PHILADELPHIA—People with medically refractory focal seizures have brains that appear on MRI about 4.5 years older than their chronological age, according to findings presented at the 69th Annual Meeting of the American Epilepsy Society. Patients with new-onset focal epilepsy, however, do not have a significant difference in their predicted and actual brain age. These findings suggest that “ongoing seizures may be responsible for the brain aging phenomenon observed in this study,” said Heath Pardoe, PhD, Assistant Professor of Neurology at New York University, and colleagues.
The investigators used multivariate analysis of neuroanatomical MRI to predict the age of people with epilepsy, compared with healthy subjects. The investigators stratified subjects with epilepsy into two groups: 45 individuals with new-onset focal epilepsy recruited as part of the Human Epilepsy Project (mean age, 31.47), and 107 individuals with intractable focal epilepsy who were being assessed for surgical resection at the NYU Comprehensive Epilepsy Center (mean age, 32.29). Seventy-nine healthy controls (mean age, 28.92) also were included in the study.
The researchers obtained whole brain T1-weighted MRI on a single scanner using an MPRAGE volumetric acquisition. Each subject’s age was predicted using the PRONTO multivariate machine learning matlab toolbox, with gray matter and white matter segmentations used as input data. The machine learning algorithm was trained to predict ages using healthy control data from publicly available imaging databases. The researchers compared predicted and actual ages in the three groups using a general linear model, with age and sex included as covariates.
Those with intractable epilepsy had a mean 4.5-year difference between predicted brain age and actual age, while those with new-onset epilepsy had a predicted brain age that was not significantly different from their chronological age.
The study highlights the importance of controlling patients’ seizures, Dr. Pardoe said. In addition, the age-prediction technique “could potentially be used to identify individuals with intractable epilepsy early in the course of their disease, and may also be useful for other applications like measuring the protective effect of antiepileptic medication,” he said.
—Jake Remaly
