Predicting post-treatment survivability of patients with breast cancer using Artificial Neural Network methods

Tan Nai Wang, Chung Hao Cheng, Hung Wen Chiu

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

3 Citations (Scopus)

Abstract

In the last decade, the use of data mining techniques has become widely accepted in medical applications, especially in predicting cancer patients' survival. In this study, we attempted to train an Artificial Neural Network (ANN) to predict the patients' five-year survivability. Breast cancer patients who were diagnosed and received standard treatment in one hospital during 2000 to 2003 in Taiwan were collected for train and test the ANN. There were 604 patients in this dataset excluding died not in breast cancer. Among them 140 patients died within five years after their first radiotherapy treatment. The artificial neural networks were created by STATISTICA® software. Five variables (age, surgery and radiotherapy type, tumor size, regional lymph nodes, distant metastasis) were selected as the input features for ANN to predict the five-year survivability of breast cancer patients. We trained 100 artificial neural networks and chose the best one to analyze. The accuracy rate is 85% and area under the receiver operating characteristic (ROC) curve is 0.79. It shows that artificial neural network is a good tool to predict the five-year survivability of breast cancer patients.

Original languageEnglish
Title of host publicationProceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
Pages1290-1293
Number of pages4
DOIs
Publication statusPublished - 2013
Event2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2013 - Osaka, Japan
Duration: Jul 3 2013Jul 7 2013

Other

Other2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2013
CountryJapan
CityOsaka
Period7/3/137/7/13

Fingerprint

Breast Neoplasms
Neural networks
Radiotherapy
Therapeutics
Medical applications
Data Mining
Surgery
Data mining
Tumors
Taiwan
ROC Curve
Neoplasms
Software
Lymph Nodes
Neoplasm Metastasis
Survival

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Biomedical Engineering
  • Health Informatics

Cite this

Wang, T. N., Cheng, C. H., & Chiu, H. W. (2013). Predicting post-treatment survivability of patients with breast cancer using Artificial Neural Network methods. In Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS (pp. 1290-1293). [6609744] https://doi.org/10.1109/EMBC.2013.6609744

Predicting post-treatment survivability of patients with breast cancer using Artificial Neural Network methods. / Wang, Tan Nai; Cheng, Chung Hao; Chiu, Hung Wen.

Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS. 2013. p. 1290-1293 6609744.

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

Wang, TN, Cheng, CH & Chiu, HW 2013, Predicting post-treatment survivability of patients with breast cancer using Artificial Neural Network methods. in Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS., 6609744, pp. 1290-1293, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2013, Osaka, Japan, 7/3/13. https://doi.org/10.1109/EMBC.2013.6609744
Wang TN, Cheng CH, Chiu HW. Predicting post-treatment survivability of patients with breast cancer using Artificial Neural Network methods. In Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS. 2013. p. 1290-1293. 6609744 https://doi.org/10.1109/EMBC.2013.6609744
Wang, Tan Nai ; Cheng, Chung Hao ; Chiu, Hung Wen. / Predicting post-treatment survivability of patients with breast cancer using Artificial Neural Network methods. Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS. 2013. pp. 1290-1293
@inproceedings{7418e43956ea493cbe252b9f5d0353d2,
title = "Predicting post-treatment survivability of patients with breast cancer using Artificial Neural Network methods",
abstract = "In the last decade, the use of data mining techniques has become widely accepted in medical applications, especially in predicting cancer patients' survival. In this study, we attempted to train an Artificial Neural Network (ANN) to predict the patients' five-year survivability. Breast cancer patients who were diagnosed and received standard treatment in one hospital during 2000 to 2003 in Taiwan were collected for train and test the ANN. There were 604 patients in this dataset excluding died not in breast cancer. Among them 140 patients died within five years after their first radiotherapy treatment. The artificial neural networks were created by STATISTICA{\circledR} software. Five variables (age, surgery and radiotherapy type, tumor size, regional lymph nodes, distant metastasis) were selected as the input features for ANN to predict the five-year survivability of breast cancer patients. We trained 100 artificial neural networks and chose the best one to analyze. The accuracy rate is 85{\%} and area under the receiver operating characteristic (ROC) curve is 0.79. It shows that artificial neural network is a good tool to predict the five-year survivability of breast cancer patients.",
author = "Wang, {Tan Nai} and Cheng, {Chung Hao} and Chiu, {Hung Wen}",
year = "2013",
doi = "10.1109/EMBC.2013.6609744",
language = "English",
isbn = "9781457702167",
pages = "1290--1293",
booktitle = "Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS",

}

TY - GEN

T1 - Predicting post-treatment survivability of patients with breast cancer using Artificial Neural Network methods

AU - Wang, Tan Nai

AU - Cheng, Chung Hao

AU - Chiu, Hung Wen

PY - 2013

Y1 - 2013

N2 - In the last decade, the use of data mining techniques has become widely accepted in medical applications, especially in predicting cancer patients' survival. In this study, we attempted to train an Artificial Neural Network (ANN) to predict the patients' five-year survivability. Breast cancer patients who were diagnosed and received standard treatment in one hospital during 2000 to 2003 in Taiwan were collected for train and test the ANN. There were 604 patients in this dataset excluding died not in breast cancer. Among them 140 patients died within five years after their first radiotherapy treatment. The artificial neural networks were created by STATISTICA® software. Five variables (age, surgery and radiotherapy type, tumor size, regional lymph nodes, distant metastasis) were selected as the input features for ANN to predict the five-year survivability of breast cancer patients. We trained 100 artificial neural networks and chose the best one to analyze. The accuracy rate is 85% and area under the receiver operating characteristic (ROC) curve is 0.79. It shows that artificial neural network is a good tool to predict the five-year survivability of breast cancer patients.

AB - In the last decade, the use of data mining techniques has become widely accepted in medical applications, especially in predicting cancer patients' survival. In this study, we attempted to train an Artificial Neural Network (ANN) to predict the patients' five-year survivability. Breast cancer patients who were diagnosed and received standard treatment in one hospital during 2000 to 2003 in Taiwan were collected for train and test the ANN. There were 604 patients in this dataset excluding died not in breast cancer. Among them 140 patients died within five years after their first radiotherapy treatment. The artificial neural networks were created by STATISTICA® software. Five variables (age, surgery and radiotherapy type, tumor size, regional lymph nodes, distant metastasis) were selected as the input features for ANN to predict the five-year survivability of breast cancer patients. We trained 100 artificial neural networks and chose the best one to analyze. The accuracy rate is 85% and area under the receiver operating characteristic (ROC) curve is 0.79. It shows that artificial neural network is a good tool to predict the five-year survivability of breast cancer patients.

UR - http://www.scopus.com/inward/record.url?scp=84886484304&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84886484304&partnerID=8YFLogxK

U2 - 10.1109/EMBC.2013.6609744

DO - 10.1109/EMBC.2013.6609744

M3 - Conference contribution

SN - 9781457702167

SP - 1290

EP - 1293

BT - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS

ER -