Atrial fibrillation (AF) is the most frequently occurring form of arrhythmia, which induces multiple fatal diseases and impairs the quality of life in patients; thus, the study of the diagnostic methods for detecting AF is clinically important. Here we present a feature extraction method for the detection of AF using a ballistocardiogram (BCG), which is based on a physiological signal database collected by a non-contact sensor. The BCG signals, including both with AF and sinus rhythm (SR), were collected from 37 subjects during overnight sleep (approximately 8 hours). The signals were split into 2915 one-minute segments (AF: 1494, SR: 1421) without overlap and labeled as AF and SR. BCG signals were transformed into BCG energy signals in order to highlight the features of AF and SR BCG signals; and four new data sequences representing different characteristics of the BCG energy signals were generated. The mean value, variance, skewness, and kurtosis of the four data sequences were calculated and 16 features were extracted for each segment. Five machine learning algorithms were used for classification. The results of this study show that the support vector machine (SVM) performed the best among the five tested classifiers and achieved sensitivity, precision, and accuracy of 0.968, 0.928, and 0.945, respectively. These results indicate that the proposed feature extraction method can be well applied to AF and SR classification and may lay foundations for the development of systems for long-term home cardiac monitoring and AF screening.

Atrial fibrillation (AF) is the most common arrhythmia and can seriously threaten patient health. Research on AF detection carries important clinical significance. This manuscript proposes an AF detection method based on ballistocardiogram (BCG) signals collected by a noncontact sensor. We first constructed a BCG signal dataset consisting of 28,214 ten-second nonoverlapping segments collected from 45 inpatients during overnight sleep, including 9438 for AF, 9570 for sinus rhythm (SR), and 9206 for motion artifacts (MA). Then, we designed a residual convolutional neural network (CNN) for AF detection. The network has four modules, namely a downsampling convolutional module, a local feature learning module, a global feature learning module, and a classification module, and it extracts local and global features from BCG signals for AF detection. The model achieved precision, sensitivity, specificity, F1 score, and accuracy of 96.8%, 93.7%, 98.4%, 95.2%, and 96.8%, respectively. The results indicate that the AF detection method proposed in this manuscript could serve as a basis for long-term screening of AF at home based on BCG signal acquisition.

Heartbeat characteristic points are the main features of an electrocardiogram (ECG), which can provide important information for ECG-based cardiac diagnosis. In this manuscript, we propose a self-supervised deep learning framework with modified Densenet to detect ECG characteristic points, including the onset, peak and termination points of P-wave, QRS complex wave and T-wave. We extracted high-level features of ECG heartbeats from the QT Database (QTDB) and two other larger datasets, MIT-BIH Arrhythmia Database (MITDB) and MIT-BIH Normal Sinus Rhythm Database (NSRDB) with no human-annotated labels as pre-training. By applying different transformations to ECG signals, the task of discriminating signals before and after transformation was defined as the pretext task. Subsequently, the convolutional layer was frozen and the weights of the self-supervised network were transferred to the downstream task of characteristic point localizations on heart beats in the QT dataset. Finally, the mean ± standard deviation of the detection errors of our proposed self-supervised learning method in QTDB for detecting the onset, peak, and termination points of P-waves, the onset and termination points of QRS waves, and the peak and termination points of T-waves were −0.24 ± 10.04, −0.48 ± 11.69, −0.28 ± 10.19, −3.72 ± 8.18, −4.12 ± 13.54, −0.68 ± 20.42, and 1.34 ± 21.04. The results show that the deep learning network based on the self-supervised framework constructed in this manuscript can accurately detect the feature points of a heartbeat, laying the foundation for automatic extraction of key information related to ECG-based diagnosis.

Ballistocardiography (BCG) is a type of non-contact measurement technique that measures the mechanical reaction of the body resulting from heart contraction and the subsequent cardiac ejection of blood. Herein, we present an algorithm for beat-to-beat heart rate estimation from BCG signals that is both highly universal and easy to implement. The algorithm is based on the correlation between heartbeats in the same section of BCG. It first generates patterns by autocorre-lation, which are then matched with the remaining signals to determine heartbeats. The agreement of the proposed algorithm with synchronized electrocardiogram has been evaluated, and a relative beat-to-beat interval error of 1.66% and a relative average heart rate error of 1.25% were observed. The proposed algorithm is a promising candidate for a non-contact, long-term cardiac monitoring system at home.