A foundation-model approach to pediatric headache classification from resting-state fMRI

Guilherme Seidyo Imai Aldeia, Clara Moon, Julie M. Shulman, Navil Sethna, Allison M Smith, Alyssa LeBel, William La Cava, Scott Holmes
Proceedings of the 11th Machine Learning for Healthcare Conference, PMLR 340:55-76, 2026.

Abstract

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 then compared NeuroSTORM with a standard neuroscience approach that uses 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) in discriminating headache from non-headache. In contrast, models trained on FC matrices showed limited performance (AUROC, 0.67 [95% CI, 0.67-0.67]; AUPRC, 0.85 [95% CI, 0.85-0.85]). In a multiclass setting, when tasked with classifying individuals as healthy controls, individuals with chronic migraine, or individuals with 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). The results suggest this approach can distinguish chronic migraine, the most common headache syndrome, 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. The findings provide proof-of-concept for fMRI-based prediction of pediatric headache using a foundation model without relying on functional connectivity features and highlight the potential of this approach for subtype identification. Further development of such tools may help clinicians improve diagnosis based on brain activity and tailor treatment strategies to individual patients.

Cite this Paper

BibTeX
@InProceedings{pmlr-v340-aldeia26a, title = {A foundation-model approach to pediatric headache classification from resting-state fMRI}, author = {Aldeia, Guilherme Seidyo Imai and Moon, Clara and Shulman, Julie M. and Sethna, Navil and Smith, Allison M and LeBel, Alyssa and Cava, William La and Holmes, Scott}, booktitle = {Proceedings of the 11th Machine Learning for Healthcare Conference}, pages = {55--76}, year = {2026}, editor = {Krishnan, Rahul G. and van Amsterdam, Wouter A. C. and Chopra, Sumit and Overgaard, Shauna and Hughes, Michael and Ötleş, Erkin and Shen, Yiqiu and Shanmugam, Divya and Nayan, Madhur and Engelhard, Matthew and Fackler, Jim and Oberst, Michael}, volume = {340}, series = {Proceedings of Machine Learning Research}, month = {12--14 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v340/main/assets/aldeia26a/aldeia26a.pdf}, url = {https://proceedings.mlr.press/v340/aldeia26a.html}, abstract = {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 then compared NeuroSTORM with a standard neuroscience approach that uses 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) in discriminating headache from non-headache. In contrast, models trained on FC matrices showed limited performance (AUROC, 0.67 [95% CI, 0.67-0.67]; AUPRC, 0.85 [95% CI, 0.85-0.85]). In a multiclass setting, when tasked with classifying individuals as healthy controls, individuals with chronic migraine, or individuals with 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). The results suggest this approach can distinguish chronic migraine, the most common headache syndrome, 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. The findings provide proof-of-concept for fMRI-based prediction of pediatric headache using a foundation model without relying on functional connectivity features and highlight the potential of this approach for subtype identification. Further development of such tools may help clinicians improve diagnosis based on brain activity and tailor treatment strategies to individual patients.} }
Endnote
%0 Conference Paper %T A foundation-model approach to pediatric headache classification from resting-state fMRI %A Guilherme Seidyo Imai Aldeia %A Clara Moon %A Julie M. Shulman %A Navil Sethna %A Allison M Smith %A Alyssa LeBel %A William La Cava %A Scott Holmes %B Proceedings of the 11th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2026 %E Rahul G. Krishnan %E Wouter A. C. van Amsterdam %E Sumit Chopra %E Shauna Overgaard %E Michael Hughes %E Erkin Ötleş %E Yiqiu Shen %E Divya Shanmugam %E Madhur Nayan %E Matthew Engelhard %E Jim Fackler %E Michael Oberst %F pmlr-v340-aldeia26a %I PMLR %P 55--76 %U https://proceedings.mlr.press/v340/aldeia26a.html %V 340 %X 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 then compared NeuroSTORM with a standard neuroscience approach that uses 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) in discriminating headache from non-headache. In contrast, models trained on FC matrices showed limited performance (AUROC, 0.67 [95% CI, 0.67-0.67]; AUPRC, 0.85 [95% CI, 0.85-0.85]). In a multiclass setting, when tasked with classifying individuals as healthy controls, individuals with chronic migraine, or individuals with 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). The results suggest this approach can distinguish chronic migraine, the most common headache syndrome, 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. The findings provide proof-of-concept for fMRI-based prediction of pediatric headache using a foundation model without relying on functional connectivity features and highlight the potential of this approach for subtype identification. Further development of such tools may help clinicians improve diagnosis based on brain activity and tailor treatment strategies to individual patients.
APA
Aldeia, G.S.I., Moon, C., Shulman, J.M., Sethna, N., Smith, A.M., LeBel, A., Cava, W.L. & Holmes, S.. (2026). A foundation-model approach to pediatric headache classification from resting-state fMRI. Proceedings of the 11th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 340:55-76 Available from https://proceedings.mlr.press/v340/aldeia26a.html.

Related Material