Feasibility of brain age predictions from clinical T1-weighted MRIs

Valdes-Hernandez, Pedro A.; Laffitte Nodarse, Chavier; Cole, James H.; Cruz-Almeida, Yenisel

doi:10.1016/j.brainresbull.2023.110811

Cited by 3 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We also found that structural brain age estimates were significantly younger in female than male participants, including both ADAD mutation carriers and non-carriers. This finding is consistent with prior observations of sex differences in brain age estimates using metabolic PET [ 26 , 27 ], structural MRI [ 14 , 25 , 29 ], and localized to prefrontal regions [ 28 ]. This result may also be informative on potential sex differences in resilience to AD pathology.…”

Section: Discussionsupporting

confidence: 91%

“…Given prior demonstrations of heterogeneity in pathological burden and age of onset between ADAD mutation variants [ 21 – 24 ], we tested whether brain age estimates captured similar differences in pathological severity. Finally, as prior studies have demonstrated differences in brain aging as a function of sex [ 14 , 25 – 29 ], education [ 30 , 31 ], and APOE genotype [ 32 ], we tested those relationships in this ADAD sample.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Advanced structural brain aging in preclinical autosomal dominant Alzheimer disease

Millar,

Gordon,

Wisch

et al. 2023

Mol Neurodegeneration

View full text Add to dashboard Cite

Background “Brain-predicted age” estimates biological age from complex, nonlinear features in neuroimaging scans. The brain age gap (BAG) between predicted and chronological age is elevated in sporadic Alzheimer disease (AD), but is underexplored in autosomal dominant AD (ADAD), in which AD progression is highly predictable with minimal confounding age-related co-pathology. Methods We modeled BAG in 257 deeply-phenotyped ADAD mutation-carriers and 179 non-carriers from the Dominantly Inherited Alzheimer Network using minimally-processed structural MRI scans. We then tested whether BAG differed as a function of mutation and cognitive status, or estimated years until symptom onset, and whether it was associated with established markers of amyloid (PiB PET, CSF amyloid-β-42/40), phosphorylated tau (CSF and plasma pTau-181), neurodegeneration (CSF and plasma neurofilament-light-chain [NfL]), and cognition (global neuropsychological composite and CDR-sum of boxes). We compared BAG to other MRI measures, and examined heterogeneity in BAG as a function of ADAD mutation variants, APOE ε4 carrier status, sex, and education. Results Advanced brain aging was observed in mutation-carriers approximately 7 years before expected symptom onset, in line with other established structural indicators of atrophy. BAG was moderately associated with amyloid PET and strongly associated with pTau-181, NfL, and cognition in mutation-carriers. Mutation variants, sex, and years of education contributed to variability in BAG. Conclusions We extend prior work using BAG from sporadic AD to ADAD, noting consistent results. BAG associates well with markers of pTau, neurodegeneration, and cognition, but to a lesser extent, amyloid, in ADAD. BAG may capture similar signal to established MRI measures. However, BAG offers unique benefits in simplicity of data processing and interpretation. Thus, results in this unique ADAD cohort with few age-related confounds suggest that brain aging attributable to AD neuropathology can be accurately quantified from minimally-processed MRI.

show abstract

Section: Discussionsupporting

confidence: 91%

mentioning

confidence: 99%

Advanced structural brain aging in preclinical autosomal dominant Alzheimer disease

Millar,

Gordon,

Wisch

et al. 2023

Mol Neurodegeneration

View full text Add to dashboard Cite

show abstract

“…The derived values of α and β are then used to correct predicted age with Corrected Predicted Age = Predicted Age + [Ω − (α × Ω + β)]. The brain age gap, a measure of lag or difference between the chronological age and the predicted brain age [8,60], was also computed. The model performance was measured using the correlation coefficient (r), r-square (R 2 ), Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE).…”

Section: Methodsmentioning

confidence: 99%

Prediction of brain age in individuals with and at risk for alcohol use disorder using brain morphological features

Kamarajan,

Ardekani,

Pandey

et al. 2024

Preprint

View full text Add to dashboard Cite

Brain age measures predicted from structural and functional brain features are increasingly being used to understand brain integrity, disorders, and health. While there is a vast literature showing aberrations in both structural and functional brain measures in individuals with and at risk for alcohol use disorder (AUD), few studies have investigated brain age in these groups. The current study examines brain age measures predicted using brain morphological features, such as cortical thickness and brain volume, in individuals with a lifetime diagnosis of AUD as well as in those at higher risk to develop AUD from families with multiple members affected with AUD (i.e., higher family history density (FHD) scores). The AUD dataset included a group of 30 adult males (mean age = 41.25 years) with a lifetime diagnosis of AUD and currently abstinent and a group of 30 male controls (mean age = 27.24 years) without any history of AUD. A second dataset of young adults who were categorized based on their FHD scores comprised a group of 40 individuals (20 males) with high FHD of AUD (mean age = 25.33 years) and a group of 31 individuals (18 males) with low FHD (mean age = 25.47 years). Brain age was predicted using 187 brain morphological features of cortical thickness and brain volume in an XGBoost regression model; a bias-correction procedure was applied to the predicted brain age. Results showed that both AUD and high FHD individuals showed an increase of 1.70 and 0.09 years (1.08 months), respectively, in their brain age relative to their chronological age, suggesting accelerated brain aging in AUD and risk for AUD. Increased brain age was associated with poor performance on neurocognitive tests of executive functioning in both AUD and high FHD individuals, indicating that brain age can also serve as a proxy for cognitive functioning and brain health. These findings on brain aging in these groups may have important implications for the prevention and treatment of AUD and ensuing cognitive decline.

show abstract

MFCA: Collaborative prediction algorithm of brain age based on multimodal fuzzy feature fusion

Ding,

Wang,

Huang

et al. 2025

Information Sciences

View full text Add to dashboard Cite

Feasibility of brain age predictions from clinical T1-weighted MRIs

Cited by 3 publications

References 26 publications

Advanced structural brain aging in preclinical autosomal dominant Alzheimer disease

Advanced structural brain aging in preclinical autosomal dominant Alzheimer disease

Prediction of brain age in individuals with and at risk for alcohol use disorder using brain morphological features

MFCA: Collaborative prediction algorithm of brain age based on multimodal fuzzy feature fusion

Contact Info

Product

Resources

About