The application of artificial neural networks and decision tree model in predicting post-operative complication for gastric cancer patients

Ching W. Chien, Yi Chih Lee, Tsochiang Ma, Tian Shyug Lee, Yang C. Lin, Weu Wang, Wei J. Lee

Research output: Contribution to journalArticle

20 Citations (Scopus)

Abstract

Background/Aims: Gastric cancer remains a leading cause of death worldwide. Post-operative complication is one important factor which causes mortality of gastric cancer patients after gastrectomy. Better prediction of post-operative complication before gastrectomy can significantly reduce post-operative mortality and morbidity. Therefore, 3 data mining techniques were applied in this study on improving prediction of post-operative complication. Methodology: A retrospective study was performed on 521 patients from 3 over 2,000 acute-bed medical centers in Taiwan during February 2002 to October 2004. Pre- and post-operative clinical data were collected and analyzed by applying 3 data mining techniques, included Artificial Neural Networks (ANN), Decision Tree (DT) and Logistic Regression (LR). Results: Results of this study indicated that ANN was a better technique than DT and LR in predicting post-operative complication. Nutritious status, pathological characteristics and operational characteristics were important predictors of post-operative complication. Conclusions: Further study on predicting post-operative complication in gastric cancer patients is still important. However, how to combine different data mining techniques to improve accuracies of prediction will be another important issue for clinicians and researchers.

Original languageEnglish
Pages (from-to)1140-1145
Number of pages6
JournalHepato-Gastroenterology
Volume55
Issue number84
Publication statusPublished - May 2008

Fingerprint

Decision Trees
Data Mining
Stomach Neoplasms
Gastrectomy
Logistic Models
Mortality
Taiwan
Cause of Death
Retrospective Studies
Research Personnel
Morbidity

Keywords

  • Artificial neural networks
  • Decision tree
  • Gastric cancer
  • Logistic regression

ASJC Scopus subject areas

  • Gastroenterology

Cite this

The application of artificial neural networks and decision tree model in predicting post-operative complication for gastric cancer patients. / Chien, Ching W.; Lee, Yi Chih; Ma, Tsochiang; Lee, Tian Shyug; Lin, Yang C.; Wang, Weu; Lee, Wei J.

In: Hepato-Gastroenterology, Vol. 55, No. 84, 05.2008, p. 1140-1145.

Research output: Contribution to journalArticle

Chien, Ching W. ; Lee, Yi Chih ; Ma, Tsochiang ; Lee, Tian Shyug ; Lin, Yang C. ; Wang, Weu ; Lee, Wei J. / The application of artificial neural networks and decision tree model in predicting post-operative complication for gastric cancer patients. In: Hepato-Gastroenterology. 2008 ; Vol. 55, No. 84. pp. 1140-1145.
@article{985f21fe7e7d4d82a3368fc345b8dd85,
title = "The application of artificial neural networks and decision tree model in predicting post-operative complication for gastric cancer patients",
abstract = "Background/Aims: Gastric cancer remains a leading cause of death worldwide. Post-operative complication is one important factor which causes mortality of gastric cancer patients after gastrectomy. Better prediction of post-operative complication before gastrectomy can significantly reduce post-operative mortality and morbidity. Therefore, 3 data mining techniques were applied in this study on improving prediction of post-operative complication. Methodology: A retrospective study was performed on 521 patients from 3 over 2,000 acute-bed medical centers in Taiwan during February 2002 to October 2004. Pre- and post-operative clinical data were collected and analyzed by applying 3 data mining techniques, included Artificial Neural Networks (ANN), Decision Tree (DT) and Logistic Regression (LR). Results: Results of this study indicated that ANN was a better technique than DT and LR in predicting post-operative complication. Nutritious status, pathological characteristics and operational characteristics were important predictors of post-operative complication. Conclusions: Further study on predicting post-operative complication in gastric cancer patients is still important. However, how to combine different data mining techniques to improve accuracies of prediction will be another important issue for clinicians and researchers.",
keywords = "Artificial neural networks, Decision tree, Gastric cancer, Logistic regression",
author = "Chien, {Ching W.} and Lee, {Yi Chih} and Tsochiang Ma and Lee, {Tian Shyug} and Lin, {Yang C.} and Weu Wang and Lee, {Wei J.}",
year = "2008",
month = "5",
language = "English",
volume = "55",
pages = "1140--1145",
journal = "Acta hepato-splenologica",
issn = "0172-6390",
publisher = "H.G.E. Update Medical Publishing Ltd.",
number = "84",

}

TY - JOUR

T1 - The application of artificial neural networks and decision tree model in predicting post-operative complication for gastric cancer patients

AU - Chien, Ching W.

AU - Lee, Yi Chih

AU - Ma, Tsochiang

AU - Lee, Tian Shyug

AU - Lin, Yang C.

AU - Wang, Weu

AU - Lee, Wei J.

PY - 2008/5

Y1 - 2008/5

N2 - Background/Aims: Gastric cancer remains a leading cause of death worldwide. Post-operative complication is one important factor which causes mortality of gastric cancer patients after gastrectomy. Better prediction of post-operative complication before gastrectomy can significantly reduce post-operative mortality and morbidity. Therefore, 3 data mining techniques were applied in this study on improving prediction of post-operative complication. Methodology: A retrospective study was performed on 521 patients from 3 over 2,000 acute-bed medical centers in Taiwan during February 2002 to October 2004. Pre- and post-operative clinical data were collected and analyzed by applying 3 data mining techniques, included Artificial Neural Networks (ANN), Decision Tree (DT) and Logistic Regression (LR). Results: Results of this study indicated that ANN was a better technique than DT and LR in predicting post-operative complication. Nutritious status, pathological characteristics and operational characteristics were important predictors of post-operative complication. Conclusions: Further study on predicting post-operative complication in gastric cancer patients is still important. However, how to combine different data mining techniques to improve accuracies of prediction will be another important issue for clinicians and researchers.

AB - Background/Aims: Gastric cancer remains a leading cause of death worldwide. Post-operative complication is one important factor which causes mortality of gastric cancer patients after gastrectomy. Better prediction of post-operative complication before gastrectomy can significantly reduce post-operative mortality and morbidity. Therefore, 3 data mining techniques were applied in this study on improving prediction of post-operative complication. Methodology: A retrospective study was performed on 521 patients from 3 over 2,000 acute-bed medical centers in Taiwan during February 2002 to October 2004. Pre- and post-operative clinical data were collected and analyzed by applying 3 data mining techniques, included Artificial Neural Networks (ANN), Decision Tree (DT) and Logistic Regression (LR). Results: Results of this study indicated that ANN was a better technique than DT and LR in predicting post-operative complication. Nutritious status, pathological characteristics and operational characteristics were important predictors of post-operative complication. Conclusions: Further study on predicting post-operative complication in gastric cancer patients is still important. However, how to combine different data mining techniques to improve accuracies of prediction will be another important issue for clinicians and researchers.

KW - Artificial neural networks

KW - Decision tree

KW - Gastric cancer

KW - Logistic regression

UR - http://www.scopus.com/inward/record.url?scp=47149105528&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=47149105528&partnerID=8YFLogxK

M3 - Article

VL - 55

SP - 1140

EP - 1145

JO - Acta hepato-splenologica

JF - Acta hepato-splenologica

SN - 0172-6390

IS - 84

ER -