[1]黄辛迪,黄 慧,刘佳俊,等.决策树及支持向量机与深度学习模型在肝癌鉴别诊断中的比较研究[J].医学信息,2023,36(15):70-74.[doi:10.3969/j.issn.1006-1959.2023.15.012]
　HUANG Xin-di,HUANG Hui,LIU Jia-jun,et al.Comparative Study of Decision Tree, Support Vector Machine and Deep Learning Model in Differential Diagnosis of Liver Cancer[J].Journal of Medical Information,2023,36(15):70-74.[doi:10.3969/j.issn.1006-1959.2023.15.012]
点击复制

决策树及支持向量机与深度学习模型在肝癌鉴别诊断中的比较研究()
分享到：

医学信息[ISSN:1006-1959/CN:61-1278/R]

卷:
36卷
期数:
2023年15期
页码:
70-74
栏目:
临床信息学
出版日期:
2023-08-01

文章信息/Info

Title:
Comparative Study of Decision Tree, Support Vector Machine and Deep Learning Model in Differential Diagnosis of Liver Cancer
文章编号:
1006-1959（2023）15-0070-05
作者:
黄辛迪; 黄 慧; 刘佳俊; 等
（1.湖南中医药大学信息科学与工程学院，湖南 长沙 410208；2.湖南省中医药大数据分析实验室，湖南 长沙 410208）
Author(s):
HUANG Xin-di; HUANG Hui; LIU Jia-jun; et al.
(1.School of Information Science and Engineering,Hunan University of Chinese Medicine,Changsha 410208,Hunan,China;2.Big Data Analysis Laboratory of Traditional Chinese Medicine in Hunan Province,Changsha 410208,Hunan,China)
关键词:
肝癌; 决策树; 支持向量机; 深度学习; 多层感知机; 卷积神经网络
Keywords:
Liver cancer; Decision tree; Support vector machine; Deep learning; Multi-layer perceptron; Convolutional neural network
分类号:
R735.7
DOI:
10.3969/j.issn.1006-1959.2023.15.012
文献标志码:
A
摘要:
目的 使用数据挖掘技术研究肝功能检查数据，分析肝功能检查指标与肝癌诊断的关联，探究肝癌早诊断、早治疗的辅助数据分析方法。方法 构建决策树C4.5模型并提取决策方法，并以Bagging方法优化；采用网格划分法和粒子群优化算法优化支持向量机模型；构建多层感知机（MLP）和卷积神经网络（CNN）进行性能比较。基于决策树和SVM模型进行特征属性分析和最优特征子集选择。结果 Bagging决策树模型、SVM、MLP模型的10交叉检验准确率分别为95.18%、95.60%、90.17%，测试准确率分别为94.34%、93.40%、89.78%。在肝功能检查指标中，碱性磷酸酶、谷丙转氨酶、天门冬氨酸转氨酶、年龄、直接胆红素是主要贡献指标，三指标联合诊断对肝癌预测率达86.08%。结论 决策树、支持向量机、多层感知机建立的肝癌分类器模型都可用于肝癌辅助诊断，SVM模型略优，预测模型对肝癌早期鉴别有较好的辅助作用。
Abstract:
Objective To study liver function test data with data mining technology, analyze the correlation between liver function test indicators and liver cancer diagnosis, and explore methods for early diagnosis and early treatment of liver cancer.Methods The decision tree C4.5 model was constructed and the decision method was extracted and optimized by Bagging method. The grid division method and particle swarm optimization algorithm were used to optimize the support vector machine model. Multi-layer perceptron (MLP) and convolutional neural network (CNN) were constructed for performance comparison. Based on decision tree and SVM model, feature attribute analysis and optimal feature subset selection were carried out.Results The 10-cross-check accuracy rates of Bagging decision tree model, SVM, and MLP model were 95.18%, 95.60%, and 90.17%, respectively, and the test accuracy were 94.34%, 93.40%, and 89.78%, respectively. Among the liver function test indicators, alkaline phosphatase, alanine aminotransferase, aspartate aminotransferase, age and direct bilirubin were important indexes in the diagnosis of liver cancer with three-index combined diagnosis up to 86.08% in accuracy.Conclusion The liver cancer classifier models established by decision tree, support vector machine and multilayer perceptron can all be used in diagnosis of liver cancer, SVM model slightly better. The prediction models are supplementary measures for early identification of liver cancer.

