发表机构
Boston Children’s Hospital; Harvard Medical School（波士顿儿童医院; 哈佛医学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究采用基础模型NeuroSTORM对rs-fMRI数据编码微调，在189次扫描的儿童数据中，其头痛分类性能优于FC矩阵模型，可区分慢性偏头痛，为儿童头痛预测提供了概念验证。
AI 中文摘要
头痛是儿童中最常见的神经系统疾病，会严重影响生活质量。本研究探究静息态功能磁共振成像（rs-fMRI）是否可通过机器学习辅助儿童头痛分类。我们使用NeuroSTORM（一种近期提出的基础模型）对rs-fMRI数据进行编码，并对其进行微调，以区分健康对照与头痛儿童，进而对头痛亚型进行分类。我们将NeuroSTORM与使用脑活动衍生的功能连接（FC）矩阵作为预测变量的标准神经科学方法进行了比较。研究使用了来自110名个体的189次rs-fMRI扫描，这些扫描采集自两次访视，任何头痛的患病率为74%。在区分头痛与非头痛时，NeuroSTORM的受试者工作特征曲线下面积（AUROC）为0.82（95%置信区间，0.82-0.82），精确召回曲线下面积（AUPRC）为0.93（95%置信区间，0.93-0.94）；相比之下，基于FC矩阵训练的模型性能更低（AUROC为0.67[95%置信区间，0.67-0.67]；AUPRC为0.85[95%置信区间，0.85-0.85]）。在对健康对照、慢性偏头痛及非慢性头痛（如病毒后头痛、新每日持续性头痛、创伤后头痛）的多分类中，NeuroSTORM的宏平均AUROC为0.69（95%置信区间，0.68-0.69）。结果表明，该方法可区分慢性偏头痛，但难以将其他头痛亚型与慢性偏头痛区分开。总体而言，在数据有限的条件下，NeuroSTORM似乎能捕捉到潜在的rs-fMRI表征，可迁移至与头痛相关的任务，且无需依赖FC特征。这些发现为基于fMRI的儿童头痛预测提供了概念验证，并凸显了其在亚型识别及个体化治疗策略方面的潜在未来应用价值。
英文摘要
Headache is the most common neurological disorder in children and substantially affects quality of life. We investigated whether resting-state functional MRI (rs-fMRI) can support pediatric headache classification using machine learning. We encoded rs-fMRI data using NeuroSTORM, a recent foundation model, and fine-tuned it to distinguish healthy controls from children with headache and subsequently classify headache subtypes. We compared NeuroSTORM with a standard neuroscience approach using functional-connectivity (FC) matrices derived from brain activity as predictors. Using 189 rs-fMRI scans from 110 individuals collected across two visits (prevalence of any headache: 74%), NeuroSTORM achieved an area under the receiver operating characteristic curve (AUROC) of 0.82 (95% CI, 0.82-0.82) and an area under the precision-recall curve (AUPRC) of 0.93 (95% CI, 0.93-0.94) for discriminating headache from non-headache. In contrast, models trained on FC matrices showed lower performance (AUROC, 0.67 [95% CI, 0.67-0.67]; AUPRC, 0.85 [95% CI, 0.85-0.85]). In multiclass classification of healthy controls, chronic migraine, and non-chronic headaches (e.g., post-viral headache, new daily persistent headache, post-traumatic headache), NeuroSTORM achieved a macro-AUROC of 0.69 (95% CI, 0.68-0.69). Results suggest that the approach can distinguish chronic migraine but has difficulty differentiating other headache subtypes from chronic migraine. Overall, under limited-data conditions, NeuroSTORM appears to capture latent rs-fMRI representations that transfer to headache-related tasks without relying on FC features. These findings provide proof of concept for fMRI-based prediction of pediatric headache and highlight potential future utility for subtype identification and individualized treatment strategies.
Comments22 pages, 6 figures. In Proceedings of Machine Learning Research, Volume 340, 2026 (Machine Learning for Healthcare Conference)
Journal refProceedings of the 11th Machine Learning for Healthcare Conference, PMLR 340:55-76, 2026
