Deyi Huang,1 Xingan Yang,2 Hongbiao Ruan,3 Yushui Zhuo,1 Kai Yuan,4 Bowen Ruan,1 Fang Li1 

1Department of Ultrasound, The People’s Hospital of Yuhuan, Yuhuan City, Zhejiang Province, People’s Republic of China; 2Department of Ultrasound, Taizhou Hospital of Zhejiang Province, Linhai City, Zhejiang Province, People’s Republic of China; 3Department of Cardiology, The People’s Hospital of Yuhuan, Yuhuan City, Zhejiang Province, People’s Republic of China; 4Department of Clinical Laboratory, The People’s Hospital of Yuhuan, Yuhuan City, Zhejiang Province, People’s Republic of China

Correspondence: Fang Li, Department of Ultrasound, The People’s Hospital of Yuhuan, No. 18, Changle Road, Yuhuan City, Zhejiang Province, 317600, People’s Republic of China, Tel +8613967672898, Email 3260772796@qq.com

Introduction: Chronic coronary artery disease (CAD) management often relies on myocardial contrast echocardiography (MCE), yet its effectiveness is limited by subjective interpretations and difficulty in distinguishing hibernating from necrotic myocardium. This study explores the integration of machine learning (ML) with radiomics to predict functional recovery in dyskinetic myocardial segments in CAD patients undergoing revascularization, aiming to overcome these limitations.
Methods: This prospective study enrolled 55 chronic CAD patients, dividing into training (39 patients, 205 segments) and testing sets (16 patients, 68 segments). Dysfunctional myocardial segments were identified by initial wall motion scores (WMS) of ≥ 2 (hypokinesis or higher). Functional recovery was defined as a decrease of ≥ 1 grade in WMS during follow-up echocardiography. Radiomics features were extracted from dyssynergic segments in end-systolic phase MCE images across five cardiac cycles post- “flash” impulse and processed through a five-step feature selection. Four ML classifiers were trained and compared using these features and MCE parameters, to identify the optimal model for myocardial recovery prediction.
Results: Functional improvement was noted in 139 out of 273 dyskinetic segments (50.9%) following revascularization. Receiver Operating Characteristic (ROC) analysis determined that myocardial blood flow (MBF) was the most precise clinical predictor of recovery, with an area under the curve (AUC) of 0.770. Approximately 1.34 million radiomics features were extracted, with nine features identified as key predictors of myocardial recovery. The random forest (RF) model, integrating MBF values and radiomics features, demonstrated superior predictive accuracy over other ML classifiers. Validation of the RF model on the testing dataset demonstrated its effectiveness, evidenced by an AUC of 0.821, along with consistent calibration and clinical utility.
Conclusion: The integration of ML with radiomics from MCE effectively predicts myocardial recovery in CAD. The RF model, combining radiomics and MBF values, presents a non-invasive, precise approach, significantly enhancing CAD management.

Keywords: coronary artery disease, myocardial contrast echocardiography, radiomics, machine learning, myocardial recovery prediction, random forest