Romozzi Marina, Lokhandwala Ammar, Vollono Catello, Vigani Giulia, Burgalassi Andrea, García-Azorín David, Calabresi Paolo, Chiarugi Alberto, Geppetti Pierangelo, Iannone Luigi Francesco
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.
Cephalalgia. 2024 Dec;44(12):3331024241262751. doi: 10.1177/03331024241262751.
The present study aimed to determine whether machine-learning (ML)-based models can predict 3-, 6, and 12-month responses to the monoclonal antibodies (mAbs) against the calcitonin gene-related peptide (CGRP) or its receptor (anti-CGRPmAbs) in patients with migraine using early predictors (up to one month) and to create an evolving prediction tool.
In this prospective cohort study data from patients with migraine who had received anti-CGRP mAbs for 12 months were collected. Demographic and monthly clinical variables were collected, including monthly headache days (MHDs), days with acute medication use, number of analgesics and Headache Impact Test-6. Response rates were categorized as <25%, 26-50%, 51-75% and >75% reduction in MHDs. ML models were trained using random forest algorithm and optimized to maximize the F1 score. ML model performance was also evaluated using standard evaluation metrics, including accuracy, precision and area under the receiver operating characteristic curve (AUC-ROC). Sequential backward feature selection was employed to identify the most relevant predictors for each model. Each model was given 11 baseline data inputs and month-based predictors for months 1, 3 and 6. Each model was then validated against an external test cohort of patients who had received anti-CGRP mAbs for 12 months.
Three hundred thirty-six patients treated with anti-CGRP mAbs were included. The external cohort included 93 patients treated with anti-CGRP mAbs. We developed six models to predict 3- 6- and 12-month responses using early predictors. ML-based models yielded predictions with an accuracy score in the range 0.40-0.73 and an AUC-ROC score in the range 0.56-0.76 during internal testing and yielding predictions with an accuracy in the range 0.39-0.64 and an AUC-ROC score in the range 0.52-0.78 when tested against an external test cohort. Shapley Additive explanations summary plots were generated to interpret the contribution of each feature for each model. Based on these findings, a response prediction tool was developed. Each model was run through a backward feature selection to find the most relevant features for the models. The MHDs reduction of the previous data point tends to be the most relevant, while the migraine with aura indicator tends to be the least effective predictor.
The response prediction tool utilizing evolving ML-based models holds promise in the early prediction of treatment outcomes for patients with migraine undergoing anti-CGRP mAbs treatment.
本研究旨在确定基于机器学习（ML）的模型能否使用早期预测指标（长达1个月）预测偏头痛患者对降钙素基因相关肽（CGRP）或其受体的单克隆抗体（mAbs）（抗CGRP mAbs）治疗3个月、6个月和12个月时的反应，并创建一个不断发展的预测工具。
在这项前瞻性队列研究中，收集了接受抗CGRP mAbs治疗12个月的偏头痛患者的数据。收集了人口统计学和每月临床变量，包括每月头痛天数（MHDs）、使用急性药物的天数、镇痛药数量和头痛影响测试-6。反应率分为MHDs减少<25%、26-50%、51-75%和>75%。使用随机森林算法训练ML模型，并进行优化以最大化F1分数。还使用标准评估指标评估ML模型的性能，包括准确性、精确性和受试者操作特征曲线下面积（AUC-ROC）。采用顺序向后特征选择来确定每个模型最相关的预测指标。每个模型有11个基线数据输入以及第1、3和6个月基于月份的预测指标。然后针对接受抗CGRP mAbs治疗12个月的外部测试队列患者对每个模型进行验证。
纳入了336例接受抗CGRP mAbs治疗的患者。外部队列包括93例接受抗CGRP mAbs治疗的患者。我们开发了六个模型，使用早期预测指标预测3个月、6个月和12个月时的反应。基于ML的模型在内部测试期间的预测准确率得分在0.40-0.73范围内，AUC-ROC得分在0.56-0.76范围内，在针对外部测试队列进行测试时，预测准确率在0.39-0.64范围内，AUC-ROC得分在0.52-0.78范围内。生成了Shapley加性解释汇总图，以解释每个特征对每个模型的贡献。基于这些发现，开发了一个反应预测工具。每个模型都经过向后特征选择，以找到模型最相关的特征。前一个数据点的MHDs减少往往是最相关的，而有先兆偏头痛指标往往是最无效的预测指标。
利用不断发展的基于ML的模型的反应预测工具在早期预测接受抗CGRP mAbs治疗的偏头痛患者的治疗结果方面具有前景。
