A Data-Driven Gaussian Process Filter for Electrocardiogram Denoising.

Gaussian Processes (𝒢𝒫)-based filters, which have been effectively used for various applications including electrocardiogram (ECG) filtering can be computationally demanding and the choice of their hyperparameters is typically ad hoc. We develop a data-driven 𝒢𝒫 filter to address both issues, using the notion of the ECG It is shown that the proposed 𝒢𝒫 filter outperforms the benchmark filter for all the tested noise levels. It also outperforms the state-of-the-art filter in terms of QT-interval estimation error bias and variance. The proposed 𝒢𝒫 filter is a versatile technique for preprocessing the ECG in clinical and research applications, is applicable to ECG of arbitrary lengths and sampling frequencies, and provides confidence intervals for its performance.