An ordinal clinical score predicts seizure freedom after minimally invasive epilepsy surgery

ObjectiveTo predict one-year seizure freedom, using a combination of relevant clinical variables, following stereotactic laser amygdalohippocampotomy for mesial temporal lobe epilepsy in a series of 101 patients. MethodsEight predictors of seizure freedom were selected based on their association with medial temporal lobe epilepsy: (1) MRI evidence of mesial temporal sclerosis (MTS); (2) unitemporal interictal epileptiform discharges; (3) absence of generalized tonic-clonic seizures; (4) history of febrile seizures; (5) onset of epilepsy <= 16 years; (6) absence of an auditory, visual, or vertiginous aura; and (7) unitemporal ictal onset; (8) unitemporal PET hypometabolism. We compared four multivariate models: "MTS," using just evidence of MTS; "FULL," using all eight binary predictors; "AIC" using backwards selection of variables; and "SCORE," using a 0-to-8-point ordinal score awarding one point for each binary predictor. ResultsIn univariate analysis, significant predictors for seizure freedom were evidence of mesial temporal sclerosis (p = 0.011, Fisher exact) and unitemporal interictal discharges (p = 0.005). For multivariate prediction (using leave one-out cross-validation), the ordinal SCORE model had a significantly higher area under the curve (AUC 0.70) than the other three models: MTS (AUC 0.54, p = 0.002, Delong's test), FULL (AUC 0.62, p = 0.003), or AIC (AUC 0.53, p < 0.001). InterpretationAn ordinal score incorporating eight independent binary clinical variables predicted seizure freedom better on novel data than a model using MTS alone, a full multivariate model, or a backwards selected model. The ordinal score model represents a simple clinical heuristic to identify which patients should be offered minimally invasive laser surgery.