Prediction of survival in patients with liver cancer using artificial neural networks and classification and regression trees

Cheng Mei Chen, Chien-Yeh Hsu, Hung Wen Chiu, Hsiao Hsien Rau

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

This study established a survival prediction model for liver cancer using data mining technology. The data were collected from the cancer registration database of a medical center in Northern Taiwan between 2004 and 2008. A total of 227 patients were newly diagnosed with liver cancer during this time. With literature review, and expert consultation, nine variables pertaining to liver cancer survival were analyzed using t-test and chi-square test. Six variables showed significant. Artificial neural network (ANN) and classification and regression tree (CART) were adopted as prediction models. The models were tested in three conditions; one variable (clinical stage alone), six significant variables, and all nine variables (significant and non significant). 5-year survival was the output prediction. The results showed that the ANN model with nine input variables was superior predictor of survival (p#60;0.001). The area under receiver operating characteristic curve (AUC) was 0.915, 0.87, 0.88, and 0.87 for accuracy, sensitivity, and specificity respectively. The ANN model is significant more accurate than CART model when predict survival for liver cancer and provide patients information for understanding the treatment outcomes.

Original languageEnglish
Title of host publicationProceedings - 2011 7th International Conference on Natural Computation, ICNC 2011
Pages811-815
Number of pages5
Volume2
DOIs
Publication statusPublished - 2011
Event2011 7th International Conference on Natural Computation, ICNC 2011 - Shanghai, China
Duration: Jul 26 2011Jul 28 2011

Other

Other2011 7th International Conference on Natural Computation, ICNC 2011
CountryChina
CityShanghai
Period7/26/117/28/11

Fingerprint

Liver Neoplasms
Liver
Neural networks
Survival
Neural Networks (Computer)
Data Mining
Chi-Square Distribution
Taiwan
ROC Curve
Area Under Curve
Referral and Consultation
Data mining
Databases
Technology
Sensitivity and Specificity
Neoplasms

Keywords

  • artificial neural networks
  • classification and regression trees
  • liver cancer
  • prediction model

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Neuroscience(all)

Cite this

Chen, C. M., Hsu, C-Y., Chiu, H. W., & Rau, H. H. (2011). Prediction of survival in patients with liver cancer using artificial neural networks and classification and regression trees. In Proceedings - 2011 7th International Conference on Natural Computation, ICNC 2011 (Vol. 2, pp. 811-815). [6022187] https://doi.org/10.1109/ICNC.2011.6022187

Prediction of survival in patients with liver cancer using artificial neural networks and classification and regression trees. / Chen, Cheng Mei; Hsu, Chien-Yeh; Chiu, Hung Wen; Rau, Hsiao Hsien.

Proceedings - 2011 7th International Conference on Natural Computation, ICNC 2011. Vol. 2 2011. p. 811-815 6022187.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Chen, CM, Hsu, C-Y, Chiu, HW & Rau, HH 2011, Prediction of survival in patients with liver cancer using artificial neural networks and classification and regression trees. in Proceedings - 2011 7th International Conference on Natural Computation, ICNC 2011. vol. 2, 6022187, pp. 811-815, 2011 7th International Conference on Natural Computation, ICNC 2011, Shanghai, China, 7/26/11. https://doi.org/10.1109/ICNC.2011.6022187
Chen CM, Hsu C-Y, Chiu HW, Rau HH. Prediction of survival in patients with liver cancer using artificial neural networks and classification and regression trees. In Proceedings - 2011 7th International Conference on Natural Computation, ICNC 2011. Vol. 2. 2011. p. 811-815. 6022187 https://doi.org/10.1109/ICNC.2011.6022187
Chen, Cheng Mei ; Hsu, Chien-Yeh ; Chiu, Hung Wen ; Rau, Hsiao Hsien. / Prediction of survival in patients with liver cancer using artificial neural networks and classification and regression trees. Proceedings - 2011 7th International Conference on Natural Computation, ICNC 2011. Vol. 2 2011. pp. 811-815
@inproceedings{5f0ff96ed2254c06acfe38014cd7b8fd,
title = "Prediction of survival in patients with liver cancer using artificial neural networks and classification and regression trees",
abstract = "This study established a survival prediction model for liver cancer using data mining technology. The data were collected from the cancer registration database of a medical center in Northern Taiwan between 2004 and 2008. A total of 227 patients were newly diagnosed with liver cancer during this time. With literature review, and expert consultation, nine variables pertaining to liver cancer survival were analyzed using t-test and chi-square test. Six variables showed significant. Artificial neural network (ANN) and classification and regression tree (CART) were adopted as prediction models. The models were tested in three conditions; one variable (clinical stage alone), six significant variables, and all nine variables (significant and non significant). 5-year survival was the output prediction. The results showed that the ANN model with nine input variables was superior predictor of survival (p#60;0.001). The area under receiver operating characteristic curve (AUC) was 0.915, 0.87, 0.88, and 0.87 for accuracy, sensitivity, and specificity respectively. The ANN model is significant more accurate than CART model when predict survival for liver cancer and provide patients information for understanding the treatment outcomes.",
keywords = "artificial neural networks, classification and regression trees, liver cancer, prediction model",
author = "Chen, {Cheng Mei} and Chien-Yeh Hsu and Chiu, {Hung Wen} and Rau, {Hsiao Hsien}",
year = "2011",
doi = "10.1109/ICNC.2011.6022187",
language = "English",
isbn = "9781424499533",
volume = "2",
pages = "811--815",
booktitle = "Proceedings - 2011 7th International Conference on Natural Computation, ICNC 2011",

