An artificial neural network based feature evaluation index for the assessment of clinical factors in breast cancer survival analysis

H. Seker, M.O. Odetayo, Dobrila Petrovic, R.N.G. Naguib

Research output: Chapter in Book/Report/Conference proceedingChapter

2 Citations (Scopus)

Abstract

This study aims to identify the most and least significant prognostic factors for breast cancer survival analysis by means of feature evaluation indices derived from multilayer feedforward backpropagation neural networks (MLFFBPNN), fuzzy k-nearest neighbour classifier (FK-NN) and a logistic regression-based backward stepwise method (ER). The data used for the survival analysis were collected from 100 women who had been clinically diagnosed with breast disease in the form of carcinoma or benign conditions. The data set consists of seven different histological and cytological prognostic factors and two corresponding outputs to be predicted (whether the patient is alive or dead within 5 years of diagnosis). The MLFFBPNN, FK-NN and LR based indices identified different subsets of the factors as the most significant sets. We therefore suggest that it could be dangerous to rely on one method's outcome for assessment of such factors. It should also be noted that "S-phase fraction" (SPF) is the common cytological factor identified by all three methods while none of the three methods identified another cytological factor, namely "minimum (start) nuclear pleomorphism index" (NPImin). We, therefore, conclude that "S-phase fraction" and "minimum (start) nuclear pleomorphism index" appear to be the most and least important prognostic factors, respectively, for survival analysis in breast cancer patients, and should be investigated thoroughly in future clinical studies in oncology.
Original languageEnglish
Title of host publicationElectrical and Computer Engineering, 2002. IEEE CCECE 2002. Canadian Conference on
PublisherIEEE
Pages1211-1215
Volume2
ISBN (Print)0-7803-7514-9
DOIs
Publication statusPublished - 2002

Fingerprint

Survival Analysis
Breast Neoplasms
S Phase
Breast Diseases
Logistic Models
Outcome Assessment (Health Care)
Carcinoma

Bibliographical note

This paper is not available on the repository. The paper was given at the Electrical and Computer Engineering, 2002. IEEE CCECE 2002

Cite this

Seker, H., Odetayo, M. O., Petrovic, D., & Naguib, R. N. G. (2002). An artificial neural network based feature evaluation index for the assessment of clinical factors in breast cancer survival analysis. In Electrical and Computer Engineering, 2002. IEEE CCECE 2002. Canadian Conference on (Vol. 2, pp. 1211-1215). IEEE. https://doi.org/10.1109/CCECE.2002.1013121

An artificial neural network based feature evaluation index for the assessment of clinical factors in breast cancer survival analysis. / Seker, H.; Odetayo, M.O.; Petrovic, Dobrila; Naguib, R.N.G.

Electrical and Computer Engineering, 2002. IEEE CCECE 2002. Canadian Conference on. Vol. 2 IEEE, 2002. p. 1211-1215.

Research output: Chapter in Book/Report/Conference proceedingChapter

Seker, H, Odetayo, MO, Petrovic, D & Naguib, RNG 2002, An artificial neural network based feature evaluation index for the assessment of clinical factors in breast cancer survival analysis. in Electrical and Computer Engineering, 2002. IEEE CCECE 2002. Canadian Conference on. vol. 2, IEEE, pp. 1211-1215. https://doi.org/10.1109/CCECE.2002.1013121
Seker H, Odetayo MO, Petrovic D, Naguib RNG. An artificial neural network based feature evaluation index for the assessment of clinical factors in breast cancer survival analysis. In Electrical and Computer Engineering, 2002. IEEE CCECE 2002. Canadian Conference on. Vol. 2. IEEE. 2002. p. 1211-1215 https://doi.org/10.1109/CCECE.2002.1013121
Seker, H. ; Odetayo, M.O. ; Petrovic, Dobrila ; Naguib, R.N.G. / An artificial neural network based feature evaluation index for the assessment of clinical factors in breast cancer survival analysis. Electrical and Computer Engineering, 2002. IEEE CCECE 2002. Canadian Conference on. Vol. 2 IEEE, 2002. pp. 1211-1215
@inbook{f3bbd0f6068349b0bb064460b7134086,
title = "An artificial neural network based feature evaluation index for the assessment of clinical factors in breast cancer survival analysis",
abstract = "This study aims to identify the most and least significant prognostic factors for breast cancer survival analysis by means of feature evaluation indices derived from multilayer feedforward backpropagation neural networks (MLFFBPNN), fuzzy k-nearest neighbour classifier (FK-NN) and a logistic regression-based backward stepwise method (ER). The data used for the survival analysis were collected from 100 women who had been clinically diagnosed with breast disease in the form of carcinoma or benign conditions. The data set consists of seven different histological and cytological prognostic factors and two corresponding outputs to be predicted (whether the patient is alive or dead within 5 years of diagnosis). The MLFFBPNN, FK-NN and LR based indices identified different subsets of the factors as the most significant sets. We therefore suggest that it could be dangerous to rely on one method's outcome for assessment of such factors. It should also be noted that {"}S-phase fraction{"} (SPF) is the common cytological factor identified by all three methods while none of the three methods identified another cytological factor, namely {"}minimum (start) nuclear pleomorphism index{"} (NPImin). We, therefore, conclude that {"}S-phase fraction{"} and {"}minimum (start) nuclear pleomorphism index{"} appear to be the most and least important prognostic factors, respectively, for survival analysis in breast cancer patients, and should be investigated thoroughly in future clinical studies in oncology.",
author = "H. Seker and M.O. Odetayo and Dobrila Petrovic and R.N.G. Naguib",
note = "This paper is not available on the repository. The paper was given at the Electrical and Computer Engineering, 2002. IEEE CCECE 2002",
year = "2002",
doi = "10.1109/CCECE.2002.1013121",
language = "English",
isbn = "0-7803-7514-9",
volume = "2",
pages = "1211--1215",
booktitle = "Electrical and Computer Engineering, 2002. IEEE CCECE 2002. Canadian Conference on",
publisher = "IEEE",
address = "United States",

}

TY - CHAP

T1 - An artificial neural network based feature evaluation index for the assessment of clinical factors in breast cancer survival analysis

AU - Seker, H.

AU - Odetayo, M.O.

AU - Petrovic, Dobrila

AU - Naguib, R.N.G.

N1 - This paper is not available on the repository. The paper was given at the Electrical and Computer Engineering, 2002. IEEE CCECE 2002

PY - 2002

Y1 - 2002

N2 - This study aims to identify the most and least significant prognostic factors for breast cancer survival analysis by means of feature evaluation indices derived from multilayer feedforward backpropagation neural networks (MLFFBPNN), fuzzy k-nearest neighbour classifier (FK-NN) and a logistic regression-based backward stepwise method (ER). The data used for the survival analysis were collected from 100 women who had been clinically diagnosed with breast disease in the form of carcinoma or benign conditions. The data set consists of seven different histological and cytological prognostic factors and two corresponding outputs to be predicted (whether the patient is alive or dead within 5 years of diagnosis). The MLFFBPNN, FK-NN and LR based indices identified different subsets of the factors as the most significant sets. We therefore suggest that it could be dangerous to rely on one method's outcome for assessment of such factors. It should also be noted that "S-phase fraction" (SPF) is the common cytological factor identified by all three methods while none of the three methods identified another cytological factor, namely "minimum (start) nuclear pleomorphism index" (NPImin). We, therefore, conclude that "S-phase fraction" and "minimum (start) nuclear pleomorphism index" appear to be the most and least important prognostic factors, respectively, for survival analysis in breast cancer patients, and should be investigated thoroughly in future clinical studies in oncology.

AB - This study aims to identify the most and least significant prognostic factors for breast cancer survival analysis by means of feature evaluation indices derived from multilayer feedforward backpropagation neural networks (MLFFBPNN), fuzzy k-nearest neighbour classifier (FK-NN) and a logistic regression-based backward stepwise method (ER). The data used for the survival analysis were collected from 100 women who had been clinically diagnosed with breast disease in the form of carcinoma or benign conditions. The data set consists of seven different histological and cytological prognostic factors and two corresponding outputs to be predicted (whether the patient is alive or dead within 5 years of diagnosis). The MLFFBPNN, FK-NN and LR based indices identified different subsets of the factors as the most significant sets. We therefore suggest that it could be dangerous to rely on one method's outcome for assessment of such factors. It should also be noted that "S-phase fraction" (SPF) is the common cytological factor identified by all three methods while none of the three methods identified another cytological factor, namely "minimum (start) nuclear pleomorphism index" (NPImin). We, therefore, conclude that "S-phase fraction" and "minimum (start) nuclear pleomorphism index" appear to be the most and least important prognostic factors, respectively, for survival analysis in breast cancer patients, and should be investigated thoroughly in future clinical studies in oncology.

U2 - 10.1109/CCECE.2002.1013121

DO - 10.1109/CCECE.2002.1013121

M3 - Chapter

SN - 0-7803-7514-9

VL - 2

SP - 1211

EP - 1215

BT - Electrical and Computer Engineering, 2002. IEEE CCECE 2002. Canadian Conference on

PB - IEEE

ER -