Migraine Without Aura
Conditions
Brief summary
Recently, radiomics combined with machine learning method has been widely used in clinical practice. Compared with traditional imaging studies that explore the underlying mechanisms, the machine learning method focuses on classification and prediction to propose personalized diagnosis and treatment strategies. However, these studies were based on thin-section research-quality brain MR imaging with section thickness of \< 2 mm. Clinical, the usage of thick-section clinical setting instead of thin-section research setting is especially important to shorten the acquisition time to reduce the patient's suffering. Here investigators want to build multiparametric diagnostic model of migraineurs without aura using radiomics features extracted from thick-section clinical-quality brain MR images.
Interventions
DIAGNOSTIC_TESTdiagnostic
using radiomics features from multiparametric thick-section clinical-quality brain MRI to distinguish migraineurs from health controls.
Sponsors
Xidian University
Study design
Observational model
COHORT
Time perspective
PROSPECTIVE
Eligibility
Sex/Gender
ALL
Age
21 Years to 55 Years
Healthy volunteers
Yes
Inclusion criteria
* right-handed * International Headache Society criteria for episodic migraine without aura
Exclusion criteria
* addition (including alcohol, nicotine, or drug) * physical illness
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| accuracy | 2018.7-2019.12 | a measure of statistical bias which measures the proportion of health controls and migrainures that are correctly identified as such. |
| sensitivity | 2018.7-2019.12 | true positive rate of detection in migraineurs which measures the proportion of actual migraineurs that are correctly identified as such. |
| specificity | 2018.7-2019.12 | true negative rate measures the proportion of actual health controls that are correctly identified as such. |
Countries
China
Outcome results
None listed