Comparison and interpretation of ultrasound-based radiomics machine learning models for assessing renal fibrosis in chronic kidney disease.
Authors
Affiliations (3)
Affiliations (3)
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Kowloon, Hong Kong. Electronic address: [email protected].
- Ultrasound Department, EDAN Instruments, Inc., Shenzhen, China.
- Department of Ultrasound, The Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, China; Department of Ultrasound, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China.
Abstract
Renal fibrosis is a key pathological feature of chronic kidney disease (CKD), yet its noninvasive evaluation remains challenging. Radiomics provides a quantitative approach for extracting image-based biomarkers from ultrasound, and machine learning techniques may further enhance diagnostic accuracy for fibrosis severity assessment. To compare and interpret machine learning models that utilize radiomics features extracted from ultrasound images for the evaluation of renal fibrosis severity in CKD patients. This study included 182 CKD patients (mean age, 40.91 ± 14.55 years; 101 men and 81 women) who underwent renal ultrasound and kidney biopsy. Radiomics features were extracted from ultrasound images to generate a radiomics signature. Five machine learning classifiers, including eXtreme Gradient Boosting, logistic regression, support vector machine, K-Nearest Neighbor, and random forest, were developed by combining the radiomics signature with key clinical variables identified through multiple algorithms. Model performance was assessed using receiver operating characteristic (ROC) and precision-recall curves. Interpretability was achieved through SHapley Additive Explanations (SHAP). The logistic regression model achieved the most favorable diagnostic performance, with an area under the curve (AUC) of 0.86 (95% CI: 0.80-0.92) and an F1 score of 0.81 (95% CI: 0.78-0.84) in the primary cohort, and an AUC of 0.84 (95% CI: 0.71-0.98) and an F1 score of 0.82 (95% CI: 0.75-0.89) in cross-validation. SHAP analysis identified estimated glomerular filtration rate (eGFR) as the most influential feature, followed by the radiomics signature, age, and renal parenchyma thickness. The logistic regression model combining ultrasound-based radiomics and clinical information demonstrates strong potential for noninvasive renal fibrosis stratification in CKD, with SHAP facilitating transparent model interpretation.