摘要
机器人与机器学习的新闻编辑每日新闻-机器学习的新研究是一篇报道的主题。根据NewsRx记者在中国人民日报广东的新闻报道，研究表明：“筛查高危人群对于肾结石的预防和治疗至关重要。在此，我们利用放射组学技术对肾结石高危患者进行筛查。”新闻记者引用广州医科大学的一篇研究报道:“将我院2020~2022年间513个独立肾脏按7:3的比例随机分配到训练和验证组,利用3Dslicer软件提取放射学特征,采用最小绝对熵选择算子(LASSO)方法从107个特征中筛选出放射学特征。”应用Logistic回归、决策树模型、Ada Boost模型和支持向量机(SVM)模型构建了CT放射学特征预测模型,其中Logistic回归算法具有最好的预测性能和稳定性,基于放射学特征的Logistic回归模型(AUC)曲线下面积在训练队列为0.858,在验证队列为0.806.采用单因素和多因素Logistic回归分析确定肾结石的独立危险因素为性别和体质量指数(BMI),结合这些独立危险因素提高了模型的预测性能。临床决策曲线分析(DCA)表明，当概率在0.2到1.0.之间时，放射学模型提供了临床获益。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Machine Learning is th e subject of a report. According to news reporting from Guangdong, People’s Repu blic of China, by NewsRx journalists, research stated, “Screening high-risk popu lations is crucial for the prevention and treatment of kidney stones. Here, we e mployed radiomics to screen high-risk patients for kidney stones.” The news correspondents obtained a quote from the research from Guangzhou Medica l University, “A total of 513 independent kidneys from our hospital between 2020 and 2022 were randomly allocated to training and validation sets at a 7:3 ratio . Radiomic features were extracted using 3Dslicer software. The least absolute s hrinkage and selection operator (LASSO) method was used to select radiomic featu res from the 107 extracted features, and logistic regression, decision tree, Ada Boost, and support vector machine (SVM) models were subsequently used to constru ct radiomic feature prediction models. Among these, the logistic regression algo rithm demonstrated the best predictive performance and stability. The area under the curve (AUC) of the logistic regression model based on radiomic features was 0.858 in the training cohort and 0.806 in the validation cohort. Furthermore, u nivariate and multivariate logistic regression analyses were performed to identi fy the independent risk factors for kidney stones, which were gender and body ma ss index (BMI). Combining these independent risk factors improved the predictive performance of the model, with AUC values of 0.860 in the training cohort and 0 .814 in the validation cohort. Clinical decision curve analysis (DCA) indicated that the radiomic model provided clinical benefit when the probability ranged fr om 0.2 to 1.0.”
NETL
NSTL