What question did this study set out to answer?

To develop an echocardiography-based radiomics model for predicting the prognosis of acute ischemic stroke.

May 8, 2026

Abstract Number: Esoc2026a373 Echocardiography-Based Clinical-Radiomics Model for Prognostic Prediction of Acute Ischemic Stroke

Key Points

To develop an echocardiography-based radiomics model for predicting the prognosis of acute ischemic stroke.
Prospective enrollment of 295 patients divided into training (n=236) and validation (n=59) sets.
Manual segmentation of mitral valve regions on echocardiographic images and application of LASSO and mRMR for feature selection.
Construction of radiomics models using logistic regression, random forest, and various support vector classification algorithms.
Identified 32 valuable features from the mitral valve annulus and 12 from the leaflets after dimensionality reduction.
CSVC model using annulus features achieved an AUC of 0.893 and 0.773 in training and validation sets, respectively.
Combined CSVC model with clinical features reached AUC values of 0.903 during cross-validation and 0.884 in external validation.

Abstract

Abstract Background and aims To establish an echocardiography-based clinical-radiomics model for predicting the prognosis of acute ischemic stroke (AIS) using three-dimensional echocardiography with a specialized LA-dedicated software. Methods A total of 295 patients were prospectively enrolled and randomly divided into a training set (n=236) and an external validation set (n=59). Two distinct mitral valve regions - leaflets (ROI1) and annulus (ROI2) - were manually segmented on echocardiographic images. After dimensionality reduction and feature selection using the minimum redundancy maximum relevance (mRMR) and least absolute shrinkage and selection operator (LASSO) methods, radiomics models were constructed by logistic regression (LR), random forest (RF), C-support vector classification (CSVC), nu-support vector classification (NuSVC), Adaptive Boosting (AdaBoost), and extreme gradient boosting (XGBoost) algorithms. Clinical features identified by mRMR were incorporated to construct a combined model, with model performance assessed through receiver operating characteristic (ROC) analysis. Results From each ROI, a total of 1595 radiomics features were derived. Following dimensionality reduction and selection processes, 32 and 12 valuable radiomic features were identified from ROI1 and ROI2, respectively. Among the various radiomics models tested, the CSVC model based on ROI2 demonstrated superior predictive efficiency and robustness, achieving an area under the curve (AUC) of 0.893 in five-fold cross-validation and 0.773 in the external validation set. Integration of clinical features further enhanced predictive performance, with the combined CSVC model attaining AUC values of 0.903 and 0.884 in cross-validation and external validation respectively. Conclusions The echocardiography-based radiomics, especially on annulus of the mitral valve holds the potential as a non-invasive tool for prognostic prediction of AIS. Conflict of interest Xia Zhang: nothing to disclose; Jiahui Yan:nothing to disclose; Fengmei Li:nothing to disclose;Chen Gang: nothing to disclose; Yanni Wu: nothing to disclose; Hui Li:nothing to disclose

Bookmark

Cite This Study

Zhang et al. (Fri,) studied this question.

synapsesocial.com/papers/69fd7fa1bfa21ec5bbf081e3 https://doi.org/https://doi.org/10.1093/esj/aakag023.273

Bookmark