A photoplethysmography-based method using an artificial neural network detected premature ventricular contractions with 92.4-93.2% sensitivity and 99.9% specificity compared to electrocardiogram.
Can a photoplethysmography-based method using an artificial neural network accurately detect premature ventricular contractions compared to electrocardiogram?
A novel PPG-based algorithm using artificial neural networks demonstrates high sensitivity and specificity for detecting premature ventricular contractions, offering a less obtrusive alternative to ECG.
This work introduces a method for detection of premature ventricular contractions (PVCs) in photoplethysmogram (PPG). The method relies on 6 features, characterising PPG pulse power, and peak-to-peak intervals. A sliding window approach is applied to extract the features, 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, namely, the MIMIC II and the MIMIC, were used for training and testing, respectively. After annotating the PPGs with respect to synchronously recorded electrocardiogram, two main types of PVCs were distinguished: with and without the observable PPG pulse. The obtained sensitivity and specificity values for both considered PVC types were 92.4/99.9% and 93.2/99.9%, respectively. The achieved high classification results form a basis for a reliable PVC detection using a less obtrusive approach than the electrocardiography-based detection methods.
Sološenko et al. (Thu,) conducted a other in Premature ventricular contractions. Photoplethysmography-based detection method vs. Electrocardiogram was evaluated on Sensitivity and specificity for PVC detection. A photoplethysmography-based method using an artificial neural network detected premature ventricular contractions with 92.4-93.2% sensitivity and 99.9% specificity compared to electrocardiogram.