PMID- 34902551
OWN - NLM
STAT- MEDLINE
DCOM- 20220202
LR  - 20230102
IS  - 1532-0480 (Electronic)
IS  - 1532-0464 (Print)
IS  - 1532-0464 (Linking)
VI  - 125
DP  - 2022 Jan
TI  - Deep graph convolutional network for US birth data harmonization.
PG  - 103974
LID - S1532-0464(21)00303-8 [pii]
LID - 10.1016/j.jbi.2021.103974 [doi]
AB  - In this paper, we developed a feasible and efficient deep-learning-based 
      framework to combine the United States (US) natality data for the last five 
      decades, with changing variables and factors, into a consistent database. We 
      constructed a graph based on the property and elements of databases, including 
      variables, and conducted a graph convolutional network (GCN) to learn the 
      embeddings of variables on the constructed graph, where the learned embeddings 
      implied the similarity of variables. Specifically, we devised a loss function 
      with a slack margin and a banlist mechanism (for a random walk) to learn the 
      desired structure (two nodes sharing more information were more similar to each 
      other.), and developed an active learning mechanism to conduct the harmonization. 
      Toward a total of 9,321 variables from 49 databases (i.e., 783 stemmed variables, 
      from 1970 to 2018), we applied our model iteratively together with human reviews 
      for four rounds, then obtained 323 hyperchains of variables. During the 
      harmonization, the first round of our model achieved recall and precision of 
      87.56%, 57.70%, respectively. Our harmonized graph neural network (HGNN) method 
      provides a feasible and efficient way to connect relevant databases at a 
      meta-level. Adapting to the database's property and characteristics, HGNN can 
      learn patterns globally, which is powerful to discover the similarity between 
      variables among databases. Our proposed method provides an effective way to 
      reduce the manual effort in database harmonization and integration of fragmented 
      data into useful databases for future research.
CI  - Copyright (c) 2021 Elsevier Inc. All rights reserved.
FAU - Yu, Lishan
AU  - Yu L
AD  - School of Biomedical Informatics, UTHealth, Houston, TX, USA; Yau Mathematical 
      Sciences Center, Tsinghua University, Beijing, China; Beijing Institute 
      Mathematical Sciences and Applications, Beijing, China.
FAU - Salihu, Hamisu M
AU  - Salihu HM
AD  - Department of Family and Community Medicine, Baylor College of Medicine, Houston, 
      TX, USA; Center of Excellence in Health Equity, Training, and Research, Baylor 
      College of Medicine, Houston, TX, USA.
FAU - Dongarwar, Deepa
AU  - Dongarwar D
AD  - Center of Excellence in Health Equity, Training, and Research, Baylor College of 
      Medicine, Houston, TX, USA.
FAU - Chen, Luyao
AU  - Chen L
AD  - School of Biomedical Informatics, UTHealth, Houston, TX, USA.
FAU - Jiang, Xiaoqian
AU  - Jiang X
AD  - School of Biomedical Informatics, UTHealth, Houston, TX, USA.
LA  - eng
GR  - R01 AG066749/AG/NIA NIH HHS/United States
GR  - R01 GM114612/GM/NIGMS NIH HHS/United States
GR  - U01 TR002062/TR/NCATS NIH HHS/United States
PT  - Journal Article
PT  - Research Support, N.I.H., Extramural
PT  - Research Support, Non-U.S. Gov't
PT  - Research Support, U.S. Gov't, Non-P.H.S.
DEP - 20211210
PL  - United States
TA  - J Biomed Inform
JT  - Journal of biomedical informatics
JID - 100970413
SB  - IM
MH  - Databases, Factual
MH  - Humans
MH  - *Neural Networks, Computer
MH  - United States
PMC - PMC8766952
MID - NIHMS1766202
OTO - NOTNLM
OT  - Database harmonization
OT  - Deep learning
OT  - Graph neural network
OT  - Natality data
COIS- CONFLICT OF INTEREST Authors have no conflict of interest to disclose.
EDAT- 2021/12/14 06:00
MHDA- 2022/02/03 06:00
PMCR- 2023/01/01
CRDT- 2021/12/13 20:16
PHST- 2021/05/31 00:00 [received]
PHST- 2021/09/03 00:00 [revised]
PHST- 2021/12/04 00:00 [accepted]
PHST- 2021/12/14 06:00 [pubmed]
PHST- 2022/02/03 06:00 [medline]
PHST- 2021/12/13 20:16 [entrez]
PHST- 2023/01/01 00:00 [pmc-release]
AID - S1532-0464(21)00303-8 [pii]
AID - 10.1016/j.jbi.2021.103974 [doi]
PST - ppublish
SO  - J Biomed Inform. 2022 Jan;125:103974. doi: 10.1016/j.jbi.2021.103974. Epub 2021 
      Dec 10.