One-step extrapolation of the prediction performance of a gene signature derived from a small study
Journal
BMJ Open
Journal Volume
5
Journal Issue
4
Date Issued
2015
Author(s)
Wang L.-Y.
Abstract
Objective: Microarray-related studies often involve a very large number of genes and small sample size. Cross-validating or bootstrapping is therefore imperative to obtain a fair assessment of the prediction/classification performance of a gene signature. A deficiency of these methods is the reduced training sample size because of the partition process in cross-validation and sampling with replacement in bootstrapping. To address this problem, we aim to obtain a prediction performance estimate that strikes a good balance between bias and variance and has a small root mean squared error. Methods: We propose to make a one-step extrapolation from the fitted learning curve to estimate the prediction/classification performance of the model trained by all the samples. Results: Simulation studies show that the method strikes a good balance between bias and variance and has a small root mean squared error. Three microarray data sets are used for demonstration. Conclusions: Our method is advocated to estimate the prediction performance of a gene signature derived from a small study. ? 2015, BMJ Publishing Group. All rights reserved.
SDGs
Other Subjects
area under the curve; Article; bootstrapping; breast cancer; cancer tissue; colon; colon cancer; controlled study; gene; gene expression; gene signature; genetic database; genetic procedures; human; human tissue; learning curve; machine learning; major clinical study; measurement error; microarray analysis; Monte Carlo method; prediction; random forest; sample size; small root mean squared error; support vector machine; variance; breast tumor; colon tumor; gene expression profiling; gene expression regulation; genetics; reproducibility; statistical model; statistics; Area Under Curve; Breast Neoplasms; Colonic Neoplasms; Gene Expression Profiling; Gene Expression Regulation, Neoplastic; Humans; Learning Curve; Linear Models; Monte Carlo Method; Reproducibility of Results; Sample Size; Statistics as Topic
Publisher
BMJ Publishing Group
Type
journal article