Key result
Piecewise polynomial approximation achieves ~99% accuracy for ECG R-peak detection on the MIT-BIH database.
A computationally efficient piecewise polynomial approximation method for ECG R-peak detection demonstrates high accuracy (>99.1% F-score), suitable for real-time monitoring in IoT devices.
A computationally efficient information technology for the automatic detection of R -peaks in electrocardiogram signals is proposed, designed for use in portable long-term monitoring systems. A piecewise polynomial approximation method based on second-order Hermite polynomials is applied to transform a discrete sequence of samples into a continuous analytical representation of the signal. This ensures the continuity of both the approximation function and its first derivative, enabling their analytical computation. This approach minimizes noise impact and ensures accurate R -peak localization despite significant baseline drift and motion artifacts. The mathematical framework is integrated into a comprehensive clinical decision support system using a microservice architecture with vector-based visualization. The results of testing on the MIT-BIH Arrhythmia Database open dataset showed the method’s high efficiency, with an average F-score exceeding 99.1%, and in some complex cases, 100% accuracy was achieved. The technology’s low computational cost makes it suitable for real-time cardiac monitoring in embedded systems and Internet of Things (IoT) devices.
No takes yet. Share an insight, caveat, or question.
Yefremov et al. (2026) studied Electrocardiogram signals. Piecewise polynomial approximation method based on second-order Hermite polynomials was evaluated on R-peak detection accuracy (F-score). A piecewise polynomial approximation method for R-peak detection in ECG signals achieved an average F-score exceeding 99.1% on the MIT-BIH Arrhythmia Database.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: