DocumentCode :
1666033
Title :
Embracing Big Data for Simulation Modelling of Emergency Department Processes and Activities
Author :
Yong-Hong Kuo ; Leung, Janny M. Y. ; Tsoi, Kelvin K. F. ; Meng, Helen M. ; Graham, Colin A.
Author_Institution :
Stanley Ho Big Data Decision Analytics Res. Centre, Chinese Univ. of Hong Kong, Hong Kong, China
fYear :
2015
Firstpage :
313
Lastpage :
316
Abstract :
Simulation has been demonstrated to be a powerful tool to mimic processes and activities in emergency departments. However, most applications only rely on the data that were manually input by the staff in the departments. First, this practice does not guarantee that the required data to build the simulation models are captured in the computer system, as some information about the processes of emergency departments are not electronically stored. Second, human errors and missing data are also common for manual inputs. A simulation model that is incapable of representing the actual system of the emergency department will deliver wrong conclusions to hospital administrators and may lead to negative consequences if they trust the simulation results. In this paper, we present a case study of developing a simulation model of an emergency department in Hong Kong and discuss the data challenges. Then we propose an RFID-enabled infrastructure to automatically capture large volumes of data regarding the patient activities in the ED in order to build simulation models of more details and a higher accuracy.
Keywords :
Big Data; digital simulation; emergency management; medical administrative data processing; radiofrequency identification; Hong Kong; RFID-enabled infrastructure; big data; emergency department processes; hospital administrators; patient activities; simulation model; Big data; Computational modeling; Computers; Data models; Hidden Markov models; Hospitals; RFID; big data; emergency department; simulation modelling;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Big Data (BigData Congress), 2015 IEEE International Congress on
Conference_Location :
New York, NY
Print_ISBN :
978-1-4673-7277-0
Type :
conf
DOI :
10.1109/BigDataCongress.2015.52
Filename :
7207236
Link To Document :
بازگشت