Department of Urology, Rainbow Babies and Children's Hospital/Case Western Reserve University School of Medicine, Cleveland, Ohio.
Division of Pediatric Urology, The Children's Hospital of Philadelphia, Philadelphia, Pennsylvania.
J Urol. 2023 May;209(5):994-1003. doi: 10.1097/JU.0000000000003267. Epub 2023 Feb 14.
Urologists rely heavily on videourodynamics to identify patients with neurogenic bladders who are at risk of upper tract injury, but their interpretation has high interobserver variability. Our objective was to develop deep learning models of videourodynamics studies to categorize severity of bladder dysfunction.
We performed a cross-sectional study of patients aged 2 months to 28 years with spina bifida who underwent videourodynamics at a single institution between 2019 and 2021. The outcome was degree of bladder dysfunction, defined as none/mild, moderate, and severe, defined by a panel of 5 expert reviewers. Reviewers considered factors that increase the risk of upper tract injury, such as poor compliance, elevated detrusor leak point pressure, and detrusor sphincter dyssynergia, in determining bladder dysfunction severity. We built 4 models to predict severity of bladder dysfunction: (1) a random forest clinical model using prospectively collected clinical data from videourodynamics studies, (2) a deep learning convolutional neural network of raw data from the volume-pressure recordings, (3) a deep learning imaging model of fluoroscopic images, (4) an ensemble model averaging the risk probabilities of the volume-pressure and fluoroscopic models.
Among 306 videourodynamics studies, the accuracy and weighted kappa of the ensemble model classification of bladder dysfunction when at least 75% expected bladder capacity was reached were 70% (95% CI 66%,76%) and 0.54 (moderate agreement), respectively. The performance of the clinical model built from data extracted by pediatric urologists was the poorest with an accuracy of 61% (55%, 66%) and a weighted kappa of 0.37.
Our models built from urodynamic pressure-volume tracings and fluoroscopic images were able to automatically classify bladder dysfunction with moderately high accuracy.
泌尿科医生依赖尿动力学录像来识别有发生上尿路损伤风险的神经源性膀胱患者，但他们的解释存在高度的观察者间变异性。我们的目的是开发尿动力学录像深度学习模型，以对膀胱功能障碍的严重程度进行分类。
我们对 2019 年至 2021 年在一家机构接受尿动力学检查的患有脊髓脊膜膨出的 2 个月至 28 岁患者进行了一项横断面研究。结局是膀胱功能障碍的程度，由 5 名专家评审小组定义为无/轻度、中度和重度。评审员在确定膀胱功能障碍的严重程度时考虑了增加上尿路损伤风险的因素，如顺应性差、逼尿肌漏点压升高和逼尿肌括约肌协同失调。我们构建了 4 种模型来预测膀胱功能障碍的严重程度：（1）使用来自尿动力学研究的前瞻性收集的临床数据的随机森林临床模型，（2）来自容积-压力记录的原始数据的深度学习卷积神经网络，（3）荧光透视图像的深度学习成像模型，（4）平均容积-压力和荧光透视模型风险概率的集成模型。
在 306 项尿动力学研究中，当达到至少 75%预期膀胱容量时，集成模型对膀胱功能障碍的分类准确性和加权 kappa 值分别为 70%（95%CI 66%，76%）和 0.54（中度一致）。由儿科泌尿科医生提取数据构建的临床模型的性能最差，准确性为 61%（55%，66%），加权 kappa 值为 0.37。
我们从尿动力压力-容积描记和荧光透视图像中构建的模型能够以中等准确度自动对膀胱功能障碍进行分类。
