Khondker Adree, Hua Stanley Bryan Z, Kwong Jethro C C, Sheth Kunj, Alvarez Daniel, Velaer Kyla N, Weaver John, Xiang Alice, Tasian Gregory E, Lorenzo Armando J, Goldenberg Anna, Rickard Mandy, Erdman Lauren
Department of Surgery, University of Toronto, Toronto, Canada.
Division of Urology, Hospital for Sick Children, Toronto, Canada.
PLOS Digit Health. 2025 Aug 4;4(8):e0000939. doi: 10.1371/journal.pdig.0000939. eCollection 2025 Aug.
The potential of deep learning to predict renal obstruction using kidney ultrasound images has been demonstrated. However, these image-based classifiers have incorporated information using only single-visit ultrasounds. Here, we developed machine learning (ML) models incorporating ultrasounds from multiple clinic visits for hydronephrosis to generate a hydronephrosis severity index score to discriminate patients into high versus low risk for needing pyeloplasty and compare these against models trained with single clinic visit data. We included patients followed for hydronephrosis from three institutions. The outcome of interest was low risk versus high risk of obstructive hydronephrosis requiring pyeloplasty. The model was trained on data from Toronto, ON and validated on an internal holdout set, and tested on an internal prospective set and two external institutions. We developed models trained with single ultrasound (single-visit) and multi-visit models using average prediction, convolutional pooling, long-short term memory and temporal shift models. We compared model performance by area under the receiver-operator-characteristic (AUROC) and area under the precision-recall-curve (AUPRC). A total of 794 patients were included (603 SickKids, 102 Stanford, and 89 CHOP) with a pyeloplasty rate of 12%, 5%, and 67%, respectively. There was no significant difference in developing single-visit US models using the first ultrasound vs. the latest ultrasound. Comparing single-visit vs. multi-visit models, all multi-visit models fail to produce AUROC or AUPRC significantly greater than single-visit models. We developed ML models for hydronephrosis that incorporate multi-visit inference across multiple institutions but did not demonstrate superiority over single-visit inference. These results imply that the single-visit models would be sufficient in aiding accurate risk stratification from single, early ultrasound images.
深度学习利用肾脏超声图像预测肾梗阻的潜力已得到证实。然而，这些基于图像的分类器仅使用单次就诊的超声信息。在此，我们开发了机器学习（ML）模型，该模型纳入了多次临床就诊时的肾积水超声数据，以生成肾积水严重程度指数评分，从而将患者区分为肾盂成形术高风险和低风险，并将这些模型与使用单次临床就诊数据训练的模型进行比较。我们纳入了来自三个机构的肾积水随访患者。感兴趣的结果是需要肾盂成形术的梗阻性肾积水的低风险与高风险。该模型在安大略省多伦多的数据上进行训练，并在内部保留集上进行验证，在内部前瞻性集和两个外部机构上进行测试。我们开发了使用平均预测、卷积池化、长短期记忆和时间偏移模型的单超声（单次就诊）和多次就诊模型。我们通过受试者工作特征曲线下面积（AUROC）和精确召回曲线下面积（AUPRC）比较模型性能。总共纳入了794例患者（603例来自 SickKids，102例来自斯坦福，89例来自CHOP），肾盂成形术发生率分别为12%、5%和67%。使用首次超声与最新超声开发单次就诊超声模型没有显著差异。比较单次就诊模型和多次就诊模型，所有多次就诊模型的AUROC或AUPRC均未显著高于单次就诊模型。我们开发了用于肾积水的ML模型，该模型纳入了多个机构的多次就诊推理，但未显示出优于单次就诊推理的优势。这些结果表明，单次就诊模型足以帮助从单次早期超声图像进行准确的风险分层。
