使用学习机器进行以患者为中心的是/否预后评估。
Patient-centered yes/no prognosis using learning machines.
作者信息
König I R, Malley J D, Pajevic S, Weimar C, Diener H-C, Ziegler A
机构信息
Institut für Medizinische Biometrie und Statistik, Universität zu Lübeck, Ratzeburger Allee 160, 23538 Lübeck, Germany.
出版信息
Int J Data Min Bioinform. 2008;2(4):289-341. doi: 10.1504/ijdmb.2008.022149.
Abstract
In the last 15 years several machine learning approaches have been developed for classification and regression. In an intuitive manner we introduce the main ideas of classification and regression trees, support vector machines, bagging, boosting and random forests. We discuss differences in the use of machine learning in the biomedical community and the computer sciences. We propose methods for comparing machines on a sound statistical basis. Data from the German Stroke Study Collaboration is used for illustration. We compare the results from learning machines to those obtained by a published logistic regression and discuss similarities and differences.
摘要
在过去15年里，已经开发出了几种用于分类和回归的机器学习方法。我们以直观的方式介绍分类与回归树、支持向量机、装袋法、提升法和随机森林的主要思想。我们讨论了生物医学领域和计算机科学在机器学习应用方面的差异。我们提出了在合理的统计基础上比较机器的方法。以德国中风研究合作项目的数据为例进行说明。我们将机器学习的结果与已发表的逻辑回归结果进行比较，并讨论异同。
相似文献
1
Patient-centered yes/no prognosis using learning machines.使用学习机器进行以患者为中心的是/否预后评估。
Int J Data Min Bioinform. 2008;2(4):289-341. doi: 10.1504/ijdmb.2008.022149.
2
A comprehensive comparison of random forests and support vector machines for microarray-based cancer classification.基于微阵列的癌症分类中随机森林与支持向量机的全面比较
BMC Bioinformatics. 2008 Jul 22;9:319. doi: 10.1186/1471-2105-9-319.
3
Machine Learning Principles for Radiology Investigators.机器学习原理在放射学研究中的应用
Acad Radiol. 2020 Jan;27(1):13-25. doi: 10.1016/j.acra.2019.07.030.
4
Performance of machine learning methods for ligand-based virtual screening.基于配体的虚拟筛选中机器学习方法的性能
Comb Chem High Throughput Screen. 2009 May;12(4):358-68. doi: 10.2174/138620709788167962.
5
Pre-operative prediction of surgical morbidity in children: comparison of five statistical models.儿童手术并发症的术前预测：五种统计模型的比较
Comput Biol Med. 2015 Feb;57:54-65. doi: 10.1016/j.compbiomed.2014.11.009. Epub 2014 Dec 8.
6
Machine learning algorithms performed no better than regression models for prognostication in traumatic brain injury.机器学习算法在预测创伤性脑损伤方面并不比回归模型表现得更好。
J Clin Epidemiol. 2020 Jun;122:95-107. doi: 10.1016/j.jclinepi.2020.03.005. Epub 2020 Mar 20.
7
A comparison of methods for classifying clinical samples based on proteomics data: a case study for statistical and machine learning approaches.基于蛋白质组学数据的临床样本分类方法比较：统计和机器学习方法的案例研究。
PLoS One. 2011;6(9):e24973. doi: 10.1371/journal.pone.0024973. Epub 2011 Sep 28.
8
Probability machines: consistent probability estimation using nonparametric learning machines.概率机器：使用非参数学习机器进行一致概率估计。
Methods Inf Med. 2012;51(1):74-81. doi: 10.3414/ME00-01-0052. Epub 2011 Sep 14.
9
[Applications of machine learning in clinical decision support in the omic era].[机器学习在组学时代临床决策支持中的应用]
Yi Chuan. 2018 Sep 20;40(9):693-703. doi: 10.16288/j.yczz.18-139.
10
Contemporary QSAR classifiers compared.当代定量构效关系分类器比较。
J Chem Inf Model. 2007 Jan-Feb;47(1):219-27. doi: 10.1021/ci600332j.
引用本文的文献
1
A novel framework for designing a multi-DoF prosthetic wrist control using machine learning.使用机器学习设计多自由度假肢腕部控制的新框架。
Sci Rep. 2021 Jul 22;11(1):15050. doi: 10.1038/s41598-021-94449-1.
2
Status and Recommendations of Technological and Data-Driven Innovations in Cancer Care: Focus Group Study.癌症护理中技术和数据驱动创新的现状和建议：焦点小组研究。
J Med Internet Res. 2020 Dec 15;22(12):e22034. doi: 10.2196/22034.
