Predicting brain age using partition modeling strategy and atlas-based attentional enhancement in the Chinese population DOI
Yingtong Wu, Yingqian Chen, Yang Yang

et al.

Cerebral Cortex, Journal Year: 2024, Volume and Issue: 34(2)

Published: Jan. 31, 2024

As a biomarker of human brain health during development, age is estimated based on subtle differences in structure from those under typical developmental. Magnetic resonance imaging (MRI) routine diagnostic method neuroimaging. Brain prediction MRI has been widely studied. However, few studies Chinese population have reported. This study aimed to construct predictive model for the across its lifespan. We developed partition transfer learning and atlas attention enhancement. The participants were separated into four groups, deep was trained each group identify regions most critical prediction. Atlas attention-enhancement also used help models focus only regions. proposed validated using 354 domestic datasets. For performance testing sets, mean absolute error 2.218 ± 1.801 years, Pearson correlation coefficient (r) 0.969, exceeding previous results wide-range In conclusion, could provide estimation assist assessing status health.

Language: Английский

Biological brain age prediction using machine learning on structural neuroimaging data: Multi-cohort validation against biomarkers of Alzheimer’s disease and neurodegeneration stratified by sex DOI Creative Commons
Irene Cumplido‐Mayoral,

Marina García‐Prat,

Grégory Operto

et al.

eLife, Journal Year: 2023, Volume and Issue: 12

Published: April 17, 2023

Brain-age can be inferred from structural neuroimaging and compared to chronological age (brain-age delta) as a marker of biological brain aging. Accelerated aging has been found in neurodegenerative disorders like Alzheimer’s disease (AD), but its validation against markers neurodegeneration AD is lacking. Here, imaging-derived measures the UK Biobank dataset (N=22,661) were used predict brain-age 2,314 cognitively unimpaired (CU) individuals at higher risk mild cognitive impaired (MCI) patients four independent cohorts with available biomarker data: ALFA+, ADNI, EPAD, OASIS. delta was associated abnormal amyloid-β, more advanced stages (AT) pathology APOE -ε4 status. positively plasma neurofilament light, neurodegeneration, sex differences effects this found. These results validate non-invasive non-demented levels biomarkers axonal injury.

Language: Английский

Citations

35
A framework of biomarkers for brain aging: a consensus statement by the Aging Biomarker Consortium DOI Creative Commons
Yujuan Jia, Jun Wang,

Jun-Rong Ren

et al.

Life Medicine, Journal Year: 2023, Volume and Issue: 2(3)

Published: May 6, 2023

China and the world are facing severe population aging an increasing burden of age-related diseases. Aging brain causes major diseases, such as neurodegenerative diseases stroke. Identifying biomarkers for effective assessment establishing a system could facilitate development intervention strategies prevention treatment aging-related Thus, experts from Biomarker Consortium (ABC) have combined latest research results practical experience to recommend form expert consensus, aiming provide basis assessing degree conducting brain-aging-related with ultimate goal improving health elderly individuals in both world.

Language: Английский

Citations

32
Positron emission tomography and magnetic resonance imaging methods and datasets within the Dominantly Inherited Alzheimer Network (DIAN) DOI Creative Commons
Nicole S. McKay, Brian A. Gordon, Russ C. Hornbeck

et al.

Nature Neuroscience, Journal Year: 2023, Volume and Issue: 26(8), P. 1449 - 1460

Published: July 10, 2023

Abstract The Dominantly Inherited Alzheimer Network (DIAN) is an international collaboration studying autosomal dominant disease (ADAD). ADAD arises from mutations occurring in three genes. Offspring families have a 50% chance of inheriting their familial mutation, so non-carrier siblings can be recruited for comparisons case–control studies. age onset highly predictable within families, allowing researchers to estimate individual’s point the trajectory. These characteristics allow candidate AD biomarker measurements reliably mapped during preclinical phase. Although represents small proportion cases, understanding neuroimaging-based changes that occur period may provide insight into early stages ‘sporadic’ also. Additionally, this study provides rich data research healthy aging through inclusion controls. Here we introduce neuroimaging dataset collected and describe how resource used by range researchers.

Language: Английский

Citations

31
BrainAGE, brain health, and mental disorders: A systematic review DOI
Johanna Seitz‐Holland, Shalaila S. Haas, Nora Penzel

et al.

Neuroscience & Biobehavioral Reviews, Journal Year: 2024, Volume and Issue: 159, P. 105581 - 105581

Published: Feb. 13, 2024

Language: Английский

Citations

11
Association of biological age with health outcomes and its modifiable factors DOI Creative Commons

Wei‐Shi Liu,

Jia You,

Yi‐Jun Ge

et al.

Aging Cell, Journal Year: 2023, Volume and Issue: 22(12)

Published: Sept. 18, 2023

Abstract Identifying the clinical implications and modifiable unmodifiable factors of aging requires measurement biological age (BA) gap. Leveraging biomedical traits involved with physical measures, biochemical assays, genomic data, cognitive functions from healthy participants in UK Biobank, we establish an integrative BA model consisting multi‐dimensional indicators. Accelerated (age gap >3.2 years) at baseline is associated incident circulatory diseases, related chronic disorders, all‐cause, cause‐specific mortality. We identify 35 for ( p < 4.81 × 10 −4 ), where pulmonary functions, body mass, hand grip strength, basal metabolic rate, estimated glomerular filtration C‐reactive protein show most significant associations. Genetic analyses replicate possible associations between health‐related outcomes further CST3 as essential gene aging, which highly expressed brain immune traits. Our study profiles landscape provides insights into preventive strategies therapeutic targets aging.

Language: Английский

Citations

22
Brain age prediction across the human lifespan using multimodal MRI data DOI
Sihai Guan,

Runzhou Jiang,

Chun Meng

et al.

GeroScience, Journal Year: 2023, Volume and Issue: 46(1), P. 1 - 20

Published: Sept. 21, 2023

Language: Английский

Citations

16
Exercise mitigates age-related metabolic diseases by improving mitochondrial dysfunction DOI
Dandan Jia, Zhenjun Tian, Ru Wang

et al.

Ageing Research Reviews, Journal Year: 2023, Volume and Issue: 91, P. 102087 - 102087

Published: Oct. 11, 2023

Language: Английский

Citations

15
Multi-center brain age prediction via dual-modality fusion convolutional network DOI

Xuebin Chang,

Xiaoyan Jia, Simon B. Eickhoff

et al.

Medical Image Analysis, Journal Year: 2025, Volume and Issue: 101, P. 103455 - 103455

Published: Jan. 10, 2025

Language: Английский

Citations

0
Brain Age Modeling and Cognitive Outcomes in Young Adults With and Without Sickle Cell Anemia DOI Creative Commons
Andria L. Ford, Slim Fellah, Yan Wang

et al.

JAMA Network Open, Journal Year: 2025, Volume and Issue: 8(1), P. e2453669 - e2453669

Published: Jan. 17, 2025

Importance Both sickle cell anemia (SCA) and socioeconomic status have been associated with altered brain structure cognitive disability, yet precise mechanisms underlying these associations are unclear. Objective To determine whether brains of individuals without SCA appear older than chronological age if modeling using gap (BAG) can estimate outcomes mediate the association disease outcomes. Design, Setting, Participants In this cross-sectional study 230 adults SCA, underwent magnetic resonance imaging (MRI) assessment. Brain was estimated DeepBrainNet, a model trained to from 14 468 structural MRIs healthy across lifespan. BAG defined as minus age. Linear regression examined clinical factors ability performance compared neuroimaging metrics health ischemic injury, such normalized whole volume, white matter mean diffusivity (MD), infarct volume. MD were tested further mediators performance. Data analyzed October 15, 2023, July 1, 2024. Exposures economic deprivation measured area index (ADI). Main Outcome Measures Executive function, crystallized processing speed, full-scale intelligence quotient (FSIQ) derived National Institutes Health (NIH) Toolbox Wechsler Abbreviated Scale Intelligence, Second Edition. Results Among included adults, 123 had (median [IQR] age, 26.4 [21.8-34.3] years; 77 female [63%]) 107 did not (control cohort; median 30.1 [26.3-34.8] [72%]). larger (IQR) in control cohort (14.2 [8.0-19.2] vs 7.3 [3.2-11.1] difference, 6.13 95% CI, 4.29-8.05 P &amp;lt; .001). Individuals demonstrated relative reference population (mean 7.52 6.32-8.72 Higher (β [SE] per 1% ADI increase, 0.079 [0.028]; 0.023 0.135; = .006), while intracranial vasculopathy [SE], 6.562 [1.883]; 2.828 10.296; .001) hemoglobin S percentage 0.089 [0.032]; 0.026 0.151; .006) participants SCA. Across health, largest effect size for (eg, executive function: r −0.430; .001), −0.365; cohort. population, mediated β 1-unit decrease ADI, −0.031 [0.014]; −0.061 −0.006), FSIQ: −3.79 [1.42]; −6.87 −1.40) −4.55 [1.82]; −8.14 −0.94) Conclusions Relevance Adults greater suggestive insufficient development, premature aging, or both. estimates may inform between chronic populations, will require confirmation longitudinal studies.

Language: Английский

Citations

0
Cross‐Sectional Comparison of Structural MRI Markers of Impairment in a Diverse Cohort of Older Adults DOI Creative Commons
Julie K. Wisch, Kalen J. Petersen, Peter R Millar

et al.

Human Brain Mapping, Journal Year: 2025, Volume and Issue: 46(2)

Published: Jan. 27, 2025

Neurodegeneration is presumed to be the pathological process measure most proximal clinical symptom onset in Alzheimer Disease (AD). Structural MRI routinely collected research and trial settings. Several quantitative MRI-based measures of atrophy have been proposed, but their low correspondence with each other has previously documented. The purpose this study was identify which commonly used structural (hippocampal volume, cortical thickness AD signature regions, or brain age gap [BAG]) had best Clinical Dementia Rating (CDR) an ethno-racially diverse sample. 2870 individuals recruited by Healthy Aging Brain Study-Health Disparities completed both CDR evaluation. Of these, 1887 were matched on ethno-racial identity (Mexican American [MA], non-Hispanic Black [NHB], White [NHW]) (27% > 0). We estimated using two pipelines (DeepBrainNet, BrainAgeR) then calculated BAG as difference between chronological age. also quantified hippocampal volumes HippoDeep thicknesses (both AD-specific average whole brain) FreeSurfer. ordinal regression evaluate associations neuroimaging test whether these differed groups. Higher (pDeepBrainNet = 0.0002; pBrainAgeR 0.00117) lower volume (p 0.0015) < 0.0001) associated worse status (higher CDR). strongest relationship (AICDeepBrainNet 2623, AICwhole cortex 2588, AICBrainAgeR 2533, AICHippocampus 2293, AICSignature Cortical Thickness 1903). groups for estimates not thickness. interpret lack interaction evidence that effectively captures sources disease-related may differ across racial ethnic association CDR. These results suggest a more sensitive generalizable marker neurodegeneration than cohorts.

Language: Английский

Citations

0