TY - GEN
T1 - Development of deep learning algorithm for detection of colorectal cancer in EHR data
AU - Wang, Yu Hsiang
AU - Nguyen, Phung Anh
AU - Mohaimenul Islam, Md
AU - Li, Yu Chuan
AU - Yang, Hsuan Chia
N1 - Funding Information:
This research was sponsored in part by Ministry of Science and Technology (MOST) 107-2634-F-038-002-, and Ministry of Science and Technology (MOST) 106-2634-F-038 -001 - CC2. We would like to thank Mr. Chia-Wei Liang for his assistant in this study.
Publisher Copyright:
© 2019 International Medical Informatics Association (IMIA) and IOS Press.
PY - 2019/8/21
Y1 - 2019/8/21
N2 - 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.
AB - 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.
KW - Algorithms
KW - Colorectal Neoplasms
KW - Electronic Health Records
UR - http://www.scopus.com/inward/record.url?scp=85071453395&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85071453395&partnerID=8YFLogxK
U2 - 10.3233/SHTI190259
DO - 10.3233/SHTI190259
M3 - Conference contribution
C2 - 31437961
AN - SCOPUS:85071453395
VL - 264
T3 - Studies in Health Technology and Informatics
SP - 438
EP - 441
BT - MEDINFO 2019
A2 - Seroussi, Brigitte
A2 - Ohno-Machado, Lucila
A2 - Ohno-Machado, Lucila
A2 - Seroussi, Brigitte
PB - IOS Press
T2 - 17th World Congress on Medical and Health Informatics, MEDINFO 2019
Y2 - 25 August 2019 through 30 August 2019
ER -
