目的:基于随机森林和XGBoost两种机器学习算法建立预测模型,探讨其对肾结石患者行输尿管软镜碎石术(flexible ureteroscopic lithotripsy,fURL)后早期结石清除率(stone-free rate, SFR)的预测价值。方法:回顾性分析201例行fURL的肾结石患者的临床资料,根据术后是否达到结石清除标准,将患者分为结石清除组和结石残留组。比较两组患者年龄、体重指数(body mass index,BMI)、结石数目、结石体积、结石密度和肾积水等因素的差异。对于肾下盏结石,需测量肾脏解剖相关指标,包括肾盂漏斗部夹角、肾下盏宽度、肾下盏长度及肾盂肾下盏高度。将上述潜在影响因素分别纳入随机森林和XGBoost算法建立预测模型,绘制受试者工作曲线,检验模型预测价值。前瞻性收集71例患者的临床资料对模型进行外部验证。结果:201例fURL手术均顺利完成,一期手术早期SFR为61.2%。利用随机森林和XGBoost算法建立预测模型并得到不同变量预测重要性评分,随机森林模型和XGBoost模型曲线下面积均为0.77。应用71例样本对模型进行外部验证结果显示,随机森林模型对检测样本的预测总准确率、特异度及灵敏度分别为74.6%、82.6%和60.0%,XGBoost模型对检测样本的预测总准确率、特异度及灵敏度分别为80.3%、87.0%和68.0%。在两种模型中,预测重要性评分排名前四位的变量均为结石体积、平均结石密度、最大结石密度和BMI。结论:基于随机森林和XGBoost算法建立的机器学习模型可准确预测肾结石患者fURL术后早期结石清除状态,有利于术前评估及临床决策。结石体积、平均结石密度、最大结石密度和BMI可能是影响肾结石fURL术后SFR的重要预测因素。

Objective: To establish predictive models based on random forest and XGBoost machine learning algorithm and to investigate their value in predicting early stone-free rate (SFR) after flexible ureteroscopic lithotripsy (fURL) in patients with renal stones.Methods: The clinical data of 201 patients with renal stones who underwent fURL were retrospectively investigated. According to the stone-free standard, the patients were divided into stone-free group (SF group) and stone-residual group (SR group). We compared a number of factors including patient age, body mass index (BMI), stone number, stone volume, stone density and hydronephrosis between the two groups. For low calyceal calculi, renal anatomic parameters including infundibular angle (IPA), infundibular width (IW), infundibular length (IL) and pelvic calyceal height (PCH), would be measured. We brought above potential predictive factors into random forest and XGBoost machine learning algorithm respectively to develop two predictive models. The receiver operating characteristic curve (ROC curve) was established in order to test the predictive ability of the model. Clinical data of 71 patients were collected prospectively to validate the predictive models externally.Results: In this study, 201 fURL operations were successfully completed. The one-phase early SFR was 61.2%. We built two predictive models based on random forest and XGBoost machine learning algorithm. The predictive variables’ importance scores were obtained. The area under the ROC curve (AUROC) of the two predictive models for early stone clearance status prediction was 0.77. In the study, 71 test samples were used for external validation. The results showed that the total predictive accuracy, predictive specificity and predictive sensitivity of the random forest and XGBoost models were 75.7%, 82.6%, 60.0%, and 81.4%, 87.0%, 68.0%, respectively. The first four predictive variables in importance were stone volume, mean stone density, maximal stone density and BMI in both random forest and XGBoost predictive models.Conclusion: The predictive models based on random forest and XGBoost machine learning algorithm can predict postoperative early stone status after fURL for renal stones accurately, which will facilitate preoperative evaluation and clinical decision-making. Stone volume, mean stone density, maximal stone density and BMI may be the important predictive factors affecting early SFR after fURL for renal stones.