Shabaniyan Tayyebe, Parsaei Hossein, Aminsharifi Alireza, Movahedi Mohammad Mehdi, Jahromi Amin Torabi, Pouyesh Shima, Parvin Hamid
Department of Medical Physics and Engineering, School of Medicine, Shiraz University of Medical Sciences, Shiraz, Iran.
Shiraz Neuroscience Research Center, Shiraz University of Medical Sciences, Shiraz, Iran.
Australas Phys Eng Sci Med. 2019 Sep;42(3):771-779. doi: 10.1007/s13246-019-00780-3. Epub 2019 Jul 22.
A decision support system (DSS) was developed to predict postoperative outcome of a kidney stone treatment procedure, particularly percutaneous nephrolithotomy (PCNL). The system can serve as a promising tool to provide counseling before an operation. The overall procedure includes data collection and prediction model development. Pre/postoperative variables of 254 patients were collected. For feature vector, we used 26 variables from three categories including patient history variables, kidney stone parameters, and laboratory data. The prediction model was developed using machine learning techniques, which includes dimensionality reduction and supervised classification. A novel method based on the combination of sequential forward selection and Fisher's discriminant analysis was developed to reduce the dimensionality of the feature space and to improve the performance of the system. Multiple classifier scheme was used for prediction. The derived DSS was evaluated by running leave-one-patient-out cross-validation approach on the dataset. The system provided favorable accuracy (94.8%) in predicting the outcome of a treatment procedure. The system also correctly estimated 85.2% of the cases that required stent placement after the removal of a stone. In predicting whether the patient might require a blood transfusion during the surgery or not, the system predicted 95.0% of the cases correctly. The results are promising and show that the developed DSS could be used in assisting urologists to provide counseling, predict a surgical outcome, and ultimately choose an appropriate surgical treatment for removing kidney stones.
开发了一种决策支持系统（DSS）来预测肾结石治疗手术，特别是经皮肾镜取石术（PCNL）的术后结果。该系统可作为一种很有前景的工具，在手术前提供咨询。整个过程包括数据收集和预测模型开发。收集了254例患者的术前/术后变量。对于特征向量，我们使用了来自三类的26个变量，包括患者病史变量、肾结石参数和实验室数据。使用机器学习技术开发预测模型，包括降维和监督分类。开发了一种基于顺序前向选择和Fisher判别分析相结合的新方法，以降低特征空间的维度并提高系统性能。使用多分类器方案进行预测。通过对数据集运行留一患者交叉验证方法对导出的DSS进行评估。该系统在预测治疗手术结果方面具有良好的准确性（94.8%）。该系统还正确估计了85.2%的结石取出后需要放置支架的病例。在预测患者手术期间是否可能需要输血方面，该系统正确预测了95.0%的病例。结果很有前景，表明开发的DSS可用于协助泌尿科医生提供咨询、预测手术结果，并最终选择合适的手术治疗方法来去除肾结石。
