首页 | 本学科首页   官方微博 | 高级检索  
检索        

甲状腺微小乳头状癌的多学科综合预测模型建立
引用本文:侯春杰,汤靖岚,何洪峰,杜佩.甲状腺微小乳头状癌的多学科综合预测模型建立[J].中国超声医学杂志,2019(8):680-683.
作者姓名:侯春杰  汤靖岚  何洪峰  杜佩
作者单位:浙江省人民医院杭州医学院附属人民医院超声科
基金项目:浙江省科技厅公益项目(No.2017C33097);浙江省卫计委一般项目(No.2016KYB008)
摘    要:目的采用Logistic回归分析建立预测模型,探讨其对甲状腺微小乳头状癌(PTMC)的预测价值。方法对319例明确病理的甲状腺微小结节患者进行多学科信息采集,纳入Logistic回归分析建立预测模型。应用模型预测120例验证组患者的PTMC风险,并与手术病理对比,采用ROC曲线评价模型预测能力。结果预测模型的ROC曲线下面积为0.914,最佳预测临界值为P=68.58、灵敏度82.50%、特异度90.20%、诊断准确率89.70%。结论该回归模型对PTMC具有较高的预测价值。

关 键 词:甲状腺微小乳头状癌  回归分析  预测

A Risk Prediction Model of Papillary Thyroid Microcarcinoma:Based on Multi-disciplinary Variables
Hou Chunjie,Tang Jinglan,He Hongfeng,Du Pei.A Risk Prediction Model of Papillary Thyroid Microcarcinoma:Based on Multi-disciplinary Variables[J].Chinese Journal of Ultrasound in Medicine,2019(8):680-683.
Authors:Hou Chunjie  Tang Jinglan  He Hongfeng  Du Pei
Institution:(Department of Ultrasonography, Zhejiang Provincial People's Hospital, People's Hospital of Hangzhou Medical College, Hangzhou, Zhejiang 310014, China)
Abstract:Objective To built a prediction model of papillary thyroid microcarcinoma(PTMC).Methods Data of 319 patients with thyroid nodules(≤10 mm)confirmed by surgical pathology were analyzed retrospectively to built a logistic regression model.Apply the model to the verification group(120 patients)to calculate the risk of PTMC.The predictive value was verified by receiver-operating characteristics(ROC)curve.Results The largest area under the ROC curve(AUC)of the model was 0.914.At the cutoff value(P=68.58),the sensitivity,specificity and diagnostic accuracy was 82.50%,90.20%and 89.70%respectively.Conclusions This regression model has high predictive value for PTMC.
Keywords:Papillary thyroid microcarcinoma  Regression analysis  Predict
本文献已被 CNKI 维普 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号