Risk classification of cancer survival using ANN with gene expression data from multiple laboratories

Yen Chen Chen, Wan Chi Ke, Hung Wen Chiu

Research output: Contribution to journalArticle

30 Citations (Scopus)

Abstract

Numerous cancer studies have combined gene expression experiments and clinical survival data to predict the prognosis of patients of specific gene types. However, most results of these studies were data dependent and were not suitable for other data sets. This study performed cross-laboratory validations for the cancer patient data from 4 hospitals. We investigated the feasibility of survival risk predictions using high-throughput gene expression data and clinical data. We analyzed multiple data sets for prognostic applications in lung cancer diagnosis. After building tens of thousands of various ANN architectures using the training data, five survival-time correlated genes were identified from 4 microarray gene expression data sets by examining the correlation between gene signatures and patient survival time. The experimental results showed that gene expression data can be used for valid predictions of cancer patient survival classification with an overall accuracy of 83.0% based on survival time trusted data. The results show the prediction model yielded excellent predictions given that patients in the high-risk group obtained a lower median overall survival compared with low-risk patients (log-rank test P-value

Original languageEnglish
Pages (from-to)1-7
Number of pages7
JournalComputers in Biology and Medicine
Volume48
Issue number1
DOIs
Publication statusPublished - May 1 2014

Fingerprint

Gene expression
Gene Expression
Survival
Genes
Neoplasms
Microarrays
Throughput
Lung Neoplasms
Experiments
Datasets

Keywords

  • Gene expression
  • Lung cancer
  • Machine learning
  • Microarray
  • Neural network
  • Outcome prediction
  • Survival analysis

ASJC Scopus subject areas

  • Computer Science Applications
  • Health Informatics
  • Medicine(all)

Cite this

Risk classification of cancer survival using ANN with gene expression data from multiple laboratories. / Chen, Yen Chen; Ke, Wan Chi; Chiu, Hung Wen.

In: Computers in Biology and Medicine, Vol. 48, No. 1, 01.05.2014, p. 1-7.

Research output: Contribution to journalArticle

@article{f362b74dc2414b5281465df175dbb81b,
title = "Risk classification of cancer survival using ANN with gene expression data from multiple laboratories",
abstract = "Numerous cancer studies have combined gene expression experiments and clinical survival data to predict the prognosis of patients of specific gene types. However, most results of these studies were data dependent and were not suitable for other data sets. This study performed cross-laboratory validations for the cancer patient data from 4 hospitals. We investigated the feasibility of survival risk predictions using high-throughput gene expression data and clinical data. We analyzed multiple data sets for prognostic applications in lung cancer diagnosis. After building tens of thousands of various ANN architectures using the training data, five survival-time correlated genes were identified from 4 microarray gene expression data sets by examining the correlation between gene signatures and patient survival time. The experimental results showed that gene expression data can be used for valid predictions of cancer patient survival classification with an overall accuracy of 83.0{\%} based on survival time trusted data. The results show the prediction model yielded excellent predictions given that patients in the high-risk group obtained a lower median overall survival compared with low-risk patients (log-rank test P-value",
keywords = "Gene expression, Lung cancer, Machine learning, Microarray, Neural network, Outcome prediction, Survival analysis",
author = "Chen, {Yen Chen} and Ke, {Wan Chi} and Chiu, {Hung Wen}",
year = "2014",
month = "5",
day = "1",
doi = "10.1016/j.compbiomed.2014.02.006",
language = "English",
volume = "48",
pages = "1--7",
journal = "Computers in Biology and Medicine",
issn = "0010-4825",
publisher = "Elsevier Limited",
number = "1",

}

TY - JOUR

T1 - Risk classification of cancer survival using ANN with gene expression data from multiple laboratories

AU - Chen, Yen Chen

AU - Ke, Wan Chi

AU - Chiu, Hung Wen

PY - 2014/5/1

Y1 - 2014/5/1

N2 - Numerous cancer studies have combined gene expression experiments and clinical survival data to predict the prognosis of patients of specific gene types. However, most results of these studies were data dependent and were not suitable for other data sets. This study performed cross-laboratory validations for the cancer patient data from 4 hospitals. We investigated the feasibility of survival risk predictions using high-throughput gene expression data and clinical data. We analyzed multiple data sets for prognostic applications in lung cancer diagnosis. After building tens of thousands of various ANN architectures using the training data, five survival-time correlated genes were identified from 4 microarray gene expression data sets by examining the correlation between gene signatures and patient survival time. The experimental results showed that gene expression data can be used for valid predictions of cancer patient survival classification with an overall accuracy of 83.0% based on survival time trusted data. The results show the prediction model yielded excellent predictions given that patients in the high-risk group obtained a lower median overall survival compared with low-risk patients (log-rank test P-value

AB - Numerous cancer studies have combined gene expression experiments and clinical survival data to predict the prognosis of patients of specific gene types. However, most results of these studies were data dependent and were not suitable for other data sets. This study performed cross-laboratory validations for the cancer patient data from 4 hospitals. We investigated the feasibility of survival risk predictions using high-throughput gene expression data and clinical data. We analyzed multiple data sets for prognostic applications in lung cancer diagnosis. After building tens of thousands of various ANN architectures using the training data, five survival-time correlated genes were identified from 4 microarray gene expression data sets by examining the correlation between gene signatures and patient survival time. The experimental results showed that gene expression data can be used for valid predictions of cancer patient survival classification with an overall accuracy of 83.0% based on survival time trusted data. The results show the prediction model yielded excellent predictions given that patients in the high-risk group obtained a lower median overall survival compared with low-risk patients (log-rank test P-value

KW - Gene expression

KW - Lung cancer

KW - Machine learning

KW - Microarray

KW - Neural network

KW - Outcome prediction

KW - Survival analysis

UR - http://www.scopus.com/inward/record.url?scp=84896347638&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84896347638&partnerID=8YFLogxK

U2 - 10.1016/j.compbiomed.2014.02.006

DO - 10.1016/j.compbiomed.2014.02.006

M3 - Article

C2 - 24631783

AN - SCOPUS:84896347638

VL - 48

SP - 1

EP - 7

JO - Computers in Biology and Medicine

JF - Computers in Biology and Medicine

SN - 0010-4825

IS - 1

ER -