Multi-modality neuroimaging brain-age in UK Biobank: relationship to biomedical, lifestyle and cognitive factors

Cole, James R.

doi:10.1101/812982

Cited by 29 publications

(44 citation statements)

References 35 publications

(38 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The inclusion of multiple brain age models can be informative in patient groups where tissue types are differently affected by disease (56, 57, 76-78), leading to varying brain age predic-tions across models. However, such models could be more closely related in healthy samples (55) such as the current cohort, which aligns with the relatively consistent results observed across models (see Figure 1).…”

Section: Discussionsupporting

confidence: 87%

Women’s brain aging: effects of sex-hormone exposure, pregnancies, and genetic risk for Alzheimer’s disease

A-M.

Barth

Kaufmann

et al. 2019

Preprint

View full text Add to dashboard Cite

Estrogen exposure may influence women's risk of Alzheimer's disease, but little is known about how it affects normal brain aging. Recent findings from the UK Biobank demonstrate less evidence of brain aging in women with a history of multiple childbirths. Here, we investigated the link between brain aging, estrogen exposure, and APOE genotype beyond the effects of parity in 16,854 UK Biobank women. Machine learning was used to predict brain age based on neuroimaging-derived measures, and the difference between an individual's predicted and chronological age was used as an estimate of brain aging. Cumulative estrogen exposure was estimated using an index including age at menarche and menopause, BMI, time since menopause, and duration of hormone replacement therapy. Endogenous hormone exposure was approximated by reproductive span, while exogenous exposure was estimated by usage, onset, and duration of hormone replacement therapy and oral contraceptives. Higher cumulative, endogenous, and exogenous estrogen exposure were each linked to higher brain age relative to chronological age. Earlier onset of hormone replacement therapy, particularly before menopause, was associated with less evident brain aging in APOE e4 carriers only, while higher circulating estradiol levels during menopause were linked to more evident brain aging in carriers and less evident brain aging in non-carriers. The results indicate that estrogen exposure and parity may differentially relate to women's brain aging, and that APOE e4-specific associations between estrogen and brain aging may be of importance for optimizing hormone replacement therapy regimes in perimenopausal women. Women's health | Estrogens | Parity | Apolipoproteins E | Neuroimaging | Machine learningCorrespondence: a.m.g.d.lange@psykologi.uio.no claudia.barth@medisin.uio.no

show abstract

“…Although previous studies have suggested better prediction with multiple imaging modalities [13,14,30,54], the current study showed equivalent prediction accuracy between the multimodal model and the gray and white matter models. The exclusion of low-quality data improved the performance of the multimodal model, suggesting that established procedures for data quality control may have implications for model performance [39,55].…”

Section: Discussioncontrasting

confidence: 75%

“…To obtain a direct comparison of β values, both the brain-age deltas and the clinical variables were standardized (subtracting the mean and dividing by the SD) before a series of multiple regressions were run. In order to adjust for a frequently observed bias in brain-age prediction leading to an overestimation of brain age in younger subjects and an underestimation of brain age in older subjects [14,15,30,51,52], chronological age was included as a covariate. Correction for multiple comparisons was performed using false-discovery rate correction [53].…”

Section: Brain Age Delta and Biomedical Measuresmentioning

confidence: 99%

“…Figure 4 shows the correlations between the multimodal and modality-specific brain-age deltas. The delta values were first corrected for age-bias [14,15,30,51,52] using linear models, and the residuals were used in the correlation analyses. Excluding low-quality data improved the multimodal model (z = 2.07, p = 0.04), but none of the other models, as shown in Table 4 Figure 2: The association between predicted and chronological age for each of the models is shown by the red line.…”

Section: Brain Age Delta and Biomedical Measuresmentioning

confidence: 99%

“…their estimated brain age is older than what is expected for their chronological age [11]. Individual variation in delta estimations are associated with a range of cognitive and biological measures [10,11,12,13,14,15,16,17], including cardiovascular health [14], and differences in brain age have been established between patient groups and healthy controls: individuals with conditions such as Alzheimer's disease, multiple sclerosis, epilepsy, and psychiatric disorders show on average older brain age relative to their chronological age [9,18,19,20,21,22]. Longitudinal studies have documented highly reliable brain age prediction in stroke patients [23], and accelerated brain aging in patients with schizophrenia and multiple sclerosis [21,24,25].…”

Section: Introductionmentioning

confidence: 98%

See 2 more Smart Citations

Multimodal brain-age prediction and cardiovascular risk: The Whitehall II MRI sub-study

Lange

Anatürk

Kaufmann

et al. 2020

Preprint

View full text Add to dashboard Cite

Brain age is becoming a widely applied imaging-based biomarker of neural aging and potential proxy for brain integrity and health. We estimated multimodal and modality-specific brain age in the Whitehall II MRI cohort using machine learning and imaging-derived measures of gray matter morphology, diffusion-based white matter microstructure, and resting state functional connectivity. Ten-fold cross validation yielded multimodal and modality-specific brain age estimates for each participant, and additional predictions based on a separate training sample was included for comparison. The results showed equivalent age prediction accuracy between the multimodal model and the gray and white matter models (R 2 of 0.34, 0.31, and 0.31, respectively), while the functional connectivity model showed a lower prediction accuracy (R 2 of 0.01). Cardiovascular risk factors, including high blood pressure, alcohol intake, and stroke risk score, were each associated with more apparent brain aging, with consistent associations across modalities.

show abstract

Multi-modality neuroimaging brain-age in UK Biobank: relationship to biomedical, lifestyle and cognitive factors

Cited by 29 publications

References 35 publications

Women’s brain aging: effects of sex-hormone exposure, pregnancies, and genetic risk for Alzheimer’s disease

Multimodal brain-age prediction and cardiovascular risk: The Whitehall II MRI sub-study

Contact Info

Product

Resources

About