Differentiating Between Migraine and Post-traumatic Headache Using a Machine Learning Classifier. (4th January 2022)

• Record Type: Journal Article
• Authors: Dumkrieger, Gina; Chong, Catherine Daniela; Ross, Katherine; Berisha, Visar; Schwedt, Todd J.
• Is Part Of: Neurology. Volume 98:Number 1(2022)Supplement 1
• Page Start: S5
• Page End: S6
• Publication Date: 2022-01-04
• Subjects: Neurology -- Periodicals; Neurology -- Periodicals; Neurologie -- Périodiques; 616.8
• DOI: 10.1212/01.wnl.0000801780.76758.b7
• Languages: English
• ISSNs: 0028-3878

Abstract

Abstract : Objective: The objective was to develop classification models differentiating persistent PTH (PPTH) and migraine using clinical data and MRI-based measures of brain structure and functional connectivity. Background: PTH and migraine commonly have similar phenotypes. Furthermore, migraine is a risk factor for developing PTH, sometimes making it difficult to differentiate PTH from exacerbation of migraine symptoms. Design/Methods: Thirty-four individuals with migraine without history of TBI and 48 individuals with mild TBI attributed to PPTH but without history of migraine or prior frequent tension type headache were included. Subjects completed questionnaires assessing headache characteristics, mood, sensory hypersensitivities and cognitive function and underwent MRI imaging during the same day. Clinical features and structural brain measures from T1-weighted imaging, diffusion tensor imaging and functional resting-state measures were included as potential variables. A classifier using ridge logistic regression of principal components (PC) was fit. Since PCs can hinder identification of significant variables in a model, a second regression model was fit directly to the data. In the non-PC based model, input variables were selected based on lowest t -test or chi-square p -value by modality. Average accuracy was calculated using leave-one-out cross validation. The importance of variables to the classifier were examined. Results: The PC-based classifier achieved an average classification accuracy of 85%. The non-PC based classifier achieved an average classification accuracy of 74.4%. Both classifiers were more accurate at classifying migraine subjects than PPTH. The PC-based model incorrectly classified 9/48 (18.8%) PPTH subjects compared to 3/34 (8.8%) migraine patients, whereas the non-PC classifier incorrectly classed 16/48 (33.3%) vs 5/34 (14.7%) of migraine subjects. Important variables in the non-PC model included static and dynamic functional connectivity values, several questions from the Beck Depression Inventory, and worsening symptoms and headaches with mental activity. Conclusions: Multivariate models including clinical characteristics, functional connectivity, and brain structural data accurately classify and differentiate PPTH vs migraine.