EUVIMEDScopri EUVIMED
ValidierungsstudieOpen access

Development and Validation of a Brain Aging Biomarker in Middle-Aged and Older Adults: Deep Learning Approach

Zihan Li iD, Jun Li iD, Jiahui Li iD, Mengying Wang iD, Andi Xu iD, Yushu Huang iD, Qi Yu iD, Lingzhi Zhang iD, Yingjun Li iD, Zilin Li iD, Xifeng Wu iD, Jiajun Bu iD and 1 more

JMIR Aging · 2025

DOI: 10.2196/73004 ↗

At a glance

Validierungsstudie in JMIR Aging, 2025. Written by Zihan Li and 12 co-authors. Institution: Center for Clinical Big Data and Analytics, The Second Affiliated Hospital and Department of Big Data in Health Science, School of Public Health, Zhe…. Major MEDLINE topics: Deep Learning, Brain, Aging, Cognitive Dysfunction. Cited 2 times so far (Crossref); 76 references. The full text is freely available in PubMed Central.

AbstractSubjectsDati bibliograficiCiteRelated studies

Abstract (original language)

Background

Precise assessment of brain aging is crucial for early detection of neurodegenerative disorders and aiding clinical practice. Existing magnetic resonance imaging (MRI)–based methods excel in this task, but they still have room for improvement in capturing local morphological variations across brain regions and preserving the inherent neurobiological topological structures.

Objective

To develop and validate a deep learning framework incorporating both connectivity and complexity for accurate brain aging estimation, facilitating early identification of neurodegenerative diseases.

Methods

We used 5889 T1-weighted MRI scans from the Alzheimer’s Disease Neuroimaging Initiative dataset. We proposed a novel brain vision graph neural network (BVGN), incorporating neurobiologically informed feature extraction modules and global association mechanisms to provide a sensitive deep learning–based imaging biomarker. Model performance was evaluated using mean absolute error (MAE) against benchmark models, while generalization capability was further validated on an external UK Biobank dataset. We calculated the brain age gap across distinct cognitive states and conducted multiple logistic regressions to compare its discriminative capacity against conventional cognitive-related variables in distinguishing cognitively normal (CN) and mild cognitive impairment (MCI) states. Longitudinal track, Cox regression, and Kaplan-Meier plots were used to investigate the longitudinal performance of the brain age gap.

Results

The BVGN model achieved an MAE of 2.39 years, surpassing current state-of-the-art approaches while obtaining an interpretable saliency map and graph theory supported by medical evidence. Furthermore, its performance was validated on the UK Biobank cohort (N=34,352) with an MAE of 2.49 years. The brain age gap derived from BVGN exhibited significant difference across cognitive states (CN vs MCI vs Alzheimer disease; P

Subjects

MeSH terms (MEDLINE)

Deep LearningBrainAgingCognitive DysfunctionHumansAgedMaleFemaleMagnetic Resonance ImagingMiddle AgedBiomarkersNeuroimagingAlzheimer DiseaseAged, 80 and over

Author keywords

MRIbrain agingdeep learningimaging biomarkermagnetic resonance imaging

Substances

Biomarkers

Authors and institutions

  • Center for Clinical Big Data and Analytics, The Second Affiliated Hospital and Department of Big Data in Health Science, School of Public Health, Zhejiang University School of Medicine, Zhejiang University, Hangzhou, Ch…
  • Department of Radiology, The First Affiliated Hospital, Zhengzhou University, First Affiliated Hospital of Zhengzhou University, Zhengzhou, China.
  • Department of Epidemiology and Health Statistics, School of Public Health, Hangzhou Medical College, Hangzhou Medical College, Hangzhou, China.
  • School of Mathematics and Statistics, Northeast Normal University, Northeast Normal University, Changchun, China.
  • Zhejiang Provincial Key Laboratory of Intelligent Preventive Medicine, Hangzhou, China.
  • Zhejiang Key Laboratory of Accessible Perception and Intelligent Systems, College of Computer Science and Technology, Zhejiang University, Hangzhou, China.

ORCID profiles: Zihan Li, Jun Li, Jiahui Li, Mengying Wang, Andi Xu, Yushu Huang, Qi Yu, Lingzhi Zhang, Yingjun Li, Zilin Li, Xifeng Wu, Jiajun Bu, Wenyuan Li

Cite

APA

Li, Z., Li, J., Li, J., Wang, M., Xu, A., Huang, Y., Yu, Q., Zhang, L., Li, Y., Li, Z., Wu, X., Bu, J., & Li, W. (2025). Development and Validation of a Brain Aging Biomarker in Middle-Aged and Older Adults: Deep Learning Approach. JMIR Aging. https://doi.org/10.2196/73004

Vancouver

Li Z, Li J, Li J, Wang M, Xu A, Huang Y, et al. Development and Validation of a Brain Aging Biomarker in Middle-Aged and Older Adults: Deep Learning Approach. JMIR Aging. 2025. doi:10.2196/73004

BibTeX
@article{Li2025,
  author = {Li, Zihan and Li, Jun and Li, Jiahui and Wang, Mengying and Xu, Andi and Huang, Yushu and Yu, Qi and Zhang, Lingzhi and Li, Yingjun and Li, Zilin and Wu, Xifeng and Bu, Jiajun and Li, Wenyuan},
  title = {Development and Validation of a Brain Aging Biomarker in Middle-Aged and Older Adults: Deep Learning Approach},
  journal = {JMIR Aging},
  year = {2025},
  doi = {10.2196/73004}
}
Start for free →