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.

  • Comment
  • Published:

Artificial intelligence to classify acquired intestinal injury in preterm neonates—a new perspective

Pediatric Research (2024)Cite this article

The last two decades have seen striking advances in our understanding of necrotizing enterocolitis (NEC) including the role of innate immune signaling in NEC and distinguishing NEC from other intestinal injury phenotypes such as spontaneous intestinal perforation (SIP).1,2,3 Nevertheless, it is recognized that NEC is a potpourri of several intestinal injury phenotypes that affect preterm and term infants varying with respect to pathophysiology, timing of onset and prognosis.1,4,5 The resulting imprecision in diagnosis of intestinal injury phenotypes confounds targeted prevention and treatment strategies. This primarily arises from ambiguity and subjectivity in interpreting clinical and radiological signs that are observer-dependent. To address this limitation, newer definitions of NEC have been proposed that aim to distinguish intestinal injury phenotypes from potentially benign conditions such as feed intolerance.1,6

The increasing awareness that computers (machines) can incorporate diverse data streams such as clinical, epidemiological, and radiological signs has resulted in an explosion of artificial intelligence-based approaches to neonatal diseases confounded by phenotypic heterogeneity and imprecision in diagnosis. Artificial intelligence refers to the capacity of a machine or computer to make interpretations and decisions using mathematical and logical processes akin to the human brain. Within artificial intelligence, machine learning is a subcategory where algorithms enable machines to learn and perform tasks using training data without explicit instructions.7,8 Most current machine learning applications concerning NEC and SIP have predominantly utilized supervised learning. In supervised learning, algorithms are trained on labeled data, with NEC or SIP outcomes predetermined.9,10,11,12,13 Conversely, only a few studies have employed either semi-supervised or unsupervised learning approaches, where the dataset may contain limited or no labeled data or predefined outcomes.14,15,16

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

Access options

Buy this article

  • Purchase on Springer Link
  • Instant access to full article PDF
Buy now

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

References

  1. Caplan, M. S. et al. Necrotizing enterocolitis: Using regulatory science and drug development to improve outcomes. J. Pediatr. 212, 208–215.e1 (2019).

    Article  PubMed  Google Scholar 

  2. Sampath, V., Martinez, M., Caplan, M., Underwood, M. A. & Cuna, A. Necrotizing enterocolitis in premature infants-A defect in the brakes? Evidence from clinical and animal studies. Mucosal Immunol. 16, 208–220 (2023).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  3. Hackam, D. J. & Sodhi, C. P. Toll-like receptor-mediated intestinal inflammatory imbalance in the pathogenesis of necrotizing enterocolitis. Cell Mol. Gastroenterol. Hepatol. 6, 229–238.e1 (2018).

    Article  PubMed  PubMed Central  Google Scholar 

  4. Kim, J. H., Sampath, V. & Canvasser, J. Challenges in diagnosing necrotizing enterocolitis. Pediatr. Res. 88, 16–20 (2020).

    Article  PubMed  Google Scholar 

  5. Gordon, P. V., Swanson, J. R., MacQueen, B. C. & Christensen, R. D. A critical question for NEC researchers: Can we create a consensus definition of NEC that facilitates research progress? Semin Perinatol. 41, 7–14 (2017).

    Article  PubMed  Google Scholar 

  6. Lueschow, S. R., Boly, T. J., Jasper, E., Patel, R. M. & McElroy, S. J. A critical evaluation of current definitions of necrotizing enterocolitis. Pediatr. Res. 91, 590–597 (2022).

    Article  PubMed  Google Scholar 

  7. McElroy, S. J. & Lueschow, S. R. State of the art review on machine learning and artificial intelligence in the study of neonatal necrotizing enterocolitis. Front Pediatr. 11, 1182597 (2023).

    Article  PubMed  PubMed Central  Google Scholar 

  8. Dick, S. Artificial intelligence. Harvard Data Sci. Rev. https://doi.org/10.1162/99608f92.92fe150c (2019).

  9. Lure, A. C. et al. Using machine learning analysis to assist in differentiating between necrotizing enterocolitis and spontaneous intestinal perforation: A novel predictive analytic tool. J. Pediatr. Surg. 56, 1703–1710 (2021).

    Article  PubMed  Google Scholar 

  10. Irles, C. et al. Estimation of neonatal intestinal perforation associated with necrotizing enterocolitis by machine learning reveals new key factors. Int. J. Environ. Res. Public Health 15, 2509 (2018).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  11. Lin, Y. C., Salleb-Aouissi, A. & Hooven, T. A. Interpretable prediction of necrotizing enterocolitis from machine learning analysis of premature infant stool microbiota. BMC Bioinforma. 23, 104 (2022).

    Article  CAS  Google Scholar 

  12. Son, J. et al. Development of artificial neural networks for early prediction of intestinal perforation in preterm infants. Sci. Rep. 12, 12112 (2022).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  13. Song, J. et al. Framework for feature selection of predicting the diagnosis and prognosis of necrotizing enterocolitis. PLoS One 17, e0273383 (2022).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  14. Sylvester, K. G. et al. A novel urine peptide biomarker-based algorithm for the prognosis of necrotising enterocolitis in human infants. Gut 63, 1284–1292 (2014).

    Article  CAS  PubMed  Google Scholar 

  15. Rusconi, B. et al. Gut sphingolipid composition as a prelude to necrotizing enterocolitis. Sci. Rep. 8, 10984 (2018).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  16. Hooven, T. A., Lin, A. Y. C. & Salleb-Aouissi, A. Multiple instance learning for predicting necrotizing enterocolitis in premature infants using microbiome data. Proc. ACM Conf. Health Inference Learn (2020) 2020, 99–109 (2020).

    Article  PubMed  PubMed Central  Google Scholar 

  17. Wolf, M. F. et al. Trends and racial and geographic differences in infant mortality in the United States due to necrotizing enterocolitis, 1999 to 2020. JAMA Netw. Open 6, e231511 (2023).

    Article  PubMed  PubMed Central  Google Scholar 

Download references

Funding

Dr. Cuna received funding from the NIH under K08DK125735. Dr. Sampath’s effort is partially supported by NIH (R01DK117296-05).

Author information

Author notes

  1. These authors contributed equally: Alain Cuna, Muralidhar H. Premkumar.

Authors and Affiliations

  1. Division of Neonatology, Children’s Mercy Kansas City, Kansas City, MO, USA

    Alain Cuna & Venkatesh Sampath

  2. School of Medicine, University of Missouri Kansas City, Kansas City, MO, USA

    Alain Cuna & Venkatesh Sampath

  3. Division of Neonatology, Baylor College of Medicine, Texas Children’s Hospital, Houston, TX, USA

    Muralidhar H. Premkumar

Authors
  1. Alain Cuna
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Muralidhar H. Premkumar
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Venkatesh Sampath
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Venkatesh Sampath.

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.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Cuna, A., Premkumar, M.H. & Sampath, V. Artificial intelligence to classify acquired intestinal injury in preterm neonates—a new perspective. Pediatr Res (2024). https://doi.org/10.1038/s41390-024-03148-w

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1038/s41390-024-03148-w

Search

Advanced search

Quick links