University Hospitals Southampton, NHS Trust, Southampton, United Kingdom.
Polytechnic University of Le Marche, Ancona, Italy.
J Endourol. 2024 Oct;38(10):1044-1055. doi: 10.1089/end.2024.0120. Epub 2024 Aug 12.
We aimed to develop machine learning (ML) algorithms for the automated prediction of postoperative ureteroscopy outcomes for pediatric kidney stones based on preoperative characteristics. Data from pediatric patients who underwent ureteroscopy for stone treatment by a single experienced surgeon, between 2010 and 2023 in Southampton General Hospital, were retrospectively collected. Fifteen ML classification algorithms were used to investigate correlations between preoperative characteristics and postoperative outcomes: primary stone-free status (SFS, defined as stone fragments <2 mm at the end of the procedure confirmed endoscopically and no evidence of stone fragments >2 mm at Xray kidney-ureters-bladder (XR KUB) or ultrasound kidney-ureters-bladder (US KUB) at 3 months follow-up) and complications. For the task of complication and stone status, an ensemble model was made out of Bagging classifier, Extra Trees classifier, and linear discriminant analysis. Also, a multitask neural network was constructed for the simultaneous prediction of all postoperative characteristics. Finally, explainable artificial intelligence techniques were used to explain the prediction made by the best models. The ensemble model produced the highest accuracy (90%) in predicting SFS, finding correlation with overall stone size (-0.205), presence of multiple stones (-0.127), and preoperative stenting (-0.102). Complications were predicted by Synthetic Minority Oversampling Technique (SMOTE) oversampled dataset (93.3% accuracy) with relation to preoperative positive urine culture (-0.060) a1nd SFS (0.003). Training ML for the multitask model, accuracies of 83.3% and 80% were respectively reached. ML has a great potential of assisting health care research, with possibilities to investigate dataset at a higher level. With the aid of this intelligent tool, urologists can implement their practice and develop new strategies for outcome prediction and patient counseling and informed shared decision-making. Our model reached an excellent accuracy in predicting SFS and complications in the pediatric population, leading the way to the validation of patient-specific predictive tools.
我们旨在开发机器学习（ML）算法，以便根据术前特征自动预测儿童肾结石经输尿管镜手术后的结果。该研究回顾性收集了 2010 年至 2023 年期间，在南安普顿综合医院由同一位经验丰富的外科医生进行输尿管镜碎石术治疗的小儿患者的数据。使用了 15 种 ML 分类算法来研究术前特征与术后结果之间的相关性：主要结石清除状态（SFS，定义为手术结束时结石碎片<2mm，并在 3 个月随访时经内镜证实，且 X 射线肾输尿管膀胱（XR KUB）或超声肾输尿管膀胱（US KUB）无>2mm 的结石碎片）和并发症。对于并发症和结石状态的任务，采用 Bagging 分类器、Extra Trees 分类器和线性判别分析构建集成模型。此外，还构建了一个多任务神经网络，用于同时预测所有术后特征。最后，使用可解释人工智能技术来解释最佳模型的预测结果。集成模型在预测 SFS 方面产生了最高的准确率（90%），发现与总体结石大小（-0.205）、存在多个结石（-0.127）和术前支架置入（-0.102）相关。并发症由 Synthetic Minority Oversampling Technique（SMOTE）过采样数据集（准确率 93.3%）预测，与术前阳性尿培养（-0.060）和 SFS（0.003）有关。在多任务模型中进行 ML 训练，分别达到了 83.3%和 80%的准确率。机器学习在辅助医疗保健研究方面具有很大的潜力，可以在更高的水平上研究数据集。有了这个智能工具，泌尿科医生可以实施他们的实践，并为结果预测和患者咨询以及知情共享决策制定新的策略。我们的模型在预测小儿人群的 SFS 和并发症方面达到了优异的准确性，为验证针对特定患者的预测工具铺平了道路。
