No abstract

Background:Mesial temporal lobe epilepsy with hippocampal sclerosis (MTLE-HS) is usually associated with a poor response to antiseizure medications. We focused on MTLE-HS patients who were seizure free on medication to: 1) determine the clinical factors associated with seizure freedom and 2) develop a machine-learning classifier to better earlier identify those patients. Methods:We performed a retrospective, multicentric study comparing 64 medically-treated seizure-free MTLE-HS patients with 200 surgically-treated drug-resistant MTLE-HS patients. First, we collected medical history and seizure semiology data. Then, we developed a machine-learning classifier based on clinical data. Results:Medically-treated seizure-free MTLE-HS patients were seizure-free for at least two years, and for a median time of 7 years at last follow-up. Compared to drug-resistant MTLE-HS patients, they exhibited: an older age at epilepsy onset (22.5 vs 8.0 years, p <0.001), a lesser rate of : febrile seizures (39.0% vs 57.5%, p=0.035), auras (56.7% vs 90.0%, p<0.001), autonomic auras in presence of aura (17.6% vs 59.4%, p<0.001), dystonic posturing of the limbs (9.8% vs 47.0%, p<0.001), gestural (27.4% vs 94.0%, p<0.001), oro-alimentary (32.3% vs 75.5%, p<0.001) or verbal automatisms (12.9% vs 36.0%, p=0.001). The classifier had a positive predictive value of 0.889, a sensitivity of 0.727, a specificity of 0.962, a negative predictive value of 0.893. Conclusions:Medically-treated seizure-free MTLE-HS patients exhibit a distinct clinical profile. A classifier built with readily available clinical data can identify them accurately with excellent positive predictive value. This may help to individualize the management of MTLE-HS patients according to their expected pharmacosensitivity.

No abstract