医学检查与临床诊断

基于机器学习利用常规检验指标建立胃癌淋巴结转移预测模型

  • 严健亮 ,
  • 谢泽宇 ,
  • 景蓉蓉 ,
  • 崔明
展开
  • 1.南通大学附属医院检验科 (江苏 南通 226006 )
    2.南通大学医学院 (江苏 南通 226006 )
    3.河海大学商学院 (南京 211100 )

收稿日期: 2023-09-22

  网络出版日期: 2024-04-08

基金资助

中国博士后科学基金资助项目(2020M681688);南通市市级基础科学研究和社会民生科技指令性项目(MS12021001)

Research on establishing gastric cancer lymph node metastasis prediction model based on machine learning and routine laboratory indicators

  • Jianliang YAN ,
  • Zeyu XIE ,
  • Rongrong JING ,
  • Ming. CUI
Expand
  • Department of Laboratory Medicine,Affiliated Hospital of Nantong University,Nantong 226006,China
    Natong University College of Medicine,Nantong 226006,China

Received date: 2023-09-22

  Online published: 2024-04-08

摘要

目的 利用机器学习算法,建立一种基于常规检验指标的胃癌淋巴结转移(lymph node metastasis, LNM)预测模型。 方法 收集南通大学附属医院2020年1月至2022年1月期间741例胃癌患者数据用于模型训练和测试,收集2023年1-10月期间102例胃癌患者数据用于模型验证;使用XGBoost方法计算指标重要性,从66个指标中过滤出重要指标集合;构建并训练5种机器学习算法:K近邻、支持向量机、多层感知器、随机森林、Adaboost进行对比分析,并在验证集中进一步验证模型的稳定性和预测能力。 结果 本研究筛选出由9个常规检验指标组成的重要指标集合,并训练构建出胃癌LNM预测模型V9。此外,通过多种机器学习算法对比实验发现,基于Boosting策略的Adaboost算法效果最好,其曲线下面积、F1值、准确率、灵敏度、特异度等评估指标均在0.833~0.968之间,在验证集上预测准确率达94.12%。 结论 V9是一种具有辅助临床诊断价值的胃癌LNM预测模型,能够准确评估患者的风险,并为临床决策提供依据。

本文引用格式

严健亮 , 谢泽宇 , 景蓉蓉 , 崔明 . 基于机器学习利用常规检验指标建立胃癌淋巴结转移预测模型[J]. 实用医学杂志, 2024 , 40(6) : 844 -849 . DOI: 10.3969/j.issn.1006-5725.2024.06.019

Abstract

Objective To establish a prediction model for lymph node metastasis (LNM) of gastric cancer based on routine laboratory indicators using machine learning algorithms. Methods This study collected data of 741 gastric cancer patients at Affiliated Hospital of Nantong University between January 2020 and January 2022 for model training and testing. Additionally, data of 102 gastric cancer patients between January 2023 and October 2023 were collected for model validation. XGBoost algorithm was used to calculate the importance of indicators and filter out a set of important indicators from 66 indicators. Five machine learning algorithms, including K-Nearest Neighbor, Support Vector Machine, Multilayer Perceptron, Random Forest and Adaboost, were constructed and trained for comparative analysis. Furthermore, the stability and accuracy of the model were further validated on the validation set. Results This study selected a set of important indicators composed of 9 routine laboratory indicators and trained the gastric cancer LNM prediction model, named V9. Additionally, through comparative experiments, it was found that the Adaboost algorithm based on the boosting strategy had the best performance, with evaluation metrics such as area under the curve, F1 score, accuracy, sensitivity, and specificity ranging from 0.833 to 0.968. The accuracy of the predictions on the validation set was 94.12%. Conclusion V9 was a gastric cancer LNM prediction model that has auxiliary clinical diagnostic value. It can be used to assess the risk of patients accurately and provide a basis for clinical decision-making.

参考文献

1 XIA C, DONG X, LI H, et al. Cancer statistics in China and United States, 2022: profiles, trends, and determinants[J]. Chin Med J (Engl), 2022,135(5):584-590. doi:10.1097/cm9.0000000000002108
2 WANG K, JIANG X, REN Y,et al. The significance of preoperative serum carcinoembryonic antigen levels in the prediction of lymph node metastasis and prognosis in locally advanced gastric cancer: a retrospective analysis[J]. BMC Gastroenterol,2020, 20(1): 100. doi:10.1186/s12876-020-01255-6
3 LI Y, XIE F, XIONG Q, et al. Machine learning for lymph node metastasis prediction of in patients with gastric cancer: A systematic review and meta-analysis[J]. Front Oncol, 2022,12:946038. doi:10.3389/fonc.2022.946038
4 TIAN H, NING Z, ZONG Z, et al. Application of Machine Learning Algorithms to Predict Lymph Node Metastasis in Early Gastric Cancer[J]. Front Med (Lausanne), 2022,8:759013. doi:10.3389/fmed.2021.759013
5 ZHANG Y, ZHANG J, YANG L, et al. A meta-analysis of the utility of transabdominal ultrasound for evaluation of gastric cancer[J]. Medicine (Baltimore),2021,100 (32):e26928. doi:10.1097/md.0000000000026928
6 CHARILAOU P, BATTAT R. Machine learning models and over-fitting considerations[J]. World J Gastroenterol,2022,28(5):605-607. doi:10.3748/wjg.v28.i5.605
7 MACEACHERN S J, FORKERT N D. Machine learning for precision medicine[J].Genome, 2021,64(4):416-425. doi:10.1139/gen-2020-0131
8 NGIAM K Y, KHOR I W. Big data and machine learning algorithms for health-care delivery[J]. Lancet Oncol,2019,20(5):e262-e273. doi:10.1016/s1470-2045(19)30149-4
9 PRABHA A, YADAV J, RABI A, et al. Design of intelligent diabetes mellitus detection system using hybrid feature selection based XGBoost classifier[J]. Comput Biol Med, 2021,136:104664. doi:10.1016/j.compbiomed.2021.104664
10 LUO Y, XUE Y, SONG H, et al. Machine learning based on routine laboratory indicators promoting the discrimination between active tuberculosis and latent tuberculosis infection[J]. J Infect, 2022,84(5):648-657. doi:10.1016/j.jinf.2021.12.046
11 ALBARADEI S, THAFAR M, ALSAEDI A, et al. Machine learning and deep learning methods that use omics data for metastasis prediction[J]. Comput Struct Biotechnol J, 2021,19:5008-5018. doi:10.1016/j.csbj.2021.09.001
12 LEI N, ZHANG X, WEI M, et al. Machine learning algorithms' accuracy in predicting kidney disease progression: a systematic review and meta-analysis[J]. BMC Med Inform Decis Mak, 2022,22(1):205. doi:10.1186/s12911-022-01951-1
13 LIU H Q, LIN S Y, SONG Y D, et al. Machine learning on MRI radiomic features: identification of molecular subtype alteration in breast cancer after neoadjuvant therapy[J]. Eur Radiol,2023,33(4):2965-2974. doi:10.1007/s00330-022-09264-7
14 SUN Y, DING S, ZHANG Z, et al. An improved grid search algorithm to optimize SVR for prediction[J]. Soft Comput,2021,25: 5633-5644. doi:10.1007/s00500-020-05560-w
15 邱晖. 中性粒细胞-淋巴细胞比对早期胃癌淋巴结转移的预测价值与预后影响分析[J]. 黑龙江医药科学,2022,45(6):144-147. doi:10.3969/j.issn.1008-0104.2022.06.059
16 YANG Z, XU Q, BAO S, et al. Learning With Multiclass AUC: Theory and Algorithms[J]. IEEE Trans Pattern Anal Mach Intell,2022,44(11):7747-7763. doi:10.1109/tpami.2021.3101125
17 罗东明,陈德伦,汪志华,等. 血清中AFP、FGA、PG、PSA在预测早期胃癌患者淋巴结转移和手术疗效监测中的临床意义[J].中国老年学杂志,2022,42(5):1081-1084. doi:10.3969/j.issn.1005-9202.2022.05.018
18 李焱芳,陶芹,李韶华,等. 卡培他滨辅助紫杉醇+顺铂化疗对胃癌患者cTnI、BNP的影响[J]. 现代消化及介入诊疗,2021,26(4):437-440.
19 HUANG C, HU C, ZHU J, et al. Establishment of Decision Rules and Risk Assessment Model for Preoperative Prediction of Lymph Node Metastasis in Gastric Cancer[J]. Front Oncol,2020,10:1638. doi:10.3389/fonc.2020.01638
20 GAO X, MA T, CUI J, et al. A radiomics-based model for prediction of lymph node metastasis in gastric cancer[J]. Eur J Radiol,2020,129:109069. doi:10.1016/j.ejrad.2020.109069
21 顾玉花. CysC、β2-MG联合检测对胃癌患者化疗后肾脏早期损害的诊断价值[J]. 山东医学高等专科学校学报,2014,36(1):49-51. doi:10.3969/j.issn.1674-0947.2014.01.022
22 YIN H M, HE Q, CHEN J, et al. Drug metabolism-related eight-gene signature can predict the prognosis of gastric adenocarcinoma[J]. J Clin Lab Anal,2021,35(12):e24085. doi:10.1002/jcla.24085
23 孙芳,许永波,崔广和,等. 基于超声特征构建机器学习模型预测浸润性乳腺癌Luminal分型[J]. 实用医学杂志,2022,38(18):2279-2283.
24 严健亮,景蓉蓉,谢泽宇,等. 机器学习在胃癌生物标志物挖掘中的应用进展[J]. 实用医学杂志,2023,39(6):783-787. doi:10.3969/j.issn.1006-5725.2023.06.023
25 YANG B, LI W, WU X, et al. Comparison of Ruptured Intracranial Aneurysms Identification Using Different Machine Learning Algorithms and Radiomics [J].Diagnostics (Basel),2023,13(16):2627. doi:10.3390/diagnostics13162627
26 TANG J, HENDERSON A, GARDNER P. Exploring AdaBoost and Random Forests machine learning approaches for infrared pathology on unbalanced data sets[J]. Analyst, 2021, 146(19):5880-5891. doi:10.1039/d0an02155e
文章导航

/