Qiu Junliang, Yan Minbo, Wang Haojie, Liu Zicheng, Wang Guojie, Wu Xianbo, Gao Qindong, Hu Hongji, Chen Junyong, Dai Yingbo
Department of Urology, Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, Guangdong, China.
Department of Radiology, Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, Guangdong, China.
Front Med (Lausanne). 2023 Aug 2;10:1202486. doi: 10.3389/fmed.2023.1202486. eCollection 2023.
To develop and validate radiomics and machine learning models for identifying encrusted stents and compare their recognition performance with multiple metrics.
A total of 354 patients with ureteral stent placement were enrolled from two medical institutions and divided into the training cohort ( = 189), internal validation cohort ( = 81) and external validation cohort ( = 84). Based on features selected by Wilcoxon test, Spearman Correlation Analysis and least absolute shrinkage and selection operator (LASSO) regression algorithm, six machine learning models based on radiomics features were established with six classifiers (LR, DT, SVM, RF, XGBoost, KNN). After comparison with those models, the most robust model was selected. Considering its feature importance as radscore, the combined model and a nomogram were constructed by incorporating indwelling time. Accuracy, sensitivity, specificity, area under the curve (AUC), decision curve analysis (DCA) and calibration curve were used to evaluate the recognition performance of models.
1,409 radiomics features were extracted from 641 volumes of interest (VOIs) and 20 significant radiomics features were selected. Considering the superior performance (AUC 0.810, 95%CI, 0.722-0.888) in the external validation cohort, feature importance of XGBoost was used as a radscore, constructing a combined model and a nomogram with indwelling time. The accuracy, sensitivity, specificity and AUC of the combined model were 98, 100, 97.3% and 0.999 for the training cohort, 83.3, 80, 84.5% and 0.867 for the internal cohort and 78.2, 76.3, 78.8% and 0.820 for the external cohort, respectively. DCA indicates the favorable clinical utility of models.
Machine learning model based on radiomics features enables to identify ureteral stent encrustation with high accuracy.
开发并验证用于识别输尿管支架结壳的放射组学和机器学习模型，并使用多种指标比较它们的识别性能。
从两家医疗机构招募了354例输尿管支架置入患者，并将其分为训练队列（n = 189）、内部验证队列（n = 81）和外部验证队列（n = 84）。基于Wilcoxon检验、Spearman相关性分析和最小绝对收缩和选择算子（LASSO）回归算法选择的特征，使用六个分类器（LR、DT、SVM、RF、XGBoost、KNN）建立了六个基于放射组学特征的机器学习模型。与这些模型进行比较后，选择了最稳健的模型。考虑到其作为radscore的特征重要性，通过纳入留置时间构建了联合模型和列线图。使用准确性、敏感性、特异性、曲线下面积（AUC）、决策曲线分析（DCA）和校准曲线来评估模型的识别性能。
从641个感兴趣体积（VOI）中提取了1409个放射组学特征，并选择了20个显著的放射组学特征。考虑到在外部验证队列中的卓越性能（AUC 0.810，95%CI，0.722 - 0.888），将XGBoost的特征重要性用作radscore，构建了一个联合模型和一个带有留置时间的列线图。联合模型在训练队列中的准确性、敏感性、特异性和AUC分别为98%、100%、97.3%和0.999，在内部队列中分别为83.3%、80%、84.5%和0.867，在外部队列中分别为78.2%、76.3%、78.8%和0.820。DCA表明模型具有良好的临床实用性。
基于放射组学特征的机器学习模型能够高精度地识别输尿管支架结壳。