参考文献/References:

[1]刘宗超,李哲轩,张阳,等.2020全球癌症统计报告解读[J].肿瘤综合治疗电子杂志,2021,7(2):1-14.[2]中华人民共和国国家卫生健康委员会.原发性肝癌诊疗指南(2022年版)[J].肿瘤防治研究,2022,49(3):251-276.[3]Singal AG,Pillai A,Tiro J.Early detection, curative treatment, and survival rates for hepatocellular carcinoma surveillance in patients with cirrhosis: a meta-analysis[J].PLoS Med,2014,11(4):e1001624.[4]王敏,陈泽峰,韩志伟,等.基于TCGA数据库分析肝细胞肝癌组织中HMMR表达与患者临床特征及预后的相关性[J].现代肿瘤医学,2021,29(7):1173-1178.[5]王玉,杨雪,靳晓杰,等.基于中医药整合药理学平台、GEO数据库芯片及分子对接探讨大黄抗肝癌的作用机制[J].中草药,2020,51(20):5207-5219.[6]Ibragimov B,Toesca DAS,Chang DT,et al.Deep learning for identification of critical regions associated with toxicities after liver stereotactic body radiation therapy[J].Med Phys,2020,47(8):3721-3731.[7]Nishida N,Yamakawa M,Shiina T,et al.Current status and perspectives for computer-aided ultrasonic diagnosis of liver lesions using deep learning technology[J].Hepatol Int,2019,13(4):416-421.[8]Owens AR,McInerney CE,Prise KM,et al.Novel deep learning-based solution for identification of prognostic subgroups in liver cancer (Hepatocellular carcinoma)[J].BMC Bioinformatics,2021,22(1):563.[9]Zheng C,Chen L,Jian J,et al.Efficacy evaluation of interventional therapy for primary liver cancer using magnetic resonance imaging and CT scanning under deep learning and treatment of vasovagal reflex[J].Journal of Supercomputing,2021,77(7):7535-7548.[10]胡仁智,赵世巧,申波,等.血清甲胎蛋白及其异质体和异常凝血酶原对原发性肝癌的诊断价值[J].中华肝脏病杂志,2019,27(8):634-637.[11]赵晓玲,王晶晶,赵巧玉,等.甲胎蛋白异质体比率在原发性肝癌鉴别诊断中的应用[J].国际检验医学杂志,2016,37(9):1228-1229,1231.[12]中华人民共和国卫生部.原发性肝癌诊疗规范(2011年版)[J].临床肝胆病杂志,2011,27(11):1141-1159.[13]张子梅.利用机器学习方法识别肝癌早期诊断标志[D].成都:电子科技大学,2021.[14]钟锐,张俊.肝功能指标在原发性肝癌中的诊断价值[J].中国现代医学杂志,2015,25(8):102-105.[15]聂斌,李欢,罗计根,等.融合GINI指数的C4.5算法的分类研究[J].江西师范大学学报(自然科学版),2019,43(5):469-472.[16]蔺轲,谢俊卿,胡永华,等.支持向量机在ICU急性肾损伤患者住院死亡风险预测中的应用[J].北京大学学报(医学版),2018,50(2):239-244.[17]余美慧,袁泉,曾书娥,等.基于超声图像的迁移学习模型在乳腺肿块良恶性鉴别诊断中的价值[J].临床超声医学杂志,2022,24(9):652-656.[18]吴树才,王新举,纪俊雨,等.基于深度学习卷积神经网络的肺结核CT诊断模型效能初探[J].中华结核和呼吸杂志,2021,44(5):450-455.[19]王钰涵,段鹏喆,张鑫,等.基于决策树和神经网络的高血压病危险因素研究[J].世界科学技术-中医药现代化,2021,23(8):2784-2794.[20]赵斌,赵经川,李昭宇.AFP联合三项血清酶对原发性肝癌的诊断评价[J].宁夏医学杂志,2010,32(1):20-21.

