临床研究中的主成分分析。
Principal components analysis in clinical studies.
作者信息
Zhang Zhongheng, Castelló Adela
机构信息
Department of Emergency Medicine, Sir Run-Run Shaw Hospital, Zhejiang University School of Medicine, Hangzhou 310016, China.
Cancer Epidemiology Unit, National Center for Epidemiology, Carlos III Institute of Health, Madrid 28029, Spain.
出版信息
Ann Transl Med. 2017 Sep;5(17):351. doi: 10.21037/atm.2017.07.12.
Abstract
In multivariate analysis, independent variables are usually correlated to each other which can introduce multicollinearity in the regression models. One approach to solve this problem is to apply principal components analysis (PCA) over these variables. This method uses orthogonal transformation to represent sets of potentially correlated variables with principal components (PC) that are linearly uncorrelated. PCs are ordered so that the first PC has the largest possible variance and only some components are selected to represent the correlated variables. As a result, the dimension of the variable space is reduced. This tutorial illustrates how to perform PCA in R environment, the example is a simulated dataset in which two PCs are responsible for the majority of the variance in the data. Furthermore, the visualization of PCA is highlighted.
摘要
在多变量分析中，自变量通常相互关联，这可能会在回归模型中引入多重共线性。解决此问题的一种方法是对这些变量应用主成分分析（PCA）。该方法使用正交变换，用线性不相关的主成分（PC）来表示潜在相关的变量集。PC按顺序排列，使得第一个PC具有最大可能的方差，并且只选择一些成分来表示相关变量。结果，变量空间的维度降低了。本教程说明了如何在R环境中执行PCA，示例是一个模拟数据集，其中两个PC负责数据中的大部分方差。此外，还重点介绍了PCA的可视化。
相似文献
1
Principal components analysis in clinical studies.临床研究中的主成分分析。
Ann Transl Med. 2017 Sep;5(17):351. doi: 10.21037/atm.2017.07.12.
2
Visualizing the Complexity of the Athlete-Monitoring Cycle Through Principal-Component Analysis.通过主成分分析可视化运动员监测周期的复杂性
Int J Sports Physiol Perform. 2019 Oct 1;14(9):1304-1310. doi: 10.1123/ijspp.2019-0045.
3
Principal component analysis of neuronal ensemble activity reveals multidimensional somatosensory representations.神经元群体活动的主成分分析揭示了多维体感表征。
J Neurosci Methods. 1999 Dec 15;94(1):121-40. doi: 10.1016/s0165-0270(99)00130-2.
4
Patient phenotypes associated with outcome following surgery for mild degenerative cervical myelopathy: a principal component regression analysis.与轻度退行性颈椎脊髓病手术后结局相关的患者表型：主成分回归分析。
Spine J. 2018 Dec;18(12):2220-2231. doi: 10.1016/j.spinee.2018.05.009. Epub 2018 May 7.
5
Incorporating Prior Knowledge of Principal Components in Genomic Prediction.在基因组预测中纳入主成分的先验知识。
Front Genet. 2018 Aug 2;9:289. doi: 10.3389/fgene.2018.00289. eCollection 2018.
6
Use of principal component analysis to evaluate the partial organ tolerance of normal tissues to radiation.运用主成分分析评估正常组织对辐射的部分器官耐受性。
Int J Radiat Oncol Biol Phys. 2005 Jul 1;62(3):829-37. doi: 10.1016/j.ijrobp.2004.11.013.
7
Comparing patterns of component loadings: principal component analysis (PCA) versus independent component analysis (ICA) in analyzing multivariate non-normal data.比较成分载荷模式：主成分分析（PCA）与独立成分分析（ICA）在分析多元非正态数据中的应用。
Behav Res Methods. 2012 Dec;44(4):1239-43. doi: 10.3758/s13428-012-0193-1.
8
Extension of quadrature orthogonal signal corrected two-dimensional (QOSC 2D) correlation spectroscopy I: principal component analysis based QOSC 2D.正交信号校正二维（QOSC 2D）相关光谱的扩展I：基于主成分分析的QOSC 2D
Appl Spectrosc. 2007 Oct;61(10):1040-4. doi: 10.1366/000370207782217761.
9
Applying stability selection to consistently estimate sparse principal components in high-dimensional molecular data.应用稳定性选择方法在高维分子数据中一致估计稀疏主成分。
Bioinformatics. 2015 Aug 15;31(16):2683-90. doi: 10.1093/bioinformatics/btv197. Epub 2015 Apr 10.
10
Selection of microbial biomarkers with genetic algorithm and principal component analysis.遗传算法和主成分分析选择微生物生物标志物。
BMC Bioinformatics. 2019 Dec 10;20(Suppl 6):413. doi: 10.1186/s12859-019-3001-4.
引用本文的文献
1
Stratification of surgical outcomes in trigeminal neuralgia using multimodal data.利用多模态数据对三叉神经痛手术结果进行分层
Brain Commun. 2025 Jun 17;7(3):fcaf178. doi: 10.1093/braincomms/fcaf178. eCollection 2025.
