Blind Separation of Mixed ECG and EEG from Electrophysiological Signal in Hearables

Hearable devices enable continuous monitoring of human electrophysiological signals, including electroencephalogram (EEG) and electrocardiogram (ECG) using in-ear electrodes. However, electrophysiological signals recorded from inside the ear canal are typically a mixture of ECG and EEG. In addition, the contribution of each component may vary substantially across subjects, posing significant challenges in cardiac monitoring. This all calls for a robust method for extracting ear-ECG or ear-EEG from the ear electrical recordings. To this end, we employ the W-Net architecture, a network combining two auto-encoders, for the separation of ECG and EEG from mixed signals recorded from inside the ears. Owing to the subtraction connections between the two auto-encoders within W-net,EEG features at each encoder step are separated from ECG. We further evaluate whether skip and subtraction connections enhance W-Net performance in ECG reconstruction and test across various input signal sizes. The best results (MSE = 0.0036 ± 0.0041) are achieved with a 2,500-sample input. Next, we perform several robustness tests: the generalization in leave-one-subject-out validation, network response to artificial signals and changes in aliased signals. We find that the network is vulnerable to pink noise and that the starting position in overlapping segments affects network's predictions. We showed that this phenomenon can in turn be used as a safety mechanism-the output of the network generated by sliding the input window can provide statistical confidence scores and can be visualized as a confidence plot. While promising for risk mitigation and human oversight, the confidence plot requires further clinical validation with expert cardiologists.