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:

Predictive model development for premature infant extubation outcomes: development and analysis

Pediatric Research volume 97, pages 2423–2430 (2025)Cite this article

Abstract

Background

Given the knowledge of the damage caused by prolonged invasive mechanical ventilation in premature newborns, withdrawing this support as quickly as possible is important to minimize morbidity. The aim of this study was to analyze the variables associated with extubation outcomes and to develop a predictive model for successful extubation in premature newborns.

Methods

Data were obtained from a multicenter study involving six public maternity hospitals. The variables with the highest correlation to the extubation outcome were used to construct the predictive model through data analysis and machine learning methods, followed by training and testing of algorithms.

Results

Data were collected from 405 premature newborns. The predictive model with the best metrics was trained and tested using the variables of gestational age, birth weight, weight at extubation, congenital infections, and time on invasive mechanical ventilation, based on 393 samples according to the extubation outcome (12 were discarded due to irretrievable missing data in important attributes). The model exhibited an accuracy of 77.78%, sensitivity of 79.41%, and specificity of 60%.

Conclusion

These variables generated a predictive model capable of estimating the probability of successful extubation in premature newborns.

Impact

  • Prolonged use of invasive mechanical ventilation in preterm newborns increases morbidity/mortality rates, emphasizing the importance of early withdrawal from invasive ventilatory support. However, the decision to extubate lacks tools with higher extubation outcome precision.

  • The use of artificial intelligence through the construction of a predictive model can assist in the decision-making process for extubating preterm newborns based on real-world data.

  • The implementation of this tool can optimize the decision to extubate preterm newborns, promoting successful extubation and reducing preterm newborns exposure to adverse events associated with extubation failure.

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: Confusion matrix model.
Fig. 2: Confusion matrix of the predictive model.

Similar content being viewed by others

References

  1. Stoll, B. J. et al. Trends in care practices, morbidity, and mortality of extremely preterm neonates, 1993-2012. JAMA 314, 103951 (2015).

    Article  Google Scholar 

  2. Chawla, S. et al. Markers of successful extubation in extremely preterm infants, and morbidity after failed extubation. J. Pediatr. 189, 113–119 (2017).

    Article  PubMed  PubMed Central  Google Scholar 

  3. Espíndola C. S. et al. Factors associated with the use of oxygen therapy and ventilatory support in premature newborns. Rev Pesqui Fisioter 12, https://doi.org/10.17267/2238-2704rpf.2022.e4921 (2022).

  4. Vliegenthart, R. J. S., van Kaan, A. H., Aarnoudse-Moens, C. S. H., van Wassenaer, A. G. & Onland, W. Duration of mechanical ventilation and neurodevelopment in preterm infants. Arch. Dis. Child Fetal Neonatal Ed. 104, 631–635 (2019).

    Article  Google Scholar 

  5. Choi, Y. B., Lee, J., Park, J. & Jun, Y. H. Impact of prolonged mechanical ventilation in very low birth weight infants: results from a national cohort study. J. Pediatr. 194, 34–39 (2018).

    Article  PubMed  Google Scholar 

  6. Gupta, D. et al. Respiratory setback associated with extubation failure in extremely preterm infants. Pediatr. Pulmonol. 56, 2081–2086 (2021).

    Article  PubMed  Google Scholar 

  7. Kidman, A. M., Manley, B. J., Boland, R. A., Davis, P. G. & Bhatia, R. Predictor and outcomes of extubation failure in extremely preterm infants. J. Paediatr. Child Health 57, 913–919 (2021).

    Article  PubMed  Google Scholar 

  8. Ministry of Health of Brazil.Maternal and Neonatal care: NHA provides important data in supplementary health. National Supplementary Health Agency, 2022. Available in: https://www.gov.br/ans/pt-br/assuntos/noticias/sobre-ans/atencao-materna-e-neonatal-ans-disponibiliza-dados-importantes-na-saude-suplementar

  9. Kwok, T. C. et al. Application and potential of artificial intelligence in neonatal medicine. Semin Fetal Neonatal Med 27, 101346 (2022).

