Online citations, reference lists, and bibliographies.

Real-time Forecasting Of Pediatric Intensive Care Unit Length Of Stay Using Computerized Provider Orders

S. Levin, E. Harley, J. Fackler, Christoph U. Lehmann, Jason W. Custer, D. France, S. Zeger
Published 2012 · Medicine
Cite This
Download PDF
Analyze on Scholarcy
Share
Objective:To develop a model to produce real-time, updated forecasts of patients’ intensive care unit length of stay using naturally generated provider orders. The model was designed to be integrated within a computerized decision support system to improve patient flow management. Design:Retrospective cohort study. Setting:Twenty-six bed pediatric intensive care unit within an urban, academic children’s hospital using a computerized order entry system. Patients:A total of 2,178 consecutive pediatric intensive care unit admissions during a 16-month time period. Measurements and Main Results:We obtained unit length of stay measurements, time-stamped provider orders, age, admission source, and readmission status. A joint discrete-time logistic regression model was developed to produce probabilistic length of stay forecasts from continuously updated provider orders. Accuracy was assessed by comparing forecasted expected discharge time with observed discharge time, rank probability scoring, and calibration curves. Cross-validation procedures were conducted. The distribution of length of stay was heavily right-skewed with a mean of 3.5 days (95% confidence interval 0.3–19.1). Provider orders were predictive of length of stay in real-time accurately forecasting discharge within a 12-hr window: 46% for patients within 1 day of discharge, 34% for patients within 2 days of discharge, and 27% for patients within 3 days of discharge. The forecast model incorporating predictive orders demonstrated significant improvements in accuracy compared with forecasts based solely on empirical and temporal information. Seventeen predictive orders were found, grouped by medication, ventilation, laboratory, diet, activity, foreign body, and extracorporeal membrane oxygenation. Conclusions:Provider orders reflect dynamic changes in patients’ conditions, making them useful for real-time length of stay prediction and patient flow management. Patients’ length of stay represent a major source of variability in intensive care unit resource utilization and if accurately predicted and communicated, may lead to proactive bed management with more efficient patient flow.
This paper references
10.1097/00000542-200306000-00029
Variability in Surgical Caseload and Access to Intensive Care Services
Michael L McManus (2003)
10.1111/j.1468-0009.2006.00448.x
The transition from excess capacity to strained capacity in U.S. hospitals.
Gloria J Bazzoli (2006)
Chapter 3 . Utilization and volume
GJ Bazzoli (2001)
10.1007/s10729-006-9000-9
Short term hospital occupancy prediction
Steven J. Littig (2007)
10.1046/j.1365-2044.2000.01552.x
Evaluation of predicted and actual length of stay in 22 Scottish intensive care units using the APACHE III system. Acute Physiology and Chronic Health Evaluation.
A. Woods (2000)
10.1136/bmjqs.2008.030007
Evaluating the effects of increasing surgical volume on emergency department patient access
Scott R. Levin (2011)
10.1542/peds.113.4.748
Preventing provider errors: online total parenteral nutrition calculator.
Christoph U. Lehmann (2004)
Values Ethics and Rationing in Critical Care Task Force: Rationing critical care beds: A systematic review Causes of delayed discharge and prolonged stay in PACU
T Sinuff (2002)
Front Office to Front Line: Essential Issues for Health Care figure 3. Forecast model accuracy within a 12-hr window (left) and calibration (right)
E Litvak (2005)
Optimizing Patient Flow by Managing Its Variability
Eugene Litvak (2005)
10.1001/jama.1993.03510240069035
A new Simplified Acute Physiology Score (SAPS II) based on a European/North American multicenter study.
J. Le Gall (1993)
Cost and quality under managed care: irreconcilable differences?
Emile Litvak (2000)
10.1097/01974520-200404000-00002
Patient Flow in Hospitals: Understanding and Controlling It Better
Carol Haraden (2004)
DELAY-ED study group: Impact of delayed transfer of critically ill patients from the emergency department to the intensive care unit
DB Chalfin (2007)
Joint Commission Resources
(2005)
10.1097/00132586-199806000-00007
Severity-adjusted mortality and length of stay in teaching and nonteaching hospitals. Results of a regional study.
