Machine-learning-based approach for predicting response to anti-calcitonin gene-related peptide (CGRP) receptor or ligand antibody treatment in patients with migraine: A multicenter Spanish study.

BACKGROUND AND PURPOSE: Several variables have been reported to be associated with anti-calcitonin gene-related peptide (CGRP) receptor or ligand antibody response, but with differing results. Our objective was to determine whether machine-learning (ML)-based models can predict 6-, 9- and 12-month responses to anti-CGRP receptor or ligand therapies among migraine patients. METHODS: We performed a multicenter analysis of prospectively collected data from patients with migraine receiving anti-CGRP therapies. Demographic and clinical variables were collected. Response rates in the 30% to 50% range, or at least 30%, in the 50% to 75% range, or at least 50%, and response rate of at least 75% regarding the reduction in the number of headache days per month at 6, 9 and 12 months were calculated. A sequential forward feature selector was used for variable selection and ML-based predictive models for the response to anti-CGRP therapies at 6, 9 and 12 months, with model accuracy not less than 70%, were generated. RESULTS: A total of 712 patients were included, 93% were women, and the mean (SD) age was 48 (11.6) years. Eighty-four percent of patients had chronic migraine. ML-based models using headache days/month, migraine days/month and the Headache Impact Test (HIT-6) yielded predictions with an F1 score range of 0.70-0.97 and an area under the receiver-operating curve score range of 0.87-0.98. SHAP (SHapley Additive exPlanations) summary plots and dependence plots were generated to evaluate the relevance of the factors associated with the prediction of the above-mentioned response rates. CONCLUSIONS: Our results show that ML models can predict anti-CGRP response at 6, 9 and 12 months. This study provides a predictive tool that can be used in a real-world setting.

MAB-MIG: registry of the spanish neurological society of erenumab for migraine prevention.

BACKGROUND: Erenumab was approved in Europe for migraine prevention in patients with ≥ 4 monthly migraine days (MMDs). In Spain, Novartis started a personalized managed access program, which allowed free access to erenumab before official reimbursement. The Spanish Neurological Society started a prospective registry to evaluate real-world effectiveness and tolerability, and all Spanish headache experts were invited to participate. We present their first results. METHODS: Patients fulfilled the ICHD-3 criteria for migraine and had ≥ 4 MMDs. Sociodemographic and clinical data were registered as well as MMDs, monthly headache days, MHDs, prior and concomitant preventive treatment, medication overuse headache (MOH), migraine evolution, adverse events, and patient-reported outcomes (PROs): headache impact test (HIT-6), migraine disability assessment questionnaire (MIDAS), and patient global improvement change (PGIC). A > 50% reduction of MMDs after 12 weeks was considered as a response. RESULTS: We included 210 patients (female 86.7%, mean age 46.4 years old) from 22 Spanish hospitals from February 2019 to June 2020. Most patients (89.5%) suffered from chronic migraine with a mean evolution of 8.6 years. MOH was present in 70% of patients, and 17.1% had migraine with aura. Patients had failed a mean of 7.8 preventive treatments at baseline (botulinum toxin type A-BoNT/A-had been used by 95.2% of patients). Most patients (67.6%) started with erenumab 70 mg. Sixty-one percent of patients were also simultaneously taking oral preventive drugs and 27.6% were getting simultaneous BoNT/A. Responder rate was 37.1% and the mean reduction of MMDs and MHDs was -6.28 and -8.6, respectively. Changes in PROs were: MIDAS: -35 points, HIT-6: -11.6 points, PIGC: 4.7 points. Predictors of good response were prior HIT-6 score < 80 points (p = 0.01), ≤ 5 prior preventive treatment failures (p = 0.026), absence of MOH (p = 0.039), and simultaneous BoNT/A treatment (p < 0.001). Twenty percent of patients had an adverse event, but only two of them were severe (0.9%), which led to treatment discontinuation. Mild constipation was the most frequent adverse event (8.1%). CONCLUSIONS: In real-life, in a personalized managed access program, erenumab shows a good effectiveness profile and an excellent tolerability in migraine prevention in our cohort of refractory patients.