Department of Urology, Boston Children's Hospital, Boston, MA, USA.
Department of Urology, Boston Children's Hospital, Boston, MA, USA.
J Pediatr Urol. 2024 Apr;20(2):271-278. doi: 10.1016/j.jpurol.2023.11.003. Epub 2023 Nov 9.
Urinary Tract Dilation (UTD) classification has been designed to be a more objective grading system to evaluate antenatal and post-natal UTD. Due to unclear association between UTD classifications to specific anomalies such as vesico-ureteral reflux (VUR), management recommendations tend to be subjective.
We sought to develop a model to reliably predict VUR from early post-natal ultrasound.
Radiology records from single institution were reviewed to identify infants aged 0-90 days undergoing early ultrasound for antenatal UTD. Medical records were reviewed to confirm diagnosis of VUR. Primary outcome defined as dilating (≥Gr3) VUR. Exclusion criteria include major congenital urologic anomalies (bilateral renal agenesis, horseshoe kidney, cross fused ectopia, exstrophy) as well as patients without VCUG. Data were split into training/testing sets by 4:1 ratio. Machine learning (ML) algorithm hyperparameters were tuned by the validation set.
In total, 280 patients (540 renal units) were included in the study (73 % male). Median (IQR) age at ultrasound was 27 (18-38) days. 66 renal units were found to have ≥ grade 3 VUR. The final model included gender, ureteral dilation, parenchymal appearance, parenchymal thickness, central calyceal dilation. The model predicted VUR with AUC at 0.81(0.73-0.88) on out-of-sample testing data. Model is shown in the figure.
We developed a ML model that can predict dilating VUR among patients with hydronephrosis in early ultrasound. The study is limited by the retrospective and single institutional nature of data source. This is one of the first studies demonstrating high performance for future diagnosis prediction in early hydronephrosis cohort.
By predicting dilating VUR, our predictive model using machine learning algorithm provides promising performance to facilitate individualized management of children with prenatal hydronephrosis, and identify those most likely to benefit from VCUG. This would allow more selective use of this test, increasing the yield while also minimizing overutilization.
尿路扩张（UTD）分类旨在成为一种更客观的分级系统，用于评估产前和产后 UTD。由于 UTD 分类与特定异常（如膀胱输尿管反流（VUR））之间的关联不明确，因此管理建议往往具有主观性。
我们试图开发一种能够从产后早期超声中可靠预测 VUR 的模型。
回顾单机构的放射学记录，以确定在产前 UTD 接受早期超声检查的 0-90 天大的婴儿。审查病历以确认 VUR 的诊断。主要结局定义为扩张（≥Gr3）VUR。排除标准包括重大先天性泌尿系统异常（双侧肾发育不全、马蹄肾、交叉融合外生、外胚层）以及无 VCUG 的患者。数据通过 4:1 的比例分为训练/测试集。通过验证集调整机器学习（ML）算法超参数。
共有 280 名患者（540 个肾脏单位）纳入研究（73%为男性）。超声检查时的中位（IQR）年龄为 27（18-38）天。66 个肾脏单位发现≥3 级 VUR。最终模型包括性别、输尿管扩张、实质外观、实质厚度、中央肾盏扩张。该模型在样本外测试数据中的 AUC 为 0.81（0.73-0.88），预测 VUR。模型如图所示。
我们开发了一种机器学习模型，可以预测早期超声中肾积水患者的扩张性 VUR。该研究受到数据来源回顾性和单机构性质的限制。这是首次在早期肾积水队列中展示高预测性能的研究之一。
通过预测扩张性 VUR，我们使用机器学习算法的预测模型为产前肾积水儿童的个体化管理提供了有前途的表现，并确定了最有可能从 VCUG 中受益的患者。这将允许更有选择性地使用这项测试，在提高产量的同时最大限度地减少过度使用。
