[1]郝晓燕,周 磊,白丛霞,等.基于机器学习方法建立血清多种肿瘤标志物联合区分胃炎和胃癌的三种模型及评价[J].现代检验医学杂志,2023,38(02):124-128.[doi:10.3969/j.issn.1671-7414.2023.02.023 ]
　HAO Xiao-yan,ZHOU Lei,BAI Cong-xia,et al.Establishment and Evaluation of Three Models for the Distinguish Gastritis and Gastric Cancer with Multiple Serum Tumor Markers Based on Machine Learning Methods[J].Journal of Modern Laboratory Medicine,2023,38(02):124-128.[doi:10.3969/j.issn.1671-7414.2023.02.023 ]
点击复制

基于机器学习方法建立血清多种肿瘤标志物联合区分胃炎和胃癌的三种模型及评价()
分享到：

《现代检验医学杂志》[ISSN:/CN:]

卷:
第38卷
期数:
2023年02期
页码:
124-128
栏目:
论著
出版日期:
2023-03-15

文章信息/Info

Title:
Establishment and Evaluation of Three Models for the Distinguish Gastritis and Gastric Cancer with Multiple Serum Tumor Markers Based on Machine Learning Methods
文章编号:
1671-7414（2023）02-124-05
作者:
郝晓燕; 周 磊; 白丛霞; 刘家云
（空军军医大学第一附属医院检验科，西安 710032）
Author(s):
HAO Xiao-yan;  ZHOU Lei;  BAI Cong-xia;  LIU Jia-yun
（Department of Clinical Laboratory，the first Affiliated Hospital of Air Force Military Medical University, Xi’an 710032, China）
关键词:
机器学习; 肿瘤标志物; 胃癌; 分类算法
分类号:
R735.2；R730.43
DOI:
10.3969/j.issn.1671-7414.2023.02.023
文献标志码:
A
摘要:
目的 基于三种机器学习方法建立多肿瘤标志物联合区分胃炎和胃癌模型。方法 选取 2010～2021 年期间来西京医院就诊诊断为胃炎和胃癌的患者 13 727 例，收集入组患者基本信息（年龄和性别）、甲胎蛋白（alpha-fetoprotein, AFP）、癌胚抗原（carcinoembryonic antigen, CEA）、糖链抗原 19-9（carbohydrate antigen 19-9, CA19-9）及糖链抗原 125（carbohydrate antigen 125, CA125）结果。采用随机森林（random forest, RF）、决策树（decision tree, DT）和 K 最邻近法（K- nearest neighbor, KNN）三种机器学习算法挖掘入组患者 6 种变量的数据，建立区分胃炎和胃癌模型。验证各模型对所有入组患者、不同年龄层的入组患者、 AFP阴性入组患者的胃炎和胃癌鉴别能力，并与单肿瘤标志物鉴别能力做对比。结果 利用机器学习算法构建的 RF-pv6，DT-pv6和 KNN-pv6 模型对所有的患者诊断曲线下面积（area under the curve, AUC）均高于 0.742，单肿瘤标志物 AUC 均低于 0.644；各模型对于小于 50 岁患者，AUC 均高于 0.668，单肿瘤标志物 AUC 均低于 0.641；各模型对于大于 50 岁患者， AUC 均高于 0.734，单肿瘤标志物 AUC 均低于 0.647；各模型对于 AFP阴性患者， AUC 均高于 0.731，单肿瘤标志物 AUC 均低于 0.639。各模型在所有入组患者及其亚组中的 AUC 高于单肿瘤标志物的 AUC。结论 通过利用机器学习算法挖掘入组患者的 6 种特征数据建立的三种模型效能均优于单肿瘤标志物对胃炎和胃癌的鉴别能力。
Abstract:
Objective To establish a multi-tumor marker combined distinguish model of gastritis and gastric cancer based on three machine learning methods. Methods A total of 13 727 patients diagnosed with gastritis and gastric cancer in Xijing Hospital from 2010 to 2021 were selected. Collected the basic information (age, sex) of patients in each group and the detection results of alpha-fetoprotein(AFP), carcinoembryonic antigen(CEA), carbohydrate antigen 19-9(CA19-9) and carbohydrate antigen 125(CA125). After preprocessing the data, three machine learning algorithms, random forest (RF), decision tree (DT) and K-nearest neighbor (KNN) were used to mine the data of 6 variables, and distinguish gastritis and gastric cancer models were established respectively. The ability of each model to discriminate gastric cancer for all enrolled patients, enrolled patients of different age groups, and AFP-negative enrolled patients was verified, and compared with the ability of single tumor marker to discriminate gastric cancer. Results The RF-pv6, DT-pv6 and KNN-pv6 models constructed by machine learning algorithms have AUC higher than 0.742 for all gastric cancer patients, AUC higher than 0.668 for patients younger than 50 years old, AUC higher than 0.734 for patients older than 50 years old, and AUC higher than 0.731 for AFP-negative patients. The AUC of each model in the diagnosis of gastric cancer in all enrolled patients and their subgroups was higher than that of a single tumor marker. Conclusion The performance of the 3 models established by mining 6 kinds of characteristic data of the enrolled patients by using machine learning algorithm was better than that of single tumor marker in the distinguish gastritis and gastric cancer.

