Stratifying vascular disease patients into homogeneous subgroups using machine learning and FLAIR MRI biomarkers

Karissa Chan; Corinne Fischer; Pejman Jabehdar Maralani; Sandra E Black; Alan R Moody; April Khademi

doi:10.1038/s44303-024-00063-x

Stratifying vascular disease patients into homogeneous subgroups using machine learning and FLAIR MRI biomarkers

Npj Imaging. 2024;2(1):56. doi: 10.1038/s44303-024-00063-x. Epub 2024 Dec 31.

Authors

Karissa Chan^{1

2}, Corinne Fischer³, Pejman Jabehdar Maralani⁴, Sandra E Black^{5

6

7

8}, Alan R Moody⁴, April Khademi^{1

2

3

4

5

9}

Affiliations

¹ Department of Electrical, Computer and Biomedical Engineering, Toronto Metropolitan University, Toronto, ON Canada.
² Institute for Biomedical Engineering, Science Tech (iBEST), a Partnership between St. Michael's Hospital and Toronto Metropolitan University, Toronto, ON Canada.
³ Keenan Research Center for Biomedical Science, St. Michael's Hospital, Unity Health Network, Toronto, ON Canada.
⁴ Department of Medical Imaging, University of Toronto, Toronto, ON Canada.
⁵ Institute of Medical Science, University of Toronto, Toronto, ON Canada.
⁶ Horvitz Brain Sciences Research Program, Sunnybrook Research Institute, Toronto, ON Canada.
⁷ Division of Neurology, Department of Medicine, Sunnybrook Health Sciences Centre, Toronto, ON Canada.
⁸ L.C. Campbell Cognitive Neurology Research Unit, Sunnybrook Health Sciences Centre, Toronto, ON Canada.
⁹ Vector Institute for Artificial Intelligence, Toronto, ON Canada.

Abstract

This study proposes a framework to stratify vascular disease patients based on brain health and cerebrovascular disease (CVD) risk using regional FLAIR biomarkers. Intensity and texture biomarkers were extracted from FLAIR volumes of 379 atherosclerosis patients. K-Means clustering identified five homogeneous subgroups. The 15 most important biomarkers for subgroup differentiation, identified via Random Forest classification, were used to generate biomarker profiles. ANOVA tests showed age and white matter lesion volume were significantly (p < 0.05) different across subgroups, while Fisher's tests revealed significant (p < 0.05) differences in the prevalence of several vascular risk factors across subgroup. Based on biomarker and clinical profiles, Subgroup 4 was characterized with neurodegeneration unrelated to CVD, Subgroup 3 identified patients with high CVD risk requiring aggressive intervention, and Subgroups 1, 2, and 5 identified patients with varying levels of moderate risk, suitable for long-term lifestyle interventions. This study supports personalized treatment and risk stratification based on FLAIR biomarkers.

Keywords: Brain imaging; Image processing.