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

Tan Nai Wang, Chung Hao Cheng, Hung Wen Chiu

研究成果: 書貢獻/報告類型會議貢獻

7 引文 斯高帕斯(Scopus)

摘要

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.
原文英語
主出版物標題Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
頁面1290-1293
頁數4
DOIs
出版狀態已發佈 - 2013
事件2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2013 - Osaka, 日本
持續時間: 七月 3 2013七月 7 2013

其他

其他2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2013
國家日本
城市Osaka
期間7/3/137/7/13

ASJC Scopus subject areas

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

指紋 深入研究「Predicting post-treatment survivability of patients with breast cancer using Artificial Neural Network methods」主題。共同形成了獨特的指紋。

引用此