参考文献/References:

[1] MACHLOWSKA J, BAJ J, SITARZ M, et al. Gastric cancer: epidemiology, risk factors, classification, genomic characteristics and treatment strategies[J]. International Journal of Molecular Sciences, 2020, 21(11): 4012.
[2] 高梓茗 , 徐惠绵 .胃癌精准外科治疗的研究新进展 [J].中华医学信息导报 , 2021, 36(1): 7-8. GAO Ziming, XU Huimian. Research progress of precision surgical treatment of gastric cancer[J]. China Medical News, 2021, 36(1): 7-8.
[3] JOHNSTON F M, BECKMAN M. Updates on management of gastric cancer[J]. Current Oncology Reports, 2019, 21(8): 67.
[4] 张筱东 , 谢星星 , 李佳 , 等 .血清外泌体 miR-221和 miR-378水平检测在胃癌诊断中的应用研究 [J].现代检验医学杂志 , 2020, 35(6): 52-55. ZHANG Xiaodong, XIE Xingxing, LI Jia, et al. Application study of serum exosome miR-221 and miR-378 detection in the diagnosis of gastric cancer [J]. Journal of Modern Laboratory Medicine, 2020, 35(6): 52-55.
[5] 田敏秀 , 沈磊 .早期胃癌的临床诊断进展 [J].医学综述 , 2020, 26(10): 1946-1950, 1955. TIAN Minxiu, SHEN Lei. Progress in clinical diagnosis of early gastric cancer[J]. Medical Recapitulate, 2020, 26(10): 1946-1950, 1955.
[6] 刘夏炎 , 余安运 , 刘益 , 等 .血清胃蛋白酶原及相关肿瘤标志物与胃癌的相关性研究 [J].现代检验医学杂志 , 2018, 33(5): 108-110, 114. LIU Xiayan, YU Anyun, LIU Yi, et al. Relationship between pepsinogen and other tumor markers and gastric cancer [J]. Journal of Modern Laboratory Medicine, 2018, 33(5): 108-110, 114.
[7] 白晶 , 刘海顺 , 万鸿飞 , 等 .乙型肝炎相关性肝癌血清标志物诊断价值及支持向量机鉴别诊断模型的建立 [J].中国医学装备 , 2019, 16(7): 119-125. BAI Jing, LIU Haishun, WAN Hongfei, et al. The diagnostic value of serum biomarkers of hepatitis B-related HCC and the establishment of differential diagnosis model of SVM [J]. China Medical Equipment, 2019, 16(7): 119-125.
[8] YANG Lei, YING Xiangji, LIU Shuo, et al. Gastric cancer: Epidemiology, risk factors and prevention strategies[J].Chin J Cancer Res, 2020, 32(6):695-704.
[9] 王宁 , 付立业 , 隋承光 , 等 .胃癌患者血清中 IGF-1与 CEA, CA125, CA199, CA724水平的相关性分析及在胃癌诊断中的意义 [J].中国实验诊断学 , 2021, 25(2): 194-197. WANG Ning, FU Liye, SUI Chengguang, et al. The correlation analysis of levels of IGF 1 and CEA,CA125,CA199,CA724 in gastric cancer patients serum and significance in the diagnosis of gastric cancer [J]. Chinese Journal of Laboratory Diagnosis, 2021, 25(2): 194-197.
