基于粗糙集和SVM的HBV再激活危险因素分析与预测  

Analysis and prediction of risk factors for HBV reactivation based on Rough Set theory and SVM

作　　者：吴冠朋 崔晓笛 刘文强 WU Guanpeng;CUI Xiaodi;LIU Wenqiang(Shandong Provincial Third Hospital,Jinan 250031,China)

机构地区：[1]山东省立第三医院,济南250031

出　　处：《智能计算机与应用》2024年第12期46-50,共5页Intelligent Computer and Applications

摘　　要：文章主要分析接受精确放疗后的原发性肝癌患者的乙型肝炎病毒(HBV)再激活的危险因素。通过收集多维度的临床数据,包括HBV DNA水平、KPS评分、甲胎蛋白(AFP)、TNM分期以及外放边界等,并利用粗糙集算法来评估各个因素对HBV病毒再激活的影响。研究发现HBV DNA水平是引起HBV病毒再激活的独立危险因素。建立了支持向量机(SVM)预测模型,用于预测HBV病毒再激活的可能性。经过验证,该模型的分类准确率达到74.46%,表明该模型在预测HBV病毒再激活方面具有一定的可靠性和有效性。The article primarily delves into the risk factors for Hepatitis B Virus(HBV)reactivation among patients with primary liver cancer after receiving precision radiotherapy.By collecting multi-dimensional clinical data,including HBV DNA levels,KPS scores,AFP(Alpha-FetoProtein),TNM staging,and external radiation boundaries,and utilizing the rough set algorithm,the article assesses the impact of various factors on HBV reactivation.Through analysis,the study finds that HBV DNA level is an independent risk factor for HBV reactivation.Based on this risk factor,a Support Vector Machine(SVM)prediction model is established to predict the possibility of HBV reactivation.After verification,the classification accuracy of this model reaches 74.46%,indicating that the model has a certain degree of reliability and effectiveness in predicting HBV reactivation.

关 键 词：HBV再激活 危险因素 粗糙集 SVM预测模型 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]