ObjectiveTo develop a score system to predict the probability of failure of monotherapy in epilepsy patients with initial treatment, and then provide pillars for early use of polytherapy.MethodsThis is a retrospective analysis of the clinical data of 189 patients with epilepsy treated in Department of Neurology, the Third Xiangya Hospital of Central South University from January 2019 to July 2020. Patients were divided into monotherapy acceptable group and monotherapy poor effect group according to their drug treatment plan and drug efficacy. The influencing factors were screened out by single factor analysis and binary logistic regression analysis. And on the basis of this β value, a quantitative scoring table for predicting the unsatisfying treatment effect of monotherapy is developed. And the receiver operating curve (ROC curve) was used to evaluate the effectiveness of the scale.ResultsBased on a standard of 75% reduction in seizures during the observation period, 138 cases (73%) were effective with monotherapy plan, while 51 cases (23%) were unsatisfactory. Regression analysis showed that multiple forms of seizures, status epilepticus (t2), brain damage, and the number of seizures ≥ 7 times before treatment are independent risk factors for poor outcome of monotherapy. The resulting score sheet has a total score of 12 points; the area under the ROC curve is 0.779, and the critical score is 6 points (sensitivity: 0.314; specificity: 0.957). Patients with more than this score have a strong probability of poor response in monotherapy.ConclusionThis prediction model can effectively assess the risk of unsatisfactory therapeutic effect of monotherapy in epilepsy patients who are initially treated, and thus has reference function for the early selection of polytherapy.