Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Original Article
  • Published:

Neonatal intensive care unit: predictive models for length of stay

Abstract

Objective:

Hospital length of stay (LOS) is important to administrators and families of neonates admitted to the neonatal intensive care unit (NICU). A prediction model for NICU LOS was developed using predictors birth weight, gestational age and two severity of illness tools, the score for neonatal acute physiology, perinatal extension (SNAPPE) and the morbidity assessment index for newborns (MAIN).

Study Design:

Consecutive admissions (n=293) to a New England regional level III NICU were retrospectively collected. Multiple predictive models were compared for complexity and goodness-of-fit, coefficient of determination (R2) and predictive error. The optimal model was validated prospectively with consecutive admissions (n=615). Observed and expected LOS was compared.

Result:

The MAIN models had best Akaike's information criterion, highest R2 (0.786) and lowest predictive error. The best SNAPPE model underestimated LOS, with substantial variability, yet was fairly well calibrated by birthweight category. LOS was longer in the prospective cohort than the retrospective cohort, without differences in birth weight, gestational age, MAIN or SNAPPE.

Conclusion:

LOS prediction is improved by accounting for severity of illness in the first week of life, beyond factors known at birth. Prospective validation of both MAIN and SNAPPE models is warranted.

This is a preview of subscription content, access via your institution

Access options

Rent or buy this article

Prices vary by article type

from$1.95

to$39.95

Prices may be subject to local taxes which are calculated during checkout

Figure 1
Figure 2
Figure 3
Figure 4
Figure 5

Similar content being viewed by others

References

  1. Knaus W, Zimmerman J, Wagner D, Draper E, Lawrence D . APACHE-acute physiology and chronic health evaluation: a physiologically based classification system. Crit Care Med 1981; 9 (8): 591–597.

    Article  CAS  PubMed  Google Scholar 

  2. LeGall J, Loirat P, Alperovitch A . A simplified acute physiology score for ICU patients. Crit Care Med 1984; 12: 975–977.

    Article  CAS  Google Scholar 

  3. Lemeshow S, Teres D, Avrunin J . Refining intensive care unit outcome prediction by using changing probabilities of mortality. Crit Care Med 1988; 16.

  4. Herridge M . Prognostication and intensive care unit outcome: the evolving role of scoring systems. Clin Chest Med 2003; 24: 751–762.

    Article  PubMed  Google Scholar 

  5. Rafkin H, Hoyt J . Objective data and quality assurance programs. Current and future trends. Crit Care Clin 1994; 10 (1): 157–177.

    Article  CAS  PubMed  Google Scholar 

  6. Zupancic J, Richardson D . Characterization of the triage process in neonatal intensive care. Pediatrics 1998; 102: 1432–1436.

    Article  CAS  PubMed  Google Scholar 

  7. Glance L, Osler T, Shinozaki T . Intensive care unit prognostic scoring systems to predict death: a cost-effectiveness analysis. Crit Care Med 1998; 26 (11): 1842–1849.

    Article  CAS  PubMed  Google Scholar 

  8. García S, Ruza F, Alvarado F, Madero R, Delgado M, Dorao P et al. Analysis of costs in a pediatric ICU. Intensive Care Med 1997; 23 (2): 218–225.

    Article  PubMed  Google Scholar 

  9. Zimmerman J, Kramer A, McNair D . Intensive care unit length of stay: benchmarking based on acute physiology and chronic health evaluation (APACHE) IV*. Crit Care Med 2006; 34: 2517–2529.

    Article  PubMed  Google Scholar 

  10. Müller-Berndorff H, Haas P, Kunzmann R, Schulte-Mönting J, Lübbert M . Comparison of five prognostic scoring systems, the French-American-British (FAB) and World Health Organization (WHO) classifications in patients with myelodysplastic syndromes: results of a single-center analysis. Ann Hematol 2006; 85 (8): 502–513.

    Article  PubMed  Google Scholar 

  11. Valeur N, Clemmensen P, Grande P, Saunamäki K, Investigators D . Prognostic evaluation by clinical exercise test scores in patients treated with primary percutaneous coronary intervention or fibrinolysis for acute myocardial infarction. Am J Cardiol 2007; 100 (7): 1074–1080.

    Article  PubMed  Google Scholar 

  12. Yeh T, Pollack M, Ruttimann U, Holbrook P, Fields A . Validation of a physiologic stability index for use in critically ill infants and children. Pediatr Res 1984; 18 (5): 445–451.

    Article  CAS  PubMed  Google Scholar 

  13. Pollack M, Ruttimann U, Getson P . Pediatric risk of mortality (PRISM) score. Crit Care Med 1988; 16 (11): 1110–1116.

