Functional Brain Age Prediction Reveals Accelerated Aging in Physio-Cognitive Decline Syndrome
Poster No:
889
Submission Type:
Abstract Submission
Authors:
Wan-Ting Hsieh1, Pei-Lin Lee2, Chen-Yuan Kuo3, Chih-Ping Chung2,3, Li-Ning Peng2,4, Liang-Kung Chen2,5, Ching-Po Lin1,2,6, Kun-Hsien Chou7,1
Institutions:
1Institute of Neuroscience, National Yang Ming Chiao Tung University, Taipei, Taiwan, 2Center for Healthy Longevity and Aging Sciences, National Yang Ming Chiao Tung University, Taipei, Taiwan, 3Department of Neurology, Neurological Institute, Taipei Veterans General Hospital, Taipei, Taiwan, 4Center for Geriatric and Gerontology, Taipei Veterans General Hospital, Taipei, Taiwan, 5Taipei Municipal Gan-Dau Hospital (managed by Taipei Veterans General Hospital), Taipei, Taiwan, 6Department of Education and Research, Taipei City Hospital, Taipei, Taiwan, 7Brain research center, National Yang Ming Chiao Tung University, Taipei, Taiwan
First Author:
Co-Author(s):
Pei-Lin Lee
Center for Healthy Longevity and Aging Sciences, National Yang Ming Chiao Tung University
Taipei, Taiwan
Center for Healthy Longevity and Aging Sciences, National Yang Ming Chiao Tung University
Taipei, Taiwan
Chen-Yuan Kuo
Department of Neurology, Neurological Institute, Taipei Veterans General Hospital
Taipei, Taiwan
Department of Neurology, Neurological Institute, Taipei Veterans General Hospital
Taipei, Taiwan
Chih-Ping Chung
Center for Healthy Longevity and Aging Sciences, National Yang Ming Chiao Tung University|Department of Neurology, Neurological Institute, Taipei Veterans General Hospital
Taipei, Taiwan|Taipei, Taiwan
Center for Healthy Longevity and Aging Sciences, National Yang Ming Chiao Tung University|Department of Neurology, Neurological Institute, Taipei Veterans General Hospital
Taipei, Taiwan|Taipei, Taiwan
Li-Ning Peng
Center for Healthy Longevity and Aging Sciences, National Yang Ming Chiao Tung University|Center for Geriatric and Gerontology, Taipei Veterans General Hospital
Taipei, Taiwan|Taipei, Taiwan
Center for Healthy Longevity and Aging Sciences, National Yang Ming Chiao Tung University|Center for Geriatric and Gerontology, Taipei Veterans General Hospital
Taipei, Taiwan|Taipei, Taiwan
Liang-Kung Chen
Center for Healthy Longevity and Aging Sciences, National Yang Ming Chiao Tung University|Taipei Municipal Gan-Dau Hospital (managed by Taipei Veterans General Hospital)
Taipei, Taiwan|Taipei, Taiwan
Center for Healthy Longevity and Aging Sciences, National Yang Ming Chiao Tung University|Taipei Municipal Gan-Dau Hospital (managed by Taipei Veterans General Hospital)
Taipei, Taiwan|Taipei, Taiwan
Ching-Po Lin
Institute of Neuroscience, National Yang Ming Chiao Tung University|Center for Healthy Longevity and Aging Sciences, National Yang Ming Chiao Tung University|Department of Education and Research, Taipei City Hospital
Taipei, Taiwan|Taipei, Taiwan|Taipei, Taiwan
Institute of Neuroscience, National Yang Ming Chiao Tung University|Center for Healthy Longevity and Aging Sciences, National Yang Ming Chiao Tung University|Department of Education and Research, Taipei City Hospital
Taipei, Taiwan|Taipei, Taiwan|Taipei, Taiwan
Kun-Hsien Chou
Brain research center, National Yang Ming Chiao Tung University|Institute of Neuroscience, National Yang Ming Chiao Tung University
Taipei, Taiwan|Taipei, Taiwan
Brain research center, National Yang Ming Chiao Tung University|Institute of Neuroscience, National Yang Ming Chiao Tung University
Taipei, Taiwan|Taipei, Taiwan
Introduction:
Physio-Cognitive Decline Syndrome (PCDS) delineates a critical preclinical state where concurrent motor and cognitive declines precede disability or dementia (Chen et al., 2020). While this syndrome offers a potential window for early intervention, the underlying neurobiological mechanisms remain to be fully elucidated. Recent neuroimaging research has demonstrated accelerated brain aging in PCDS populations through morphometry-based Brain Age prediction approaches [2], highlighting its potential as a biomarker for early detection. However, structural neuroimaging approaches are inherently limited in detecting early-stage neurological changes, as morphological alterations typically emerge in later disease progression. The emergence of functional connectivity analysis offers a promising avenue for detecting subtle neural changes that may precede observable structural alterations. To address this gap, we developed an innovative functional connectivity-based Brain Age prediction model [3], leveraging whole-brain functional connectivity patterns to identify early neurobiological signatures of accelerated aging in PCDS.
