Are machine learning approaches the future to study patients with migraine?

One of the most exciting developments in modern neuroscience has been the expansion of imaging techniques that can provide insights into human brain structures and networks that could be involved in the pathophysiology of diseases. A series of MRI techniques have been extensively applied to the study of patients with migraine. It is now widely accepted that migraine should be viewed as a complex brain network disorder with a strong genetic basis that involves the interplay of multiple neuronal systems to account for the pain and the wide constellation of symptoms characterizing the migraine attack.1 Widespread structural and functional abnormalities in cortical and subcortical areas involved in multisensory processing, including pain, occur in patients with migraine, both in the course of an acute attack and during the interictal phase.2,3 Whether such alterations represent a potential migraine biomarker that can help to discriminate patients with migraine from controls and from patients with other chronic pain conditions is still a matter of debate.