INTRODUCTION: Cognitive decline is a major concern in aging populations. Detecting it before clinical symptoms emerge remains a significant challenge. A precise, reliable, and non-invasive biomarker for cognitive health could revolutionize how we monitor normal aging and lifestyle impacts. Such a tool would not only identify individuals at risk of cognitive decline years before symptoms manifest but also aid in early interventions and treatments. METHODS: Longitudinal MRI data from 121 high cognitive reserve (HCR) individuals were compared to matched low cognitive reserve (LCR) individuals to evaluate four biomarkers for early cognitive decline and disease progression: brain age delta, cortical thickness, AD cortical signature, and hippocampal volume. Cross-sectional analyses were conducted at baseline, alongside longitudinal assessments spanning 1 to 12 years, to compare the performance and properties of these biomarkers. RESULTS: The brain age metric emerged as the most reliable biomarker, demonstrating a significant ability to differentiate between groups at baseline (β = 1.250, t = 3.521, p = 0.0009; linear regression model; AUC = 0.73). Furthermore, this biomarker maintained its robustness as the strongest predictor of group membership over a follow-up period of up to 12 years (β = 0.409, p = 0.025; mixed-effects model), underscoring its potential for longitudinal monitoring of cognitive decline. DISCUSSION: The brain age biomarker demonstrates potential as an effective indicator for early cognitive decline, capable of detecting changes years before clinical symptoms appear and tracking age-related brain and cognitive changes over time. These findings suggest that integrating MRI biomarkers with machine learning approaches could yield more accurate and reliable tools for assessing cognitive health, surpassing the limitations of relying solely on MRI biomarkers.

The authors have declared no competing interest.

This study did not receive any funding

I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.

Yes

The details of the IRB/oversight body that provided approval or exemption for the research described are given below:

Data, Ethical agreements The data used in this study were obtained from ADNI database, as outlined in Section 2. Ethical approval was secured for the ADNI project, and all participants provided written informed consent. Access to ADNI data is available to researchers through a Data Use Agreement (DUA), which ensures adherence to ethical standards, including the protection of participant confidentiality and proper data handling.

I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.

Yes

I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).

Yes

I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable.

Yes

Data, Ethical agreements and Code Availability The data used in this study were obtained from ADNI database, as outlined in Section 2. Ethical approval was secured for the ADNI project, and all participants provided written informed consent. Access to ADNI data is available to researchers through a Data Use Agreement (DUA), which ensures adherence to ethical standards, including the protection of participant confidentiality and proper data handling.