相关实验视频

Updated: Jul 12, 2025

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

统计机器学习在生物标志物选择中的应用

Ritwik Vashistha¹, Zubdahe Noor², Shibasish Dasgupta^3,4

¹Department of Statistics and Data Sciences, The University of Texas at Austin, Austin, TX, USA.

Scientific reports

|October 26, 2023

概括

这项研究评估了来自JAVELIN Bladder 100试验的晚期泌尿器癌 (aUC) 患者生物标志物识别的可变选择方法. 一些方法显示出希望,但数据中的高对线性为生物标志物发现带来了挑战.

科学领域:

在瘤学瘤学.
生物统计学生物统计学
基因组医学是基因组医学.

背景情况:

晚期泌尿腺癌 (aUC) 治疗从维持疗法中获益,正如JAVELIN Bladder 100试验所示.
鉴定生物标志物对于aUC的精密医学至关重要,但由于基因组数据中的高对线性和低信号存在挑战.
由于JAVELIN Bladder 100数据集的特性,使用标准变量选择方法很难可靠地识别生物标志物.

研究的目的:

评估各种可变选择方法在发现aUC患者的预后和预测生物标志物的性能.
为了比较处罚回归,随机生存森林和贝叶斯变量选择方法.
为贝叶斯方法提出一个修改的贝叶斯信息标准 (BIC) 值规则.

主要方法:

一项模拟研究评估了高维数据的流行的变量选择技术.
使用了处罚回归模型,随机生存森林和贝叶斯变量选择.
这些方法应用于JAVELIN Bladder 100数据集,以确定与生存相关的生物标志物.

主要成果:

变量选择方法通常具有较低的错误发现率,但在高对线性方面遇到了困难.
与拉索相关的方法在JAVELIN Bladder 100数据中确定了潜在的生物相关变量.
随机搜索变量选择和随机生存森林显示了数据集对线性和低信号的限制.

结论:

对于在高维,直线aUC数据中发现生物标志物而言,没有一种单一变量选择方法是普遍优越的.
需要进一步的研究来开发新的可变选择方法,以便在这种患者群体中进行可靠的生物标志物识别.
这项研究强调了在晚期泌尿腺癌中发现生物标志物的复杂性,并为未来的研究方向提供了信息.

更多相关视频

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

相关概念视频

Kaplan-Meier Approach

Kaplan-Meier Approach

The Kaplan-Meier estimator is a non-parametric method used to estimate the survival function from time-to-event data. In medical research, it is frequently employed to measure the proportion of patients surviving for a certain period after treatment. This estimator is fundamental in analyzing time-to-event data, making it indispensable in clinical trials, epidemiological studies, and reliability engineering. By estimating survival probabilities, researchers can evaluate treatment effectiveness,...

Overview of Biostatistics in Health Sciences

Overview of Biostatistics in Health Sciences

Biostatistics involves the application of statistical techniques to scientific research in health-related fields, including biology and public health. These techniques are essential for designing studies, collecting data, and analyzing it to draw meaningful conclusions. Given the complexity of biological processes, particularly in studies involving human subjects, biostatistical methods are crucial for effectively organizing and interpreting data that might otherwise obscure underlying patterns...