A random forests algorithm achieved a Matthews correlation coefficient of 0.921, mean sensitivity of 0.938, and mean specificity of 0.982 for detecting atrial fibrillation from ballistocardiograms.
Can machine learning algorithms accurately detect atrial fibrillation from cardiac vibration signals (ballistocardiograms) recorded by unobtrusive bedmounted sensors?
Machine learning applied to ballistocardiogram signals from bedmounted sensors can accurately detect atrial fibrillation, offering a potential tool for unobtrusive home monitoring.
We present a study on the feasibility of the automatic detection of atrial fibrillation (AF) from cardiac vibration signals (ballistocardiograms/BCGs) recorded by unobtrusive bedmounted sensors. The proposed system is intended as a screening and monitoring tool in home-healthcare applications and not as a replacement for ECG-based methods used in clinical environments. Based on BCG data recorded in a study with 10 AF patients, we evaluate and rank seven popular machine learning algorithms (naive Bayes, linear and quadratic discriminant analysis, support vector machines, random forests as well as bagged and boosted trees) for their performance in separating 30 s long BCG epochs into one of three classes: sinus rhythm, atrial fibrillation, and artifact. For each algorithm, feature subsets of a set of statistical time-frequency-domain and time-domain features were selected based on the mutual information between features and class labels as well as first- and second-order interactions among features. The classifiers were evaluated on a set of 856 epochs by means of 10-fold cross-validation. The best algorithm (random forests) achieved a Matthews correlation coefficient, mean sensitivity, and mean specificity of 0.921, 0.938, and 0.982, respectively.
Brüser et al. (Tue,) conducted a other in Atrial fibrillation (n=10). Machine learning algorithms on ballistocardiograms was evaluated on Classification performance (separating sinus rhythm, atrial fibrillation, and artifact). A random forests algorithm achieved a Matthews correlation coefficient of 0.921, mean sensitivity of 0.938, and mean specificity of 0.982 for detecting atrial fibrillation from ballistocardiograms.