Scholarlink

<p>In this work we provide an algorithm that improves Pan-Tompkins algorithm to draw the accurate and efficient detection of QRS complex using electrocardiogram (ECG) signals. The suggested algorithm gets around issues like noise sensitivity, baseline drift, and heavy computation load that are typically encountered with conventional methods. We put the algorithm to the test using a variety of databases, including the Computing in Cardiology Challenge 2014 (CinC 2014 DB), the European ST-T database (European ST-T DB), the St. Petersburg 12-lead Arrhythmia database (St. Petersburg INCART DB), the MIT-BIH Arrhythmia database (MIT-BIH Arrhythmia DB), and a new private ECG database (private ECG DB) that we gathered with a budget-friendly portable ECG acquisition device. The suggested approach uses Savitzky-Golay smoothing, adjusts the threshold dynamically, and classifies based on the slope to accurately detect the QRS complex, even with noise and changing signals. The results indicate that the proposed algorithm performs better than current methods, which include wavelet transform, Hamilton algorithm, original Pan-Tompkins, and neural network-based models. In every database, it produced outstanding performance metrics. On the MIT-BIH Arrhythmia DB, it, e.g., attains a sensitivity of 95.35%, a positive predictive value of 95.71% and an F1 score of 98.1%, with a very low rate of false positives (FP%) of only 0.55 and a processing time of 52&#xa0;s, which is optimal in real-time applications. Using a portable, budget-friendly ECG acquisition system to validate the algorithm highlights its practicality in settings with limited resources, providing a reliable and cost-effective option for monitoring heart health. This work marks a notable leap forward in QRS detection methods, striking a great balance between accuracy, efficiency, and real-time performance.</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

A novel improved Pan-Tompkins method for QRS complex detection of the ECG signal

  • 期刊论文

  • 发表日期：

    2025年8月6日

查看全文
  • Anas Fouad Ahmed

摘要

In this work we provide an algorithm that improves Pan-Tompkins algorithm to draw the accurate and efficient detection of QRS complex using electrocardiogram (ECG) signals. The suggested algorithm gets around issues like noise sensitivity, baseline drift, and heavy computation load that are typically encountered with conventional methods. We put the algorithm to the test using a variety of databases, including the Computing in Cardiology Challenge 2014 (CinC 2014 DB), the European ST-T database (European ST-T DB), the St. Petersburg 12-lead Arrhythmia database (St. Petersburg INCART DB), the MIT-BIH Arrhythmia database (MIT-BIH Arrhythmia DB), and a new private ECG database (private ECG DB) that we gathered with a budget-friendly portable ECG acquisition device. The suggested approach uses Savitzky-Golay smoothing, adjusts the threshold dynamically, and classifies based on the slope to accurately detect the QRS complex, even with noise and changing signals. The results indicate that the proposed algorithm performs better than current methods, which include wavelet transform, Hamilton algorithm, original Pan-Tompkins, and neural network-based models. In every database, it produced outstanding performance metrics. On the MIT-BIH Arrhythmia DB, it, e.g., attains a sensitivity of 95.35%, a positive predictive value of 95.71% and an F1 score of 98.1%, with a very low rate of false positives (FP%) of only 0.55 and a processing time of 52 s, which is optimal in real-time applications. Using a portable, budget-friendly ECG acquisition system to validate the algorithm highlights its practicality in settings with limited resources, providing a reliable and cost-effective option for monitoring heart health. This work marks a notable leap forward in QRS detection methods, striking a great balance between accuracy, efficiency, and real-time performance.