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.

  • Clinical Research Article
  • Published:

Development and validation of a model predicting preterm infant discharge in level 2 care

Pediatric Research (2026)Cite this article

Abstract

Background

To develop and validate a model for predicting upcoming discharge home of preterm infants in a level 2 neonatal ward.

Methods

This retrospective cohort study included preterm infants admitted to the two-location study site between January 2016 and December 2023. A multivariable logistic regression model was developed using backward selection, with day 7 of admission selected as the prediction time. Primary outcome was discharge within one week (i.e. between admission day 7 and 14). On our wards, discharge required a minimum postconceptional age (PCA) of 35 weeks. Thus, infants with a PCA < 33 weeks at admission were excluded.

Results

The 1083 infants included were allocated to the development (n = 614) or validation (n = 469) set. Nine predictors were identified: mode of delivery, syndromal diagnoses, gestational and postconceptional age, tube feeding, provision of mother’s own milk, weight, monitor surveillance, and caffeine administration. Internal and external validation showed excellent discrimination (AUC 0.93, CI 0.90–0.95) and acceptable calibration (slope 1.13, CI 0.91–1.35; intercept −0.14, CI −0.45 to 0.16). A probability threshold of 0.60 provided a sensitivity of 88% and specificity of 89%.

Conclusion

A combination of perinatal and neonatal characteristics can adequately predict upcoming discharge home of preterm infants in a level 2 neonatal setting.

Impact

  • Although models estimating total length of hospital stay in preterm infants have been reported, no models predict upcoming discharge, and the level 2 neonatal population remains underreported.

  • We developed a tool to estimate the odds of discharge home within one week from the time of prediction, identifying nine (mainly clinical neonatal) predictors.

  • The tool showed excellent discrimination and acceptable calibration, providing high sensitivity and specificity.

  • The tool could optimize parent-provider communication and hospital capacity management, and should be validated further in prospective studies.

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

Access options

Buy this article

  • Purchase on SpringerLink
  • Instant access to the full article PDF.

USD 39.95

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

Fig. 1: Flow diagram of screening and inclusion of participants.
Fig. 2: Visual overview of calibration and discrimination metrics of external validation of model 1.
Fig. 3: Example of a clinical tool based on final prediction model.

Similar content being viewed by others

Data availability

The datasets generated during and/or analysed during the current study are available from the corresponding author on reasonable request.

References

  1. Ingram, J. et al. Preparing for Home: a before-and-after study to investigate the effects of a neonatal discharge package aimed at increasing parental knowledge, understanding and confidence in caring for their preterm infant before and after discharge from hospital. Heal Serv. Deliv. Res. 4, 1–114 (2016).

    Article  Google Scholar 

  2. Bernstein, H. H. et al. Postpartum discharge: Do varying perceptions of readines impact health outcomes?. Ambul. Pediatr. 2, 388–395 (2002).

    Article  PubMed  Google Scholar 

  3. Spence, C. M., Stuyvenberg, C. L., Kane, A. E., Burnsed, J. & Dusing, S. C. Parent experiences in the NICU and transition to home. Int. J. Environ. Res. Public Health 20, 6050 (2023).

    Article  PubMed  PubMed Central  Google Scholar 

  4. Aydon, L., Hauck, Y., Murdoch, J., Siu, D. & Sharp, M. Transition from hospital to home: Parents’ perception of their preparation and readiness for discharge with their preterm infant. J. Clin. Nurs. 27, 269–277 (2018).

    Article  PubMed  Google Scholar 

  5. Osborne, A. D., Worsley, D., Cullen, C., Martin, A. & Christ, L. Enhancing NICU care and communication: perspectives of moderately preterm infant parents. Pediatrics 153, e2023064419 (2024).

    Article  PubMed  Google Scholar 

  6. Hua, W. et al. Understanding preparation for preterm infant discharge from parents’ and healthcare providers’ perspectives: challenges and opportunities. J. Adv. Nurs. 77, 1379–1390 (2021).

