Key result
A novel MATLAB-based algorithm combined with a Support Vector Machine classifier achieved 78.1% accuracy and an AUC of 0.85 in distinguishing LQTS patients with prolonged versus normal QTc intervals.
Why the study?
Myocardial repolarization and QT duration are crucial markers for diagnosis and monitoring of congenital long QT syndrome, motivating the development of automated estimation methods.
Does a novel MATLAB-based algorithm accurately estimate the QT interval and classify prolonged QTc in patients with congenital long QT syndrome compared to expert manual measurement?
Cross-Sectional (n=506)
No
Does a novel MATLAB-based algorithm accurately estimate the QT interval and classify prolonged QTc in patients with congenital long QT syndrome compared to expert manual measurement?
The automated MATLAB algorithm provides a transparent and reproducible approach to QT interval estimation, achieving high specificity and 78.1% accuracy in classifying prolonged QTc in LQTS patients when combined with machine learning.
Answers are grounded in this paper and cite their sources.
May aid automated LQTS QTc classification; hypothesis-generating and requires prospective validation before clinical use.
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.
No takes yet. Share an insight, caveat, or question.
Tzvi et al. (2025) conducted a cross-sectional in Congenital Long-QT Syndrome (n=506). MATLAB algorithm for automated QT interval estimation vs. Manual expert measurement and MUSE system was evaluated on Classification of prolonged vs normal QTc interval using SVM classifier (AUC 0.85). A novel MATLAB-based algorithm combined with a Support Vector Machine classifier achieved 78.1% accuracy and an AUC of 0.85 in distinguishing LQTS patients with prolonged versus normal QTc intervals.
Synapse has enriched 10 related papers. Consider them for comparative context: