Cross-Sectional and Longitudinal MRI Brain Scans Reveal Accelerated Brain Aging in Multiple Sclerosis

Area of Science:

• Neuroimaging
• Machine Learning
• Neurology

Background:

• Multiple Sclerosis (MS) is a central nervous system inflammatory disorder.
• Understanding the relationship between brain aging and MS progression is crucial for patient management.
• Machine learning-based brain age estimation offers a novel approach to quantify brain aging.

Purpose of the Study:

• To test if Multiple Sclerosis (MS) patients have a higher brain age than healthy controls (HC).
• To investigate if the rate of brain aging in MS patients correlates with disease severity and clinical course.
• To evaluate the utility of brain age gap (BAG) as a biomarker for MS.

Main Methods:

• Longitudinal MRI-based brain morphometry and brain age estimation using a machine learning model.
• Comparison of brain age gap (BAG) between 76 MS patients and 235 HC.
• Assessment of the longitudinal change rate in BAG in MS patients over a mean follow-up of 4.4 years.

Main Results:

• MS patients demonstrated a significantly higher BAG (4.4 ± 6.6 years) compared to HC (p = 4.0 × 10^-6).
• Longitudinal analysis revealed an accelerated rate of brain aging in MS patients (0.41 years/year, p = 0.008).
• Accelerated brain aging in MS was associated with increased brain atrophy (Cohen's D = 0.86) and white matter lesion load (WMLL) (Cohen's D = 0.55).

Conclusions:

• MS patients exhibit significantly higher brain age compared to healthy individuals.
• Progressive brain aging in MS is linked to brain atrophy and increased WMLL.
• Brain age estimation is a promising tool for evaluating subtle brain changes in MS and potentially predicting clinical outcomes.