search for


Developing the data analysis-based emergency room congestion predictive model for the resolution of overcrowded emergency room
Journal of the Korean Data & Information Science Society 2018;29:1201-14
Published online September 30, 2018
© 2018 Korean Data and Information Science Society.

Byeo Wool Kim1 · Yong Ik Yoon2

12School of IT Engineering, Sookmyung Women’s University
Correspondence to: Professor, School of IT Engineering, Sookmyung Women‘s University, Seoul 04310, Korea. E-mail:
This research was supported by the MSIT (Ministry of Science and ICT), Korea, under the ITRC (Information Technology Research Center) support program (IITP-2018-2016-0-00311) supervised by the IITP (National IT Industry Promotion Agency).
Received July 9, 2018; Revised September 3, 2018; Accepted September 10, 2018.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License ( which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
This research developed a model that predicts the congestion of the emergency room in real time based on the 2017 data of 414 emergency medical institutions nationwide. In the development of the predictive model, data mining techniques such as multiple linear regression analysis, subset selection, ridge regression, Lasso and principal component regression were applied, and principal component regression method showed high prediction power. The predictive power of the subdivided prediction models (especially regional emergency medical center (97.37%)) according to the types of emergency medical institution was higher than that of the predictive model based on the entire emergency medical institutions (92.73%). The emergency room congestion predictive model developed in this research can be used as basic data to solve the problem of overcrowding of emergency room and form a regional network between the emergency rooms.
Keywords : Emergency room congestion, multiple linear regression, principal component regression, subset selection