Comparison of artificial neural networks with other statistical approaches

Results from medical data sets

Daniel J. Sargent

Research output: Contribution to journalArticle

201 Citations (Scopus)

Abstract

BACKGROUND. In recent years, considerable attention has been given to the development of sophisticated techniques for exploring data sets. One such class of techniques is artificial neural networks (ANNs). Artificial neural networks have many attractive theoretic properties, specifically, the ability to detect non predefined relations such as nonlinear effects and/or interactions. These theoretic advantages come at the cost of reduced interpretability of the model output. Many authors have analyzed the same data set, based on these factors, with both standard statistical methods (such as logistic or Cox regression) and ANN. METHODS. The goal of this work is to review the literature comparing the performance of ANN with standard statistical techniques when applied to medium to large data sets (sample size > 200 patients). A thorough literature search was performed, with specific criteria for a published comparison to be included in this review. RESULTS. In the 28 studies included in this review, ANN outperformed regression in 10 cases (36%), was outperformed by regression in 4 cases (14%), and the 2 methods had similar performance in the remaining 14 cases (50%). However, in the 8 largest studies (sample size > 5000), regression and ANN tied in 7 cases, with regression winning in the remaining case. In addition, there is some suggestion of publication bias. CONCLUSIONS. Neither method achieves the desired performance. Both methods should continue to be used and explored in a complementary manner. However, based on the available data, ANN should not replace standard statistical approaches as the method of choice for the classification of medical data.

Original languageEnglish (US)
Pages (from-to)1636-1642
Number of pages7
JournalCancer
Volume91
Issue number8 SUPPL.
StatePublished - Apr 15 2001

Fingerprint

Sample Size
Publication Bias
Datasets

Keywords

  • Artificial neural network
  • Cox regression
  • Literature review
  • Logistic regression

ASJC Scopus subject areas

  • Cancer Research
  • Oncology

Cite this

Comparison of artificial neural networks with other statistical approaches : Results from medical data sets. / Sargent, Daniel J.

In: Cancer, Vol. 91, No. 8 SUPPL., 15.04.2001, p. 1636-1642.

Research output: Contribution to journalArticle

@article{a41e6b0a269b4e8ea3bca1022a8e6fbe,
title = "Comparison of artificial neural networks with other statistical approaches: Results from medical data sets",
abstract = "BACKGROUND. In recent years, considerable attention has been given to the development of sophisticated techniques for exploring data sets. One such class of techniques is artificial neural networks (ANNs). Artificial neural networks have many attractive theoretic properties, specifically, the ability to detect non predefined relations such as nonlinear effects and/or interactions. These theoretic advantages come at the cost of reduced interpretability of the model output. Many authors have analyzed the same data set, based on these factors, with both standard statistical methods (such as logistic or Cox regression) and ANN. METHODS. The goal of this work is to review the literature comparing the performance of ANN with standard statistical techniques when applied to medium to large data sets (sample size > 200 patients). A thorough literature search was performed, with specific criteria for a published comparison to be included in this review. RESULTS. In the 28 studies included in this review, ANN outperformed regression in 10 cases (36{\%}), was outperformed by regression in 4 cases (14{\%}), and the 2 methods had similar performance in the remaining 14 cases (50{\%}). However, in the 8 largest studies (sample size > 5000), regression and ANN tied in 7 cases, with regression winning in the remaining case. In addition, there is some suggestion of publication bias. CONCLUSIONS. Neither method achieves the desired performance. Both methods should continue to be used and explored in a complementary manner. However, based on the available data, ANN should not replace standard statistical approaches as the method of choice for the classification of medical data.",
keywords = "Artificial neural network, Cox regression, Literature review, Logistic regression",
author = "Sargent, {Daniel J.}",
year = "2001",
month = "4",
day = "15",
language = "English (US)",
volume = "91",
pages = "1636--1642",
journal = "Cancer",
issn = "0008-543X",
publisher = "John Wiley and Sons Inc.",
number = "8 SUPPL.",

}

TY - JOUR

T1 - Comparison of artificial neural networks with other statistical approaches

T2 - Results from medical data sets

AU - Sargent, Daniel J.

PY - 2001/4/15

Y1 - 2001/4/15

N2 - BACKGROUND. In recent years, considerable attention has been given to the development of sophisticated techniques for exploring data sets. One such class of techniques is artificial neural networks (ANNs). Artificial neural networks have many attractive theoretic properties, specifically, the ability to detect non predefined relations such as nonlinear effects and/or interactions. These theoretic advantages come at the cost of reduced interpretability of the model output. Many authors have analyzed the same data set, based on these factors, with both standard statistical methods (such as logistic or Cox regression) and ANN. METHODS. The goal of this work is to review the literature comparing the performance of ANN with standard statistical techniques when applied to medium to large data sets (sample size > 200 patients). A thorough literature search was performed, with specific criteria for a published comparison to be included in this review. RESULTS. In the 28 studies included in this review, ANN outperformed regression in 10 cases (36%), was outperformed by regression in 4 cases (14%), and the 2 methods had similar performance in the remaining 14 cases (50%). However, in the 8 largest studies (sample size > 5000), regression and ANN tied in 7 cases, with regression winning in the remaining case. In addition, there is some suggestion of publication bias. CONCLUSIONS. Neither method achieves the desired performance. Both methods should continue to be used and explored in a complementary manner. However, based on the available data, ANN should not replace standard statistical approaches as the method of choice for the classification of medical data.

AB - BACKGROUND. In recent years, considerable attention has been given to the development of sophisticated techniques for exploring data sets. One such class of techniques is artificial neural networks (ANNs). Artificial neural networks have many attractive theoretic properties, specifically, the ability to detect non predefined relations such as nonlinear effects and/or interactions. These theoretic advantages come at the cost of reduced interpretability of the model output. Many authors have analyzed the same data set, based on these factors, with both standard statistical methods (such as logistic or Cox regression) and ANN. METHODS. The goal of this work is to review the literature comparing the performance of ANN with standard statistical techniques when applied to medium to large data sets (sample size > 200 patients). A thorough literature search was performed, with specific criteria for a published comparison to be included in this review. RESULTS. In the 28 studies included in this review, ANN outperformed regression in 10 cases (36%), was outperformed by regression in 4 cases (14%), and the 2 methods had similar performance in the remaining 14 cases (50%). However, in the 8 largest studies (sample size > 5000), regression and ANN tied in 7 cases, with regression winning in the remaining case. In addition, there is some suggestion of publication bias. CONCLUSIONS. Neither method achieves the desired performance. Both methods should continue to be used and explored in a complementary manner. However, based on the available data, ANN should not replace standard statistical approaches as the method of choice for the classification of medical data.

KW - Artificial neural network

KW - Cox regression

KW - Literature review

KW - Logistic regression

UR - http://www.scopus.com/inward/record.url?scp=0035871395&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035871395&partnerID=8YFLogxK

M3 - Article

VL - 91

SP - 1636

EP - 1642

JO - Cancer

JF - Cancer

SN - 0008-543X

IS - 8 SUPPL.

ER -