Skip to main content
Journal cover image

Impact of missing data in evaluating artificial neural networks trained on complete data.

Publication ,  Journal Article
Markey, MK; Tourassi, GD; Margolis, M; DeLong, DM
Published in: Comput Biol Med
May 2006

This study investigated the impact of missing data in the evaluation of artificial neural network (ANN) models trained on complete data for the task of predicting whether breast lesions are benign or malignant from their mammographic Breast Imaging and Reporting Data System (BI-RADS) descriptors. A feed-forward, back-propagation ANN was tested with three methods for estimating the missing values. Similar results were achieved with a constraint satisfaction ANN, which can accommodate missing values without a separate estimation step. This empirical study highlights the need for additional research on developing robust clinical decision support systems for realistic environments in which key information may be unknown or inaccessible.

Duke Scholars

Published In

Comput Biol Med

DOI

ISSN

0010-4825

Publication Date

May 2006

Volume

36

Issue

5

Start / End Page

516 / 525

Location

United States

Related Subject Headings

  • Software
  • Sensitivity and Specificity
  • Radiographic Image Interpretation, Computer-Assisted
  • ROC Curve
  • Neural Networks, Computer
  • Models, Theoretical
  • Mammography
  • Humans
  • Female
  • Diagnosis, Computer-Assisted
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Markey, M. K., Tourassi, G. D., Margolis, M., & DeLong, D. M. (2006). Impact of missing data in evaluating artificial neural networks trained on complete data. Comput Biol Med, 36(5), 516–525. https://doi.org/10.1016/j.compbiomed.2005.02.001
Markey, Mia K., Georgia D. Tourassi, Michael Margolis, and David M. DeLong. “Impact of missing data in evaluating artificial neural networks trained on complete data.Comput Biol Med 36, no. 5 (May 2006): 516–25. https://doi.org/10.1016/j.compbiomed.2005.02.001.
Markey MK, Tourassi GD, Margolis M, DeLong DM. Impact of missing data in evaluating artificial neural networks trained on complete data. Comput Biol Med. 2006 May;36(5):516–25.
Markey, Mia K., et al. “Impact of missing data in evaluating artificial neural networks trained on complete data.Comput Biol Med, vol. 36, no. 5, May 2006, pp. 516–25. Pubmed, doi:10.1016/j.compbiomed.2005.02.001.
Markey MK, Tourassi GD, Margolis M, DeLong DM. Impact of missing data in evaluating artificial neural networks trained on complete data. Comput Biol Med. 2006 May;36(5):516–525.
Journal cover image

Published In

Comput Biol Med

DOI

ISSN

0010-4825

Publication Date

May 2006

Volume

36

Issue

5

Start / End Page

516 / 525

Location

United States

Related Subject Headings

  • Software
  • Sensitivity and Specificity
  • Radiographic Image Interpretation, Computer-Assisted
  • ROC Curve
  • Neural Networks, Computer
  • Models, Theoretical
  • Mammography
  • Humans
  • Female
  • Diagnosis, Computer-Assisted