Elucidating biopsychosocial mechanisms in migraine: an integrative analytics approach combining genetics, neuroimaging, and machine learning
Abstract
BACKGROUND: Migraine is a complex and disabling neurological disorder shaped by the interplay of biological, psychological, and behavioral factors. Current evidence lacks an integrated causal perspective spanning macro-level epidemiology, micro-level causal mechanisms, and clinical prediction.
METHODS: We employed a multilevel analytical approach integrating genetic causal inference and neuroimaging. First, we used a two-step mediation framework to investigate causal pathways from biological markers to migraine via psychological intermediaries. Second, we examined the mediating role of brain imaging phenotypes in linking psychological factors to migraine risk. Finally, we developed a machine learning prediction model based on the identified biopsychosocial features.
RESULTS: Genetic causal inference revealed that several biological factors influence migraine risk indirectly through psychological mediators, including neuroticism and depressive symptoms. Neuroimaging mediation analysis further identified that these psychological effects operate through structural alterations in key brain regions, including amygdala volume and the microstructural integrity of fronto-limbic white matter pathways. A random forest model incorporating the identified biopsychosocial features achieved exceptional predictive performance in classifying migraine status (Area under the receiver operating characteristic curve [AUROC] = 0.995), with psychological traits and body mass index among the most…
Read the paper
Related studies
- Meta-analysis of genome-wide association for migraine in six population-based European cohorts
- New and sex-specific migraine susceptibility loci identified from a multiethnic genome-wide meta-analysis
- microRNA profiling in atherosclerosis, diabetes, and migraine
- Genome‐Wide‐Associated Variants in Migraine Susceptibility: A Replication Study From North I ndia
- Pharmacoinformatics elucidation of potential drug targets against migraine to target ion channel protein KCNK18
- Upregulation of IL-1 Receptor Antagonist in a Mouse Model of Migraine
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.