Scholarlink

<p>Myocardial repolarization and QT duration are crucial markers for diagnosis and monitoring of congenital long QT syndrome (LQTS). Here we present a novel algorithm to automatically estimate the QT interval based on Lepeschkin’s tangent method, as well as parameters underlying T-wave morphology in digital electrocardiograms (ECGs) of 466 patients with LQTS. The algorithm’s performance was validated using ECG data from 40 healthy controls. The results were compared against expert measurement of the QT interval, as well as against the results of the ECG device MUSE™ system. Applying an optimizable Support Vector Machine classifier on the algorithm’s outcomes achieved an accuracy of 78.1% and area under the curve of 0.85 in classifying LQTS patients with a prolonged QTc interval (upon QT_GS) from those with a normal QTc interval. The presented MATLAB®-based algorithm offers a transparent and reproducible approach to automatic QT interval estimation and QTc calculation in LQTS patients, potentially improving automatized screening, diagnostic precision and patient management.</p> Graphical Abstract <p></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 MATLAB Algorithm to Automatically Estimate the QT Interval and Other ECG Parameters and Validation Using a Machine Learning Approach in Congenital Long-QT Syndrome

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年9月30日

查看全文
  • Elinor Tzvi-Minker,
  • Sven Dittmann,
  • Corinna Rickert,
  • Andreas Keck,
  • Eric Schulze-Bahr

摘要

Myocardial repolarization and QT duration are crucial markers for diagnosis and monitoring of congenital long QT syndrome (LQTS). Here we present a novel algorithm to automatically estimate the QT interval based on Lepeschkin’s tangent method, as well as parameters underlying T-wave morphology in digital electrocardiograms (ECGs) of 466 patients with LQTS. The algorithm’s performance was validated using ECG data from 40 healthy controls. The results were compared against expert measurement of the QT interval, as well as against the results of the ECG device MUSE™ system. Applying an optimizable Support Vector Machine classifier on the algorithm’s outcomes achieved an accuracy of 78.1% and area under the curve of 0.85 in classifying LQTS patients with a prolonged QTc interval (upon QT_GS) from those with a normal QTc interval. The presented MATLAB®-based algorithm offers a transparent and reproducible approach to automatic QT interval estimation and QTc calculation in LQTS patients, potentially improving automatized screening, diagnostic precision and patient management.

Graphical Abstract