|
|
|
| Fibrosis and Inflammatory Activity Analysis of Chronic Hepatitis C Based on Random Forest |
| Cai Jiaxin1* ,Qiu Xuan2,Huang Zhili1,Luo Ronglan1 |
1(School of Applied Mathematics, Xiamen University of Technology, Xiamen 361024, Fujian, China)
2(Department of Information, The 180th Hospital of PLA, Quanzhou 362000, Fujian, China) |
|
|
|
|
Abstract In order to predict the fibrosis stage and inflammatory activity grade of chronic hepatitis C, an auto-grading system based on two-stage random forest was proposed in this paper. Firstly, the feature importance of each serological index was obtained by learning the first stage random forest to evaluate its relevance to fibrosis stage and inflammatory activity grade. Secondly, the serological indices whose feature importance were above the predetermined threshold were chosen for the next classification step. Finally, the second stage random forest based on the chosen features was employed for determining the fibrosis stage and inflammatory activity grade. The proposed method has been tested on 123 clinical data of chronic hepatitis C based on serological indexes. Experimental results showed that the classification accuracy of fibrosis stage, fibrosis stage S4 and inflammatory activity grade are 68.29%, 100% and 73.17%. At last the most important serological indexes related to the fibrosis stage and inflammatory activity level ofchronic hepatitis C were determined as total cholesterol, HDL, ALT and AST. Experimental results demonstrated that the proposed method has the advantages of high recognition accuracy and low cost to get examination results and perform calculations, which makes it helpful for clinical diagnosis of chronic hepatitis C.
|
|
Received: 30 October 2017
|
|
|
|
|
|
[1] Chinnaratha MA, JeffreyGP, Macquillan G, et al. Prediction of morbidity and mortality in patients with chronic hepatitis C by non-invasive liver fibrosis models.[J]. Liver International, 2014, 34(5):720-720.
[2] Thomas DL. Diagnosis, Management, and treatment of hepatitis C: An update docx[J]. Hepatology, 2010, 50(1):322-322.
[3] 陈明丽, 黄咏红, 王怡,等. 超声纹理分析方法诊断乙型肝炎早期肝硬化的价值[J]. 肝脏, 2010, 15(6):414-416.
[4] 丁红兵,陈永鹏,冯筱榕.慢性乙型肝炎肝纤维化分期与血清肝纤维化标志物的相关性分析[J].中华肝脏病杂志,2001,9(2):78-80.
[5] 关鹏,何苗,周宝森. 基于BP人工神经网络的病毒性肝炎发病率自回归预测模型[J]. 中国卫生统计,2003,20 (5):269-271.
[6] 吴冠朋,刘毅慧,王帅. 基于遗传算法特征选择的HBV再激活分类预测模型[J].生物信息学, 2016,14 (4):243-248.
[7] 王刚, 刘元宁, 陈慧灵,等. 粗糙集与支持向量机在肝炎诊断中的应用[J]. 吉林大学学报(工学版), 2011, 41(1):160-164.
[8] Mahmoud-Ghoneim D, Cherel Y, Lemaire L, et al. Texture analysis of magnetic resonance images of rat muscles during atrophy and regeneration[J]. Magnetic Resonance Imaging, 2006, 24(2):167-171.
[9] Wu Zhuo, Matsui O, Kitao A, et al. Hepatitis C related chronic liver cirrhosis: feasibility of texture analysis of MR images for classification of fibrosis stage and necro in flammatory activity grade[J]. PLoS ONE, 2015, 10(3):e0118297.
[10] 蒋红卫,夏结来,李园.偏最小二乘判别分析在基因微阵列分型中的应用[J].中国卫生统计,2007,24(4):372-374.
[11] Breiman L. Random forests[J]. Machine Learning, 2001, 45(1):5-32.
[12] 阚红星, 张璐瑶, 董昌武. 一种2型糖尿病中医证型的舌图像识别方法[J]. 中国生物医学工程学报, 2016, 35(6):658-664.
[13] 屠睿博, 陈中华, 王洪凯. 基于随机森林算法的小鼠micro-CT影像中骨骼关节特征点定位[J]. 中国生物医学工程学报, 2017, 36(3):257-266.
[14] 李勇明, 杨刘洋, 刘玉川,等. 基于语音样本重复剪辑和随机森林的帕金森病诊断算法研究[J]. 生物医学工程学杂志, 2016, 33(6):1053-1059.
[15] 蔡加欣, 冯国灿, 汤鑫,等. 基于局部轮廓和随机森林的人体行为识别[J]. 光学学报, 2014, 34(10):204-213.
[16] 张武.重型肝炎患者丁酰胆碱酯酶、胆固醇、凝血酶原活动度及AST/ALT的临床意义[J]. 河北医药, 2000, 22(6):441-442
[17] 马轶.慢性丙型肝炎患者血清生化指标和肝组织病理的相关性分析[J]. 中国当代医药,2009,16(12):156-159.
[18] 岑立冲,赵国根,顾慧华.慢性丙型肝炎患者血清HCV-RNA载量和肝组织病变关系研究[J]. 中国卫生检验杂志, 2011,21(1):143-144.
[19] 李颖,丁洋,王雪莲. 慢性丙型肝炎患者血清HCV-RNA, ALT与肝脏病理间的关系[J]. 世界华人消化杂志, 2006,14(9):916-919.
[20] 刘沁毅,裴彬,孙琳,等.慢性乙型肝炎患者肝组织病理变化与常规检测指标的关系[J].肝脏,2013,18(6):386-389.
[21] 魏芳芳, 张晓红. 慢性丙型肝炎合并脂肪肝的发病机制[J]. 临床肝胆病杂志, 2015, 31(2):288-290. |
|
|
|
