Short-Term Forecasting of the Emergency Department Daily Patient Number: Incremental Contribution of Morning Hours

2.50
Hdl Handle:
http://hdl.handle.net/10755/304014
Category:
Abstract
Type:
Presentation
Title:
Short-Term Forecasting of the Emergency Department Daily Patient Number: Incremental Contribution of Morning Hours
Author(s):
Plakht, Ygal; Shiyovich, Artur
Lead Author STTI Affiliation:
Non-member
Author Details:
Ygal Plakht, RN, PhD, Plakht@bgu.ac.il; Artur Shiyovich, MD;
Abstract:

Session presented on: Monday, July 22, 2013

Purpose: The ability to predict the emergency department daily patient number (DPN) could assist in avoiding overcrowding. Most of the forecasting models are based on various calendar-dependent variables.  A models' accuracy is determined by the percentage of variability - R2 (higher values indicate a better accuracy) and the mean of absolute percentage error - MAPE (lower values indicate a better accuracy). The present study assesses the number of ED visits during the morning hours, as an incremental predictor of DPN. 

Methods: Data of patient visits to the Medical Center ED were collected retrospectively throughout 1/1/2007-31/12/2011 (training set - TS) and 1/1-2/10/2012 (validation set - VS). A linear regression forecasting model for DPN comprised calendar-dependent data and the number of visits during morning hours in a given day.

 Results: The mean DPN was: 559.3±94.2 (TS) and 615.1±101.8 (VS). DPNs differed according to the study years and weekdays (p<0.001 for each), yet not the months. Throughout two consecutive morning hours (8am-10am) a mean of 9.1±1.8% of the DPN occurred. The latter correlated with the DPN (r=0.79, p<0.001) and had an incremental prediction ability over the model based on calendar-dependent variables (year and weekday) both in the TS (R2 of 0.833 vs. 0.782) and the VS (R2 of 0.813 vs. 0.728) (p<0.001 for each). The MAPE decreased from 5.98 to 5.38 (TS) and from 6.57 to 5.55 (VS) (p<0.001 for each).

 Conclusion: The number of ED visits during two specific morning hours is a robust predictor of DPN in a given day and has incremental prediction over calendar data alone. Accurate forecasting of DPN can help in optimizing hospital resources, avoiding overcrowding, and improve a healthcare quality.

Keywords:
Forecasting; Daily Patient Number; Emergency Department
Repository Posting Date:
22-Oct-2013
Date of Publication:
22-Oct-2013
Conference Date:
2013
Conference Name:
24th International Nursing Research Congress
Conference Host:
Sigma Theta Tau International, the Honor Society of Nursing
Conference Location:
Prague, Czech Republic
Description:
24th International Nursing Research Congress Theme: Bridge the Gap Between Research and Practice Through Collaboration. Held at the Hilton Prague Hotel.
Note:
This is an abstract-only submission. If the author has submitted a full-text item based on this abstract, you may find it by browsing the Virginia Henderson Global Nursing e-Repository by author. If author contact information is available in this abstract, please feel free to contact him or her with your queries regarding this submission.

Full metadata record

DC FieldValue Language
dc.language.isoen_USen_GB
dc.type.categoryAbstracten_GB
dc.typePresentationen_GB
dc.titleShort-Term Forecasting of the Emergency Department Daily Patient Number: Incremental Contribution of Morning Hoursen_GB
dc.contributor.authorPlakht, Ygalen_GB
dc.contributor.authorShiyovich, Arturen_GB
dc.contributor.departmentNon-memberen_GB
dc.author.detailsYgal Plakht, RN, PhD, Plakht@bgu.ac.il; Artur Shiyovich, MD;en_GB
dc.identifier.urihttp://hdl.handle.net/10755/304014-
dc.description.abstract<p>Session presented on: Monday, July 22, 2013</p><b>Purpose: </b>The ability to predict the emergency department daily patient number (DPN) could assist in avoiding overcrowding. Most of the forecasting models are based on various calendar-dependent variables.  A models' accuracy is determined by the percentage of variability - R<sup>2</sup> (higher values indicate a better accuracy) and the mean of absolute percentage error - MAPE (lower values indicate a better accuracy). The present study assesses the number of ED visits during the morning hours, as an incremental predictor of DPN.  <p><b>Methods: </b>Data of patient visits to the Medical Center ED were collected retrospectively throughout 1/1/2007-31/12/2011 (training set - TS) and 1/1-2/10/2012 (validation set - VS). A linear regression forecasting model for DPN comprised calendar-dependent data and the number of visits during morning hours in a given day. <p> <b>Results: </b>The mean DPN was: 559.3±94.2 (TS) and 615.1±101.8 (VS). DPNs differed according to the study years and weekdays (p<0.001 for each), yet not the months. Throughout two consecutive morning hours (8am-10am) a mean of 9.1±1.8% of the DPN occurred. The latter correlated with the DPN (r=0.79, p<0.001) and had an incremental prediction ability over the model based on calendar-dependent variables (year and weekday) both in the TS (R<sup>2</sup> of 0.833 vs. 0.782) and the VS (R<sup>2 </sup>of 0.813 vs. 0.728) (p<0.001 for each). The MAPE decreased from 5.98 to 5.38 (TS) and from 6.57 to 5.55 (VS) (p<0.001 for each). <p> <b>Conclusion: </b>The number of ED visits during two specific morning hours is a robust predictor of DPN in a given day and has incremental prediction over calendar data alone. Accurate forecasting of DPN can help in optimizing hospital resources, avoiding overcrowding, and improve a healthcare quality.en_GB
dc.subjectForecastingen_GB
dc.subjectDaily Patient Numberen_GB
dc.subjectEmergency Departmenten_GB
dc.date.available2013-10-22T20:27:38Z-
dc.date.issued2013-10-22-
dc.date.accessioned2013-10-22T20:27:38Z-
dc.conference.date2013en_GB
dc.conference.name24th International Nursing Research Congressen_GB
dc.conference.hostSigma Theta Tau International, the Honor Society of Nursingen_GB
dc.conference.locationPrague, Czech Republicen_GB
dc.description24th International Nursing Research Congress Theme: Bridge the Gap Between Research and Practice Through Collaboration. Held at the Hilton Prague Hotel.en_GB
dc.description.noteThis is an abstract-only submission. If the author has submitted a full-text item based on this abstract, you may find it by browsing the Virginia Henderson Global Nursing e-Repository by author. If author contact information is available in this abstract, please feel free to contact him or her with your queries regarding this submission.en_GB
All Items in this repository are protected by copyright, with all rights reserved, unless otherwise indicated.