Related Experiment Video
Updated: Jun 30, 2026
Ultrasonic Assessment of Myocardial Microstructure
Published on: January 14, 2014
A machine learning approach using echocardiographic and hematological parameters to classify cerebral small vessel
1Department of Cardiology, Nanchong Second People's Hospital, Nanchong, Sichuan, China.
Insights
Machine learning models using echocardiography and blood tests can effectively stratify cerebral small vessel disease (CSVD) burden. This approach offers a valuable alternative to MRI for identifying patients at high risk.
Area of Science:
- Cardiology
- Neurology
- Biomedical Engineering
Background:
- Cerebral small vessel disease (CSVD) is a major cause of stroke and dementia.
- Brain MRI is the standard for CSVD assessment but has limitations.
- Cardiac and hematological factors are linked to CSVD.
Purpose of the Study:
- To develop machine learning (ML) models for CSVD burden stratification.
- Utilize routine echocardiographic and hematological parameters.
- Provide an alternative to MRI for CSVD assessment.
Main Methods:
- Retrospective study of 446 patients with MRI-confirmed CSVD.
- Classified patients into low-burden (CSVD-L) and high-burden (CSVD-H) groups.
- Employed eight ML algorithms for binary classification, assessing model performance and feature importance.
Main Results:
- High CSVD burden linked to echocardiographic changes and lower fibrin(ogen) degradation products (FDP), D-dimer, and fibrin formation rate (FbFR).
- The Random Forest (RF) model demonstrated high discriminative performance (AUC 0.885).
- FbFR was identified as the most crucial feature using SHAP analysis.
Conclusions:
- ML models integrating echocardiographic and hematological data effectively stratify CSVD burden.
- The RF model shows potential as a supplementary tool for CSVD risk stratification where MRI is inaccessible.
- External validation is needed to confirm generalizability and clinical utility.
Background:
Cerebral small vessel disease (CSVD) is a leading cause of stroke and dementia and is associated with cardiac and hematological biomarkers. Although brain magnetic resonance imaging (MRI) remains the reference standard for assessing CSVD burden, its cost and contraindications limit widespread clinical application.
Aim:
To develop machine learning (ML) models based on routine echocardiographic and hematological parameters for CSVD burden stratification.
Methods:
In this retrospective study, 446 patients with MRI-confirmed CSVD were classified into low-burden (CSVD-L, n = 314) and high-burden (CSVD-H, n = 132) groups using the validated total CSVD score (0-2 vs. 3-4). Clinical characteristics, echocardiographic parameters, and hematological biomarkers were compared between the two groups. Variables significant on univariate analysis were entered into eight ML algorithms for binary classification of CSVD burden. Model performance and feature importance were assessed.
Results:
Patients with high CSVD burden exhibited distinct echocardiographic alterations suggestive of structural remodeling and subclinical diastolic dysfunction, as well as significantly lower fibrin(ogen) degradation products (FDP), D-dimer, and fibrin formation rate (FbFR). The Random Forest (RF) model achieved the highest discriminative performance (AUC 0.885). Shapley Additive exPlanations (SHAP) analysis identified FbFR as the most important feature.
Conclusion:
Integration of routine echocardiographic and hematological parameters within a machine learning framework can effectively stratify CSVD burden. The RF model shows promise as a supplementary tool for CSVD risk stratification in settings where MRI is unavailable. Future prospective external validation is warranted to confirm the generalizability and clinical utility of this approach.
More Related Videos
07:30Evaluation of the Cognitive Performance of Hypertensive Patients with Silent Cerebrovascular Lesions
Published on: April 23, 2021
11:13Quantification of Mouse Heart Left Ventricular Function, Myocardial Strain, and Hemodynamic Forces by Cardiovascular Magnetic Resonance Imaging
Published on: May 24, 2021
