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

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

  • By

  • Antonios Danelakis

  • Tjaša Kumelj

  • Bendik S Winsvold

  • Marte Helene Bjørk

  • Parashkev Nachev

  • Manjit Matharu

  • Dominic Giles

  • Erling Tronvik

  • Helge Langseth

  • Anker Stubberud

  • The International Headache Genetics Consortium

  • Verneri Anttila

  • Ville Artto

  • Andrea C Belin

  • Anna Bjornsdottir

  • Gyda Bjornsdottir

  • Dorret I Boomsma

  • Sigrid Børte

  • Mona A Chalmer

  • Daniel I Chasman

  • Bru Cormand

  • Ester Cuenca-Leon

  • George Davey-Smith

  • Irene de Boer

  • Martin Dichgans

  • Tonu Esko

  • Tobias Freilinger

  • Padhraig Gormley

  • Lyn R Griffiths

  • Eija Hämäläinen

  • Thomas F Hansen

  • Aster V E Harder

  • Heidi Hautakangas

  • Marjo Hiekkala

  • Maria G Hrafnsdottir

  • M Arfan Ikram

  • Marjo-Riitta Järvelin

  • Risto Kajanne

  • Mikko Kallela

  • Jaakko Kaprio

  • Mari Kaunisto

  • Lisette J A Kogelman

  • Espen S Kristoffersen

  • Christian Kubisch

  • Mitja Kurki

  • Tobias Kurth

  • Lenore Launer

  • Terho Lehtimäki

  • Davor Lessel

  • Lannie Ligthart

  • Sigurdur H Magnusson

  • Rainer Malik

  • Bertram Müller-Myhsok

  • Carrie Northover

  • Dale R Nyholt

  • Jes Olesen

  • Aarno Palotie

  • Priit Palta

  • Linda M Pedersen

  • Nancy Pedersen

  • Matti Pirinen

  • Danielle Posthuma

  • Patricia Pozo-Rosich

  • Alice Pressman

  • Olli Raitakari

  • Caroline Ran

  • Gudrun R Sigurdardottir

  • Hreinn Stefansson

  • Kari Stefansson

  • Olafur A Sveinsson

  • Gisela M Terwindt

  • Thorgeir E Thorgeirsson

  • Arn M J M van den Maagdenberg

  • Cornelia van Duijn

  • Maija Wessman

  • Bendik S Winsvold

  • John-Anker Zwart

  • May 6, 2025

  • 0 min

Share

Clinical Scorecard: Identifying Migraine Through Genome-Wide Genotyping Data: An Analysis Using Machine Learning Techniques

At a Glance

CategoryDetail
ConditionMigraine
Key MechanismsPolygenic basis with additive and non-additive (interactive) genetic effects; involvement of signal transduction and neurological pathways including calcitonin gene-related peptide receptor and botulinum toxin-related pathways
Target PopulationAdults from the general population (mean age 54.6 years, 51% women) participating in the Trøndelag Health Study
Care SettingPopulation-based genetic and phenotypic research setting; potential future clinical genetic risk stratification

Key Highlights

  • Machine learning models outperform polygenic risk scoring in classifying migraine from genome-wide genotype data (AUC ~0.62-0.63 vs 0.52-0.59).
  • Migraine heritability is incompletely explained by known genetic variants; machine learning captures non-additive gene-gene interactions contributing to missing heritability.
  • Unique biological pathways identified by machine learning include those related to signal transduction, neurological function, botulinum toxins, and calcitonin gene-related peptide receptor.

Guideline-Based Recommendations

Diagnosis

  • Migraine diagnosis remains clinical based on International Classification of Headache Disorders criteria; genetic data may augment future diagnostic precision.

Management

  • Current management is clinical; understanding genetic architecture may inform future personalized therapies targeting pathways such as CGRP receptor.

Monitoring & Follow-up

  • No current genetic monitoring recommended; future models may enable genetic risk stratification and monitoring of migraine susceptibility.

Risks

  • Genetic risk variants explain only a portion of migraine heritability; reliance solely on additive polygenic risk scores may underestimate genetic risk.

Patient & Prescribing Data

Adults with or at risk for migraine identified through population-based genotyping

Genetic insights highlight pathways (e.g., CGRP receptor) targeted by existing migraine therapies; machine learning may refine patient selection for targeted treatments in the future.

Clinical Best Practices

  • Use validated clinical criteria for migraine diagnosis as genetic tools are investigational.
  • Consider genetic complexity including gene-gene interactions when interpreting genetic risk.
  • Support further research with larger datasets to improve machine learning models for migraine genetics.

References

Original Source(s)

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

  • by Antonios Danelakis, Tjaša Kumelj, Bendik S Winsvold, Marte Helene Bjørk, Parashkev Nachev, Manjit Matharu, Dominic Giles, Erling Tronvik, Helge Langseth, Anker Stubberud, The International Headache Genetics Consortium, Verneri Anttila, Ville Artto, Andrea C Belin, Anna Bjornsdottir, Gyda Bjornsdottir, Dorret I Boomsma, Sigrid Børte, Mona A Chalmer, Daniel I Chasman, Bru Cormand, Ester Cuenca-Leon, George Davey-Smith, Irene de Boer, Martin Dichgans, Tonu Esko, Tobias Freilinger, Padhraig Gormley, Lyn R Griffiths, Eija Hämäläinen, Thomas F Hansen, Aster V E Harder, Heidi Hautakangas, Marjo Hiekkala, Maria G Hrafnsdottir, M Arfan Ikram, Marjo-Riitta Järvelin, Risto Kajanne, Mikko Kallela, Jaakko Kaprio, Mari Kaunisto, Lisette J A Kogelman, Espen S Kristoffersen, Christian Kubisch, Mitja Kurki, Tobias Kurth, Lenore Launer, Terho Lehtimäki, Davor Lessel, Lannie Ligthart, Sigurdur H Magnusson, Rainer Malik, Bertram Müller-Myhsok, Carrie Northover, Dale R Nyholt, Jes Olesen, Aarno Palotie, Priit Palta, Linda M Pedersen, Nancy Pedersen, Matti Pirinen, Danielle Posthuma, Patricia Pozo-Rosich, Alice Pressman, Olli Raitakari, Caroline Ran, Gudrun R Sigurdardottir, Hreinn Stefansson, Kari Stefansson, Olafur A Sveinsson, Gisela M Terwindt, Thorgeir E Thorgeirsson, Arn M J M van den Maagdenberg, Cornelia van Duijn, Maija Wessman, Bendik S Winsvold, John-Anker Zwart

  • May 6, 2025

Related Content

Activation and sensitization of meningeal nociceptors by PACAP-38: implications for migraine headache

Migraine, comorbidity, and risks of severe maternal and neonatal morbidity or mortality: a population-based cohort study

Floaters May Signal Higher Risk Than Flashes

New study examines retinal detachment risk in primary care presentations