signal processing and manual Electrocardiogram (ECG) analysis, resulting in reduced accuracy and added complexity in diagnosis. To overcome these challenges, we present an innovative framework that integrates GQRS detection of RR peaks and intervals from ECG data. We then propose a hybrid CNN-LSTM network specifically designed for CHF diagnosis. What sets our approach apart is the strategic application of deep learning, combining the feature extraction strengths of Convolutional Neural Networks (CNNs) with the temporal processing capabilities of LSTM networks. This combination enhances diagnostic outcomes, significantly improving the accuracy of CHF detection and representing a notable advancement in clinical diagnostics. Our research highlights the potential of deep learning to enhance diagnostic precision and support clinical decision-making for CHF. By leveraging advanced technologies and methodologies, we aim to revolutionize cardiovascular health monitoring and contribute to more effective patient care strategies. This innovative approach achieves an impressive accuracy rate of 98.77

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

Hybrid CNN-LSTM Framework for Enhanced Congestive Heart Failure Diagnosis: Integrating GQRS Detection

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Aditya Oza,
  • Sanskriti Patel,
  • Bhavesh Gyanchandani,
  • Abhinav Roy,
  • Santosh Kumar

摘要

Our research tackles the critical issue of congestive heart failure (CHF), a serious cardiovascular condition in which the heart’s ability to pump blood effectively is compromised, leading to fluid buildup. Existing diagnostic methods often struggle with signal processing and manual Electrocardiogram (ECG) analysis, resulting in reduced accuracy and added complexity in diagnosis. To overcome these challenges, we present an innovative framework that integrates GQRS detection of RR peaks and intervals from ECG data. We then propose a hybrid CNN-LSTM network specifically designed for CHF diagnosis. What sets our approach apart is the strategic application of deep learning, combining the feature extraction strengths of Convolutional Neural Networks (CNNs) with the temporal processing capabilities of LSTM networks. This combination enhances diagnostic outcomes, significantly improving the accuracy of CHF detection and representing a notable advancement in clinical diagnostics. Our research highlights the potential of deep learning to enhance diagnostic precision and support clinical decision-making for CHF. By leveraging advanced technologies and methodologies, we aim to revolutionize cardiovascular health monitoring and contribute to more effective patient care strategies. This innovative approach achieves an impressive accuracy rate of 98.77