相似文献/References:

[1]修朋程,李 腾,李雅林,等.泰山山慈菇对小鼠肝癌的治疗作用及相关免疫机制研究[J].医学信息,2018,31(09):8.[doi:10.3969/j.issn.1006-1959.2018.09.003]
　XIU Peng-cheng,LI Teng,LI Ya-lin,et al.Study on the Therapeutic Effect and Mechanism of Taishan Mountain Mushroom on Liver Cancer in Mice[J].Journal of Medical Information,2018,31(15):8.[doi:10.3969/j.issn.1006-1959.2018.09.003]
[2]崔康健,杜成友.肝动脉化疗栓塞联合射频消融治疗肝癌的研究进展[J].医学信息,2018,31(09):16.[doi:10.3969/j.issn.1006-1959.2018.09.005]
　CUI Kang-jian,DU Cheng-you.Research Progress of Transcatheter Arterial Chemoembolization Combined with Radiofrequency Ablation for Liver Cancer[J].Journal of Medical Information,2018,31(15):16.[doi:10.3969/j.issn.1006-1959.2018.09.005]
[3]许 吉.基于知识图谱和专利地图的我国抗肝癌药物研发态势研究[J].医学信息,2018,31(21):19.[doi:10.3969/j.issn.1006-1959.2018.21.007]
　XU Ji.Research and Development Situation of Anti-liver Cancer Drugs in China Based on Knowledge Map and Patent Map[J].Journal of Medical Information,2018,31(15):19.[doi:10.3969/j.issn.1006-1959.2018.21.007]
[4]兰福全,李秀云,卢 斌.四种肿瘤标志物对肝癌诊断的临床意义[J].医学信息,2018,31(21):164.[doi:10.3969/j.issn.1006-1959.2018.21.048]
　LAN Fu-quan,LI Xiu-yun,LU Bin.The Clinical Significance of Four Tumor Markers in the Diagnosis of Liver Cancer[J].Journal of Medical Information,2018,31(15):164.[doi:10.3969/j.issn.1006-1959.2018.21.048]
[5]戴晓敏,丁 勇.分类算法在高血压诊断中的应用研究[J].医学信息,2019,32(01):1.[doi:10.3969/j.issn.1006-1959.2019.01.001]
　DAI Xiao-min,DING Yong.Application of Classification Algorithm in Diagnosis of Hypertension[J].Journal of Medical Information,2019,32(15):1.[doi:10.3969/j.issn.1006-1959.2019.01.001]
[6]赵瑶瑶,高 川,胡佳杰.循环miRNA监测肝细癌的研究[J].医学信息,2019,32(08):48.[doi:10.3969/j.issn.1006-1959.2019.08.016]
　ZHAO Yao-yao,GAO Chuan,HU Jia-jie.Research on the Study of Circulating miRNA for Monitoring Hepatocellular Carcinoma[J].Journal of Medical Information,2019,32(15):48.[doi:10.3969/j.issn.1006-1959.2019.08.016]
[7]李 闯,叶劲松,刘 昕,等.ZBP-89与缺氧信号因子HIF-1α在肝癌细胞中的 相关性研究[J].医学信息,2019,32(15):74.[doi:10.3969/j.issn.1006-1959.2019.15.023]
　LI Chuang,YE Jin-song,LIU Xin,et al.Correlation between ZBP-89 and Hypoxia Signaling Factor HIF-1α in Hepatoma Cells[J].Journal of Medical Information,2019,32(15):74.[doi:10.3969/j.issn.1006-1959.2019.15.023]
[8]孙 逊.性化护理对肝癌患者CT引导下射频消融术后 负性情绪及生活质量的影响[J].医学信息,2019,32(17):187.[doi:10.3969/j.issn.1006-1959.2019.17.065]
　SUN Xun.Effect of Humanized Nursing on Negative Emotion and Quality of Life after CT-guided Radiofrequency Ablation in Patients with Liver Cancer[J].Journal of Medical Information,2019,32(15):187.[doi:10.3969/j.issn.1006-1959.2019.17.065]
[9]徐 蓓,魏霞丽,常艳琴.肝癌患者术后自我饮食管理体验的质性研究[J].医学信息,2019,32(20):180.[doi:10.3969/j.issn.1006-1959.2019.20.058]
　XU Bei,WEI Xia-li,CHANG Yan-qin.Qualitative Study of Postoperative Self-Catering Management Experience in Patients with Liver Cancer[J].Journal of Medical Information,2019,32(15):180.[doi:10.3969/j.issn.1006-1959.2019.20.058]
[10]田 明,常伟平.UbcH10在肝癌中的表达及其与预后的关系[J].医学信息,2019,32(12):77.[doi:10.3969/j.issn.1006-1959.2019.12.024]
　IAN Ming,CHANG Wei-ping.Expression of UbcH10 in Hepatocellular Carcinoma and Its Relationship with Prognosis[J].Journal of Medical Information,2019,32(15):77.[doi:10.3969/j.issn.1006-1959.2019.12.024]

更新日期/Last Update: 1900-01-01