Page 212 - Data Science Algorithms in a Week

196 Abdulrahman Albar, Ahmad Elshennawy, Mohammed Basingab et al.

demand, patient complexity, staffing level, clinician workload, and boarding status when
defining the crowding level. The hierarchical fuzzy logic approach is utilized to
accomplish the goals of this framework by combining a diverse pool of healthcare expert
perspectives while addressing the complexity of the overcrowding issue.

Keywords: Overcrowding, Healthcare, Emergency Department, Expert Knowledge,
Fuzzy logic

INTRODUCTION

The demand of healthcare services continues to grow, and lack of access to care
services has become a dilemma due to the limited capacity and inefficient use of
resources in healthcare. (Bellow & Gillespie, 2014). This supply-demand imbalance and
resulting access block is causing overcrowding in healthcare facilities, one type of which
is emergency departments. These essential healthcare centers serve as a hospital’s front
door and provide emergency care service to patients regardless of their ability to pay.
According to the American Hospital Association (AHA) annual survey, the visits to
emergency departments in the USA exceeded 130 million in 2011 (AHA, 2014). In Saudi
Arabia, the Ministry of Health (MoH) reported nearly 21 million visits in 2012 (MOH,
2014). With this massive demand on emergency care services, emergency departments
mostly operate over capacity and sometimes report ambulance diversion.
When ED crowding started to become a serious problem, a need appeared to quantify
the problem to offer support in making emergency care operational decisions (Johnson &
Winkelman, 2011). As a result, four ED crowding measurement scales were developed
which are Real-time Emergency Analysis of Demand Indicators (READI) (Reeder &
Garrison, 2001), Emergency Department Work Index (EDWIN) (Bernstein, Verghese,
Leung, Lunney, & Perez, 2003), National Emergency Department Overcrowding Score
(NEDOCS) (Weiss et al., 2004), and Work Score (Epstein & Tian, 2006). However,
many criticized the reliability, reproducibility, and validity of these crowding
measurement scales when implemented in emergency settings outside of the regions they
were originally developed in. Moreover, their efficiency has been a concern, especially
with regards to their dependency solely on emergency physicians’ and nurses’
perspectives.
Currently, ED crowding has become a serious issue in many healthcare organizations
which affects both operational and clinical aspects of emergency care systems (Eitel,
Rudkin, Malvehy, Killeen, & Pines, 2010; Epstein et al., 2012). To evaluate such an
issue, healthcare decision makers should be provided with a robust quantitative tool that
measures the problem and aids in ED operational decision making (Hwang et al., 2011).
To achieve this, the proposed study aims to develop a quantitative measurement tool of
evaluating ED crowding that captures healthcare experts’ opinions and other ED