Appl Clin Inform 2016; 07(02): 275-289
DOI: 10.4338/ACI-2015-09-RA-0127
Research Article
Schattauer GmbH

Time Series Analysis for Forecasting Hospital Census: Application to the Neonatal Intensive Care Unit

Muge Capan
1   Christiana Care Health System, Value Institute, Newark, DE
,
Stephen Hoover
1   Christiana Care Health System, Value Institute, Newark, DE
,
Eric V. Jackson
1   Christiana Care Health System, Value Institute, Newark, DE
,
David Paul
2   Christiana Care Health System, Division of Neonatology, Newark, DE
,
Robert Locke
2   Christiana Care Health System, Division of Neonatology, Newark, DE
› Institutsangaben
Weitere Informationen

Publikationsverlauf

received: 29. September 2015

accepted: 14. Februar 2016

Publikationsdatum:
16. Dezember 2017 (online)

Summary

Background

Accurate prediction of future patient census in hospital units is essential for patient safety, health outcomes, and resource planning. Forecasting census in the Neonatal Intensive Care Unit (NICU) is particularly challenging due to limited ability to control the census and clinical trajectories. The fixed average census approach, using average census from previous year, is a forecasting alternative used in clinical practice, but has limitations due to census variations.

Objective

Our objectives are to: (i) analyze the daily NICU census at a single health care facility and develop census forecasting models, (ii) explore models with and without patient data characteristics obtained at the time of admission, and (iii) evaluate accuracy of the models compared with the fixed average census approach.

Methods

We used five years of retrospective daily NICU census data for model development (January 2008 - December 2012, N=1827 observations) and one year of data for validation (January - December 2013, N=365 observations). Best-fitting models of ARIMA and linear regression were applied to various 7-day prediction periods and compared using error statistics.

Results

The census showed a slightly increasing linear trend. Best fitting models included a nonseasonal model, ARIMA(1,0,0), seasonal ARIMA models, ARIMA(1,0,0)×(1,1,2)7 and ARIMA(2,1,4)×(1,1,2)14, as well as a seasonal linear regression model. Proposed forecasting models resulted on average in 36.49% improvement in forecasting accuracy compared with the fixed average census approach.

Conclusions

Time series models provide higher prediction accuracy under different census conditions compared with the fixed average census approach. Presented methodology is easily applicable in clinical practice, can be generalized to other care settings, support shortand long-term census forecasting, and inform staff resource planning.

