Evaluation of Brain Age on Magnetic Resonance Imaging Using Machine Learning Techniques in Patients With Hearing Loss

Hearing impairment is strongly linked to cognitive decline, with individuals having mild-to-severe hearing loss estimated as having a twofold to fivefold increased risk of all-cause dementia. Given the lack of a cure for dementia, addressing conditions associated with increased dementia risk, like hearing loss, is essential. "Brain age," estimated from magnetic resonance imaging (MRI) scans, has emerged as a promising objective marker of brain health, aging, and dementia risk. This study aimed to evaluate brain age and the brain age gap (BAG) in patients with severe-to-profound hearing loss using MRI and explore correlations between these measures and clinical factors such as age, hearing loss onset, duration of auditory deprivation, and etiology.

Prospective monocentric observational study conducted from January 2021 to September 2024 at a tertiary referral center. Sixty-nine patients aged over 18 with severe-to-profound hearing loss eligible for cochlear implantation were included based on national guidelines. All underwent a three-dimensional T1-weighted brain MRI before implantation to estimate brain MRI age and BAG in patients with severe-to-profound hearing loss.

The cohort included 30 women and 39 men with a mean age of 64.07 ± 14.4 years. The mean estimated brain age was 69.57 ± 6.89 years, resulting in a mean BAG of 5.86 ± 8.94 years, indicating accelerated brain aging. Causes of hearing loss included congenital factors (17 patients), presbycusis (16), otosclerosis (8), trauma (8), chronic otitis (8), Ménière disease (7), sudden sensorineural hearing loss (4), and ototoxicity (2). Estimated brain age and BAG showed statistically significant differences based on patient etiology ( p = 0.04 and p = 0.03, respectively). Significant positive correlations were found between estimated brain age and chronological age ( ρ = 0.87; p < 0.001), hearing loss onset age ( ρ = 0.31; p = 0.01), and age at auditory rehabilitation ( ρ = 0.50; p < 0.001). BAG was negatively correlated with chronological age ( ρ = -0.94; p < 0.001), hearing loss onset age ( ρ = -0.35; p < 0.01), and age at rehabilitation ( ρ = -0.53; p < 0.001).

Patients with severe-to-profound hearing loss had a higher estimated brain age and increased BAG, providing evidence of altered brain aging patterns in adults with hearing loss, which have been associated with increased dementia risk in prior studies. Early-onset hearing loss, prolonged auditory deprivation, and delayed rehabilitation were linked to increased BAG, emphasizing the need for timely intervention to mitigate potential vulnerability associated with altered brain aging patterns.