AlAzab Rami, Ghammaz Owais, Ardah Nabil, Al-Bzour Ayah, Zeidat Layan, Mawali Zahraa, Ahmed Yaman B, Alguzo Tha'er Abdulkareem, Al-Alwani Azhar Mohanad, Samara Mahmoud
Department of General Surgery and Urology, King Abdullah University Hospital, Irbid, Jordan.
Faculty of Medicine, Jordan University of Science and Technology, Irbid, Jordan.
Int J Nephrol Renovasc Dis. 2023 Sep 11;16:197-206. doi: 10.2147/IJNRD.S427404. eCollection 2023.
The study aimed to create a machine learning model (MLM) to predict the stone-free status (SFS) of patients undergoing percutaneous nephrolithotomy (PCNL) and compare its performance to the S.T.O.N.E. and Guy's stone scores.
This is a retrospective study that included 320 PCNL patients. Pre-operative and post-operative variables were extracted and entered into three MLMs: RFC, SVM, and XGBoost. The methods used to assess the performance of each were mean bootstrap estimate, 10-fold cross-validation, classification report, and AUC. Each model was externally validated and evaluated by mean bootstrap estimate with CI, classification report, and AUC.
Out of the 320 patients who underwent PCNL, the SFS was found to be 69.4%. The RFC mean bootstrap estimate was 0.75 and 95% CI: [0.65-0.85], 10-fold cross-validation of 0.744, an accuracy of 0.74, and AUC of 0.761. The XGBoost results were 0.74 [0.63-0.85], 0.759, 0.72, and 0.769, respectively. The SVM results were 0.70 [0.60-0.79], 0.725, 0.74, and 0.751, respectively. The AUC of Guy's stone score and the S.T.O.N.E. score were 0.666 and 0.71, respectively. The RFC external validation set had a mean bootstrap estimate of 0.87 and 95% CI: [0.81-0.92], an accuracy of 0.70, and an AUC of 0.795, While the XGBoost results were 0.84 [0.78-0.91], 0.74, and 0.84, respectively. The SVM results were 0.86 [0.80-0.91], 0.79, and 0.858, respectively.
MLMs can be used with high accuracy in predicting SFS for patients undergoing PCNL. MLMs we utilized predicted the SFS with AUCs superior to those of GSS and S.T.O.N.E scores.
本研究旨在创建一个机器学习模型（MLM），以预测接受经皮肾镜取石术（PCNL）患者的无石状态（SFS），并将其性能与S.T.O.N.E.和盖伊结石评分进行比较。
这是一项回顾性研究，纳入了320例PCNL患者。提取术前和术后变量并输入三个MLM：随机森林分类器（RFC）、支持向量机（SVM）和极端梯度提升（XGBoost）。用于评估每个模型性能的方法有平均自助法估计、十折交叉验证、分类报告和曲线下面积（AUC）。每个模型通过带有置信区间（CI）的平均自助法估计、分类报告和AUC进行外部验证和评估。
在320例行PCNL的患者中，发现SFS为69.4%。RFC的平均自助法估计值为0.75，95%CI：[0.65 - 0.85]，十折交叉验证值为0.744，准确率为0.74，AUC为0.761。XGBoost的结果分别为0.74 [0.63 - 0.85]、0.759、0.72和0.769。SVM的结果分别为0.70 [0.60 - 0.79]、0.725、0.74和0.751。盖伊结石评分和S.T.O.N.E.评分的AUC分别为0.666和0.71。RFC外部验证集的平均自助法估计值为0.87，95%CI：[0.81 - 0.92]，准确率为0.70，AUC为0.795，而XGBoost的结果分别为0.84 [0.78 - 0.91]、0.74和0.84。SVM的结果分别为0.86 [0.80 - 0.91]、0.79和0.858。
MLM可高精度地用于预测接受PCNL患者的SFS。我们使用的MLM预测SFS的AUC优于GSS和S.T.O.N.E评分。