2
The Brain in Cross-Cultural Adjustment: A Pilot Study of Japanese Expatriates Living in the United States.跨文化适应中的大脑：对生活在美国的日本侨民的一项初步研究。
Brain Sci. 2025 Jun 7;15(6):617. doi: 10.3390/brainsci15060617.
3
GWAS and multi-omics integrative analysis reveal novel loci and their molecular mechanisms for circulating fatty acids.全基因组关联研究（GWAS）与多组学整合分析揭示了循环脂肪酸的新基因座及其分子机制。
HGG Adv. 2025 Jun 21;6(4):100470. doi: 10.1016/j.xhgg.2025.100470.
4
Using Structural Equation Modeling to Examine Barriers and Facilitators of HIV Pre-Exposure Prophylaxis Willingness and Length of Use in Men Who Have Sex with Men Who Use Substances in Eight Southern US Cities.运用结构方程模型检验美国南部八个城市中使用毒品的男男性行为者接受HIV暴露前预防的意愿及使用时长的障碍因素和促进因素。
AIDS Patient Care STDS. 2025 Jun;39(6):245-256. doi: 10.1089/apc.2025.0036. Epub 2025 May 22.
5
Association prediction of lncRNAs and diseases using multiview graph convolution neural network.基于多视图图卷积神经网络的lncRNA与疾病关联预测
Front Genet. 2025 Apr 15;16:1568270. doi: 10.3389/fgene.2025.1568270. eCollection 2025.
6
A multiple regression model for peak skin dose using principal component analysis in interventional radiology.介入放射学中使用主成分分析的皮肤峰值剂量多元回归模型。
Radiol Phys Technol. 2025 Jun;18(2):439-450. doi: 10.1007/s12194-025-00893-3. Epub 2025 Mar 16.
7
Biochemical differences based on sex and clusters of biomarkers in patients with COVID-19: analysis from the CARDIO COVID 19-20 registry.新型冠状病毒肺炎患者基于性别和生物标志物簇的生化差异：来自CARDIO COVID 19-20注册研究的分析
BMC Cardiovasc Disord. 2025 Mar 5;25(1):147. doi: 10.1186/s12872-025-04565-3.
8
The clinical value and most informative threshold of polygenic risk score in the Quebec City Case-Control Asthma Cohort.魁北克市哮喘病例对照队列中多基因风险评分的临床价值及最具信息性的阈值
BMC Pulm Med. 2025 Jan 15;25(1):21. doi: 10.1186/s12890-025-03486-3.
9
Modeling the Impact of Extracellular Vesicle Cargoes in the Diagnosis of Coronary Artery Disease.模拟细胞外囊泡货物在冠状动脉疾病诊断中的影响
Biomedicines. 2024 Nov 25;12(12):2682. doi: 10.3390/biomedicines12122682.
10
Attention control in the peripartum period: a longitudinal study.围产期的注意力控制：一项纵向研究。
Arch Womens Ment Health. 2025 Jun;28(3):613-622. doi: 10.1007/s00737-024-01530-5. Epub 2024 Nov 11.
本文引用的文献
1
Increased Early Systemic Inflammation in ICU-Acquired Weakness; A Prospective Observational Cohort Study.重症监护病房获得性肌无力中早期全身炎症增加；一项前瞻性观察队列研究。
Crit Care Med. 2017 Jun;45(6):972-979. doi: 10.1097/CCM.0000000000002408.
2
Least absolute shrinkage and selection operator type methods for the identification of serum biomarkers of overweight and obesity: simulation and application.用于识别超重和肥胖血清生物标志物的最小绝对收缩和选择算子类型方法：模拟与应用
BMC Med Res Methodol. 2016 Nov 14;16(1):154. doi: 10.1186/s12874-016-0254-8.
3
Collinearity and Causal Diagrams: A Lesson on the Importance of Model Specification.共线性与因果图：关于模型设定重要性的一课
Epidemiology. 2017 Jan;28(1):47-53. doi: 10.1097/EDE.0000000000000554.
4
Reproducibility of data-driven dietary patterns in two groups of adult Spanish women from different studies.来自不同研究的两组成年西班牙女性中数据驱动饮食模式的可重复性。
Br J Nutr. 2016 Aug;116(4):734-42. doi: 10.1017/S000711451600252X. Epub 2016 Jul 4.
5
Evaluating the Applicability of Data-Driven Dietary Patterns to Independent Samples with a Focus on Measurement Tools for Pattern Similarity.评估数据驱动的饮食模式在独立样本中的适用性，重点关注模式相似性的测量工具。
J Acad Nutr Diet. 2016 Dec;116(12):1914-1924.e6. doi: 10.1016/j.jand.2016.05.008. Epub 2016 Jun 28.
6
Biplots in biomedical research.生物医学研究中的双标图
Stat Med. 1990 May;9(5):469-85. doi: 10.1002/sim.4780090502.
Zotero 插件