Methods:
This study recruited 662 participants (age range: 50–90 years; 315 males, 347 females) for resting-state fMRI (rs-fMRI) using a 3T scanner, with participants categorized into PCDS and Robust groups based on established criteria (Kuo et al., 2023). The brain age model was developed using rs-fMRI data from additional 1,111 healthy individuals (age range: 17–72 years; 489 males, 622 females) across five sites. Theses rs-fMRI data underwent standard preprocessing procedures, followed by brain parcellation into 460 regions of interest (ROIs). Functional connectivity matrices were constructed using Pearson correlations between ROI pairs and Fisher's r-to-z transformation. Our methodological approach incorporated a novel two-stage model, wherein Support Vector Regression with Radial Basis Function kernel first predicted regional brain age by analyzing each ROI's connectivity patterns, followed by Random Forest regression integration for global brain age estimation. Model performance evaluation used Mean Absolute Error (MAE) and R-squared (R²) through 5-fold cross-validation. To assess accelerated aging, we calculated the Brain Age Gap (BAG) between predicted and chronological age. Statistical analysis used ANCOVA model, accounting for age, age², sex, education years, and mean frame-wise displacement, with significance at p<0.05 and FDR correction for regional analyses.
Results:
1. Global Brain Age Analysis (Fig 1):
The functional brain-age prediction model demonstrated robust performance, achieving a MAE of 8.76 years and an R² of 0.70. Group comparison of global BAG revealed a significant accelerated aging in PCDS group, who showed an average of 3.62 years greater than the Robust group (p = 0.0035). Age-stratified analysis uncovered a distinct pattern: participants under 65 years with PCDS exhibited significant accelerated brain aging (p = 0.0075), while no significant BAG difference was observed in those aged 65 and above (p = 0.65).
2. Regional Brain Age Analysis (Fig 2):
The group comparison of regional BAG between the Robust and PCDS groups revealed 45 brain regions with significant difference after FDR correction. These regions were primarily localized within the Default Mode Network (DMN) and Somatomotor Network (SMN).
The functional brain-age prediction model demonstrated robust performance, achieving a MAE of 8.76 years and an R² of 0.70. Group comparison of global BAG revealed a significant accelerated aging in PCDS group, who showed an average of 3.62 years greater than the Robust group (p = 0.0035). Age-stratified analysis uncovered a distinct pattern: participants under 65 years with PCDS exhibited significant accelerated brain aging (p = 0.0075), while no significant BAG difference was observed in those aged 65 and above (p = 0.65).
2. Regional Brain Age Analysis (Fig 2):
The group comparison of regional BAG between the Robust and PCDS groups revealed 45 brain regions with significant difference after FDR correction. These regions were primarily localized within the Default Mode Network (DMN) and Somatomotor Network (SMN).
·Fig. 1: Comparison of the brain-age gap between the Robust and PCDS groups.
·Fig. 2: Regionally significant differences in BAG categorized into networks.
Conclusions:
This study establishes functional brain age as a promising biomarker for detecting accelerated aging in PCDS, particularly effective in adults under 65 years. The observed network-specific alterations, predominantly in the DMN and SMN, provide new insights into the neural substrates underlying PCDS. The functional connectivity-based brain age prediction offers a complementary approach to existing structural measures for understanding accelerated aging patterns. These results lay the groundwork for developing more comprehensive screening tools for PCDS and potentially inform early intervention strategies.
Lifespan Development:
Aging 1
Modeling and Analysis Methods:
Connectivity (eg. functional, effective, structural)
fMRI Connectivity and Network Modeling 2
Novel Imaging Acquisition Methods:
BOLD fMRI
Keywords:
Aging
FUNCTIONAL MRI
Machine Learning
Other - Brain Age
1|2Indicates the priority used for review
Abstract Information
By submitting your proposal, you grant permission for the Organization for Human Brain Mapping (OHBM) to distribute your work in any format, including video, audio print and electronic text through OHBM OnDemand, social media channels, the OHBM website, or other electronic publications and media.
The Open Science Special Interest Group (OSSIG) is introducing a reproducibility challenge for OHBM 2025. This new initiative aims to enhance the reproducibility of scientific results and foster collaborations between labs. Teams will consist of a “source” party and a “reproducing” party, and will be evaluated on the success of their replication, the openness of the source work, and additional deliverables. Click here for more information. Propose your OHBM abstract(s) as source work for future OHBM meetings by selecting one of the following options:
Please indicate below if your study was a "resting state" or "task-activation” study.
Healthy subjects only or patients (note that patient studies may also involve healthy subjects):
Was this research conducted in the United States?
Were any human subjects research approved by the relevant Institutional Review Board or ethics panel? NOTE: Any human subjects studies without IRB approval will be automatically rejected.
Were any animal research approved by the relevant IACUC or other animal research panel? NOTE: Any animal studies without IACUC approval will be automatically rejected.
Please indicate which methods were used in your research:
For human MRI, what field strength scanner do you use?
Which processing packages did you use for your study?
Provide references using APA citation style.
2. Cole, J. H., Poudel, R. P. K., Tsagkrasoulis, D., Caan, M. W. A., Steves, C., Spector, T. D., & Montana, G. (2017). Predicting brain age with deep learning from raw imaging data results in a reliable and heritable biomarker. NeuroImage, 163, 115–124.
3. Kuo, C. Y., Lee, P. L., Peng, L. N., Lee, W. J., Wang, P. N., Chen, L. K., Chou, K. H., Chung, C. P., & Lin, C. P. (2023). Advanced brain age in community-dwelling population with combined physical and cognitive impairments. Neurobiology of aging, 130, 114–123.