 
  • References

  • 1 Rogowski JA, Staiger D, Patrick T, Horbar J, Kenny M, Lake ET. Nurse Staffing and NICU Infection Rates. JAMA Pediatr 2013; 167 (05) 444-450.
  • 2 Cho SH, Ketefian S, Barkauskas VH, Smith DG. The Effects of Nurse Staffing on Adverse Events, Morbidity, Mortality and Medical Costs. Nurs Res 2003; 52 (02) 71-79.
  • 3 Penoyer DA. Nurse staffing and patient outcomes in critical care: A concise review. Crit Care Med 2010; 38 (07) 1521-1528.
  • 4 Cescutti-Butler L, Galvin K. Parents’ perceptions of staff competency in a neonatal intensive care unit. J Clin Nurs 2003; 12: 752-761.
  • 5 Braithwaite M. Nurse Burnout and Stress in the NICU. Adv in Neonatal Care 2008; 08 (06) 343-347.
  • 6 Scheward L, Hunt J, Hagen S, Macleod M, Ball J. The relationship between UK hospital nurse staffing and emotional exhaustion and job dissatisfaction. J Nurs Manag 2005; 13: 51-60.
  • 7 Aiken LH, Clarke SP, Sloane DM, Sochalski J, Silber JH. Hospital Nurse Staffing and Patient Mortality, Nurse Burnout, and Job Dissatisfaction. JAMA 2002; 288 (16) 1987-1993.
  • 8 Neonatal Intensive Care. A History of Excellence, NIH Publication No. 92-2786 1992 Available from: http://www.neonatology.org/classics/nic.nih1985.pdf (accessed September 28, 2015).
  • 9 American Academy of Pediatrics. Levels of Neonatal Care. Pediatrics. 2004 114. 05 Available from: http://dx.doi.org/10.1542/peds.2004-1697
  • 10 Hamilton KE, Redshaw ME, Tarnow-Mordi W. Nurse staffing in relation to risk-adjusted mortality in neonatal care. Arch Dis Child Fetal Neonatal Ed 2007; 92: F99-F103.
  • 11 Kilbride HW, Powers R, Wirtschafter DD, Sheehan MB, Charsha DS, LaCorte M, Finer N, Goldmann DA. Evaluation and development of potentially better practices to prevent neonatal nosocomial bacteremia. Pediatrics 2003; 111: e504-e518.
  • 12 Reis BY, Mandl KD. Time Series Modeling for syndromic surveillance. BMC Med Inform Decis Mak. 2003 03. (2): Available from: http://doi.org/10.1186/1472-6947-3-2.
  • 13 Brillman JC, Burr T, Forslund D, Joyce E, Picard R, Umland E. Modeling emergency department visit patterns for infectious disease complaints: Results and application to disease surveillance. BMC Med Inform Decis Mak 2005; 05 (01) 4.
  • 14 Guo H, Tang J, Qu G. Historical Data Driven Nurse Flexible Scheduling Problem. 2013 25th Chinese Control and Decision Conference (CCDC). 25-27 May 2013. Guiyang City Guiyang, China.:
  • 15 Jones SS, Thomas A, Evans RS, Welch SJ, Haug PJ, Snow GL. Forecasting Daily Patient Volumes in the Emergency Department. Acad Emerg Med 2008; 15 (02) 159-170.
  • 16 Kam H, Sung J, Par R. Prediction of Daily Patient Numbers for a Regional Emergency Medical Center Using Time Series Analysis. Healthc Inform Res 2010; 16 (03) 158-165.
  • 17 Schweigler LM, Desmond JS, McCarthy ML, Bukowski KJ, Ionides EL, Younger JG. Forecasting Models of Emergency Department Crowding. Acad Emerg Med 2009; 16: 1-8.
  • 18 Champion R, Kinsman LD, Lee GA, Masman KA, May EA, Mills TM, Taylor MD, Thomas PR, Williams RJ. Forecasting emergency department presentations. Aust Health Rev 2007; 31 (01) 83-90.
  • 19 Tandberg D, Qualls C. Time Series Forecasts of Emergency Department Patient Volume, Length of Stay and Acuity. Ann Emerg Med 1994; 23 (02) 299-305.
  • 20 Yu Y, Lin H, Cheng B. The application of Prediction Modeling of the Optimal Emergency Nurse Scheduling. Advances in Information Sciences and Service Sciences 2013; 05 (12) 38-45.
  • 21 Marcilio I, Hajat S, Gouveia N. Forecasting Daily Emergent Department Visits using Calendar Variables and Ambient Temperature Readings. Acad Emerg Med 2013; 20 (08) 179-177.
  • 22 Sun Y, Heng BH, Seow YT, Seow E. Forecasting daily attendances at an emergency department to aid resource planning. BMC Emerg Med. 2009 09. (1): Available from: http://doi.org/10.1186/1471-227X-9-1
  • 23 Temple MW, Lehmann CU, Fabbri D. Predicting Discharge Dates From the NICU Using Progress Note Data. Pediatrics 2015; 136 (02) e395-e405.
  • 24 Levin SR, Harley ET, Fackler JC, Lehmann CU, Custer JW, France D, Zeger SL. Real-time forecasting of pediatric intensive care unit length of stay using computerized provider orders. Crit Care Med 2012; 40 (11) 3058-3064.
  • 25 Koestler DC, Ombao H, Bender J. Ensemble-based methods for forecasting census in hospital units. BMC Med Res Methodol 2013; 13: 67.
  • 26 Shumway R, Stoffer D. Time Series Analysis and Its Applications: With R Examples. 3rd ed.. New York: Springer Texts in Statistics; 2011
  • 27 Lewis CD. Industrial and business forecasting methods: A practical guide to exponential smoothing and curve fitting. London: Butterworth Scientific; 1982
  • 28 Ellison PT, Valeggia CR, Sherry DS. Human birth seasonality. In: Brockman DK, van Schaik CP. editors. Seasonality in Primates: Studies of Living and Extinct Human and Non-Human Primates. Cambridge University Press; 2005: 379-399