Related Experiment Video
Updated: Aug 10, 2025
05:12
A Mouse Model for Vascular Cognitive Impairment and Dementia Based on Needle-guided Asymmetric Bilateral Common Carotid Artery Stenosis
Published on: November 22, 2024
640
Unsupervised machine learning model to predict cognitive impairment in subcortical ischemic vascular disease
Qi Qin1, Junda Qu2,3, Yunsi Yin1
1Department of Neurology & Innovation Center for Neurological Disorders, Xuanwu Hospital, Capital Medical University, National Center for Neurological Disorders, Beijing, China.
Alzheimer'S & Dementia : the Journal of the Alzheimer'S Association
|February 14, 2023
Summary
Predicting progression from subcortical ischemic vascular disease (SIVD) to vascular cognitive impairment (SVCI) is challenging. An unsupervised machine learning model using routine imaging accurately identifies patients at risk, aiding early intervention.
Area of Science:
- Neurology
- Radiology
- Artificial Intelligence
Background:
- Subcortical ischemic vascular disease (SIVD) poses a challenge in predicting progression to subcortical vascular cognitive impairment (SVCI).
- Early identification of at-risk patients is crucial for timely intervention and management.
Purpose of the Study:
- To develop and validate an accurate and accessible clinical tool for predicting SVCI progression in SIVD patients.
- To leverage unsupervised machine learning and multimodal imaging data for risk stratification.
Main Methods:
- Collected clinical, neuropsychological, and multimodal imaging data (T1, DTI, rs-fMRI) from SIVD and SVCI patients.
- Developed an unsupervised machine learning model for SVCI prediction.
- Validated the model on an independent external cohort.
Main Results:
- The unsupervised machine learning model achieved high accuracy (86.03% internal, 80.52% external).
- Demonstrated strong sensitivity and specificity in both internal and external validation cohorts.
- The model effectively distinguished patients with SIVD at risk for SVCI progression.
Conclusions:
- An accurate and accessible clinical tool for predicting SIVD to SVCI progression has been developed.
- The model utilizes routine imaging data and is portable for clinical practice.
- This tool can aid in identifying patients requiring closer monitoring and intervention.
