SpringerLink
Log in

Machine learning risk stratification for high-risk infant follow-up of term and late preterm infants

  • Clinical Research Article
  • Published:
Pediatric Research Submit manuscript

Abstract

Background

Term and late preterm infants are not routinely referred to high-risk infant follow-up programs at neonatal intensive care unit (NICU) discharge. We aimed to identify NICU factors associated with abnormal developmental screening and develop a risk-stratification model using machine learning for high-risk infant follow-up enrollment.

Methods

We performed a retrospective cohort study identifying abnormal developmental screening prior to 6 years of age in infants born ≥34 weeks gestation admitted to a level IV NICU. Five machine learning models using NICU predictors were developed by classification and regression tree (CART), random forest, gradient boosting TreeNet, multivariate adaptive regression splines (MARS), and regularized logistic regression analysis. Performance metrics included sensitivity, specificity, accuracy, precision, and area under the receiver operating curve (AUC).

Results

Within this cohort, 87% (1183/1355) received developmental screening, and 47% had abnormal results. Common NICU predictors across all models were oral (PO) feeding, follow-up appointments, and medications prescribed at NICU discharge. Each model resulted in an AUC > 0.7, specificity >70%, and sensitivity >60%.

Conclusion

Stratification of developmental risk in term and late preterm infants is possible utilizing machine learning. Applying machine learning algorithms allows for targeted expansion of high-risk infant follow-up criteria.

Impact

  • This study addresses the gap in knowledge of developmental outcomes of infants ≥34 weeks gestation requiring neonatal intensive care.

  • Machine learning methodology can be used to stratify early childhood developmental risk for these term and late preterm infants.

  • Applying the classification and regression tree (CART) algorithm described in the study allows for targeted expansion of high-risk infant follow-up enrollment to include those term and late preterm infants who may benefit most.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
EUR 32.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or Ebook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1: Study design flow diagram.
Fig. 2: Study cohort flow diagram.
Fig. 3: Classification and regression tree (CART) model.

Similar content being viewed by others

Data availability

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

References

  1. Manuck, T. A. et al. Preterm neonatal morbidity and mortality by gestational age: a contemporary cohort. Am. J. Obstet. Gynecol. 215, 103.e101–103.e114 (2016).

    Article  Google Scholar 

  2. Harrison, W. & Goodman, D. Epidemiologic trends in neonatal intensive care, 2007-2012. JAMA Pediatr. 169, 855–862 (2015).

    Article  PubMed  Google Scholar 

  3. Braun, D. et al. Trends in neonatal intensive care unit utilization in a large integrated health care system. JAMA Netw. Open 3, e205239 (2020).

    Article  PubMed  PubMed Central  Google Scholar 

  4. Jarjour, I. T. Neurodevelopmental outcome after extreme prematurity: a review of the literature. Pediatr. Neurol. 52, 143–152 (2015).

    Article  PubMed  Google Scholar 

  5. Raju, T. N., Higgins, R. D., Stark, A. R. & Leveno, K. J. Optimizing care and outcome for late-preterm (near-Term) infants: a summary of the workshop sponsored by the National Institute of Child Health and Human Development. Pediatrics 118, 1207–1214 (2006).

    Article  PubMed  Google Scholar 

  6. Gurka, M. J., LoCasale-Crouch, J. & Blackman, J. A. Long-term cognition, achievement, socioemotional, and behavioral development of healthy late-preterm infants. Arch. Pediatr. Adolesc. Med. 164, 525–532 (2010).

    Article  PubMed  PubMed Central  Google Scholar 

  7. Subedi, D., DeBoer, M. D. & Scharf, R. J. Developmental trajectories in children with prolonged NICU stays. Arch. Dis. Child 102, 29–34 (2017).

    Article  PubMed  Google Scholar 

  8. van Wassenaer‐Leemhuis, A. G. et al. Rethinking preventive post‐discharge intervention programmes for very preterm infants and their parents. Dev. Med. Child Neurol. 58, 67–73 (2016).

    Article  PubMed  Google Scholar 

  9. Santos, J., Pearce, S. E. & Stroustrup, A. Impact of hospital-based environmental exposures on neurodevelopmental outcomes of preterm infants. Curr. Opin. Pediatr. 27, 254–260 (2015).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  10. Synnes, A. & Hicks, M. Neurodevelopmental outcomes of preterm children at school age and beyond. Clin. Perinatol. 45, 393–408 (2018).