[10] 胡惠静 .血清肿瘤标志物在结直肠癌诊断中的应用价值 [J].中国卫生标准管理 , 2019, 10(12): 91-93. HU Huijing. The value of serum tumor markers in the diagnosis of colorectal cancer [J]. China Health Standard Management, 2019, 10(12): 91-93.
[11] 谢春霞 , 张磊 , 王淑惠 , 等 .PG , CEA, CA-199, CK 及 CK-MB 联合检测在胃癌筛查中的应用价值探讨 [J].浙江临床医学 , 2019, 21(10): 1310-1311,1314. XIE Chunxia, ZHANG Lei, WANG Shuhui, et al. The application value of combined detection of PG,CEA,CA-199,CK and CK-MB in gastric cancer screening [J]. Zhejiang Clinical Medical Journal, 2019, 21(10): 1310-1311, 1314.
[12] 孙运涛 .胃蛋白酶原联合肿瘤标志物 CA199, CA125和 CEA对胃癌的诊断价值分析 [J].中国实用医药 , 2019, 14(16): 22-23. SUN Yuntao. Analysis of value of pepsinogen combined with tumor markers CA199, CA125 and CEA in diagnosis of gastric cancer [J]. China Practical Medicine, 2019, 14(16): 22-23.
[13] 彭咏 , 谢永林 , 周芳 .口服胃肠超声检查联合血清肿瘤标记物对中老年胃癌的诊断价值 [J].中国医药科学 , 2020, 10(13): 155-158. PENG Yong, XIE Yonglin, ZHOU Fang. Diagnostic value of oral gastrointestinal ultrasound combined with serum tumor markers in elderly gastric cancer[J]. China Medicine and Pharmacy, 2020, 10(13): 155-158.
[14] 陆兴俊 , 赵太云 , 王胤 , 等 .血清 CA724, CA19-9水平联合内镜在胃癌诊断及预后中的价值 [J].中国老年学杂志 , 2022, 42(15): 3666-3668. LU Xingjun, ZHAO Taiyun, WANG Yin, et al. The value of serum CA724 and CA19-9 levels combined with endoscopy in the diagnosis and prognosis of gastric cancer[J]. Chinese Journal of Gerontology, 2022, 42(15): 3666-3668.
[15] 王有法 .肿瘤标志物 CA724, CEA, CA242, CA199联合检测在胃癌临床诊断中的价值分析 [J].中国社区医师 , 2021, 37(26): 130-131. WANG Youfa. Value analysis of the combined detection of tumor markers CA724,CEA,CA242,CA199 in the clinical diagnosis of gastric cancer [J]. Chinese Community Doctors, 2021, 37(26): 130-131.
[16] 董红瑶 , 王弈丹 , 李丽红 .随机森林优化算法综述 [J].信息与电脑 , 2021, 33(17): 34-37. DONG Hongyao, WANG Yidan, LI Lihong. A review of random forest optimization algorithms [J]. China Computer & Communication, 2021, 33(17): 34-37.
[17] 李颖 .基于决策树算法的信息系统数据挖掘研究 [J].信息技术 , 2022, 2: 116-120, 126. LI Ying. Research on information system data mining based on decision tree algorithm[J]. Information Technology, 2022, 2: 116-120, 126.
[18] 李惠萍 ,胡安民 .基于 KNN和 RF算法构建危重患者全因死亡预测模型的研究 [J].中国卫生统计 , 2020, 37(2): 224-227. LI Huiping, HU Anmin. Study on the construction of all-cause death prediction model for critically ill patients based on KNN and RF algorithms [J]. Chinese Journal of Health Statistics,2020,37(2): 224-227.

