Abstract

Abstract Background Often chronological age is not the most accurate marker of an individual’s health status since ageing is a heterogeneous process across individuals. Machine learning can be used to quantify the relationship between structural brain MRI data and chronological age, to estimate an individual’s ‘brain age’, which, when subtracted from chronological age, provides a brain predicted-age difference score (BrainPAD) [1]. BrainPAD reflects the biological ageing of the brain. Increased complexity in neurovascular signals has been shown to be associated with poorer cognitive performance and physical frailty [2]. The aim of this study was to investigate associations between the complexity of frontal-lobe oxygenation (tissue saturation index (TSI)) data and BrainPAD in a cohort of older community-dwelling adults. Methods To calculate BrainPAD, machine learning was applied to 1,359 T1-weighted MRI brain scans from various open-access repositories, and this model was subsequently applied to MRI data acquired from the study cohort. TSI was non-invasively measured in the left frontal lobe using near-infrared spectroscopy. TSI data were acquired continuously during five minutes of supine rest and the last minute was utilized in this analysis. The complexity of TSI signals was quantified using sample entropy (SampEn). Multivariable linear regression was employed, controlling for age, sex, education, antihypertensive medications, diabetes, cardiovascular conditions, smoking, alcohol, depression, BMI, physical activity, and blood pressure. Results Complete data were available for 397 individuals (age: 67.9 ± 7.7 years; 53.7% female). An increase in TSI SampEn of 0.1 was associated with an increase in BrainPAD of 0.9 years (P = 0.007, 95%CIs: 0.3 to 1.6). Similar results were found with and without the inclusion of chronological age in the models. Conclusion This study reports significant associations between higher complexity in peripherally measured frontal lobe oxygenation concentration and accelerated brain ageing.

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.