    Article  PubMed  Google Scholar 

  11. Williams, C. N., Kirby, A. & Piantino, J. If you build it, they will come: initial experience with a multi-disciplinary pediatric neurocritical care follow-up clinic. Children (Basel) 4, 83 (2017).

    PubMed  Google Scholar 

  12. Vohr, B. et al. Follow-up care of high-risk infants. Pediatrics 114, 1377–1397 (2004).

  13. McAdams, R. M. et al. Predicting clinical outcomes using artificial intelligence and machine learning in neonatal intensive care units: a systematic review. J. Perinatol. 42, 1561–1575 (2022).

    Article  PubMed  Google Scholar 

  14. Mangold, C. et al. Machine learning models for predicting neonatal mortality: a systematic review. Neonatology 118, 394–405 (2021).

    Article  PubMed  Google Scholar 

  15. Hathaway, Q. A. et al. Machine-learning to stratify diabetic patients using novel cardiac biomarkers and integrative genomics. Cardiovasc. Diabetol. 18, 78 (2019).

    Article  PubMed  PubMed Central  Google Scholar 

  16. Cheraghlou, S., Sadda, P., Agogo, G. O. & Girardi, M. A machine-learning modified cart algorithm informs Merkel cell carcinoma prognosis. Australas. J. Dermatol 62, 323–330 (2021).

    Article  PubMed  Google Scholar 

  17. Sheikhtaheri, A., Zarkesh, M. R., Moradi, R. & Kermani, F. Prediction of neonatal deaths in NICUs: development and validation of machine learning models. BMC Med Inf. Decis. Mak. 21, 131 (2021).

    Article  Google Scholar 

  18. Guedalia, J. et al. Primary risk stratification for neonatal jaundice among term neonates using machine learning algorithm. Early Hum. Dev. 165, 105538 (2022).

    Article  CAS  PubMed  Google Scholar 

  19. Van Laere, D. et al. Machine learning to support hemodynamic intervention in the neonatal intensive care unit. Clin. Perinatol. 47, 435–448 (2020).

    Article  PubMed  Google Scholar 

  20. Boyle, C. A. et al. Trends in the prevalence of developmental disabilities in US children, 1997–2008. Pediatrics 127, 1034–1042 (2011).

    Article  PubMed  Google Scholar 

  21. Holmes, J. F. et al. Validation of a prediction rule for the identification of children with intra-abdominal injuries after Blunt Torso Trauma. Ann. Emerg. Med 54, 528–533 (2009).

    Article  PubMed  Google Scholar 

  22. Eisenbrown, K., Nimmer, M., Ellison, A. M., Simpson, P. & Brousseau, D. C. Which febrile children with sickle cell disease need a chest x-ray? Acad. Emerg. Med 23, 1248–1256 (2016).

    Article  PubMed  Google Scholar 

  23. Rigatti, S. J. Random forest. J. Insur Med. 47, 31–39 (2017).

    Article  PubMed  Google Scholar 

  24. Zhang, Z., Zhao, Y., Canes, A., Steinberg, D. & Lyashevska, O. Predictive analytics with gradient boosting in clinical medicine. Ann. Transl. Med. 7, 152 (2019).

    Article  PubMed  PubMed Central  Google Scholar 

  25. Lu, R. et al. The application of multivariate adaptive regression splines in exploring the influencing factors and predicting the prevalence of Hba1c improvement. Ann. Palliat. Med. 10, 1296–1303 (2021).

    Article  PubMed  Google Scholar 

  26. Brathwaite, R. et al. Predicting the individualized risk of poor adherence to art medication among adolescents living with Hiv in Uganda: The Suubi+Adherence study. J. Int. AIDS Soc. 24, e25756 (2021).

    Article  PubMed  PubMed Central  Google Scholar 

  27. Glinianaia, S. V. et al. Long-term survival of children born with congenital anomalies: a systematic review and meta-analysis of population-based studies. PLoS Med. 17, e1003356 (2020).

    Article  PubMed  PubMed Central  Google Scholar 

  28. Awad, A., Bader-El-Den, M., McNicholas, J. & Briggs, J. Early hospital mortality prediction of intensive care unit patients using an ensemble learning approach. Int. J. Med Inf. 108, 185–195 (2017).

    Article  Google Scholar 

  29. Ye, C. et al. A real-time early warning system for monitoring inpatient mortality risk: prospective study using electronic medical record data. J. Med Internet Res 21, e13719 (2019).