3
Statistical learning approaches in the genetic epidemiology of complex diseases.复杂疾病遗传流行病学中的统计学习方法。
Hum Genet. 2020 Jan;139(1):73-84. doi: 10.1007/s00439-019-01996-9. Epub 2019 May 2.
4
Towards phenotyping stroke: Leveraging data from a large-scale epidemiological study to detect stroke diagnosis.迈向卒中表型分析：利用大规模流行病学研究数据进行卒中诊断检测。
PLoS One. 2018 Feb 14;13(2):e0192586. doi: 10.1371/journal.pone.0192586. eCollection 2018.
5
Optimal SVM parameter selection for non-separable and unbalanced datasets.针对不可分和不平衡数据集的最优支持向量机参数选择
Struct Multidiscipl Optim. 2014 Oct 1;50(4):523-535. doi: 10.1007/s00158-014-1105-z.
6
Risk estimation and risk prediction using machine-learning methods.利用机器学习方法进行风险评估和预测。
Hum Genet. 2012 Oct;131(10):1639-54. doi: 10.1007/s00439-012-1194-y. Epub 2012 Jul 3.
7
Data analysis and data mining: current issues in biomedical informatics.数据分析与数据挖掘：生物医学信息学中的当前问题
Methods Inf Med. 2011;50(6):536-44. doi: 10.3414/ME11-06-0002.
8
Probability machines: consistent probability estimation using nonparametric learning machines.概率机器：使用非参数学习机器进行一致概率估计。
Methods Inf Med. 2012;51(1):74-81. doi: 10.3414/ME00-01-0052. Epub 2011 Sep 14.
9
On safari to Random Jungle: a fast implementation of Random Forests for high-dimensional data.随机森林的随机丛林之旅：一种用于高维数据的随机森林的快速实现。
Bioinformatics. 2010 Jul 15;26(14):1752-8. doi: 10.1093/bioinformatics/btq257. Epub 2010 May 26.
10
An introduction to recursive partitioning: rationale, application, and characteristics of classification and regression trees, bagging, and random forests.递归分区介绍：分类和回归树、装袋和随机森林的原理、应用和特点。
Psychol Methods. 2009 Dec;14(4):323-48. doi: 10.1037/a0016973.
本文引用的文献
1
Picking single-nucleotide polymorphisms in forests.在森林中挑选单核苷酸多态性。
BMC Proc. 2007;1 Suppl 1(Suppl 1):S59. doi: 10.1186/1753-6561-1-s1-s59. Epub 2007 Dec 18.
2
Data mining, neural nets, trees--problems 2 and 3 of Genetic Analysis Workshop 15.数据挖掘、神经网络、决策树——遗传分析研讨会15的问题2和问题3。
Genet Epidemiol. 2007;31 Suppl 1:S51-60. doi: 10.1002/gepi.20280.
3
Practical experiences on the necessity of external validation.外部验证必要性的实践经验。
Stat Med. 2007 Dec 30;26(30):5499-511. doi: 10.1002/sim.3069.
4
Bias in random forest variable importance measures: illustrations, sources and a solution.随机森林变量重要性度量中的偏差：示例、来源及解决方案
BMC Bioinformatics. 2007 Jan 25;8:25. doi: 10.1186/1471-2105-8-25.
5
What is a support vector machine?什么是支持向量机？
Nat Biotechnol. 2006 Dec;24(12):1565-7. doi: 10.1038/nbt1206-1565.
6
Gene selection and classification of microarray data using random forest.使用随机森林进行微阵列数据的基因选择与分类
BMC Bioinformatics. 2006 Jan 6;7:3. doi: 10.1186/1471-2105-7-3.
7
A review of two journals found that articles using multivariable logistic regression frequently did not report commonly recommended assumptions.对两份期刊的一项综述发现，使用多变量逻辑回归的文章常常未报告普遍推荐的假设。
J Clin Epidemiol. 2004 Nov;57(11):1147-52. doi: 10.1016/j.jclinepi.2003.05.003.
8
Information assessment on predicting protein-protein interactions.预测蛋白质-蛋白质相互作用的信息评估
BMC Bioinformatics. 2004 Oct 18;5:154. doi: 10.1186/1471-2105-5-154.
9
BagBoosting for tumor classification with gene expression data.用于基于基因表达数据的肿瘤分类的BagBoosting算法
Bioinformatics. 2004 Dec 12;20(18):3583-93. doi: 10.1093/bioinformatics/bth447. Epub 2004 Oct 5.
10
A new approach to modelling interactions between treatment and continuous covariates in clinical trials by using fractional polynomials.一种通过使用分数多项式对临床试验中治疗与连续协变量之间的相互作用进行建模的新方法。
Stat Med. 2004 Aug 30;23(16):2509-25. doi: 10.1002/sim.1815.
Zotero 插件