Determination of aortic valve opening time and left ventricular peak filling rate from the peripheral pulse amplitude in patients with ectopic beats

Enhanced premature ventricular contraction pulse detection and classification using deep convolutional neural network

Access to accurate and precise monitoring systems for cardiac arrhythmia could contribute significantly to preventing damage and subsequent heart disorders. The present research concentrates on using photoplethysmography (PPG) and arterial blood pressure (ABP) with deep convolutional neural networks (CNN) for the classification and detection of fetal cardiac arrhythmia or premature ventricular contractions (PMVCs). The framework for the study entails (Icentia 11k) a public dataset of ECG signals consisting of different cardiac abnormalities. Following this, the weights obtained from the Icentia 11k dataset are transferred to the proposed CNN. Finally, fine-tuning was carried out to improve the accuracy of classification. Results obtained showcase the capacity of the proposed method to detect and classify PMVCs into three types: Normal, P1, and P2 with an accuracy of 99.9%, 99.8%, and 99.5%.

Heartbeat Detection by Laser Doppler Vibrometry and Machine Learning

Background: Heartbeat detection is a crucial step in several clinical fields. Laser Doppler Vibrometer (LDV) is a promising non-contact measurement for heartbeat detection. The aim of this work is to assess whether machine learning can be used for detecting heartbeat from the carotid LDV signal. Methods: The performances of Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF) and K-Nearest Neighbor (KNN) were compared using the leave-one-subject-out cross-validation as the testing protocol in an LDV dataset collected from 28 subjects. The classification was conducted on LDV signal windows, which were labeled as beat, if containing a beat, or no-beat, otherwise. The labeling procedure was performed using electrocardiography as the gold standard. Results: For the beat class, the f1-score (f1) values were 0.93, 0.93, 0.95, 0.96 for RF, DT, KNN and SVM, respectively. No statistical differences were found between the classifiers. When testing the SVM on the full-length (10 min long) LDV signals, to simulate a real-world application, we achieved a median macro-f1 of 0.76. Conclusions: Using machine learning for heartbeat detection from carotid LDV signals showed encouraging results, representing a promising step in the field of contactless cardiovascular signal analysis.

Photoplethysmography-Based Method for Automatic Detection of Premature Ventricular Contractions

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.

Variations in the pre-ejection period induced by ventricular extra systoles may be feasible to predict fluid responsiveness

Monitoring that can predict fluid responsiveness is an unsettled matter for spontaneously breathing patients. Based on the convincing results with dynamic monitoring based on preload variations induced by mechanical ventilation, we hypothesised that the extra systolic post-ectopic beat could constitute a similar intermittent preload shift inducing a brief variation in blood pressure and that the magnitude of this variation could predict the hemodynamic response to volume expansion in sedated pigs. Ten pigs were sedated and hemodynamically monitored and four intravascular volume shifts were made: blood depletion (25% of estimated blood volume; 660 ml), retransfusion (of 500 ml depleted blood), and two sequential volume expansions (500 ml colloid each). Between volume shifts, supraventricular and ventricular extra systoles were induced by a pacemaker. Hemodynamic variables such as pulse pressure (PP) and pre-ejection period (PEP) were determined for each heart beat and the hemodynamic changes in the post-ectopic beats compared to sinus beats was extracted (e.g. ∆PP and ∆PEP) and used to predict fluid responsiveness of subsequent volume expansions which was determined by receiver operating characteristic (ROC) curves. Ventricular extra systoles were generally useful for fluid responsiveness prediction (ROC areas >0.65). ∆PEP variables best predicted fluid responsiveness: ∆PEP derived from arterial pressure curve and ECG had ROC area of 0.84 and sensitivity of 0.77 and specificity of 0.71; ∆PEP derived from plethysmographic curve and ECG had ROC area of 0.79 and sensitivity of 0.71 and specificity of 0.70. However, ∆PP was not a useful variable in this study (ROC area <0.65). Hemodynamic analysis of post ectopic beats may be a feasible method for fluid responsiveness prediction.