    Article  PubMed  Google Scholar 

  10. Dai D. et al. Bronchopulmonary dysplasia predicted by developing a machine learning model of genetic and clinical information. Front Genet. 12, https://doi.org/10.3389/fgene.2021.689071 (2021).

  11. Cabrera-Quiros, L., kommers, D., Wolvers, M. K. & Oosterwijk, L. Prediction of late-onset sepsis in preterm infants using monitoring signals and machine learning. Crit. Care Explor 3, e0302 (2021).

    PubMed  PubMed Central  Google Scholar 

  12. Jin, Y. et al. Identification of infants at high-risk for autism spectrum disorder using multiparameter multiscale White matter connectivity networks. Hum. Brain Mapp. 36, 4880–4896 (2015).

    Article  PubMed  PubMed Central  Google Scholar 

  13. Mueller, M. et al. Predicting extubations outcome in preterm newborns: a comparison of neural networks with clinical expertise and statistical modeling. Pediatr. Res. 56, 11–18 (2004).

    Article  PubMed  Google Scholar 

  14. Mueller, M., Almeida, J. S., Stanislaus, R. & Wagner, C. L. Can machine learning methods predict extubation outcome in premature infants as well as cliniciams? J. Neonatal Biol. 2, 1000118 (2013).

    PubMed  PubMed Central  Google Scholar 

  15. Kanbar, L. J. et al. Automated prediction of extubation success in extremely preterm infants: the APEX multicenter study. Pediatr. Res 93, 1041–1049 (2023).

    Article  CAS  PubMed  Google Scholar 

  16. Portney, L. G. Foundations of Clinical Research: Applications to Evidence-Based Practice. 4th edn (ed. Davis, F. A.) (2020).

  17. Rossum, G. V. Python reference manual. Department of Computer Science, CWI (1995).

  18. Chollet, F. Keras. GitHub, 2015. Available: https://github.com/keras-team/keras.

  19. Ohnstad, M. O., Stensvold, H. J., Tvedt, C. R. & Ronnestad, A. E. Duration of mechanical ventilation and extubation success among extremely premature infants. Neonatology 118, 90–97 (2021).

    Article  PubMed  Google Scholar 

  20. He, F. et al. Predictors of extubation outcomes among extremely and very preterm infants: a retrospective cohort study. J. Pediatr. 98, 648–654 (2022).

    Article  Google Scholar 

  21. Shalish, W., Latremouille, S., Papenburg, J. & Sant’Anna, G. M. ’ Predictors of extubation readiness in preterm infants: a systematic review and meta-analysis. Arch. Dis. Child Fetal Neonatal 104, F89–F97 (2019).

    Article  Google Scholar 

  22. Shalish, W. et al. The impact of time interval between extubation and reintubation on death or bronchopulmonary dysplasia in extremely preterm infants. J. Pediatr. 205, 70–76 (2018).

    Article  PubMed  Google Scholar 

  23. Ohnstad, M. O. et al. Predictors of extubation success: a population-based study of neonates below a gestacional age of 26 weeks. BMJ Paediatrics Open 6, e001542 (2022).

    Article  PubMed  PubMed Central  Google Scholar 

  24. Manley, B., Doyle, L. W., Owen, L. S. & Davis, P. G. Extubating extremely preterm infants: predictors of success and outcomes following failure. J. Pediatr. 173, 45–49 (2016). 2016.

    Article  PubMed  Google Scholar 

  25. World Health Organization. Preterm birth [internet]. Geneva: WHO, up date Feb 2018. Disponível em: http://www.who.int/mediacenter/factsheets/fs363/en/

  26. Teixeira, R. F. et al. Factors associated with extubation failure in very low birth weight infants: a cohort study in the northeast Brazil. J. Perinat. Med 49, 506–513 (2021).

