Brain Age from the Electroencephalogram of Sleep

TL;DR

This study develops an interpretable machine learning model to estimate brain age from sleep EEG data, revealing its potential as a biomarker for healthy brain aging and deviations due to diseases.

Contribution

The paper introduces a novel interpretable model for predicting brain age from sleep EEG, validated on large datasets, and demonstrates its relevance for assessing brain health and aging.

Findings

Mean absolute deviation of 8.1 years in healthy participants

Longitudinal analysis shows a 5.5-year difference in brain age over 5 years

Older brain age associated with neurological, psychiatric, and metabolic conditions

Abstract

The human electroencephalogram (EEG) of sleep undergoes profound changes with age. These changes can be conceptualized as "brain age", which can be compared to an age norm to reflect the deviation from normal aging process. Here, we develop an interpretable machine learning model to predict brain age based on two large sleep EEG datasets: the Massachusetts General Hospital sleep lab dataset (MGH, N = 2,621) covering age 18 to 80; and the Sleep Hearth Health Study (SHHS, N = 3,520) covering age 40 to 80. The model obtains a mean absolute deviation of 8.1 years between brain age and chronological age in the healthy participants in the MGH dataset. As validation, we analyze a subset of SHHS containing longitudinal EEGs 5 years apart, which shows a 5.5 years difference in brain age. Participants with neurological and psychiatric diseases, as well as diabetes and hypertension medications show an older brain age compared to chronological age. The findings raise the prospect of using sleep EEG as a biomarker for healthy brain aging.