2019
DOI: 10.1016/j.neurobiolaging.2018.10.016
|View full text |Cite
|
Sign up to set email alerts
|

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 mo… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

5
86
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
5
2
1

Relationship

1
7

Authors

Journals

citations
Cited by 82 publications
(91 citation statements)
references
References 44 publications
(50 reference statements)
5
86
0
Order By: Relevance
“…This multivariable prediction of age from the EEG enables the estimation of functional brain maturity to within 1-2 weeks of PMA; an accuracy that generalized to an independent validation dataset acquired under a considerably different EEG recording environment. The margin of error is far lower than similar predictions in preterm infants based on functional neuroimaging with fMRI (31), and orders of magnitude lower than what is achieved over later stages of life using EEG or MRI (error margins of 5-10 years) (32)(33)(34). Our findings are also comparable to an array of somatic anatomical methods over similar preterm age ranges based on measures of femur length, head circumference, weight, and structural MRI (cortical folding, thickness) (35)(36)(37)(38).…”
Section: Discussionmentioning
confidence: 79%
“…This multivariable prediction of age from the EEG enables the estimation of functional brain maturity to within 1-2 weeks of PMA; an accuracy that generalized to an independent validation dataset acquired under a considerably different EEG recording environment. The margin of error is far lower than similar predictions in preterm infants based on functional neuroimaging with fMRI (31), and orders of magnitude lower than what is achieved over later stages of life using EEG or MRI (error margins of 5-10 years) (32)(33)(34). Our findings are also comparable to an array of somatic anatomical methods over similar preterm age ranges based on measures of femur length, head circumference, weight, and structural MRI (cortical folding, thickness) (35)(36)(37)(38).…”
Section: Discussionmentioning
confidence: 79%
“…With the latter, the goal is always to improve model prediction, while with the former, improved model prediction may mean that anyone's age can be accurately predicted, but the concept of deviation loses value. Previous research has not always screened for healthy people model training, or at least has not reported that this was the case (Smith, et al, 2019, Sun, et al, 2019. This means that potentially the brain-age difference metrics (i.e., brain-age gap, brainage delta) do not reflect actual deviations from healthy brain ageing and thus may be less sensitive to subsequent relationships with other measures or more prone to false positives.…”
Section: Discussionmentioning
confidence: 99%
“…The metric was associated with neurological or psychiatric disease, plus hypertension and diabetes. Brain age index (defined as the difference between brain age and chronological age) from sleep EEG could be a potential biomarker for healthy brain ageing …”
Section: Enhanced Psg Signal Analysis Methodsmentioning
confidence: 99%
“…The intriguing aspect of this study is that the system used unprocessed EEG signals as training data and the convolutional layers automatically identified useful feature for classification of the micro-events. In another study, a feedforward neural network was used to predict a person's age from the sleep EEG, 30 with deviation from chronological age being used as measure of 'brain age'. The metric was associated with neurological or psychiatric disease, plus hypertension and diabetes.…”
Section: Box 1: Research Agendamentioning
confidence: 99%
See 1 more Smart Citation