    Article  PubMed  Google Scholar 

  7. Larsson, C., Wågström, U., Normann, E. & Thernström Blomqvist, Y. Parents experiences of discharge readiness from a Swedish neonatal intensive care unit. Nurs. Open 4, 90–95 (2016).

    Article  PubMed  PubMed Central  Google Scholar 

  8. Weiss, M. E. & Lokken, L. Predictors and outcomes of postpartum mothers’ perceptions of readiness for discharge after birth. JOGNN J. Obstet. Gynecol. Neonatal Nurs. 38, 406–417 (2009).

    Article  PubMed  Google Scholar 

  9. Smith, V. C., Hwang, S. S., Dukhovny, D., Young, S. & Pursley, D. M. Neonatal intensive care unit discharge preparation, family readiness and infant outcomes: connecting the dots. J. Perinatol. 33, 415–421 (2013).

    Article  CAS  PubMed  Google Scholar 

  10. Smith, V. C., Young, S., Pursley, D. M., McCormick, M. C. & Zupancic, J. A. F. Are families prepared for discharge from the NICU? J. Perinatol. 29, 623–629 (2009).

    Article  CAS  PubMed  Google Scholar 

  11. Ingram, J. et al. “Giving us hope”: Parent and neonatal staff views and expectations of a planned family-centred discharge process (Train-to-Home). Heal Expect. 20, 751–759 (2017).

    Article  Google Scholar 

  12. Arwehed, S. et al. Nordic survey showed wide variation in discharge practices for very preterm infants. Acta Paediatr. 113, 48–55 (2024).

    Article  PubMed  Google Scholar 

  13. Landsem, I. P. & Handegård, B. H. Parental reports of hospital- and community-based follow-up services, self-efficacy, and symptoms of depression a few months after discharge of a prematurely born child. BMC Public Health 24, 1630 (2024).

    Article  PubMed  PubMed Central  Google Scholar 

  14. Itoshima, R., Ojasalo, V. & Lehtonen, L. Impact of discharge criteria on the length of stay in preterm infants: a retrospective study in Japan and Finland. Early Hum. Dev. 193, 106016 (2024).

    Article  PubMed  Google Scholar 

  15. Melnyk, B. M. et al. Reducing premature infants’ length of stay and improving parents’ mental health outcomes with the Creating Opportunities for Parent Empowerment (COPE) neonatal intensive care unit program: a randomized, controlled trial. Pediatrics 118, e1414–e1427 (2006).

    Article  PubMed  Google Scholar 

  16. Wreesmann, W. J. W. et al. The functions of adequate communication in the neonatal care unit: a systematic review and meta-synthesis of qualitative research. Patient Educ. Couns. 104, 1505–1517 (2021).

    Article  PubMed  Google Scholar 

  17. Tiryaki, Ö, Çınar, N. & Caner, İ. The effect of family integrated care on preparing parents with premature infants hospitalized in the neonatal intensive care unit for discharge. J. Perinatol. 44, 1014–1021 (2024).

    Article  PubMed  PubMed Central  Google Scholar 

  18. Altman, M., Vanpée, M., Bendito, A. & Norman, M. Shorter hospital stay for moderately preterm infants. Acta Paediatr. Int J. Paediatr. 95, 1228–1233 (2006).

    Article  Google Scholar 

  19. Fleming, P. J., Ingram, J., Johnson, D. & Blair, P. S. Estimating discharge dates using routinely collected data: Improving the preparedness of parents of preterm infants for discharge home. Arch. Dis. Child Fetal Neonatal Ed. 102, F170–F172 (2017).

    Article  PubMed  Google Scholar 

  20. Seaton, S. E. et al. What factors predict length of stay in a neonatal unit: a systematic review. BMJ Open 6, e010466 (2016).

    Article  PubMed  PubMed Central  Google Scholar 

  21. Murki, S. et al. Predictors of length of hospital stay among preterm infants admitted to neonatal intensive care unit: data from a multicentre collaborative network from India (INNC: Indian National Neonatal Collaborative). J. Paediatr. Child Health 56, 1584–1589 (2020).

