TY - GEN
T1 - Mapping Common Data Elements to a Domain Model Using an Artificial Neural Network
AU - Renner, Robinette
AU - Li, Shengyu
AU - Huang, Yulong
AU - Tan, Shaobo
AU - Li, Dongqi
AU - Zijp-Tan, Ada Chaeli Van Der
AU - Benton, Ryan
AU - Borchert, Glen M.
AU - Huang, Jingshan
AU - Jiang, Guoqian
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2019/1/21
Y1 - 2019/1/21
N2 - The medical community uses a variety of data standards for clinical and research reporting needs. ISO 11179 Common Data Elements (CDEs) is one such standard that provides robust data point definitions. The Biomedical Research Integrated Domain Group (BRIDG) model is a domain analysis model that provides a contextual framework for biomedical and clinical research data. Manually mapping the CDEs to the BRIDG model can facilitate mapping the CDEs to other standards. Unfortunately, the error-prone, labor-intensive manual mapping process creates a significant barrier for researchers who use CDEs. In this paper, we present our preliminary work to develop a semi-automated algorithm to map CDEs to likely BRIDG classes. First, we extended and improved our previously developed artificial neural network (ANN) alignment algorithm. We then used a collection of 1,284 CDEs mapped to BRIDG classes as the gold standard to train and obtain the appropriate weights of six CDE attributes. Finally, we recommended a list of candidate BRIDG classes to which the CDE of interest may belong. Preliminary testing has proven the effectiveness and efficiency of our proposed methodology in mapping CDEs to BRIDG classes.
AB - The medical community uses a variety of data standards for clinical and research reporting needs. ISO 11179 Common Data Elements (CDEs) is one such standard that provides robust data point definitions. The Biomedical Research Integrated Domain Group (BRIDG) model is a domain analysis model that provides a contextual framework for biomedical and clinical research data. Manually mapping the CDEs to the BRIDG model can facilitate mapping the CDEs to other standards. Unfortunately, the error-prone, labor-intensive manual mapping process creates a significant barrier for researchers who use CDEs. In this paper, we present our preliminary work to develop a semi-automated algorithm to map CDEs to likely BRIDG classes. First, we extended and improved our previously developed artificial neural network (ANN) alignment algorithm. We then used a collection of 1,284 CDEs mapped to BRIDG classes as the gold standard to train and obtain the appropriate weights of six CDE attributes. Finally, we recommended a list of candidate BRIDG classes to which the CDE of interest may belong. Preliminary testing has proven the effectiveness and efficiency of our proposed methodology in mapping CDEs to BRIDG classes.
KW - Biomedical Research Integrated Domain Group (BRIDG) model
KW - artificial neural network (ANN)
KW - common data element (CDE)
KW - schema mapping
UR - http://www.scopus.com/inward/record.url?scp=85062500685&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85062500685&partnerID=8YFLogxK
U2 - 10.1109/BIBM.2018.8621535
DO - 10.1109/BIBM.2018.8621535
M3 - Conference contribution
AN - SCOPUS:85062500685
T3 - Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018
SP - 1532
EP - 1535
BT - Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018
A2 - Schmidt, Harald
A2 - Griol, David
A2 - Wang, Haiying
A2 - Baumbach, Jan
A2 - Zheng, Huiru
A2 - Callejas, Zoraida
A2 - Hu, Xiaohua
A2 - Dickerson, Julie
A2 - Zhang, Le
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018
Y2 - 3 December 2018 through 6 December 2018
ER -