Gary E. Rosenthal (1997)
10.1007/BF01704719
An objective method to evaluate rationing of pediatric intensive care beds
J. J. Stambouly (2005)
10.2307/2527342
Evaluating Density Forecasts with Applications to Financial Risk Management
Francis X. Diebold (1998)
10.1007/s10729-005-2012-z
Length of Stay-Based Patient Flow Models: Recent Developments and Future Directions
Adele H. Marshall (2005)
Forecasting Demand for Pediatric Critical Care
S Levin (2011)
10.1097/01.CCM.0000266585.74905.5A
Impact of delayed transfer of critically ill patients from the emergency department to the intensive care unit*
Donald B. Chalfin (2007)
10.1097/01.CCM.0000130175.38521.9F
Rationing critical care beds: A systematic review*
Tasnim Sinuff (2004)
10.1007/s10729-005-4142-8
Modelling Variability in Hospital Bed Occupancy
G. Harrison (2005)
Length of staybased patient flow models : Recent developments and future directions
A Marshall (2005)
10.2307/2987588
The Comparison and Evaluation of Forecasters.
Morris H. Degroot (1983)
10.1097/01.CCM.0000162497.86229.E9
Variation in outcomes in Veterans Affairs intensive care units with a computerized severity measure*
Marta L. Render (2005)
Causes of delayed discharge and prolonged stay in PACU
D Krishnaprasad (2002)
10.1097/01.CCM.0000257337.63529.9F
Assessing contemporary intensive care unit outcome: An updated Mortality Probability Admission Model (MPM0-III)*
Thomas L. Higgins (2007)
10.1175/1520-0450(1969)008<0985:ASSFPF>2.0.CO;2
A Scoring System for Probability Forecasts of Ranked Categories
E. Epstein (1969)
10.1378/chest.08-2591
Mortality probability model III and simplified acute physiology score II: assessing their value in predicting length of stay and comparison to APACHE IV.
Eduard E. Vasilevskis (2009)
10.1097/01.CCM.0000240233.01711.D9
Intensive care unit length of stay: Benchmarking based on Acute Physiology and Chronic Health Evaluation (APACHE) IV*
Jack E. Zimmerman (2006)
American Hospital Association: The Cost of Caring: Drivers of Spending on Hospital Care, TrendWatch
Intensive care unit length of stay: Benchmarking based on Acute Physiology and Chronic Health Evaluation
J E Zimmerman
Institute of Medicine: Hospital-Based Emergency Care: At the Breaking Point. Washington
(2006)
Optimiz - ing cardiology capacity to reduce emergency department boarding : A systems engineering approach
Levin (2008)
National Academy of Engineering and Institute of Medicine: Building a Better Delivery System: A New Engineering/Heath Care Partnership
(2005)
American Hospital Association: Chapter 3. Utilization and volume In: Trendwatch Chartbook 2010: Trends Affecting Hospitals and Health Systems
(2012)
10.1111/j.1553-2712.2000.tb00492.x
Critical care in the emergency department: A physiologic assessment and outcome evaluation.
H B Nguyen (2000)
10.1016/j.ahj.2008.07.007
Optimizing cardiology capacity to reduce emergency department boarding: a systems engineering approach.
Scott R. Levin (2008)
Institute of Medicine: Hospital-Based Emergency Care: At the Breaking Point
(2006)
Crit Care Med
(2012)
10.1177/1077558704266768
Increasing Value: A Research Agenda for Addressing the Managerial and Organizational Challenges Facing Health Care Delivery in the United States
Stephen M. Shortell (2004)
10.1097/01.CCM.0000133021.22188.35
Survival of critically ill patients hospitalized in and out of intensive care units under paucity of intensive care unit beds*
Elisheva Simchen (2004)



This paper is referenced by
10.1002/hpm.2771
A comprehensive modelling framework to forecast the demand for all hospital services.
Muhammed Ordu (2019)
10.1093/jamia/ocv124
Cardiac catheterization laboratory inpatient forecast tool: a prospective evaluation
Matthew F. Toerper (2016)
Forecasting Cardiology Admissions from Catheterization Laboratory
Avishek Choudhury (2018)
10.15587/1729-4061.2016.75690
Development of multi-agent system of neural network diagnostics and remote monitoring of patient
Natalia Axak (2016)
10.4338/ACI-2015-09-RA-0127
Time Series Analysis for Forecasting Hospital Census: Application to the Neonatal Intensive Care Unit.
