A machine learning approach: predicted brain age gaps correlate with financial literacy
Poster No:
939
Submission Type:
Late-Breaking Abstract Submission
Authors:
Nicolas Lok1, Junhong Yu2
Institutions:
1Nanyang Technological University, Singapore, Singapore, 2Nanyang Technological University, Singapore, NA
First Author:
Co-Author:
Introduction:
Past studies have shown that aging is associated with a decline in performance across a wide range of cognitive domains (Park et al., 2003). Two widely researched domains are executive functioning and memory, whereby older adults tend to show a decline in their abilities to retain or manipulate information to meet task demands (Saikia & Tripathi, 2024). This decline is thought to be linked to structural and functional changes in the brain, particularly in areas responsible for working memory, decision-making, and problem-solving (Lacreuse et al., 2020).
Previous brain studies on financial literacy have concluded that it involves the storage and adaptation of conceptual knowledge relating to numbers and arithmetic operations (Han et al., 2014; Sherod et al., 2009). This suggests that financial literacy, much like other cognitive skills, could potentially deteriorate with age due to an underlying decline in both executive functioning and memory. However, existing research has predominantly focused on comparisons across the dementia spectrum, with little emphasis on its relation to general ageing (Griffith et al., 2010; Tolbert et al., 2019). Consequently, the current study aims to elucidate this research gap by examining the relationship between financial literacy and predicted brain age gap.
Previous brain studies on financial literacy have concluded that it involves the storage and adaptation of conceptual knowledge relating to numbers and arithmetic operations (Han et al., 2014; Sherod et al., 2009). This suggests that financial literacy, much like other cognitive skills, could potentially deteriorate with age due to an underlying decline in both executive functioning and memory. However, existing research has predominantly focused on comparisons across the dementia spectrum, with little emphasis on its relation to general ageing (Griffith et al., 2010; Tolbert et al., 2019). Consequently, the current study aims to elucidate this research gap by examining the relationship between financial literacy and predicted brain age gap.
Methods:
We trained a Support Vector Machine (SVM) with a radial basis function using whole-brain resting-state scans acquired from 248 healthy subjects from the Cambridge Centre for Ageing and Neuroscience (Cam-CAN) database (mean age = 70.3, SD = 9.15). The model was validated and used to predict brain age in the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset consisting of 489 older adults (mean age = 72.6, SD = 7.57). The predicted brain age gaps underwent bias correction using Beheshti et al.'s method (2019). We then tested associations between brain age gap and the Financial Capacity Instrument (FCI; Marson et al., 2017). The process was repeated for each of the seven intrinsic networks, as well as for subcortical connectivity.
Results:
We predicted chronological age using whole-brain connectivity (mean absolute error = 6.02 years, 1.40 bias adjusted), as well as with connectivity derived from each of the parcellated regions (mean absolute error range = 5.97 – 6.32 years, 1.26 – 2.11 bias adjusted). After controlling for age, whole-brain-predicted brain age gap was negatively associated with FCI score (β = -0.20; 95% CI, -0.10 to -0.30). Likewise, a smaller brain age gap predicted higher financial conceptual knowledge (β = -0.17; 95% CI, -0.08 to -0.27) and better cheque book (β = -0.18; 95% CI, -0.08 to -0.27) and bank statement management (β = -0.20; 95% CI, -0.10 to -0.30). In contrast, participants with lower brain age gaps completed financial tasks more quickly (β = 0.16; 95% CI, -0.06 to 0.27). Similar patterns were observed between FCI variables and brain age gaps derived from regional connectivity.
Conclusions:
Findings from the current study suggest that higher financial literacy is associated with a slower decline in brain health, indicating a potential protective mechanism against ageing-related neurodegeneration. Additionally, the study revealed that financial literacy is linked to nearly all intrinsic brain networks, underscoring the role of global brain connectivity in managing financial tasks. This suggests that financial literacy engages widespread neural systems supporting multiple cognitive domains, including executive function, memory, and attention.
Higher Cognitive Functions:
Executive Function, Cognitive Control and Decision Making
Lifespan Development:
Aging 1
Modeling and Analysis Methods:
Task-Independent and Resting-State Analysis 2
Novel Imaging Acquisition Methods:
BOLD fMRI
Keywords:
ADULTS
Aging
Cognition
Computational Neuroscience
FUNCTIONAL MRI
Machine Learning
Other - Financial literacy
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.
Griffith, H. R., Stewart, C. C., Stoeckel, L. E., Okonkwo, O. C., den Hollander, J. A., Martin, R. C., Belue, K., Copeland, J. N., Harrell, L. E., Brockington, J. C., Clark, D. G., & Marson, D. C. (2010). Mri volume of the angular gyri predicts financial skill deficits in patients with amnestic mild cognitive impairment. Journal of the American Geriatrics Society, 58(2), 265–274.
Han, S. D., Boyle, P. A., Yu, L., Fleischman, D. A., Arfanakis, K., Leurgans, S., & Bennett, D. A. (2014). Financial literacy is associated with medial brain region functional connectivity in old age. Archives of Gerontology and Geriatrics, 59(2), 429–438.
Lacreuse, A., Raz, N., Schmidtke, D., Hopkins, W. D., & Herndon, J. G. (2020). Age-related decline in executive function as a hallmark of cognitive ageing in primates: An overview of cognitive and neurobiological studies. Philosophical Transactions of the Royal Society B: Biological Sciences, 375(1811), 20190618.
Marson, D., Triebel, K. L., Gerstenecker, A., Martin, R. C., Edwards, K., Pankratz, V. S., Swenson-Dravis, D., & Petersen, R. C. (2017). Financial capacity instrument—Short form [Dataset].
Park, H. L., O’Connell, J. E., & Thomson, R. G. (2003). A systematic review of cognitive decline in the general elderly population. International Journal of Geriatric Psychiatry, 18(12), 1121–1134.
Saikia, B., & Tripathi, R. (2024). Executive functions, processing speed, and memory performance: Untangling the age-related effects. Journal of Psychiatry Spectrum, 3(1), 12–19.
Sherod, M. G., Griffith, H. R., Copeland, J., Belue, K., Krzywanski, S., Zamrini, E. Y., Harrell, L. E., Clark, D. G., Brockington, J. C., Powers, R. E., & Marson, D. C. (2009). Neurocognitive predictors of financial capacity across the dementia spectrum: Normal aging, mild cognitive impairment, and Alzheimer’s disease. Journal of the International Neuropsychological Society, 15(2), 258–267.
Tolbert, S., Liu, Y., Hellegers, C., Petrella, J. R., Weiner, M. W., Wong, T. Z., Doraiswamy, P. M., & ADNI Study Group. (2019). Financial management skills in aging, mci and dementia: Cross sectional relationship to 18f-florbetapir pet cortical β-amyloid deposition. The Journal of Prevention of Alzheimer’s Disease, 6(4), 274–282.