    Article  PubMed  PubMed Central  Google Scholar 

  30. Ambalavanan, N. & Carlo, W. A. Comparison of the prediction of extremely low birth weight neonatal mortality by regression analysis and by neural networks. Early Hum. Dev. 65, 123–137 (2001).

    Article  CAS  PubMed  Google Scholar 

  31. Ambalavanan, N. et al. Prediction of death for extremely low birth weight neonates. Pediatrics 116, 1367–1373 (2005).

    Article  PubMed  Google Scholar 

  32. Warren, M. G. et al. Gastrostomy tube feeding in extremely low birthweight infants: frequency, associated comorbidities, and long-term outcomes. J. Pediatr. 214, 41–46.e45 (2019).

    Article  PubMed  PubMed Central  Google Scholar 

  33. Lagatta, J. M. et al. Actual and potential impact of a home nasogastric tube feeding program for infants whose neonatal intensive care unit discharge is affected by delayed oral feedings. J. Pediatr. 234, 38–45.e32 (2021).

    Article  PubMed  PubMed Central  Google Scholar 

  34. Patra, K. & Greene, M. M. Health care utilization after NICU discharge and neurodevelopmental outcome in the first 2 years of life in preterm infants. Am. J. Perinatol. 35, 441–447 (2018).

    Article  PubMed  Google Scholar 

  35. Gaglioti, P. et al. Fetal cerebral ventriculomegaly: outcome in 176 cases. Ultrasound Obstet. Gynecol. 25, 372–377 (2005).

    Article  CAS  PubMed  Google Scholar 

  36. Brosig, C. L. et al. Preschool neurodevelopmental outcomes in children with congenital heart disease. J. Pediatr. 183, 80–86.e81 (2017).

    Article  PubMed  PubMed Central  Google Scholar 

  37. Patra, K. & Greene, M. M. Impact of feeding difficulties in the NICU on neurodevelopmental outcomes at 8 and 20 months corrected age in extremely low gestational age infants. J. Perinatol. 39, 1241–1248 (2019).

    Article  CAS  PubMed  Google Scholar 

  38. Giannì, M. L. et al. Effect of co-morbidities on the development of oral feeding ability in pre-term infants: a retrospective study. Sci. Rep. 5, 16603 (2015).

    Article  PubMed  PubMed Central  Google Scholar 

  39. Wolthuis-Stigter, M. I. et al. The association between sucking behavior in preterm infants and neurodevelopmental outcomes at 2 years of age. J. Pediatr. 166, 26–30.e21 (2015).

    Article  PubMed  Google Scholar 

Download references

Funding

This project was supported by the National Center for Advancing Translational Sciences, National Institutes of Health, through Grant Numbers UL1TR001436 and TL1TR001437. Its contents are solely the responsibility of the authors and do not necessarily represent the official views of the NIH.

Author information

Authors and Affiliations

  1. Department of Pediatrics, Division of Neonatology, Medical College of Wisconsin, Milwaukee, WI, USA

    Katherine Carlton, Erwin Cabacungan & Susan Cohen

  2. Department of Pediatrics, Division of Quantitative Health Sciences, Medical College of Wisconsin, Milwaukee, WI, USA

    Jian Zhang & Ke Yan

  3. Medical College of Wisconsin, Milwaukee, WI, USA

    Sofia Herrera

  4. Department of Neurology, Division of Neuropsychology, Medical College of Wisconsin, Milwaukee, WI, USA

    Jennifer Koop

Authors
  1. Katherine Carlton
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jian Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Erwin Cabacungan
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Sofia Herrera
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Jennifer Koop
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Ke Yan
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Susan Cohen
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

All authors (K.C., J.Z., E.C., S.H., J.K., K.Y., and S.C.) made substantial contributions to conception, design, and data acquisition, analysis, and interpretation for this manuscript. Authors K.C., E.C., and S.C. drafted the article with authors J.Z., S.H., J.K., and K.Y. providing revisions critically important for the manuscript’s intellectual content. All authors provided final approval of this version to be published.

Corresponding author

Correspondence to Katherine Carlton.

Ethics declarations

Competing interests

The authors declare no competing interests.

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

Carlton, K., Zhang, J., Cabacungan, E. et al. Machine learning risk stratification for high-risk infant follow-up of term and late preterm infants. Pediatr Res (2024). https://doi.org/10.1038/s41390-024-03338-6

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1038/s41390-024-03338-6

  • Springer Nature America, Inc.

Search

Navigation