Muge Capan (2016)
10.1177/0951484817696212
Patient length of stay and mortality prediction: A survey
Aya Awad (2017)
10.1109/BIBM.2014.6999225
Admission duration model for infant treatment (ADMIT)
Keith Feldman (2014)
10.1109/ICHI.2016.26
Forecasting Patient Outflow from Wards having No Real-Time Clinical Data
S. Gopakumar (2016)
10.1109/MIS.2013.51
Using Artificial Intelligence to Improve Hospital Inpatient Care
Daniel B. Neill (2013)
10.2196/14756
Readmission Risk Trajectories for Patients With Heart Failure Using a Dynamic Prediction Approach: Retrospective Study
Wanjun Jiang (2019)
10.1097/PCC.0000000000001425
PICU Length of Stay: Factors Associated With Bed Utilization and Development of a Benchmarking Model
Murray M. Pollack (2018)
10.1016/j.pediatrneurol.2016.04.014
Hospitalized Children With Encephalitis in the United States: A Pediatric Health Information System Database Study.
D. Bagdure (2016)
10.1186/s12874-019-0847-0
Incorporating repeated measurements into prediction models in the critical care setting: a framework, systematic review and meta-analysis
Joost D. J. Plate (2019)
10.1093/jamia/ocv106
Real-time prediction of inpatient length of stay for discharge prioritization
Sean L. Barnes (2016)
10.1097/CCE.0000000000000062
Pediatric Trauma Patient Intensive Care Resource Utilization in U.S. Military Operations in Iraq and Afghanistan
Hannah L Gale (2019)
10.1016/j.cmpb.2013.03.018
Development of a daily mortality probability prediction model from Intensive Care Unit patients using a discrete-time event history analysis
Ying Che Huang (2013)
10.18745/TH.21813
Demand and Capacity Modelling of Acute Services Using Simulation and Optimization Techniques
Muhammed Ordu (2019)
10.1007/978-3-030-35252-3_1
World of Virtual Reality (VR) in Healthcare
Bright Keswani (2020)
10.1287/educ.2019.0202
Health System Innovation: Analytics in Action
Martin S. Copenhaver (2019)
10.1016/j.pcl.2015.12.002
Electronic Health Record-Enabled Research in Children Using the Electronic Health Record for Clinical Discovery.
Scott M Sutherland (2016)
Modeling and Predicting Patient Length of Stay : A Survey
Aya Awad (2016)
10.12788/jhm.2802
The TEND (Tomorrow’s Expected Number of Discharges) Model Accurately Predicted the Number of Patients Who Were Discharged from the Hospital the Next Day
C. van Walraven (2018)
10.1145/3019612.3019667
MILES: multiclass imbalanced learning in ensembles through selective sampling
Ali Azari (2017)
10.2196/medinform.5650
Forecasting Daily Patient Outflow From a Ward Having No Real-Time Clinical Data
S. Gopakumar (2016)
10.7912/C2PP9Z
An Interoperable Electronic Medical Record-Based Platform for Personalized Predictive Analytics.
Hamed Abedtash (2017)
10.2139/ssrn.3301665
Cardiology Admissions from Catheterization Laboratory: Time Series Forecasting
Avishek Choudhury (2018)
Machine learning in healthcare : an investigation into model stability
S. Gopakumar (2017)
10.1016/J.ORHC.2015.03.001
Forecasting demand for health services: Development of a publicly available toolbox
Mehdi Jalalpour (2015)
10.4172/2375-4273.1000173
Automated Discharge Planning Systems: Perceived Challenges and Recommendations
Alghamdi Aa (2016)
10.1561/0200000036
Matching Supply and Demand for Hospital Services
Diwakar Gupta (2016)
Predicting surgical inpatients' discharges at Massachusetts General Hospital
Jonathan Zanger (2018)
10.1542/peds.2015-0456
Predicting Discharge Dates From the NICU Using Progress Note Data
Michael W. Temple (2015)
See more
Semantic Scholar Logo Some data provided by SemanticScholar