    Article  PubMed  Google Scholar 

  27. Oswaldo Cruz Foundation.National Institute of health for women, children and adolescents Fernandes Figueira. Portal of best practices in Women’s, Children’s, and Adolescent Health: minimal handling of the newborn, 2018. Available: http://portaldeboaspraticas.iff.fiocruz.br/atencao/recem-nascido/manuseio-minimo-do-recem-nascido/.

  28. Lourenço, A. F. E. et al. TORCH group infections: epidemiological and laboratory analysis of a high-risk pregnancy group enphasis no toxoplasma gondii infections. Rev Goiana de Medicina 45, 11–16 (2014).

  29. Gupta, D. et al. A predictive model for extubation readiness in extremely preterm infants. J. Perinatol. 39, 1663–1669 (2019).

    Article  PubMed  Google Scholar 

  30. Patino, C. M. & Ferreira, J. C. Internal and external validity: can you apply research study results to your patinete? J. Bras. Pneumol. 44, 183–183 (2018).

    Article  PubMed  PubMed Central  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Master of Physiotherapy - Santa Catarina State University, Florianópolis, Santa Catarina, Brazil

    Camila S. Espíndola & Emanuella C. Cordeiro

  2. Department of Computer Science and faculty member of the Graduate Program in Applied Computing - Santa Catarina State University, Joinville, Santa Catarina, Brazil

    Yuri K. Lopes

  3. Bachelor’s Degree in Computer Science and Postgraduate student of the Graduate Program in Applied Computing - Santa Catarina State University, Joinville, Santa Catarina, Brazil

    Grasiela S. Ferreira

  4. Department of Physiotherapy and faculty member of the Graduate Program in Physiotherapy - Rio Grande do Norte Federal University, Natal, Rio Grande do Norte, Brazil

    Silvana A. Pereira

  5. Department of Physiotherapy and faculty member of the Graduate Program in Physiotherapy - Santa Catarina State University, Florianópolis, Santa Catarina, Brazil

    Dayane Montemezzo

Authors
  1. Camila S. Espíndola
    View author publications

    Search author on:PubMed Google Scholar

  2. Yuri K. Lopes
    View author publications

    Search author on:PubMed Google Scholar

  3. Grasiela S. Ferreira
    View author publications

    Search author on:PubMed Google Scholar

  4. Emanuella C. Cordeiro
    View author publications

    Search author on:PubMed Google Scholar

  5. Silvana A. Pereira
    View author publications

    Search author on:PubMed Google Scholar

  6. Dayane Montemezzo
    View author publications

    Search author on:PubMed Google Scholar

Contributions

Substantial contributions to conception and design, acquisition of data, or analysis and interpretation of data: Camila S. Espíndola, Yuri K Lopes, Grasiela S Ferreira, Emanuella C Cordeiro, Silvana A Pereira, Dayane Montemezzo. Drafting the article or revising it critically for important intellectual content: Camila S. Espíndola, Yuri K Lopes, Grasiela S Ferreira, Dayane Montemezzo. Final approval of the version to be published: Camila S. Espíndola, Yuri K Lopes, Grasiela S Ferreira, Emanuella C Cordeiro, Silvana A Pereira, Dayane Montemezzo.

Corresponding author

Correspondence to Dayane Montemezzo.

Ethics declarations

Competing interests

The authors declare no competing interests.

Ethical approval

Patient consente was not required. This study was approved by the Human Research Ethics Committee of UDESC - CAAE 36371320.5.1001.0118. In accordance with the Brazilian resolution (CNS N° 510/2016), this study did not require consente term as it involved secondary data without identifying participants.

Additional information

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

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

Espíndola, C.S., Lopes, Y.K., Ferreira, G.S. et al. Predictive model development for premature infant extubation outcomes: development and analysis. Pediatr Res 97, 2423–2430 (2025). https://doi.org/10.1038/s41390-024-03643-0

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Version of record:

  • Issue date:

  • DOI: https://doi.org/10.1038/s41390-024-03643-0

Search

Advanced search

Quick links