A 1D Convolutional Neural Network trained on weakly supervised Ballistocardiography signals achieved an estimated 77.7% accuracy for sleep apnea detection against clinical ground truth.
Does a 1D Convolutional Neural Network using non-invasive Ballistocardiography signals accurately detect sleep apnea?
A weakly supervised CNN using non-invasive ballistocardiography can detect sleep apnea with 77.7% estimated accuracy, potentially reducing the need for resource-intensive polysomnography.
The clinical diagnosis of sleep apnea conventionally necessitates resource-intensive Polysomnography (PSG). We propose a weakly supervised framework to detect apnea using non-invasive Ballistocardiography (BCG), thereby addressing the critical scarcity of labeled BCG data. Instead of manual annotation, our pipeline transfers knowledge from a synchronized ECG signal, using it as a “teacher” to generate pseudo-labels for the BCG model. We formulated a User-Defined Function (UDF) that combines Heart Rate Variability and ECG-Derived Respiration to autonomously label the BCG windows. These pseudo-labels were subsequently employed to train a 1D Convolutional Neural Network. Testing on a public dataset, the CNN model achieved 71.8% accuracy against the pseudo-labels. When projected against the clinical ground truth, we estimate a true accuracy of 77.7%. These results validate that ECG-based supervision can effectively train low-cost home sensors without the bottleneck of manual medical annotation.
Sivo et al. (Sun,) conducted a other in Sleep apnea. 1D Convolutional Neural Network using Ballistocardiography vs. Clinical ground truth was evaluated on Accuracy against clinical ground truth. A 1D Convolutional Neural Network trained on weakly supervised Ballistocardiography signals achieved an estimated 77.7% accuracy for sleep apnea detection against clinical ground truth.