    Article  PubMed  Google Scholar 

  22. Hintz, S. R. et al. Predicting time to hospital discharge for extremely preterm infants. Pediatrics 125, e146–e154 (2010).

    Article  PubMed  Google Scholar 

  23. Seaton, S. E. et al. Estimating neonatal length of stay for babies born very preterm. Arch. Dis. Child Fetal Neonatal Ed. 104, F182–F186 (2018).

    Article  PubMed  PubMed Central  Google Scholar 

  24. Hinchliffe, S. R. et al. Modelling time to death or discharge in neonatal care: an application of competing risks. Paediatr. Perinat. Epidemiol. 27, 426–433 (2013).

    Article  PubMed  Google Scholar 

  25. Lee, H. C., Bennett, M. V., Schulman, J., Gould, J. B. & Profit, J. Estimating length of stay by patient type in the neonatal intensive care unit. Am. J. Perinatol. 33, 751–757 (2016).

    Article  PubMed  Google Scholar 

  26. Lee, H. C., Bennett, M. V., Schulman, J. & Gould, J. B. Accounting for variation in length of NICU stay for extremely low birth weight infants. J. Perinatol. 33, 872–876 (2013).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  27. Arkin, N., Zhao, T., Yang, Y. & Wang, L. Development and validation of a novel risk classification tool for predicting long length of stay in NICU blood transfusion infants. Sci. Rep. 14, 6877 (2024).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  28. Rao, P. et al. Prediction score for prolonged hospital stay in meconium aspiration syndrome: a multicentric collaborative cohort of South India. Pediatr. Pulmonol. 57, 2383–2389 (2022).

    Article  PubMed  Google Scholar 

  29. Frostig, T. et al. Developing a length of stay prediction model for newborns, achieving better accuracy with greater usability. Int. J. Med Inf. 180, 105267 (2023).

    Article  Google Scholar 

  30. Ohuma, E. O. et al. National, regional, and global estimates of preterm birth in 2020, with trends from 2010: a systematic analysis. Lancet 402, 1261–1271 (2023).

    Article  PubMed  Google Scholar 

  31. Van Veenendaal, N. R. et al. Association of a zero-separation neonatal care model with stress in mothers of preterm infants. JAMA Netw. open 5, e224514 (2022).

    Article  PubMed  PubMed Central  Google Scholar 

  32. Collins G. S., Reitsma J. B., Altman D. G. & Moons K. G. M. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): The TRIPOD statement. BMJ. 350. https://doi.org/10.1136/bmj.g7594 (2015).

  33. Moons, K. G. M., Royston, P., Vergouwe, Y., Grobbee, D. E. & Altman, D. G. Prognosis and prognostic research: What, why, and how?. BMJ 338, b375 (2009).

    Article  PubMed  Google Scholar 

  34. Van Veenendaal, N. R. et al. Association of a family integrated care model with paternal mental health outcomes during neonatal hospitalization. JAMA Netw. Open 5, e2144720 (2022).

    Article  PubMed  PubMed Central  Google Scholar 

  35. van Buuren, S. & Groothuis-Oudshoorn, K. mice: multivariate imputation by chained equations in R. J. Stat. Softw. 45, 1–67 (2011).

    Article  Google Scholar 

  36. Youden, W. J. Index for rating diagnostic tests. Cancer 3, 32–35 (1950).

    Article  CAS  PubMed  Google Scholar 

  37. Robledo, K. P., Libesman, S. & Yelland, L. N. We should do better in accounting for multiple births in neonatal randomised trials: a methodological systematic review. Arch. Dis. Child Fetal Neonatal Ed. 110, 362–368 (2025).

    Article  PubMed  PubMed Central  Google Scholar 

  38. Kurek Eken, M., Tüten, A., Özkaya, E., Karatekin, G. & Karateke, A. Major determinants of survival and length of stay in the neonatal intensive care unit of newborns from women with premature preterm rupture of membranes. J. Matern Neonatal Med 30, 1972–1975 (2017).

