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

Q: What is the clinical evidence from this study?

Study design: Observational. Population: Atherosclerotic disease (carotid artery disease) (n=379). Intervention: FLAIR MRI biomarker profiling. Primary outcome: Patient stratification into homogeneous subgroups using K-Means clustering of FLAIR biomarkers (p=<0.001).

Q: What does this research mean for the field?

FLAIR MRI texture and intensity biomarkers can successfully stratify atherosclerosis patients into distinct subgroups with significantly different cerebrovascular disease risk profiles and neurodegeneration levels. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

Q: What question did this study set out to answer?

This research aims to stratify vascular disease patients into homogeneous subgroups using machine learning techniques and FLAIR MRI biomarkers.

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

doi:10.1038/s44303-024-00063-x

December 31, 2024npj ImagingOpen Access

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

View Full Paper

Ask AI

Bookmark

Share

Key result

FLAIR MRI biomarkers stratify atherosclerosis patients into 5 subgroups with distinct CVD and neurodegeneration profiles.

P<0.001
n=379

Figures

Key Points

This research aims to stratify vascular disease patients into homogeneous subgroups using machine learning techniques and FLAIR MRI biomarkers.
Extracted intensity and texture biomarkers from FLAIR MRI volumes of 379 atherosclerosis patients.
Applied K-Means clustering to identify five subgroups based on biomarkers.
Used Random Forest classification to determine the 15 most important biomarkers for subgroup differentiation.
ANOVA tests showed significant differences in age and white matter lesion volume across subgroups (p < 0.05).
Fisher’s tests indicated significant differences in vascular risk factors prevalence across subgroup (p < 0.05).
Subgroup 3 included high CVD risk patients needing aggressive intervention, while Subgroup 4 featured neurodegeneration unrelated to CVD.

Study Design

Type

Observational (n=379)

Multicenter

Yes

Structured PICO

P

Population

379 adult patients with mild to severe carotid artery disease (carotid stenosis ≥ 30%) evaluated using baseline FLAIR MRI to identify cerebrovascular disease risk subgroups.

E

Exposure

Stratification using K-Means clustering and Random Forest classification based on regional FLAIR MRI biomarkers (intensity and texture).

O

Outcome

Identification of homogeneous patient subgroups based on brain health and cerebrovascular disease (CVD) risk.surrogate

Main Result

p-value: p=<0.001

Limitations

Majority of the cohort had mild stenosis, limiting evaluation of severe carotid artery disease.
Relatively low proportion of female subjects.
Did not consider the effects of treatments or medications.
Cross-sectional analysis limits conclusions about dynamic disease processes.

Ask about this paper

Answers are grounded in this paper and cite their sources.

Implication

Machine learning applied to FLAIR MRI biomarkers can successfully stratify patients with carotid artery disease into distinct subgroups with varying cerebrovascular risk profiles, potentially guiding personalized intervention strategies.

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.

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Chan et al. (2024) conducted an observational in Atherosclerotic disease (carotid artery disease) (n=379). FLAIR MRI biomarker profiling was evaluated on Patient stratification into homogeneous subgroups using K-Means clustering of FLAIR biomarkers (p=<0.001).

synapsesocial.com/papers/6a22e5c356c3bf7831208423 https://doi.org/10.1038/s44303-024-00063-x

View Full Paper

Ask AI

Bookmark

Share

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

Figures

Key Points

Study Design

Structured PICO

Main Result

Limitations

Ask about this paper

Implication

Abstract

Discussion

Cite This Study

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

Figures

Key Points

Study Design

Structured PICO

Main Result

Limitations

Ask about this paper

Implication

Abstract

Discussion

Cite This Study

Keep reading

Keep reading