摘要
一位新闻记者兼机器人与机器学习的新闻编辑每日新闻-纤维瘤的新研究是一篇报道的主题。根据NewsRx记者在中华人民共和国北京的新闻报道，研究表明：“在这项研究中，我们的目的是开发和验证各种放射学模型在术前区分颌骨纤维异常增殖症(FD)和骨化性纤维瘤(OF)的有效性。我们招募了220名确诊为FD或OF的患者。”新闻记者引用了该研究的一句话：“我们从未增强的CT图像中提取放射学特征，经过降维和特征选择，利用Logistic回归、支持向量机、随机森林、光梯度增强机、极梯度增强机构建放射学模型，然后利用受试者OPE评分特征(ROC)曲线分析确定最佳放射学模型，并将放射学特征与临床特征结合起来。”我们建立了一个综合模型，ROC曲线和Decisio N曲线分析(DCA)显示了模型的鲁棒性和临床价值，从CT图像中提取了1834个放射学特征，将其简化为8个有价值的特征，预测效率高，曲线下面积(AUC)超过0.95，最终建立了综合评价放射学和临床数据的组合模型。显示出优越的辨别能力（AUC：训练队列0.970；试验队列0.967）。DCA强调了其最佳临床疗效。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Fibroma is the subject of a report. According to news reporting from Beijing, People’s Republic of Chi na, by NewsRx journalists, research stated, “In this study, our aim was to devel op and validate the effectiveness of diverse radiomic models for distinguishing between gnathic fibrous dysplasia (FD) and ossifying fibroma (OF) before surgery . We enrolled 220 patients with confirmed FD or OF.” The news correspondents obtained a quote from the research, “We extracted radiom ic features from nonenhanced CT images. Following dimensionality reduction and f eature selection, we constructed radiomic models using logistic regression, supp ort vector machine, random forest, light gradient boosting machine, and eXtreme gradient boosting. We then identified the best radiomic model using receiver ope rating characteristic (ROC) curve analysis. After combining radiomics features w ith clinical features, we developed a comprehensive model. ROC curve and decisio n curve analysis (DCA) demonstrated the models’ robustness and clinical value. W e extracted 1834 radiomic features from CT images, reduced them to eight valuabl e features, and achieved high predictive efficiency, with area under curves (AUC ) exceeding 0.95 for all the models. Ultimately, our combined model, which integ rates radiomic and clinical data, displayed superior discriminatory ability (AUC : training cohort 0.970; test cohort 0.967). DCA highlighted its optimal clinica l efficacy.”
NETL
NSTL