PROJECT TITLE :

Photoplethysmography-Based Method for Automatic Detection of Premature Ventricular Contractions

ABSTRACT:

This work introduces a technique for detection of premature ventricular contractions (PVCs) in photoplethysmogram (PPG). The tactic depends on half dozen features, characterising PPG pulse power, and peak-to-peak intervals. A sliding window approach is applied to extract the options, which are later normalized with respect to an estimated heart rate. Artificial neural network with either linear and non-linear outputs was investigated as a feature classifier. PhysioNet databases, specifically, the MIMIC II and therefore the MIMIC, were used for coaching and testing, respectively. Once annotating the PPGs with respect to synchronously recorded electrocardiogram, 2 main varieties of PVCs were distinguished: with and while not the observable PPG pulse. The obtained sensitivity and specificity values for both thought-about PVC types were 92.4/ninety nine.9% and ninety three.2/99.ninepercent, respectively. The achieved high classification results form a basis for a reliable PVC detection using a less obtrusive approach than the electrocardiography-primarily based detection strategies.