Development of deep learning algorithm for detection of colorectal cancer in EHR data

Yu Hsiang Wang, Phung Anh Nguyen, Md Mohaimenul Islam, Yu Chuan Li, Hsuan Chia Yang

研究成果: 書貢獻/報告類型會議貢獻

2 引文 斯高帕斯(Scopus)

摘要

We aimed to develop a deep learning model for the prediction of the risk of advanced colorectal cancer in Taiwanese adults. We collected data of 58152 patients from the Taiwan National Health Insurance database from 1999 to 2013. All patients' comorbidities and medications history were included in the development of the convolution neural network (CNN) model. We also used 3-year medical data of all patients before the diagnosed colorectal cancer (CRC) as the dimensional time in the model. The area under the receiver operating characteristic curve (AUC), sensitivity, and specificity were computed to measure the performance of the model. The results showed the mean (SD) of AUC of the model was 0.922 (0.004). Moreover, the performance of the model observed the sensitivity of 0.837, specificity of 0.867, and 0.532 for PPV value. Our study utilized CNN to develop a prediction model for CRC, based on non-image and multi-dimensional medical records.
原文英語
主出版物標題MEDINFO 2019
主出版物子標題Health and Wellbeing e-Networks for All - Proceedings of the 17th World Congress on Medical and Health Informatics
編輯Brigitte Seroussi, Lucila Ohno-Machado, Lucila Ohno-Machado, Brigitte Seroussi
發行者IOS Press
頁面438-441
頁數4
ISBN(電子)9781643680026
DOIs
出版狀態已發佈 - 八月 21 2019
事件17th World Congress on Medical and Health Informatics, MEDINFO 2019 - Lyon, 法国
持續時間: 八月 25 2019八月 30 2019

出版系列

名字Studies in Health Technology and Informatics
264
ISSN(列印)0926-9630
ISSN(電子)1879-8365

會議

會議17th World Congress on Medical and Health Informatics, MEDINFO 2019
國家法国
城市Lyon
期間8/25/198/30/19

ASJC Scopus subject areas

  • Biomedical Engineering
  • Health Informatics
  • Health Information Management

指紋 深入研究「Development of deep learning algorithm for detection of colorectal cancer in EHR data」主題。共同形成了獨特的指紋。

引用此