TY - GEN
T1 - Visualizing article similarities via sparsified article network and map projection for systematic reviews
AU - Ji, Xiaonan
AU - Machiraju, Raghu
AU - Ritter, Alan
AU - Yen, Po Yin
N1 - Funding Information:
This work was supported by the Agency for Healthcare Research and Quality (AHRQ), R03HS025047-01.
Publisher Copyright:
© 2017 International Medical Informatics Association (IMIA) and IOS Press.
PY - 2017
Y1 - 2017
N2 - Systematic Reviews (SRs) of biomedical literature summarize evidence from high-quality studies to inform clinical decisions, but are time and labor intensive due to the large number of article collections. Article similarities established from textual features have been shown to assist in the identification of relevant articles, thus facilitating the article screening process efficiently. In this study, we visualized article similarities to extend its utilization in practical settings for SR researchers, aiming to promote human comprehension of article distributions and hidden patterns. To prompt an effective visualization in an interpretable, intuitive, and scalable way, we implemented a graph-based network visualization with three network sparsification approaches and a distance-based map projection via dimensionality reduction. We evaluated and compared three network sparsification approaches and the visualization types (article network vs. article map). We demonstrated the effectiveness in revealing article distribution and exhibiting clustering patterns of relevant articles with practical meanings for SRs.
AB - Systematic Reviews (SRs) of biomedical literature summarize evidence from high-quality studies to inform clinical decisions, but are time and labor intensive due to the large number of article collections. Article similarities established from textual features have been shown to assist in the identification of relevant articles, thus facilitating the article screening process efficiently. In this study, we visualized article similarities to extend its utilization in practical settings for SR researchers, aiming to promote human comprehension of article distributions and hidden patterns. To prompt an effective visualization in an interpretable, intuitive, and scalable way, we implemented a graph-based network visualization with three network sparsification approaches and a distance-based map projection via dimensionality reduction. We evaluated and compared three network sparsification approaches and the visualization types (article network vs. article map). We demonstrated the effectiveness in revealing article distribution and exhibiting clustering patterns of relevant articles with practical meanings for SRs.
KW - Data display
KW - Information storage and retrieval
UR - http://www.scopus.com/inward/record.url?scp=85040517856&partnerID=8YFLogxK
U2 - 10.3233/978-1-61499-830-3-422
DO - 10.3233/978-1-61499-830-3-422
M3 - Conference contribution
C2 - 29295129
AN - SCOPUS:85040517856
T3 - Studies in Health Technology and Informatics
SP - 422
EP - 426
BT - MEDINFO 2017
A2 - Dongsheng, Zhao
A2 - Gundlapalli, Adi V.
A2 - Marie-Christine, Jaulent
PB - IOS Press
T2 - 16th World Congress of Medical and Health Informatics: Precision Healthcare through Informatics, MedInfo 2017
Y2 - 21 August 2017 through 25 August 2017
ER -