Diagnosing migraine from genome-wide genotype data: a machine learning analysis

Migraine has an assumed polygenic basis, but the genetic risk variants identified in genome-wide association studies only explain a proportion of the heritability. We aimed to develop machine learning models, capturing non-additive and interactive effects, to address the missing heritability. This was a cross-sectional population-based study of participants in the second and third Trøndelag Health Study. Individuals underwent genome-wide genotyping and were phenotyped based on validated modified criteria of the International Classification of Headache Disorders. Four datasets of increasing numbers of genetic variants were created using different thresholds of linkage disequilibrium and univariate genome-wide associated P-values. A series of machine learning and deep learning methods were optimized and evaluated. The genotype tools PLINK and LDPred2 were used for polygenic risk scoring. Models were trained on a partition of the dataset and tested in a hold-out set. The area under the receiver operating characteristics curve was used as the primary scoring metric. Classification by machine learning was statistically compared to that of polygenic risk scoring. Finally, we explored the biological functions of the variants unique to the machine learning approach. Overall, 43 197 individuals (51% women), with a mean age of 54.6 years, were included in the modelling. A light gradient boosting machine performed best for the three smallest datasets (108, 7771 and 7840 variants), all with hold-out test set area under curve at 0.63. A multinomial naïve Bayes model performed best in the largest dataset (140 467 variants) with a hold-out test set area under curve of 0.62. The models were statistically significantly superior to polygenic risk scoring (area under curve 0.52 to 0.59) for all the datasets (P < 0.001 to P = 0.02). Machine learning identified many of the same genes and pathways identified in genome-wide association studies, but also several unique pathways, mainly related to signal transduction and neurological function. Interestingly, pathways related to botulinum toxins, and pathways related to the calcitonin gene-related peptide receptor also emerged. This study suggests that migraine may follow a non-additive and interactive genetic causal structure, potentially best captured by complex machine learning models. Such structure may be concealed where the data dimensionality (high number of genetic variants) is insufficiently supported by the scale of available data, leaving a misleading impression of purely additive effects. Future machine learning models using substantially larger sample sizes could harness both the additive and the interactive effects, enhancing precision and offering deeper understanding of genetic interactions underlying migraine.

Authors

Institutions

Publication Details

Journal
Brain
Published
2025-05-03
DOI
https://doi.org/10.1093/brain/awaf172
Citations
1
Primary Topic
Migraine and Headache Studies
Type
article
Field-Weighted Citation Impact
1.47

Funders

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

Diagnosing migraine from genome-wide genotype data: a machine learning analysis

Jaakko A. Kaprio, Verneri Anttila, Sigurður H. Magnússon, Bru Cormand et al.
1 citations
Brain
Migraine and Headache Studies
1.47
article

Diagnosing migraine from genome-wide genotype data: a machine learning analysis

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

Abstract

Migraine has an assumed polygenic basis, but the genetic risk variants identified in genome-wide association studies only explain a proportion of the heritability. We aimed to develop machine learning models, capturing non-additive and interactive effects, to address the missing heritability. This was a cross-sectional population-based study of participants in the second and third Trøndelag Health Study. Individuals underwent genome-wide genotyping and were phenotyped based on validated modified criteria of the International Classification of Headache Disorders. Four datasets of increasing numbers of genetic variants were created using different thresholds of linkage disequilibrium and univariate genome-wide associated P-values. A series of machine learning and deep learning methods were optimized and evaluated. The genotype tools PLINK and LDPred2 were used for polygenic risk scoring. Models were trained on a partition of the dataset and tested in a hold-out set. The area under the receiver operating characteristics curve was used as the primary scoring metric. Classification by machine learning was statistically compared to that of polygenic risk scoring. Finally, we explored the biological functions of the variants unique to the machine learning approach. Overall, 43 197 individuals (51% women), with a mean age of 54.6 years, were included in the modelling. A light gradient boosting machine performed best for the three smallest datasets (108, 7771 and 7840 variants), all with hold-out test set area under curve at 0.63. A multinomial naïve Bayes model performed best in the largest dataset (140 467 variants) with a hold-out test set area under curve of 0.62. The models were statistically significantly superior to polygenic risk scoring (area under curve 0.52 to 0.59) for all the datasets (P < 0.001 to P = 0.02). Machine learning identified many of the same genes and pathways identified in genome-wide association studies, but also several unique pathways, mainly related to signal transduction and neurological function. Interestingly, pathways related to botulinum toxins, and pathways related to the calcitonin gene-related peptide receptor also emerged. This study suggests that migraine may follow a non-additive and interactive genetic causal structure, potentially best captured by complex machine learning models. Such structure may be concealed where the data dimensionality (high number of genetic variants) is insufficiently supported by the scale of available data, leaving a misleading impression of purely additive effects. Future machine learning models using substantially larger sample sizes could harness both the additive and the interactive effects, enhancing precision and offering deeper understanding of genetic interactions underlying migraine.

BrainVol. 149(1)
Oslo University Hospital (NO), Norwegian University of Science and Technology (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
Openalex Percentile: Top 20%
Migraine and Headache Studies
1.47
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.