1. The Hydronephrosis Severity Index guides paediatric antenatal hydronephrosis management based on artificial intelligence applied to ultrasound images alone
- Author
-
Lauren Erdman, Mandy Rickard, Erik Drysdale, Marta Skreta, Stanley Bryan Hua, Kunj Sheth, Daniel Alvarez, Kyla N. Velaer, Michael E. Chua, Joana Dos Santos, Daniel Keefe, Norman D. Rosenblum, Megan A. Bonnett, John Weaver, Alice Xiang, Yong Fan, Bernarda Viteri, Christopher S. Cooper, Gregory E. Tasian, Armando J. Lorenzo, and Anna Goldenberg
- Subjects
Medicine ,Science - Abstract
Abstract Antenatal hydronephrosis (HN) impacts up to 5% of pregnancies and requires close, frequent follow-up monitoring to determine who may benefit from surgical intervention. To create an automated HN Severity Index (HSI) that helps guide clinical decision-making directly from renal ultrasound images. We applied a deep learning model to paediatric renal ultrasound images to predict the need for surgical intervention based on the HSI. The model was developed and studied at four large quaternary free-standing paediatric hospitals in North America. We evaluated the degree to which HSI corresponded with surgical intervention at each hospital using area under the receiver-operator curve, area under the precision-recall curve, sensitivity, and specificity. HSI predicted subsequent surgical intervention with > 90% AUROC, > 90% sensitivity, and > 70% specificity in a test set of 202 patients from the same institution. At three external institutions, HSI corresponded with AUROCs ≥ 90%, sensitivities ≥ 80%, and specificities > 50%. It is possible to automatically and reliably assess HN severity directly from a single ultrasound. The HSI stratifies low- and high-risk HN patients thus helping to triage low-risk patients while maintaining very high sensitivity to surgical cases. HN severity can be predicted from a single patient ultrasound using a novel image-based artificial intelligence system.
- Published
- 2024
- Full Text
- View/download PDF