相似文献/References:

[1]王红梅,陈晔洲,田晶晶,等.新型肿瘤标志物人PF4重组表达、活性鉴定及单克隆抗体制备[J].现代检验医学杂志,2015,30(05):12.[doi:10.3969/j.issn.1671-7414.2015.05.005]
　WANG Hong-mei,CHEN Ye-zhou,TIAN Jing-jing,et al.Recombination，Expression，Activity Identification and Monoclonal Antibody Preparation of the Human Platelet Factor 4 as a New Cancer Marker[J].Journal of Modern Laboratory Medicine,2015,30(02):12.[doi:10.3969/j.issn.1671-7414.2015.05.005]
[2]余安运,陶丹,刘夏炎,等.肿瘤标志物在消化系统肿瘤早期诊断中的应用[J].现代检验医学杂志,2015,30(06):133.[doi:10.3969/j.issn.1671-7414.2015.06.041]
　YU An-yun,TAO Dan,LIU Xia-yan,et al.Clinical Value of Blood Serums Tumor Marker in Early Diagnosis of Digestive System Neoplasms[J].Journal of Modern Laboratory Medicine,2015,30(02):133.[doi:10.3969/j.issn.1671-7414.2015.06.041]
[3]万 军.血清肿瘤标志物CA153,CA125,CEA和HER-2联合检测在乳腺癌诊断中的价值[J].现代检验医学杂志,2018,33(06):119.[doi:10.3969/j.issn.1671-7414.2018.06.031]
　WAN Jun.Value of Combined Detection of Tumor Markers CA153,CA125,CEA and HER-2 in the Diagnosis of Breast Cancer[J].Journal of Modern Laboratory Medicine,2018,33(02):119.[doi:10.3969/j.issn.1671-7414.2018.06.031]
[4]王 麟,周朝琼,徐晓华,等.血清肿瘤标志物的参考变化值和参考变化因子应用比较研究[J].现代检验医学杂志,2020,35(01):150.[doi:10.3969/j.issn.1671-7414.2020.01.040]
　WANG Lin,ZHOU Chao-qiong,XU Xiao-hua,et al.Comparative Study on the Reference Change Value and Reference Change Factor of Serum Tumor Markers[J].Journal of Modern Laboratory Medicine,2020,35(02):150.[doi:10.3969/j.issn.1671-7414.2020.01.040]
[5]张　磊a,李德涛a,朱　艳a,等.6 种化学发光系统检测肿瘤标志物的应用评估分析[J].现代检验医学杂志,2020,35(02):88.[doi:10.3969/j.issn.1671-7414.2020.02.025]
　ZHANG Leia,LI De-taoa,ZHU Yana,et al.Methodological Evaluation of Six Chemiluminescence DetectionSystems for Tumor Markers[J].Journal of Modern Laboratory Medicine,2020,35(02):88.[doi:10.3969/j.issn.1671-7414.2020.02.025]
[6]李　辉,汪春新,秦明明,等.肺癌患者血清7项肿瘤标志物联合检测在病理分型及临床分期中的应用价值研究[J].现代检验医学杂志,2021,36(04):5.[doi:10.3969/j.issn.1671-7414.2021.04.002]
　LI Hui,WANG Chun-xin,QIN Ming-ming,et al.Study on the Application Value of Combined Detection of 7 Tumor Markersin Serum of Patients with Lung Cancer in Pathological Classificationand Clinical Staging[J].Journal of Modern Laboratory Medicine,2021,36(02):5.[doi:10.3969/j.issn.1671-7414.2021.04.002]

备注/Memo

备注/Memo:
收稿日期：2022-06-20修回日期：2022-12-06
作者简介：郝晓燕（1993-），女，硕士，初级技师，研究方向：挖掘检验大数据对疾病诊断的价值， E-mail：1792850160@qq.com。
通讯作者：刘家云（1971-）， E-mail：jiayun@fmmu.edu.cn。

更新日期/Last Update: 2023-03-15