Do try this at home: Age prediction from sleep and meditation with large-scale low-cost mobile EEG

Abstract

EEG is an established method for quantifying large-scale neuronal dynamics which enables diverse real-world biomedical applications including brain-computer interfaces, epilepsy monitoring and sleep staging. Advances in sensor technology have freed EEG from traditional laboratory settings, making low-cost ambulatory or at-home assessments of brain function possible. While ecologically valid brain assessments are becoming more practical, the impact of their reduced spatial resolution and susceptibility to noise remain to be investigated. This study set out to explore the potential of at-home EEG assessments for biomarker discovery using machine learning with a four-channel consumer EEG headset. We analyzed recordings from more than 5200 human subjects (18-81 years) during meditation and sleep, focusing on the emerging brain age framework as an example of biomarker discovery. With cross-validated R2 scores between 0.3-0.5, prediction performance was within the range of results obtained by recent benchmarks focused on laboratory-grade EEG. While age prediction was successful from both meditation and sleep recordings, the latter led to higher performance. Analysis by sleep stage uncovered that N2-N3 stages contained most of the signal. When combined, EEG features extracted from all sleep stages gave the best performance, suggesting that the entire night of sleep contains valuable age-related information. Furthermore, model comparisons suggested that information was spread out across electrodes and frequencies, supporting the use of multivariate modeling approaches. Thanks to our unique dataset of longitudinal repeat sessions spanning 153 to 529 days from eight subjects, we finally evaluated the variability of EEG-based age predictions, showing that they reflect both trait- and state-like information. Overall, our results demonstrate that state-of-the-art machine learning approaches based on age prediction can be readily applied to real-world EEG recordings obtained during at-home sleep and meditation practice.

Brain-age estimation with a low-cost EEG-headset: effectiveness and implications for large-scale screening and brain optimization

“…Aside from this report, we are aware of only one other study utilizing EEG recordings from a low-cost device for brain-age prediction. Banville et al ( 2023 ) used extended EEG recordings obtained during sleep and meditation, in contrast to our recordings which were obtained during the conscious resting-state. Nevertheless, both studies achieved strong prediction performance suggesting the feasibility of using low-cost EEG devices for monitoring general brain health and aging.…”

“…Engemann et al ( 2022 ) compared various machine-learning and deep-learning methods for brain-age estimation based on a large, combined set of archival EEG recordings (53 EEG channels per recording) and obtained best cross-validated MAE values from 7–8 years and R 2 values up to ~0.75. Most recently, Banville et al ( 2023 ) implemented ML-based brain-age prediction using EEG data collected with a low-cost headset during meditation and sleep and achieved a cross-validated R 2 between 0.3 and 0.5, although with low test-retest reliability over relatively short intervals (i.e., days).…”

Machine learning of brain-specific biomarkers from EEG

“…In this work, the ShallowNet and Riemann benchmarks reached a score around 84% (Table S2 in supplement). This argues for the utility of the generative modeling framework and the covariance-based models derived from it beyond its initial exploration for age prediction and brain age (Banville et al, 2023;Mellot et al, 2023;Sabbagh et al, 2020Sabbagh et al, , 2023.…”