    Article  CAS  PubMed  Google Scholar 

  14. Klem S, Pollack M, Glass N, Spohn W, Kanter R, Zucker A et al. Resource use, efficiency, and outcome prediction in pediatric intensive care of trauma patients. J Trauma 1990; 30 (1): 32–36.

    Article  CAS  PubMed  Google Scholar 

  15. Cockburn F, Cooke R . The CRIB (clinical risk index for babies) score: a tool for assessing initial neonatal risk. Lancet 1993; 342 (8865): 193–198.

    Article  Google Scholar 

  16. Gray J, Richardson D, McCormick M, Workman-Daniels K, Goldmann D . Neonatal therapeutic intervention scoring system: a therapy-based severity-of-illness index. Pediatrics 1992; 90: 561–567.

    CAS  PubMed  Google Scholar 

  17. Verma A, Weir A, Drummond J, Mitchell B . Performance profile of an outcome measure: morbidity assessment index for newborns. J Epidemiol Community Health 2005; 59: 420–426.

    Article  PubMed  PubMed Central  Google Scholar 

  18. Escobar G, Fischer A, Li D, Kremers R, Armstrong M . Score for neonatal acute physiology: validation in three kaiser permanente neonatal intensive care units. Pediatrics 1995; 96: 918–922.

    CAS  PubMed  Google Scholar 

  19. Verma A, Okun N, Maguire T, Mitchell B . Morbidity Assessment Index for Newborns: a composite tool for measuring newborn health. Am J Obstet Gynecol 1999; 181: 701–708.

    Article  CAS  PubMed  Google Scholar 

  20. Richardson D, Gray J, McCormick M, Workman K, Goldmann D . Score for neonatal acute physiology: a physiologic severity index for neonatal intensive care. Pediatrics 1993; 91: 617–623.

    CAS  PubMed  Google Scholar 

  21. Richardson D, Corcoran J, Escobar G, Lee S . SNAP-II and SNAPPE-II: simplified newborn illness severity and mortality risk scores. J Pediatr 2001; 138: 92–100.

    Article  CAS  PubMed  Google Scholar 

  22. Shulman J . Studying determinants of length of hospital stay. J Perinatology 2006; 26: 243–245.

    Article  Google Scholar 

  23. Nakagawa S, Freckleton R . Missing inaction: the dangers of ignoring missing data. Trends Ecol Evol 2008; 23 (11): 592–596.

    Article  PubMed  Google Scholar 

  24. Akaike H . A new look at the statistical model identification. IEEE Transact Automatic Control 1974; 19 (6): 716–723.

    Article  Google Scholar 

  25. Fanaroff AA, Stoll BJ, Wright LL, Carlo WA, Ehrenkranz RA, Stark AR et al. Trends in neonatal morbidity and mortality for very low birthweight infants. Am J Obstet Gynecol (2007196); 147: e141–e147 .e148.

    Google Scholar 

  26. Meadow W, Reimshisel T, Lantos J . Birth weight-specific mortality for extremely low birth weight infants vanishes by four days of life: epidemiology and ethics in the neonatal intensive care unit. Pediatrics 1996; 97 (5): 636–643.

    CAS  PubMed  Google Scholar 

  27. Singh Jaideep, Lantos John, Meadow William . End-of-life after birth: death and dying in a neonatal intensive care unit. Pediatrics 2004; 114: 1620–1626.

    Article  CAS  PubMed  Google Scholar 

  28. Bannwart D, Rebello C, Sadek L, Pontes M, Ramos J, Leone C . Prediction of length of hospital stay in neonatal units for very low birthweight infants. J Perinatology 1999; 19 (2): 92–96.

    Article  Google Scholar 

  29. Cotten C, Oh W, McDonald S, Carlo W, Fanaroff A, Duara S et al. Prolonged hospital stay for extremely premature infants: risk factors, center differences, and the impact of mortality on selecting a best-performing center. J Perinatology 2005; 25: 650–655.

    Article  Google Scholar 

Download references

Acknowledgements

This study was funded by the Department of Pediatrics, Women & Infants’ Hospital of Rhode Island.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to G J Bender.

Ethics declarations

Competing interests

The authors declare no conflict of interest.

Additional information

Supplementary Information accompanies the paper on the Journal of Perinatology website

Supplementary information

Rights and permissions

Reprints and permissions

About this article

Cite this article

Bender, G., Koestler, D., Ombao, H. et al. Neonatal intensive care unit: predictive models for length of stay. J Perinatol 33, 147–153 (2013). https://doi.org/10.1038/jp.2012.62

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/jp.2012.62

Keywords

This article is cited by

Search

Quick links