    Article  Google Scholar 

  39. Morrow, C. B., McGrath-Morrow, S. A. & Collaco, J. M. Predictors of length of stay for initial hospitalization in infants with bronchopulmonary dysplasia. J. Perinatol. 38, 1258–1265 (2018).

    Article  PubMed  PubMed Central  Google Scholar 

  40. Altman, M., Vanpée, M., Cnattingius, S. & Norman, M. Moderately preterm infants and determinants of length of hospital stay. Arch. Dis. Child Fetal Neonatal Ed. 94, F414–F418 (2009).

    Article  CAS  PubMed  Google Scholar 

  41. Carlton K. et al. Machine learning risk stratification for high-risk infant follow-up of term and late preterm infants. Pediatr Res. Published online 2024:Online ahead of print. https://doi.org/10.1038/S41390-024-03338-6.

  42. Chung, H. W. et al. Developing a practical neurodevelopmental prediction model for targeting high-risk very preterm infants during visit after NICU: a retrospective national longitudinal cohort study. BMC Med. 22, 68 (2024).

    Article  PubMed  PubMed Central  Google Scholar 

  43. Barnes, S., Hamrock, E., Toerper, M., Siddiqui, S. & Levin, S. Real-time prediction of inpatient length of stay for discharge prioritization. J. Am. Med. Inform. Assoc. 23, e2–e10 (2016).

    Article  PubMed  Google Scholar 

  44. Steyerberg, E. W. & Harrell, F. E. Prediction models need appropriate internal, internal-external, and external validation. J. Clin. Epidemiol. 69, 245–247 (2015).

    Article  PubMed  PubMed Central  Google Scholar 

  45. Sperrin, M., Riley, R. D., Collins, G. S. & Martin, G. P. Targeted validation: validating clinical prediction models in their intended population and setting. Diagnostic Progn. Res. 6, 1–6 (2022).

    Article  Google Scholar 

  46. Van Calster, B. et al. Calibration: The Achilles heel of predictive analytics. BMC Med. 17, 1–7 (2019).

    Google Scholar 

  47. Stark, A. R. et al. Hospital discharge of the high-risk neonate. Pediatrics 122, 1119–1126 (2008).

    Article  Google Scholar 

  48. Gupta, M., Pursley, D. M. & Smith, V. C. Preparing for discharge from the neonatal intensive care unit. Pediatrics 143, e20182915 (2019).

    Article  PubMed  Google Scholar 

  49. Franck, L. S. & O’Brien, K. The evolution of family-centered care: from supporting parent-delivered interventions to a model of family integrated care. Birth Defects Res. 111, 1044–1059 (2019).

    Article  CAS  PubMed  Google Scholar 

  50. Benzies, K. M. et al. Effectiveness of Alberta Family Integrated Care on infant length of stay in level II neonatal intensive care units: a cluster randomized controlled trial. BMC Pediatr. 20, 535 (2020).

    Article  PubMed  PubMed Central  Google Scholar 

  51. Alsadaan, N. et al. Impacts of integrating family-centered care and developmental care principles on neonatal neurodevelopmental outcomes among high-risk neonates. Child 10, 1751 (2023).

    Article  Google Scholar 

  52. Hei, M. et al. Family integrated care for preterm infants in China: a cluster randomized controlled trial. J. Pediatr. 228, 36–43.e2 (2020).

    Article  PubMed  Google Scholar 

  53. van Veenendaal N. R. et al. Development and psychometric evaluation of the CO-PARTNER tool for collaboration and parent participation in neonatal care. Alves E., ed. PLoS One. 16:e0252074. https://doi.org/10.1371/journal.pone.0252074 (2021).

  54. Chant, K. et al. Job satisfaction and intent to stay in neonatal nursing in England and Wales: a study protocol. BMC Health Serv. Res. 24, 913 (2024).

