AIPEDURO

Sloan et al. (2023)

June 7, 2024

Written by:

Hydronephrosis Classification

Article DOI	https://doi.org/10.4111/icu.20230170
Objective	To identify high-grade hydronephrosis from renal ultrasound extracted features
AI Approach	SVM
Data Source(s)	Single institutional series (592 patients)
Model Input	Radiomic quantitative features from renal ultrasound including contrast, correlation, difference entropy/energy, and gray-level co-occurrence matrix
Model Outcome	High vs. Low grade hydronephrosis
Model Metrics	AUC 0.86, sensitivity 76%, specificity 86%
Model Usability	NA

AI = Artificial intelligence, SVM = Support vector machines, AUC = Area under the receiver operator characteristic