}

TY - GEN

T1 - Prediction of survival in patients with liver cancer using artificial neural networks and classification and regression trees

AU - Chen, Cheng Mei

AU - Hsu, Chien-Yeh

AU - Chiu, Hung Wen

AU - Rau, Hsiao Hsien

PY - 2011

Y1 - 2011

N2 - This study established a survival prediction model for liver cancer using data mining technology. The data were collected from the cancer registration database of a medical center in Northern Taiwan between 2004 and 2008. A total of 227 patients were newly diagnosed with liver cancer during this time. With literature review, and expert consultation, nine variables pertaining to liver cancer survival were analyzed using t-test and chi-square test. Six variables showed significant. Artificial neural network (ANN) and classification and regression tree (CART) were adopted as prediction models. The models were tested in three conditions; one variable (clinical stage alone), six significant variables, and all nine variables (significant and non significant). 5-year survival was the output prediction. The results showed that the ANN model with nine input variables was superior predictor of survival (p#60;0.001). The area under receiver operating characteristic curve (AUC) was 0.915, 0.87, 0.88, and 0.87 for accuracy, sensitivity, and specificity respectively. The ANN model is significant more accurate than CART model when predict survival for liver cancer and provide patients information for understanding the treatment outcomes.

AB - This study established a survival prediction model for liver cancer using data mining technology. The data were collected from the cancer registration database of a medical center in Northern Taiwan between 2004 and 2008. A total of 227 patients were newly diagnosed with liver cancer during this time. With literature review, and expert consultation, nine variables pertaining to liver cancer survival were analyzed using t-test and chi-square test. Six variables showed significant. Artificial neural network (ANN) and classification and regression tree (CART) were adopted as prediction models. The models were tested in three conditions; one variable (clinical stage alone), six significant variables, and all nine variables (significant and non significant). 5-year survival was the output prediction. The results showed that the ANN model with nine input variables was superior predictor of survival (p#60;0.001). The area under receiver operating characteristic curve (AUC) was 0.915, 0.87, 0.88, and 0.87 for accuracy, sensitivity, and specificity respectively. The ANN model is significant more accurate than CART model when predict survival for liver cancer and provide patients information for understanding the treatment outcomes.

KW - artificial neural networks

KW - classification and regression trees

KW - liver cancer

KW - prediction model

UR - http://www.scopus.com/inward/record.url?scp=80053389359&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80053389359&partnerID=8YFLogxK

U2 - 10.1109/ICNC.2011.6022187

DO - 10.1109/ICNC.2011.6022187

M3 - Conference contribution

AN - SCOPUS:80053389359

SN - 9781424499533

VL - 2

SP - 811

EP - 815

BT - Proceedings - 2011 7th International Conference on Natural Computation, ICNC 2011

ER -