    Article  PubMed  PubMed Central  Google Scholar 

  55. Clements, K. M., Barfield, W. D., Ayadi, M. F. & Wilber, N. Preterm birth-associated cost of early intervention services: an analysis by gestational age. Pediatrics 119, e866–e874 (2007).

    Article  PubMed  Google Scholar 

  56. Bernstein, H. H. et al. Unreadiness for postpartum discharge following healthy term pregnancy: Impact on health care use and outcomes. Acad. Pediatr. 13, 27–39 (2013).

    Article  PubMed  Google Scholar 

Download references

Acknowledgements

We would like to thank Ariena Rasker for being so kind to guide us through the use of the CTcue software.

Funding

No funding was received for this study.

Author information

Authors and Affiliations

  1. Department of Pediatrics/Neonatology, OLVG, Amsterdam, The Netherlands

    Hannah Hoeben, Nicole R. van Veenendaal & Anne A. M. W. van Kempen

  2. Emma Children’s Hospital Department of Pediatrics, Amsterdam University Medical Center, University of Amsterdam, Vrije Universiteit University, Amsterdam, The Netherlands

    Hannah Hoeben, Nicole R. van Veenendaal & Johannes B. van Goudoever

  3. Department of Research and Epidemiology, OLVG, Amsterdam, The Netherlands

    Nini H. Jonkman

  4. Eva Servicecentrum, Amsterdam University Medical Center, Amsterdam, The Netherlands

    Annika Rausch

  5. Northwest Academy, Northwest Clinics Alkmaar, Alkmaar, The Netherlands

    Ingrid S. van Maurik

  6. Department of Epidemiology and Data Science, Amsterdam Public Health Research Institute, Amsterdam University Medical Center, University of Amsterdam, Amsterdam, The Netherlands

    Ingrid S. van Maurik & Martijn W. Heymans

  7. Department of Neonatology, Wilhelmina Children’s Hospital, University Medical Center Utrecht, Utrecht, The Netherlands

    Sophie R. D. van der Schoor

Authors
  1. Hannah Hoeben
    View author publications

    Search author on:PubMed Google Scholar

  2. Nini H. Jonkman
    View author publications

    Search author on:PubMed Google Scholar

  3. Annika Rausch
    View author publications

    Search author on:PubMed Google Scholar

  4. Ingrid S. van Maurik
    View author publications

    Search author on:PubMed Google Scholar

  5. Nicole R. van Veenendaal
    View author publications

    Search author on:PubMed Google Scholar

  6. Martijn W. Heymans
    View author publications

    Search author on:PubMed Google Scholar

  7. Sophie R. D. van der Schoor
    View author publications

    Search author on:PubMed Google Scholar

  8. Johannes B. van Goudoever
    View author publications

    Search author on:PubMed Google Scholar

  9. Anne A. M. W. van Kempen
    View author publications

    Search author on:PubMed Google Scholar

Contributions

Conceptualization/design: H.H., N.V., S.S., A.K. Methodology: H.H., N.J., A.R., I.M., M.H., A.K. Data acquisition: H.H., N.J., A.R., S.S., A.K. Analysis and interpretation of data: H.H., N.J., A.R., I.M., M.H., S.S., J.G., A.K. Writing of draft: H.H., N.J., I.M., A.K. Revising draft: H.H., N.J., A.R., I.M., N.V., M.H., S.S., J.G., A.K. All authors approved the final version of the manuscript.

Corresponding author

Correspondence to Anne A. M. W. van Kempen.

Ethics declarations

Competing interests

The authors declare no competing interests.

Ethical statement

This study was approved by the Medical Ethics Review Board (MEC-U, Nieuwegein, the Netherlands). Study reference: WO 21.175. Retrieving patient consent was considered unnecessary after review.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Hoeben, H., Jonkman, N.H., Rausch, A. et al. Development and validation of a model predicting preterm infant discharge in level 2 care. Pediatr Res (2026). https://doi.org/10.1038/s41390-026-04782-2

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Version of record:

  • DOI: https://doi.org/10.1038/s41390-026-04782-2

Search

Advanced search

Quick links