Artifact detection and localization in single-channel mobile EEG for sleep research using deep learning and attention mechanisms

Artifacts in the electroencephalogram (EEG) degrade signal quality and impact the analysis of brain activity. Current methods for detecting artifacts in sleep EEG rely on simple threshold-based algorithms that require manual intervention, which is time-consuming and impractical due to the vast volume of data that novel mobile recording systems generate. We propose a convolutional neural network (CNN) model incorporating a convolutional block attention module (CNN-CBAM) to detect and identify the location of artifacts in the sleep EEG with attention maps. We benchmarked this model against six other machine learning and signal processing approaches. We trained/tuned all models on 72 manually annotated EEG recordings obtained during home-based monitoring from 18 healthy participants with a mean (SD) age of 68.05 y ($\pm$5.02). We tested them on 26 separate recordings from 6 healthy participants with a mean (SD) age of 68.33 y ($\pm$4.08), with contained artifacts in 4\% of epochs. CNN-CBAM achieved the highest area under the receiver operating characteristic curve (0.88), sensitivity (0.81), and specificity (0.86) when compared to the other approaches. The attention maps from CNN-CBAM localized artifacts within the epoch with a sensitivity of 0.71 and specificity of 0.67. This work demonstrates the feasibility of automating the detection and localization of artifacts in wearable sleep EEG.

Benchmarking real-time algorithms for in-phase auditory stimulation of low amplitude slow waves with wearable EEG devices during sleep

Auditory stimulation of EEG slow waves (SW) during non-rapid eye movement (NREM) sleep has shown to improve cognitive function when it is delivered at the up-phase of SW. SW enhancement is particularly desirable in subjects with low-amplitude SW such as older adults or patients suffering from neurodegeneration such as Parkinson disease (PD). However, existing algorithms to estimate the up-phase suffer from a poor phase accuracy at low EEG amplitudes and when SW frequencies are not constant. We introduce two novel algorithms for real-time EEG phase estimation on autonomous wearable devices. The algorithms were based on a phase-locked loop (PLL) and, for the first time, a phase vocoder (PV). We compared these phase tracking algorithms with a simple amplitude threshold approach. The optimized algorithms were benchmarked for phase accuracy, the capacity to estimate phase at SW amplitudes between 20 and 60 microV, and SW frequencies above 1 Hz on 324 recordings from healthy older adults and PD patients. Furthermore, the algorithms were implemented on a wearable device and the computational efficiency and the performance was evaluated on simulated sleep EEG, as well as prospectively during a recording with a PD patient. All three algorithms delivered more than 70% of the stimulation triggers during the SW up-phase. The PV showed the highest capacity on targeting low-amplitude SW and SW with frequencies above 1 Hz. The testing on real-time hardware revealed that both PV and PLL have marginal impact on microcontroller load, while the efficiency of the PV was 4% lower than the PLL. Active auditory stimulation did not influence the phase tracking. This work demonstrated that phase-accurate auditory stimulation can be delivered during home-based sleep interventions with a wearable device also in populations with low-amplitude SW.