基于多检验变量和机器学习算法的结肠癌诊断模型建立及价值评估

doi:10.6040/j.issn.1671-7554.0.2023.1092

摘要/Abstract

摘要： 目的采用不同机器学习算法,建立基于多检验变量的结肠癌诊断模型,并评估其临床应用价值。方法收集119例结肠癌患者(结肠癌组)和125例健康对照(健康对照组)的血清样本,提取血清外泌体,采用RT-qPCR方法测定miR-214-3p分子在两组中的表达水平,进而绘制受试者工作特征(receiver operating characteristic, ROC)曲线,评估其对结肠癌的诊断效能。同时,收集结肠癌组和健康对照组的常规检验项目结果。将以上指标均纳入研究筛选出特征性变量,采用11种不同算法结合ROC曲线和机器学习曲线综合评价筛选出最优算法,建立结肠癌诊断模型。结果结肠癌组血清外泌体中miR-214-3p 的表达水平明显高于健康对照组(P<0.001),其诊断结肠癌的ROC曲线下面积(area under curve, AUC)为0.820,具有较好的诊断效能。将结肠癌组和健康对照组的血清外泌体miR-214-3p及30种常规检验指标纳入后,筛选出尿素、癌胚抗原、单核细胞计数、外泌体miR-214-3p共4个特征性变量,且逻辑回归算法是建立机器学习模型的最优算法,其AUC为0.93,且学习曲线呈现很好的拟合状态。结论血清外泌体miR-214-3p是结肠癌的潜在标志物,基于4个特征性变量和逻辑回归算法建立的机器学习模型对结肠癌有良好的诊断效能。

关键词: 结肠癌, miR-214-3p, 外泌体, 机器学习

Abstract: Objective To establish a colon cancer diagnostic model based on multiple variables using various machine learning algorithms and to assess its clinical application value. Methods Serum samples from 119 colon cancer patients and 125 healthy controls were collected. Serum exosome was extracted, and miRNA 214-3p(miR-214-3p)level was measured using RT-qPCR. Receiver operating characteristic(ROC)curve was plotted to evaluate the diagnostic efficiency of colon cancer. Additionally, 30 routine laboratory items of colon cancer patients and healthy controls were collected. Characteristic variables were screened, and 11 algorithms were used to establish the diagnostic model. The optimal model was selected with ROC and machine learning curves. Results The expression level of miR-214-3p in colon cancer patients was significantly higher than that in healthy controls(P<0.001), with the area under the ROC curve(AUC)being 0.820, indicating good diagnostic performance. After the expression level of miR-214-3p and other 30 routine laboratory items were enrolled, 4 characteristic variables were screened to establish the diagnostic model, including UREA, carcinoembryonic antigen, monocyte and miR-214-3p. The Logistic regression algorithm was identified as the optimal one(AUC=0.93). Conclusion Serum exosome miR-214-3p is a potential biomarker of colon cancer. The model based on 4 characteristic variables and Logistic regression algorithm has an excellent diagnostic performance for diagnosing colon cancer.

Key words: Colon cancer, miR-214-3p, Exosome, Machine learning

中图分类号:

R783

梁永媛,蔡培飞,郑桂喜. 基于多检验变量和机器学习算法的结肠癌诊断模型建立及价值评估[J]. 山东大学学报 (医学版), 2024, 62(2): 51-59.

LIANG Yongyuan, CAI Peifei, ZHENG Guixi. Establishment and value assessment of colon cancer diagnostic models based on multiple variables and different machine learning algorithms[J]. Journal of Shandong University (Health Sciences), 2024, 62(2): 51-59.

