Nearest Neighbor Search-Based Modification of RRI Data with Premature Atrial Contraction and Premature Ventricular Contraction

Heart rate variability (HRV) analysis plays an essential role in healthcare. HRV features cannot be extracted accurately from the R-R interval (RRI) when RRI data contains artifacts. Previous research for modifying RRI data with artifacts considered premature atrial contraction (PAC) and premature ventricular contraction (PVC), which are the most common types of extrasystoles occurring every day in healthy persons. This research proposed three new RRI modification algorithms for PAC and PVC using nearest neighbor search (NNS) algorithms: k-nearest neighbors (KNN), clustering-KNN (CKNN), and approximate nearest neighbors (ANN). The present work demonstrated that the ANNbased RRI modification (ANN-RM) algorithm achieved lower root mean squared errors (RMSEs) than the CKNN-based RRI modification algorithm and the highest computational speed. The RMSEs of ANN-RM for PAC and PVC were 23.0 ms and 26.2 ms, respectively.