Predicting White Matter Hyperintensity: Leveraging Portable Magnetic Resonance Imaging for Accessible Brain Health Screening

DOI: 10.3174/ajnr.a8734 Publication Date: 2025-03-13T16:54:36Z
ABSTRACT
<h3>ABSTRACT</h3> <h3>BACKGROUND AND PURPOSE:</h3> Portable MRI (pMRI) has emerged as a cost-effective and accessible tool for the identification of white matter hyperintensities (WMH), an independent risk factor stroke dementia. Our objective was to confirm that pMRI can produce accurate WMH measurements develop validate model predict on purpose identifying patients who may benefit from screening. <h3>MATERIALS METHODS:</h3> The development (N=143) validation (N=127) cohorts included without acute neurologic pathology received at tertiary care hospital between May 2020 July 2024. cohort pMRIs collected part prospective screening pilot program in emergency department. retrospective collection obtained separate research purposes. Conventional MRIs (cMRIs) within 3 months were used additional device agreement. primary outcome burden greater than 10 mL, assessed via axial T2-FLAIR sequence acquired 0.064 T quantified using segmentation software developed process sequences any resolution. We backwards selection screen candidate variables report area under curve resulting model. <h3>RESULTS:</h3> final model, which age, systolic blood pressure &gt;140, atrial fibrillation, tobacco use, achieved AUC 0.83 (95% CI 0.75-0.90) (N=143, 62.4±12.6 years, 44% female, 36% non-white race) 0.85 0.77-0.92) (N=127, 65.2±16.8 51% 34% race), with similar results derived cMRI (N=120, p=0.98, AUC=0.86, 95% 0.77-0.93). Additionally, we confirmed agreement volumes r=0.93, 0.90-0.95, p&lt;0.001). <h3>CONCLUSIONS:</h3> score demonstrated performance reproducibility across cohorts, supporting its potential significant burden. Appropriately targeted high-risk individuals could allow providers proactively manage vascular factors improve neurological outcomes. ABBREVIATIONS: = portable magnetic resonance imaging; conventional hyperintensity; hypertension HTN; diabetes DM; fibrillation AFib; SBP; hyperlipidemia HLD; AUC; receiver operating characteristic ROC.
SUPPLEMENTAL MATERIAL
Coming soon ....
REFERENCES (0)
CITATIONS (0)