Adaptive beat-to-beat heart rate estimation in ballistocardiograms.

A ballistocardiograph records the mechanical activity of the heart. We present a novel algorithm for the detection of individual heart beats and beat-to-beat interval lengths in ballistocardiograms (BCGs) from healthy subjects. An automatic training step based on unsupervised learning techniques is used to extract the shape of a single heart beat from the BCG. Using the learned parameters, the occurrence of individual heart beats in the signal is detected. A final refinement step improves the accuracy of the estimated beat-to-beat interval lengths. Compared to many existing algorithms, the new approach offers heart rate estimates on a beat-to-beat basis. The agreement of the proposed algorithm with an ECG reference has been evaluated. A relative beat-to-beat interval error of 1.79% with a coverage of 95.94% was achieved on recordings from 16 subjects.

Applying machine learning to detect individual heart beats in ballistocardiograms.

Ballistocardiography is a technique in which the mechanical activity of the heart is recorded. We present a novel algorithm for the detection of individual heart beats in ballistocardiograms (BCGs). In a training step, unsupervised learning techniques are used to identify the shape of a single heart beat in the BCG. The learned parameters are combined with so-called "heart valve components" to detect the occurrence of individual heart beats in the signal. A refinement step improves the accuracy of the estimated beat-to-beat interval lengths. Compared to other algorithms this new approach offers heart rate estimates on a beat-to-beat basis and is designed to cope with arrhythmias. The proposed algorithm has been evaluated in laboratory and home settings for its agreement with an ECG reference. A beat-to-beat interval error of 14.16 ms with a coverage of 96.87% was achieved. Averaged over 10 s long epochs, the mean heart rate error was 0.39 bpm.