Key result
Training an atrial fibrillation detection model on standard ECG data and evaluating it on capacitive ECG data achieved an AUC of 0.874, performing better than models trained solely on the noisier capacitive ECG data.
Why the study?
Capacitive ECG enables unobtrusive cardiac monitoring without skin contact, but motion artifacts and environmental factors degrade signal quality, leaving its AF screening performance compared to standard ECG unclear.
Does training machine learning models on standard ECG improve atrial fibrillation detection performance on capacitive ECG (cECG) in patients undergoing unobtrusive monitoring?
Does training machine learning models on standard ECG improve atrial fibrillation detection performance on capacitive ECG (cECG) in patients undergoing unobtrusive monitoring?
Absolute Event Rate: 0.874% vs 0.873%
Training diagnostic algorithms on standard ECG data improves the detection of atrial fibrillation on noisier, non-invasive capacitive ECG signals, facilitating unobtrusive longitudinal monitoring.
May aid unobtrusive cECG AF monitoring; leaves open prospective validation before clinical use.
Unobtrusive collection of vital signs using sensors embedded in beds, chairs, and automobile seats can longitudinally monitor patients for abnormal heart conditions outside of the hospital to inform both preventative and postdiagnosis care. The capacitive electrocardiogram (cECG) shows potential for collecting electrical information about a patient's heart without requiring skin contact like regular electrocardiogram (ECG). However, motion artifacts and environmental factors easily corrupt cECG signal quality and reduce the diagnostic value of unobtrusively collected cECG. To evaluate the atrial fibrillation (AF) screening performance of cECG compared to ECG, we conduct three different experiments on the clinical UnoViS dataset consisting of 55 min of concurrent ECG and cECG signals from 92 patients with manual clinician annotations of AF. First, we trained and evaluated models to detect AF events on cECG and ECG separately. Then, we trained a model using ECG and evaluated it on cECG to measure the interchangeability of the ECG and cECG domains. For each experiment five-fold subjectwise, class-stratified cross-validation was used to assess trained algorithm performance on hold-out test sets and three different algorithmic methodologies were assessed. Although evaluating the trained ECG model on cECG data (AUC: 0.874 ± 0.067,F1-score: 0.553 ± 0.148) performed slightly worse than evaluating on ECG, it did perform better than the model trained and evaluated on cECG alone, which suggests that utilizing ECG data for model training can effectively screen similar conditions in cECG data.
No takes yet. Share an insight, caveat, or question.
Zhang et al. (2023) studied Atrial Fibrillation (n=90). Model trained on standard ECG and evaluated on capacitive ECG (cECG) vs. Model trained and evaluated solely on capacitive ECG (cECG) was evaluated on Area under the receiver operating characteristic curve (AUC) for atrial fibrillation detection. Training an atrial fibrillation detection model on standard ECG data and evaluating it on capacitive ECG data achieved an AUC of 0.874, performing better than models trained solely on the noisier capacitive ECG data.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: