Prognostic models in patients with non-small-cell lung cancer using artificial neural networks in comparison with logistic regression

Taizo Hanai, Yasushi Yatabe, Yusuke Nakayama, Takashi Takahashi, Hiroyuki Honda, Tetsuya Mitsudomi, Takeshi Kobayashi

研究成果: ジャーナルへの寄稿記事

14 引用 (Scopus)

抄録

It is difficult to precisely predict the outcome of each individual patient with non-small-cell lung cancer (NSCLC) by using conventional statistical methods and ordinary clinico-pathological variables. We applied artificial neural networks (ANN) for this purpose. We constructed a prognostic model for 125 NSCLC patients with 17 potential input variables, including 12 clinico-pathological variables (age, sex, smoking index, tumor size, p factor, pT, pN, stage, histology) and 5 immunohistochemical variables (p27 percentage, p27 intensity, p53, cyclin D1, retinoblastoma (RB)), by using the parameter-increasing method (PIM). Using the resultant ANN model, prediction was possible in 104 of 125 patients (83%, judgment ratio (JR)) and accuracy for prediction of survival at 5 years was 87%. On the other hand, JR and survival prediction accuracy in the logistic regression (LR) model were 37% and 78%, respectively. In addition, ANN out-performed LR for prediction of survival at 1 or 3 years. In these cases, PIM selected p27 intensity and cyclin D1 for the 3-year survival model and p53 for the 1-year survival model in addition to clinico-pathological variables. Finally, even in an independent validation data set of 48 patients, who underwent surgery 10 years later, the present ANN model could predict outcome of patients at 5 years with the JR and accuracy of 81% and 77%, respectively. This study demonstrates that ANN is a potentially more useful tool than conventional statistical methods for predicting survival of patients with NSCLC and that inclusion of relevant molecular markers as input variables enhances its predictive ability.

元の言語英語
ページ(範囲)473-477
ページ数5
ジャーナルCancer Science
94
発行部数5
DOI
出版物ステータス出版済み - 5 1 2003

Fingerprint

Non-Small Cell Lung Carcinoma
Logistic Models
Survival
Neural Networks (Computer)
Cyclin D1
Aptitude
Retinoblastoma
Histology
Smoking
Neoplasms

All Science Journal Classification (ASJC) codes

  • Oncology
  • Cancer Research

これを引用

Prognostic models in patients with non-small-cell lung cancer using artificial neural networks in comparison with logistic regression. / Hanai, Taizo; Yatabe, Yasushi; Nakayama, Yusuke; Takahashi, Takashi; Honda, Hiroyuki; Mitsudomi, Tetsuya; Kobayashi, Takeshi.

:: Cancer Science, 巻 94, 番号 5, 01.05.2003, p. 473-477.

研究成果: ジャーナルへの寄稿記事

Hanai, Taizo ; Yatabe, Yasushi ; Nakayama, Yusuke ; Takahashi, Takashi ; Honda, Hiroyuki ; Mitsudomi, Tetsuya ; Kobayashi, Takeshi. / Prognostic models in patients with non-small-cell lung cancer using artificial neural networks in comparison with logistic regression. :: Cancer Science. 2003 ; 巻 94, 番号 5. pp. 473-477.
@article{4b1a0dd424174c1b87aaaade09f7bcc2,
title = "Prognostic models in patients with non-small-cell lung cancer using artificial neural networks in comparison with logistic regression",
abstract = "It is difficult to precisely predict the outcome of each individual patient with non-small-cell lung cancer (NSCLC) by using conventional statistical methods and ordinary clinico-pathological variables. We applied artificial neural networks (ANN) for this purpose. We constructed a prognostic model for 125 NSCLC patients with 17 potential input variables, including 12 clinico-pathological variables (age, sex, smoking index, tumor size, p factor, pT, pN, stage, histology) and 5 immunohistochemical variables (p27 percentage, p27 intensity, p53, cyclin D1, retinoblastoma (RB)), by using the parameter-increasing method (PIM). Using the resultant ANN model, prediction was possible in 104 of 125 patients (83{\%}, judgment ratio (JR)) and accuracy for prediction of survival at 5 years was 87{\%}. On the other hand, JR and survival prediction accuracy in the logistic regression (LR) model were 37{\%} and 78{\%}, respectively. In addition, ANN out-performed LR for prediction of survival at 1 or 3 years. In these cases, PIM selected p27 intensity and cyclin D1 for the 3-year survival model and p53 for the 1-year survival model in addition to clinico-pathological variables. Finally, even in an independent validation data set of 48 patients, who underwent surgery 10 years later, the present ANN model could predict outcome of patients at 5 years with the JR and accuracy of 81{\%} and 77{\%}, respectively. This study demonstrates that ANN is a potentially more useful tool than conventional statistical methods for predicting survival of patients with NSCLC and that inclusion of relevant molecular markers as input variables enhances its predictive ability.",
author = "Taizo Hanai and Yasushi Yatabe and Yusuke Nakayama and Takashi Takahashi and Hiroyuki Honda and Tetsuya Mitsudomi and Takeshi Kobayashi",
year = "2003",
month = "5",
day = "1",
doi = "10.1111/j.1349-7006.2003.tb01467.x",
language = "English",
volume = "94",
pages = "473--477",
journal = "Cancer Science",
issn = "1347-9032",
publisher = "Wiley-Blackwell",
number = "5",

}

TY - JOUR

T1 - Prognostic models in patients with non-small-cell lung cancer using artificial neural networks in comparison with logistic regression

AU - Hanai, Taizo

AU - Yatabe, Yasushi

AU - Nakayama, Yusuke

AU - Takahashi, Takashi

AU - Honda, Hiroyuki

AU - Mitsudomi, Tetsuya

AU - Kobayashi, Takeshi

PY - 2003/5/1

Y1 - 2003/5/1

N2 - It is difficult to precisely predict the outcome of each individual patient with non-small-cell lung cancer (NSCLC) by using conventional statistical methods and ordinary clinico-pathological variables. We applied artificial neural networks (ANN) for this purpose. We constructed a prognostic model for 125 NSCLC patients with 17 potential input variables, including 12 clinico-pathological variables (age, sex, smoking index, tumor size, p factor, pT, pN, stage, histology) and 5 immunohistochemical variables (p27 percentage, p27 intensity, p53, cyclin D1, retinoblastoma (RB)), by using the parameter-increasing method (PIM). Using the resultant ANN model, prediction was possible in 104 of 125 patients (83%, judgment ratio (JR)) and accuracy for prediction of survival at 5 years was 87%. On the other hand, JR and survival prediction accuracy in the logistic regression (LR) model were 37% and 78%, respectively. In addition, ANN out-performed LR for prediction of survival at 1 or 3 years. In these cases, PIM selected p27 intensity and cyclin D1 for the 3-year survival model and p53 for the 1-year survival model in addition to clinico-pathological variables. Finally, even in an independent validation data set of 48 patients, who underwent surgery 10 years later, the present ANN model could predict outcome of patients at 5 years with the JR and accuracy of 81% and 77%, respectively. This study demonstrates that ANN is a potentially more useful tool than conventional statistical methods for predicting survival of patients with NSCLC and that inclusion of relevant molecular markers as input variables enhances its predictive ability.

AB - It is difficult to precisely predict the outcome of each individual patient with non-small-cell lung cancer (NSCLC) by using conventional statistical methods and ordinary clinico-pathological variables. We applied artificial neural networks (ANN) for this purpose. We constructed a prognostic model for 125 NSCLC patients with 17 potential input variables, including 12 clinico-pathological variables (age, sex, smoking index, tumor size, p factor, pT, pN, stage, histology) and 5 immunohistochemical variables (p27 percentage, p27 intensity, p53, cyclin D1, retinoblastoma (RB)), by using the parameter-increasing method (PIM). Using the resultant ANN model, prediction was possible in 104 of 125 patients (83%, judgment ratio (JR)) and accuracy for prediction of survival at 5 years was 87%. On the other hand, JR and survival prediction accuracy in the logistic regression (LR) model were 37% and 78%, respectively. In addition, ANN out-performed LR for prediction of survival at 1 or 3 years. In these cases, PIM selected p27 intensity and cyclin D1 for the 3-year survival model and p53 for the 1-year survival model in addition to clinico-pathological variables. Finally, even in an independent validation data set of 48 patients, who underwent surgery 10 years later, the present ANN model could predict outcome of patients at 5 years with the JR and accuracy of 81% and 77%, respectively. This study demonstrates that ANN is a potentially more useful tool than conventional statistical methods for predicting survival of patients with NSCLC and that inclusion of relevant molecular markers as input variables enhances its predictive ability.

UR - http://www.scopus.com/inward/record.url?scp=0038081320&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0038081320&partnerID=8YFLogxK

U2 - 10.1111/j.1349-7006.2003.tb01467.x

DO - 10.1111/j.1349-7006.2003.tb01467.x

M3 - Article

C2 - 12824896

AN - SCOPUS:0038081320

VL - 94

SP - 473

EP - 477

JO - Cancer Science

JF - Cancer Science

SN - 1347-9032

IS - 5

ER -