A MAGNETIC RESONANCE IMAGING-BASED CLASSIFIER TO ACCURATELY DIAGNOSE PERSISTENT POST-TRAUMATIC HEADACHE AND TO DIFFERENTIATE IT FROM CHRONIC MIGRAINE

Project: Research project

Project Details

Description

Background: Traumatic brain injury (TBI) and post-traumatic headache (PTH) are common conditions that exert substantial impacts in the military and in the civilian population. TBI is a signature injury of U.S. Soldiers during modern warfare with 20% of Operation Enduring Freedom and Operation Iraqi Freedom Veterans having experienced TBI, 75% of which are mild TBI (mTBI). In addition, approximately 1.7 million American civilians seek medical attention each year for TBI and there are 1.6-3.8 million sports-related mTBIs annually. Headache is the most common symptom following mTBI, with estimates of headache prevalence following mTBI as high as 90%. PTH is often persistent (i.e., endures for >3 months following the injury), with about 66% of people with mTBI reporting continued headaches at 3 months post-injury. Although progress has been achieved in understanding PTH epidemiology, there are significant shortcomings in the description of PTH mechanisms, diagnosis, and treatment. A major challenge for the investigation, diagnosis, and treatment of PTH is the inability to accurately diagnose persistent post-traumatic headache (PPTH) attributed to mTBI and to reliably differentiate PPTH attributed to mTBI from chronic migraine (CM). Rationale: It is often impossible to clinically differentiate the patient who had an exacerbation of their underlying migraine pattern following TBI, from the patient who had a new onset of migraine following TBI, from the patient with true PPTH. According to International Classification of Headache Disorders diagnostic criteria, the only evidence for headache being attributable to a preceding head injury is that the headache begins within 7 days of the injury. However, a substantial proportion of military PTH starts after a longer interval (up to 60% of cases), the majority of PPTH is phenotypically indistinguishable from CM according to information typically collected in the clinical setting (60%-97%), and many Soldiers and civilians with presumed PPTH have a personal history of migraine preceding the mTBI. Thus, it is commonly challenging to differentiate PPTH from CM in the clinical setting. The inability to accurately diagnose PPTH attributed to mTBI and differentiate it from CM has substantial negative implications on patient care and the ability to conduct meaningful research on PPTH.Objective: The objective of this study is to use machine-learning algorithms to construct multivariate models of structural and functional imaging data and patient symptoms that accurately diagnose PPTH attributed to mTBI and differentiate it from CM.Study Design: Functional and structural magnetic resonance imaging (MRI) data and patient symptoms will be used to build and test automated diagnostic models that most accurately diagnose PPTH attributed to mTBI and differentiate it from CM. This investigation uses MRI sequences that could easily be employed during the clinical investigation of patients, without adding risk to the patient, without the need for contrast administration, and with little additional financial burden. The specific aims are: (1) Phenotyping: Contrast detailed symptom data from patients with PPTH attributed to mTBI and no history of preceding migraine to symptoms from CM patients with no history of head trauma. (2) Brain MRI: Contrast PPTH, CM, and control subjects (mTBI with no PTH, healthy controls) using structural and fMRI data collected via high-resolution structural imaging, diffusion tensor imaging, and resting state functional connectivity analyses. (3) Diagnostic Modeling: Develop and evaluate diagnostic models consisting of imaging findings and phenotypic data that best diagnose PPTH attributed to mTBI, differentiating it from CM.Short- and Long-Term Impact: PPTH attributed to mTBI and CM are disorders that exert substantial impacts on the U.S. military and on the civilian population. Differentiating PPTH from CM is currently a major challenge. The inability to accurately diagnose PPTH leads to misdiagnosis and maltreatment and is an inhibitor of research that will lead to improved treatment of PPTH. The results from this proposed research could relatively quickly translate into the clinical realm as computer-aided diagnostic tools that would assist clinicians and scientists in diagnosing PPTH and differentiating it from CM.Relevance to Topic Area: This research is directly relevant for the 'chronic migraine and post-traumatic headaches' topic area.

StatusFinished
Effective start/end date9/15/159/14/18

Funding

  • Congressionally Directed Medical Research Programs: $1,570,257.00

Fingerprint

Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.