Machine Diagnostics and Machine Phenotyping of Migraine

BACKGROUND AND OBJECTIVES: In the absence of biomarkers, the true biological footprint of migraine remains incompletely understood. It could perhaps be best characterized using machine learning models of multimodal data. The aim of this study was to (1) develop diagnostic models of migraine using multimodal data and (2) identify data-driven migraine phenotypes. METHODS: This was a cross-sectional machine learning analysis of demographics, self-reported clinical and headache data, and genome-wide genotype data from the Trøndelag Health Study (data collected 1995-1997 and 2006-2008). All participants who were genotyped and completed the headache questionnaire were included. First, predictive machine learning models were developed using genotype data and general clinical data (excluding headache data) to diagnose individuals with migraine vs headache-free controls. Models were optimized on a training set and evaluated on a held-out test set, scored with the area under the receiver operating characteristic curve (AUC). Second, unsupervised models were trained on the headache data and the most predictive features from the diagnostic models to identify subgroups. The subgroups were compared using genome-wide association analyses, conventional polygenic risk scores (PRSs), and machine learning-based genetic risk scores. RESULTS: A total of 43,197 individuals were included in the diagnostic models, and 12,185 individuals were included in the data-driven phenotyping (mean [SD] age 49.1 [16.7] years; 51.7% women). The top-performing diagnostic model was a light gradient boosting machine, with a test set AUC of 0.80 (95% CI 0.78-0.81). Two main clusters were identified, one with 1,425 individuals, 94% of whom met diagnostic criteria for migraine, and another with 10,760 individuals, whereof 71% had nonmigraine headaches. The former was subclustered into 4 relatively distinct groups: one with only men, one with prominent neck pain, one with more musculoskeletal pain, anxiety and depression, and one with "classic" migraine. The groups were better discriminated by machine learning-based genetic risk scores compared with PRSs. DISCUSSION: Migraine can accurately be diagnosed from nonheadache data, suggesting that it is biologically describable by combinations of clinical, genetic, and environmental data. Data-driven phenotyping with such data identifies migraine subgroups with distinct phenotypic and genotypic signals, possibly not captured by current diagnostic criteria-but with potential implications for management.

Authors

Institutions

Publication Details

Journal
Neurology
Published
2026-06-16
DOI
https://doi.org/10.1212/wnl.0000000000218076
Citations
1
Primary Topic
Migraine and Headache Studies
Type
article
Field-Weighted Citation Impact
12.80

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Machine Diagnostics and Machine Phenotyping of Migraine

Verneri Anttila, Sigurður H. Magnússon, Mikko Kallela, Tōnu Esko et al.
1 citations
Neurology
Migraine and Headache Studies
12.80
article

Machine Diagnostics and Machine Phenotyping of Migraine

Verneri Anttila, Sigurður H. Magnússon, Mikko Kallela, Tōnu Esko, Hreinn Stefánsson, Sigrid Børte, Arn M. J. M. van den Maagdenberg, Christian Kubisch, Daniel I. Chasman, Manjit Singh Matharu, J Kaprio, Parashkev Nachev, Bendik S. Winsvold, Davor Lessel, Antonios Danelakis, Erling Tronvik, Lisette J. A. Kogelman, Dale R. Nyholt, Ólafur Á. Sveinsson, Gyða Björnsdóttir, Tobias Kurth, Knut Hagen, Caroline Ran, Daniëlle Posthuma, Nancy Pedersen, George Davey-Smith, Dominic Giles, Irene de Boer, Anna Bjornsdottir, Gudrun R. Sigurdardottir, Jes Olesen, Anker Stubberud, Priit Palta, M. Arfan Ikram, Ester Cuenca-León, Marjo‐Riitta Järvelin, Marte‐Helene Bjørk, Aster V. E. Harder, T Lehtimäki, Tjaša Kumelj, Padhraig Gormley, Lannie Ligthart, Maija Wessman, Fahim Faisal, Lenore Launer, CM van Duijn, D.I. Boomsma, Mitja Kurki, Eija Hämäläinen, Aarno Palotie, Risto Kajanne, Andrea C. Belin, Mari Kaunisto, Thomas F. Hansen, Olli Raitakari, Ville Artto, Kari Stefansson, Mona A. Chalmer, Rainer Malik, Tobias Freilinger, Marjo Hiekkala, Maria G. Hrafnsdottir, Lyn R. Griffiths, Gisela M. Terwindt, Patricia Pozo-Rosich, Håkon Kvisle Abildsnes, Bertram Müller-Myhsok, Heidi Hautakangas, Bru Cormand, Alice Pressman, Bendik S. Winsvold, Martin Dichgans, Thorgeir E. Thorgeirsson, John-Anker Zwart, Espen S. Kristoffersen, Carrie Northover, Linda M. Pedersen, Matti Pirinen
article en
1 citations

Abstract

BACKGROUND AND OBJECTIVES: In the absence of biomarkers, the true biological footprint of migraine remains incompletely understood. It could perhaps be best characterized using machine learning models of multimodal data. The aim of this study was to (1) develop diagnostic models of migraine using multimodal data and (2) identify data-driven migraine phenotypes. METHODS: This was a cross-sectional machine learning analysis of demographics, self-reported clinical and headache data, and genome-wide genotype data from the Trøndelag Health Study (data collected 1995-1997 and 2006-2008). All participants who were genotyped and completed the headache questionnaire were included. First, predictive machine learning models were developed using genotype data and general clinical data (excluding headache data) to diagnose individuals with migraine vs headache-free controls. Models were optimized on a training set and evaluated on a held-out test set, scored with the area under the receiver operating characteristic curve (AUC). Second, unsupervised models were trained on the headache data and the most predictive features from the diagnostic models to identify subgroups. The subgroups were compared using genome-wide association analyses, conventional polygenic risk scores (PRSs), and machine learning-based genetic risk scores. RESULTS: A total of 43,197 individuals were included in the diagnostic models, and 12,185 individuals were included in the data-driven phenotyping (mean [SD] age 49.1 [16.7] years; 51.7% women). The top-performing diagnostic model was a light gradient boosting machine, with a test set AUC of 0.80 (95% CI 0.78-0.81). Two main clusters were identified, one with 1,425 individuals, 94% of whom met diagnostic criteria for migraine, and another with 10,760 individuals, whereof 71% had nonmigraine headaches. The former was subclustered into 4 relatively distinct groups: one with only men, one with prominent neck pain, one with more musculoskeletal pain, anxiety and depression, and one with "classic" migraine. The groups were better discriminated by machine learning-based genetic risk scores compared with PRSs. DISCUSSION: Migraine can accurately be diagnosed from nonheadache data, suggesting that it is biologically describable by combinations of clinical, genetic, and environmental data. Data-driven phenotyping with such data identifies migraine subgroups with distinct phenotypic and genotypic signals, possibly not captured by current diagnostic criteria-but with potential implications for management.

NeurologyVol. 107(1)
Oslo University Hospital (NO), Norwegian University of Science and Technology (NO), Levanger Hospital (NO), Haukeland University Hospital (NO), St Olav's University Hospital (NO), National Hospital for Neurology and Neurosurgery (GB), University of Bergen (NO), University College London (GB)
Norges Teknisk-Naturvitenskapelige Universitet, Helse Midt-Norge, Norges Forskningsråd, National Institutes of Health, Faculty of Medicine and Health, University of Sydney, Norwegian Institute of Public Health
Reduced inequalities
Openalex Percentile: Top 1%
Migraine and Headache Studies
12.80
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.