Transplant renal artery stenosis: utilization of machine learning to identify ancillary sonographic and doppler parameters to predict stenosis in patients with graft dysfunction

• Published in: Abdominal imaging Vol. 48; no. 6; pp. 2102 - 2110
• Main Authors: Blain, Yamile, Alessandrino, Francesco, Scortegagna, Eduardo, Balcacer, Patricia
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.06.2023; Springer Nature B.V
• Subjects: Algorithms; Aliasing; Bladder; Chi-square test; Constriction, Pathologic; Gastroenterology; Gray scale; Hepatology; Humans; Imaging; Kidney; Kidney transplantation; Kidneys; Learning algorithms; Machine learning; Mathematical models; Medicine; Medicine & Public Health; Parameter identification; Parameter sensitivity; Radiology; Renal artery; Renal Artery Obstruction - diagnostic imaging; Renal function; Retroperitoneum; Retrospective Studies; Sensitivity; Statistical analysis; Stenosis; Training; Ultrasonography, Doppler; Ureters; Velocity; Renal transplant; Transplant renal artery stenosis; Doppler ultrasound; Machine learning
• ISSN: 2366-0058; 2366-004X; 2366-0058
• DOI: 10.1007/s00261-023-03872-7

Purpose To determine if ancillary sonographic and Doppler parameters can be used to predict transplant renal artery stenosis in patients with renal graft dysfunction. Materials and methods IRB-approved, HIPAA-compliant retrospective study included 80 renal transplant patients who had renal US followed by renal angiogram between January 2018 and December 2019. A consensus read of two radiologists recorded these parameters: peak systolic velocity, persistence of elevated velocity, grayscale narrowing, parvus tardus, delayed systolic upstroke, angle of the systolic peak (SP angle), and aliasing. Univariate analysis using t-test or chi-square was performed to determine differences between patients with and without stenosis. P values under 0.05 were deemed statistically significant. We used machine learning algorithms to determine parameters that could better predict the presence of stenosis. The algorithms included logistic regression, random forest, imbalanced random forest, boosting, and CART. All 80 cases were split between training and testing using stratified sampling using a 75:25 split. Results We found a statistically significant difference in grayscale narrowing ( p  = 0.0010), delayed systolic upstroke ( p  = 0.0002), SP angle ( p  = 0.0005), and aliasing ( p  = 0.0024) between the two groups. No significant difference was found for an elevated peak systolic velocity ( p  = 0.1684). The imbalanced random forest (IRF) model was selected for improved accuracy, sensitivity, and specificity. Specificity, sensitivity, AUC, and normalized Brier score for the IRF model using all parameters were 73%, 81%, 0.82, and 69 in the training set, and 78%, 58%, 0.78, and 80 in the testing set. VIMP assessment showed that the combination of variables that resulted in the most significant change of the training set performance was that of grayscale narrowing and SP angle. Conclusion Elevated peak systolic velocity did not discriminate between patients with and without TRAS. Adding ancillary parameters into the machine learning algorithm improved specificity and sensitivity similarly in the training and testing sets. The algorithm identified the combination of lumen narrowing coupled with the angle of the systolic peak as better predictor of TRAS. This model may improve the accuracy of ultrasound for transplant renal artery stenosis.