作者: Catherine D Chong , Nathan Gaw , Yinlin Fu , Jing Li , Teresa Wu
关键词: Functional connectivity 、 Resting state fMRI 、 Magnetic resonance imaging 、 Insula 、 Neuroimaging 、 Migraine 、 Amygdala 、 Medicine 、 Healthy control 、 Audiology 、 Neuroscience
摘要: BackgroundThis study used machine-learning techniques to develop discriminative brain-connectivity biomarkers from resting-state functional magnetic resonance neuroimaging (rs-fMRI) data that distinguish between individual migraine patients and healthy controls.MethodsThis included 58 (mean age = 36.3 years; SD = 11.5) 50 controls age = 35.9 SD = 11.0). The connections of 33 seeded pain-related regions were as input for a brain classification algorithm tested the accuracy determining whether an MRI belongs someone with or control.ResultsThe best using 10-fold cross-validation method was 86.1%. Resting connectivity right middle temporal, posterior insula, cingulate, left ventromedial prefrontal bilateral amygdala discriminated control. Migraineurs longer disease durations cla...