Related Experiment Video
Updated: Dec 2, 2025
Hybrid PET/MRI Imaging of Alzheimer's Disease Based on 18F-AV-1451
Published on: April 18, 2025
Prediction of amyloid β PET positivity using machine learning in patients with suspected cerebral amyloid angiopathy
Young Hee Jung1,2,3, Hyejoo Lee2,3,4, Hee Jin Kim2,3,4
1Department of Neurology, College of Medicine, Myoungji Hospital, Hanyang University, Goyang, Republic of Korea.
Abstract:
Amyloid-β(Aβ) PET positivity in patients with suspected cerebral amyloid angiopathy (CAA) MRI markers is predictive of a worse cognitive trajectory, and it provides insights into the underlying vascular pathology (CAA vs. hypertensive angiopathy) to facilitate prognostic prediction and appropriate treatment decisions. In this study, we applied two interpretable machine learning algorithms, gradient boosting machine (GBM) and random forest (RF), to predict Aβ PET positivity in patients with CAA MRI markers. In the GBM algorithm, the number of lobar cerebral microbleeds (CMBs), deep CMBs, lacunes, CMBs in dentate nuclei, and age were ranked as the most influential to predict Aβ positivity. In the RF algorithm, the absence of diabetes was additionally chosen. Cut-off values of the above variables predictive of Aβ positivity were as follows: (1) the number of lobar CMBs > 16.4(GBM)/14.3(RF), (2) no deep CMBs(GBM/RF), (3) the number of lacunes > 7.4(GBM/RF), (4) age > 74.3(GBM)/64(RF), (5) no CMBs in dentate nucleus(GBM/RF). The classification performances based on the area under the receiver operating characteristic curve were 0.83 in GBM and 0.80 in RF. Our study demonstrates the utility of interpretable machine learning in the clinical setting by quantifying the relative importance and cutoff values of predictive variables for Aβ positivity in patients with suspected CAA markers.
Insights
Machine learning models predict amyloid-β PET positivity in suspected cerebral amyloid angiopathy (CAA) using MRI markers. Key predictors include microbleeds, lacunes, and age, aiding in prognostic assessment for better patient care.
Area of Science:
- Neurology
- Radiology
- Artificial Intelligence
Background:
- Cerebral amyloid angiopathy (CAA) is a significant cause of cognitive decline.
- Amyloid-β (Aβ) PET positivity indicates underlying pathology and predicts cognitive trajectory.
- Distinguishing CAA from hypertensive angiopathy is crucial for prognosis and treatment.
Purpose of the Study:
- To apply interpretable machine learning (gradient boosting machine and random forest) to predict Aβ PET positivity in patients with suspected CAA MRI markers.
- To identify key MRI-derived predictors of Aβ PET positivity.
- To establish cutoff values for these predictors to aid clinical decision-making.
Main Methods:
- Utilized gradient boosting machine (GBM) and random forest (RF) algorithms.
- Input features included various cerebral microbleed (CMB) locations, lacunes, age, and diabetes status.
- Evaluated classification performance using the area under the receiver operating characteristic curve (AUC).
Main Results:
- GBM identified lobar CMBs, deep CMBs, lacunes, dentate nucleus CMBs, and age as most influential.
- RF included the absence of diabetes as an additional predictor.
- Achieved AUCs of 0.83 for GBM and 0.80 for RF, demonstrating strong predictive performance.
- Specific cutoff values for key predictors were determined.
Conclusions:
- Interpretable machine learning models effectively predict Aβ PET positivity in suspected CAA.
- Quantified the relative importance and established cutoff values for MRI-based predictors.
- These findings support the clinical utility of machine learning for prognostic prediction in CAA.
More Related Videos
09:31Visualization of Amyloid β Deposits in the Human Brain with Matrix-assisted Laser Desorption/Ionization Imaging Mass Spectrometry
Published on: March 7, 2019
08:25Detecting Amyloid-β Accumulation via Immunofluorescent Staining in a Mouse Model of Alzheimer's Disease
Published on: April 19, 2021