参考文献

[1] 闫超, 陕飞, 李子禹. 2020年中国与全球结直肠癌流行概况分析[J]. 中华肿瘤杂志, 2023, 45(3): 221-229. YAN Chao, SHAN Fei, LI Ziyu. Epidemiological analysis of colorectal cancer in China and the world in 2020. Chinese Journal of Cancer, 2019, 45(3): 221-229.
[2] Fabregas JC, Ramnaraign B, George TJ. Clinical updates for colon cancer care in 2022[J]. Clin Colorectal Cancer, 2022, 21(3): 198-203.
[3] Su Y, Tian X, Gao R, et al. Colon cancer diagnosis and staging classification based on machine learning and bioinformatics analysis[J]. Comput Biol Med, 2022, 145: 105409. doi: 10.1016/j.compbiomed.2022.105409.
[4] Tang S, Cheng J, Yao Y, et al. Combination of four serum exosomal miRNAs as novel diagnostic biomarkers for early-stage gastric cancer[J]. Front Genet, 2020, 11: 237. doi:10.3389/fgene.2020.00237.
[5] Miao C, Zhang W, Feng L, et al. Cancer-derived exosome miRNAs induce skeletal muscle wasting by Bcl-2-mediated apoptosis in colon cancer cachexia[J]. Mol Ther Nucleic Acids, 2021, 24: 923-938. doi: 10.1016/j.omtn.2021.04.015.
[6] Wei W, Li Y, Huang T. Using machine learning methods to study colorectal cancer tumor micro-environment and its biomarkers[J]. Int J Mol Sci, 2023, 24(13): 11133. doi: 10.3390/ijms241311133.
[7] Nguyen QTN, Nguyen PA, Wang CJ, et al. Machine learning approaches for predicting 5-year breast cancer survival: a multicenter study[J]. Cancer Sci, 2023, 114(10): 4063-4072.
[8] Lannagan TR, Jackstadt R, Leedham SJ, et al. Advances in colon cancer research: in vitro and animal models[J]. Curr Opin Genet Dev, 2021, 66: 50-56. doi: 10.1016/j.gde.2020.12.003.
[9] Ahmed M. Colon cancer: a clinicians perspective in 2019[J]. Gastroenterology Res, 2020, 13(1): 1-10.
[10] Khan SZ, Lengyel CG. Challenges in the management of colorectal cancer in low- and middle-income countries[J]. Cancer Treat Res Commun, 2023, 35: 100705. doi: 10.1016/j.ctarc.2023.100705.
[11] Verkuijl SJ, Jonker JE, Trzpis M, et al. Functional outcomes of surgery for colon cancer: a systematic review and meta-analysis[J]. Eur J Surg Oncol, 2021, 47(5): 960-969.
[12] 刘睿清, 卢云. 基于循证医学的早期结肠癌外科治疗进展[J]. 中华胃肠外科杂志,2022, 25(12): 1144-1149. LIU Ruiqing, LU Yun. Advances in surgical treatment of early colon cancer based on evidence-based medicine[J]. Chinese Journal of Gastrointestinal Surgery, 2002, 25(12): 1144-1149.
[13] Chan SCH, Liang JQ. Advances in tests for colorectal cancer screening and diagnosis[J]. Expert Rev Mol Diagn, 2022, 22(4): 449-460.
[14] Birgisson H, Olafsdottir EJ, Sverrisdottir A, et al. Screening for cancer of the colon and rectum a review on incidence, mortality, cost and benefit[J]. Laeknabladid, 2021, 107(9): 398-405.
[15] Jain S, Maque J, Galoosian A, et al. Optimal strategies for colorectal cancer screening[J]. Curr Treat Options Oncol, 2022, 23(4): 474-493.
[16] Shaukat A, Levin TR. Current and future colorectal cancer screening strategies[J]. Nat Rev Gastroenterol Hepatol, 2022, 19(8): 521-531.
[17] Liang G, Zhu Y, Ali DJ, et al. Engineered exosomes for targeted co-delivery of miR-21 inhibitor and chemotherapeutics to reverse drug resistance in colon cancer[J]. J Nanobiotechnology, 2020, 18(1): 10. doi: 10.1186/s12951-019-0563-2.
[18] Wang L, Song X, Yu M, et al. Serum exosomal miR-377-3p and miR-381-3p as diagnostic biomarkers in colorectal cancer[J]. Future Oncol, 2022, 18(7): 793-805.
[19] Maeda K, Sasaki H, Ueda S, et al. Serum exosomal microRNA-34a as a potential biomarker in epithelial ovarian cancer[J]. J Ovarian Res, 2020, 13(1): 47. doi: 10.1186/s13048-020-00648-1.
[20] Karimi E, Dehghani A, Azari H, et al. Molecular mechanisms of miR-214 involved in cancer and drug resistance[J]. Curr Mol Med, 2023, 23(7): 589-605.
[21] He GN, Bao NR, Wang S, et al. Ketamine induces ferroptosis of liver cancer cells by targeting lncRNA PVT1/miR-214-3p/GPX4[J]. Drug Des Devel Ther, 2021, 15: 3965-3978. doi: 10.2147/dddt.S332847.
[22] Wu Y, Xu X. Long non-coding RNA signature in colorectal cancer: research progression and clinical application[J]. Cancer Cell Int, 2023, 23(1): 28. doi: 10.1186/s12935-023-02867-0.
[23] Sukmana BI, Al-Hawary SIS, Abosaooda M, et al. A thorough and current study of miR-214-related targets in cancer[J]. Pathol Res Pract, 2023, 249:154770. doi: 10.1016/j.prp.2023.154770.
[24] Hossain MS, Karuniawati H, Jairoun AA, et al. Colorectal cancer: a review of carcinogenesis, global epidemiology, current challenges, risk factors, preventive and treatment strategies[J]. Cancers(Basel), 2022, 14(7): 1732. doi: 10.3390/cancers14071732.
[25] Wang C, Sun H, Liu J. BUN level is associated with cancer prevalence[J]. Eur J Med Res, 2023, 28(1): 213. doi: 10.1186/s40001-023-01186-4.
[26] Qin WH, Yang ZS, Li M, et al. High serum levels of cholesterol increase antitumor functions of nature killer cells and reduce growth of liver tumors in mice[J]. Gastroenterology, 2020, 158(6): 1713-1727.
[27] Larionova I, Patysheva M, Iamshchikov P, et al. PFKFB3 overexpression in monocytes of patients with colon but not rectal cancer programs pro-tumor macrophages and is indicative for higher risk of tumor relapse[J]. Front Immunol, 2022, 13: 1080501. doi: 10.3389/fimmu.2022.1080501.
[28] Yu K, Qiang G, Peng S, et al. Potential diagnostic value of the hematological parameters lymphocyte-monocyte ratio and hemoglobin-platelet ratio for detecting colon cancer[J]. J Int Med Res, 2022, 50(9): 3000605221122742. doi: 10.1177/03000605221122742.

相关文章 15

[1]	廖原,门丹,李一帆,李怀臣,龙飞,刘铱. PM_2.5短期暴露对结核病发病风险的个体精准评估[J]. 山东大学学报 (医学版), 2026, 64(3): 116-123.
[2]	刘禹,霍娅娅,龚丞,梁婷,李斌. 基于机器学习的骨科生物材料设计与优化[J]. 山东大学学报 (医学版), 2026, 64(2): 22-33.
[3]	王建民,李晓峰,由志涛,董圣杰,赵宇驰,李占菊,邹德鑫,张剑锋,孙涛,杜伟. 基于可解释机器学习的后路腰椎椎体间融合术后慢性疼痛风险预测模型构建[J]. 山东大学学报 (医学版), 2026, 64(2): 78-88.
[4]	王丽云,高天勤,刘雨佳,陈青,陈柳,沙凯辉. 基于机器学习产后压力性尿失禁风险预测模型的构建及验证[J]. 山东大学学报 (医学版), 2025, 63(6): 55-66.
[5]	王静,刘晓菲,曾荣,许长娟,张锦涛,董亮. 基于机器学习算法鉴定哮喘的坏死性凋亡相关生物标志物[J]. 山东大学学报 (医学版), 2024, 62(7): 21-32.
[6]	郭振江,王宁,赵光远,杜立强,崔朝勃,刘防震. 基于机器学习建立术前预测近端胃癌食管切缘阳性模型[J]. 山东大学学报 (医学版), 2024, 62(7): 78-83.
[7]	冯绪梅,宋相庆,季冠虹,赵小刚,肖兆华. 血浆外泌体miR-548k在食管鳞癌中的表达及诊断价值[J]. 山东大学学报 (医学版), 2024, 62(5): 79-88.
[8]	刘爱静,李雁儒,高惠茹,段伟丽,李培龙,李娟,杜鲁涛,王传新. 自噬相关蛋白5在结肠癌中的表达及对结肠癌细胞迁移及侵袭能力的影响[J]. 山东大学学报 (医学版), 2024, 62(4): 14-23.
[9]	王玉涛,孙岩. 单细胞转录组学与机器学习综合分析揭示腹主动脉瘤潜在生物标志物[J]. 山东大学学报 (医学版), 2024, 62(11): 40-53.
[10]	张景慧,王娟,赵玉洁,段淼,刘毅然,林敏娟,谯旭,李真,左秀丽. 基于机器学习的胃肠道疾病舌诊模型构建[J]. 山东大学学报 (医学版), 2024, 62(1): 38-47.
[11]	董雅琪,王新慧,赵颖慧,王传新. 血清外泌体LINC02163作为结直肠癌远处转移标志物的临床价值[J]. 山东大学学报 (医学版), 2023, 61(9): 19-28.
[12]	赵元元,路军涛,吴小华. 人脐带间充质干细胞外泌体miR-100对多囊卵巢综合征患者颗粒细胞炎症的影响[J]. 山东大学学报 (医学版), 2023, 61(5): 51-58.
[13]	刘亚军,郎昭,郭安忆,刘文勇. 骨科冲击波治疗的智能化发展现状及趋势分析[J]. 山东大学学报 (医学版), 2023, 61(3): 7-13.
[14]	吴南,仉建国,朱源棚,陈癸霖,陈泽夫. 人工智能在脊柱畸形诊疗中的应用[J]. 山东大学学报 (医学版), 2023, 61(3): 14-20.
[15]	朱正阳,沈靖菲,陈思璇,叶梅萍,杨惠泉,周佳南,梁雪,张鑫,张冰. 磁敏感加权成像不同影像组学模型预测胶质瘤IDH基因突变[J]. 山东大学学报 (医学版), 2023, 61(12): 44-50.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed