Key result
An automatic atrial fibrillation detection method based on non-contact ballistocardiogram signals achieved an average accuracy of 96.1%, precision of 96.5%, recall of 97.3%, and F1 score of 96.9%.
Why the study?
AF is one of the most common cardiac arrhythmias worldwide, making the development of early screening methods crucial.
Does an automatic detection method based on non-contact ballistocardiogram (BCG) signals accurately detect atrial fibrillation during sleep?
Does an automatic detection method based on non-contact ballistocardiogram (BCG) signals accurately detect atrial fibrillation during sleep?
An automatic detection method using non-contact ballistocardiogram signals from bed-mounted sensors demonstrated high accuracy (>96%) in detecting atrial fibrillation during sleep.
May support contactless AF detection during sleep; leaves open need for larger prospective validation before clinical adoption.
Atrial fibrillation (AF) is one of the most common cardiac arrhythmias worldwide, posing a significant threat to patients’ health and a heavy burden to national economy. Developing early screening methods for AF is crucial. Thus, an automatic AF detection method based on non-contact ballistocardiogram (BCG) signals collected from unobtrusive bed-mounted sensors was proposed. BCG signals from 50 subjects during their sleep were collected, which were divided into non-overlapping 30-second segments, including 12,311 AF segments and 9,940 sinus rhythm (SR) segments. After signal preprocessing, the autocorrelation transformation and energy signal transformation for data augmentation were implemented, followed by random kernels convolution. Dual pooling methods including maximum value and proportion of positive value (PPV) were employed to extract features afterward. A logistic regression classifier distinguished AF from SR, with model generalizability rigorously validated through five-fold cross-validation and inter-subject testing. The AF detection achieved the average precision, recall, F1 score, and accuracy of 96.5%, 97.3%, 96.9% and 96.1%, respectively.
No takes yet. Share an insight, caveat, or question.
Zhao et al. (2025) studied Atrial fibrillation (n=50). Automatic AF detection method based on BCG signals was evaluated on AF detection accuracy. An automatic atrial fibrillation detection method based on non-contact ballistocardiogram signals achieved an average accuracy of 96.1%, precision of 96.5%, recall of 97.3%, and F1 score of 96.9%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: