机器学习在肿瘤分子标志物挖掘中的研究进展  

Research progress of machine learning in mining of tumor markers

作　　者：娄笑迎 崔巍 Lou Xiaoying;Cui Wei(State Key Laboratory of Molecular Oncology,Department of Clinical Laboratory,National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital,Chinese Academy of Medical Sciences and Peking Union Medical College,Beijing 100021,China)

机构地区：[1]国家癌症中心/国家肿瘤临床医学研究中心,中国医学科学院北京协和医学院肿瘤医院,北京100021

出　　处：《中华检验医学杂志》2021年第6期532-536,共5页Chinese Journal of Laboratory Medicine

基　　金：国家自然科学基金面上项目(81772272);中国医学科学院医学与健康科技创新工程项目(2017-HM-3-005)。

摘　　要：随着高通量测序和多组学技术的应用,越来越多的生物标志物被挖掘并用于疾病诊断、风险分层、疗效评估及预后预测的研究中。由于机器学习能处理复杂数据,并通过建立模型等方法较好预测临床疾病变化,因此其在肿瘤标志物的挖掘和应用中具有一定的优势。通过总结近年来常用的机器学习方法,阐述其在标志物挖掘中的应用进展,并总结不同的机器学习方法在标志物挖掘中的优劣。With the development and application of high-throughput sequencing and multi-omics techniques,more and more biomarkers have been excavated and used in disease diagnosis,risk stratification,treatment response evaluation and prognosis predication.Machine learning has certain advantages in mining and evaluating of tumor markers due to the capacity of dealing with complicated data and building models.This article summarized common machine learning methods,and detailed current applications of machine learning in mining of tumor markers.Additionally,our review aimed to provide the advantages and disadvantages of different machine learning methods in mining of tumor markers.

关 键 词：机器学习 肿瘤标志物 数据挖掘 

分 类 号：R730.43[医药卫生—肿瘤]