用于预测抗降钙素基因相关肽单克隆抗体反应的列线图：CGRP评分

A nomogram for the prediction of response to anti-CGRP mAbs: the CGRP score.

作者信息

Romozzi Marina, Lokhandwala Ammar, Vollono Catello, García-Azorín David, Vigani Giulia, De Cesaris Francesco, Altamura Claudia, Vernieri Fabrizio, Calabresi Paolo, Di Tella Sonia, Iannone Luigi Francesco

机构信息

Dipartimento Universitario di Neuroscienze, Università Cattolica del Sacro Cuore, Rome, Italy.

Neurologia, Dipartimento di Neuroscienze, Organi di Senso e Torace, Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Rome, Italy.

出版信息

J Headache Pain. 2025 Sep 1;26(1):190. doi: 10.1186/s10194-025-02138-5.

DOI:10.1186/s10194-025-02138-5

PMID:40890582

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC12403356/

Abstract

INTRODUCTION

Real-world studies have explored potential predictors of response to anti-calcitonin gene related peptide (CGRP) monoclonal antibodies (mAbs), though results have remained inconsistent. Machine learning (ML) algorithms are becoming increasingly relevant in migraine research, offering a data-driven approach to identifying predictors of response to preventive treatments. To maximize their potential, a clinically applicable and user-oriented framework is needed to promote the use of these algorithms in research and, eventually, as supportive tools in clinical practice.

METHODS

This prospective cohort study included adults with migraine treated with anti-CGRP mAbs (anti-ligand and receptor) at two headache centers. Responders were defined as patients achieving ≥ 50% reduction in monthly headache days (MHDs) at 12 months. A logistic regression model was trained (80%) and tested (20%) using 11 baseline variables, including age, sex, migraine subtype, medication overuse, MHDs, and disability scores. Model performance was evaluated using accuracy, precision, recall, and F1-score. A nomogram was created for future research and clinical application. The model was then validated against an external test cohort treated with anti-CGRP mAbs.

RESULTS

Among 429 patients, 310 completed twelve months of treatment, with 236 (55.0%) classified as responders. The external test set included 109 patients. The ML model achieved an overall average weighted F1-score of 70.5% between the two test sets, with good performance in identifying “responders” (precision: 0.75, recall: 0.84, F1-score: 0.79). The model yielded predictions with an overall accuracy of 74% when tested against an external test cohort. Chronic migraine status, older age, and lower baseline MHDs were associated with higher response likelihood. Medication overuse and frequent analgesic use were negatively associated with response. The nomogram provided a clinically interpretable tool to estimate response probability, providing a total score named “CGRP Score” (GRP mAbs lobal esponse rediction).

CONCLUSION

This ML-based predictive score achieved a good performance in identifying responders to anti-CGRP mAbs. The nomogram has the potential to be a practical, user-friendly tool for supporting clinical decision-making after validation.

SUPPLEMENTARY INFORMATION

The online version contains supplementary material available at 10.1186/s10194-025-02138-5.

摘要

引言

真实世界研究已经探索了抗降钙素基因相关肽（CGRP）单克隆抗体（mAb）反应的潜在预测因素，但其结果仍不一致。机器学习（ML）算法在偏头痛研究中变得越来越重要，它提供了一种数据驱动的方法来识别预防性治疗反应的预测因素。为了最大限度地发挥其潜力，需要一个临床适用且以用户为导向的框架，以促进这些算法在研究中的应用，并最终作为临床实践中的支持工具。

方法

这项前瞻性队列研究纳入了在两个头痛中心接受抗CGRP mAb（抗配体和受体）治疗的偏头痛成年患者。反应者定义为在12个月时每月头痛天数（MHD）减少≥50%的患者。使用11个基线变量（包括年龄、性别、偏头痛亚型、药物过度使用、MHD和残疾评分）训练（80%）和测试（20%）逻辑回归模型。使用准确率、精确率、召回率和F1分数评估模型性能。为未来的研究和临床应用创建了列线图。然后根据接受抗CGRP mAb治疗的外部测试队列对该模型进行验证。

结果

在429例患者中，310例完成了12个月的治疗，其中236例（55.0%）被分类为反应者。外部测试集包括109例患者。ML模型在两个测试集之间的总体平均加权F1分数为70.5%，在识别“反应者”方面表现良好（精确率：0.75，召回率：0.84，F1分数：0.79）。当针对外部测试队列进行测试时，该模型的预测总体准确率为74%。慢性偏头痛状态、年龄较大和较低的基线MHD与较高的反应可能性相关。药物过度使用和频繁使用镇痛药与反应呈负相关。列线图提供了一个临床可解释的工具来估计反应概率，提供了一个名为“CGRP评分”（GRP mAbs全球反应预测）的总分。