MCH-Guard: Multimodal Machine Learning Framework for Risk Stratification of Cerebral Microhemorrhage Risk in the Alzheimer’s Disease Neuroimaging Initiative
Discuss this preprint
Start a discussion What are Sciety discussions?Listed in
This article is not in any list yet, why not save it to one of your lists.Abstract
Background
Efficient cerebral microhemorrhage (MCH) monitoring is critical for anti-amyloid therapy safety due to ARIA-H risk. We developed MCH-Guard, a multimodal machine-learning framework, to stratify MCH risk using ADNI data (N=813).
Methods
Nested models integrated clinical history, fluid biomarkers, and imaging to predict MCH presence, incidence, and stability.
Results
The comprehensive model detected baseline MCH with high accuracy (AUC 0.86). Notably, the “minimal” model (M1), utilizing only demographics and clinical history, achieved robust performance (AUC 0.82). Longitudinal models predicted time-to-onset (R 2 =0.68) and stratified four-year risk. Furthermore, we identified a transient vascular instability phenotype—where MCH status fluctuates— which was strongly predicted by hepatic factors.
Conclusions
MCH-Guard offers a flexible clinical decision-support tool for optimizing spontaneous MCH & ARIA surveillance. The strong performance of the clinical-only M1 model supports equitable risk assessment in resource-limited settings, while the characterization of vascular instability addresses a critical confounder in safety monitoring.
