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:

Predicting the effectiveness of drugs used for treating cardiovascular conditions in newborn infants

Pediatric Research volume 95, pages 1124–1131 (2024)Cite this article

Abstract

Background

Cardiovascular support (CVS) treatment failure (TF) is associated with a poor prognosis in preterm infants.

Methods

Medical charts of infants with a birth weight <1500 g who received either dopamine (Dp) or dobutamine (Db), were reviewed. Treatment response (TR) occurred if blood pressure increased >3rd centile for gestational age or superior vena cava flow was maintained >55 ml/kg/min, with decreased lactate or less negative base excess, without additional CVS. A predictive model of Dp and Db on TR was designed and the impact of TR on survival was analyzed.

Results

Sixty-six infants (median gestational age 27.3 weeks, median birth weight 864 g) received Dp (n = 44) or Db (n = 22). TR occurred in 59% of the cases treated with Dp and 31% with Db, p = 0.04. Machine learning identified a model that correctly labeled Db response in 90% of the cases and Dp response in 61.4%. Sixteen infants died (9% of the TR group, 39% of the TF group; p = 0.004). Brain or gut morbidity-free survival was observed in 52% vs 30% in the TR and TF groups, respectively (p = 0.08).

Conclusions

New predictive models can anticipate Db but not Dp effectiveness in preterm infants. These algorithms may help the clinicians in the decision-making process.

Impact

  • Failure of cardiovascular support treatment increases the risk of mortality in very low birth weight infants.

  • A predictive model built with machine learning techniques can help anticipate treatment response to dobutamine with high accuracy.

  • Predictive models based on artificial intelligence may guide the clinicians in the decision-making process.

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

Fig. 1: Machine learning models.
Fig. 2: The estimated probability of correctly labeling TR (with the 95% confidence interval) for every single infant receiving dopamine (Dp) and dobutamine (Db) according to the selected model (LR model using L1 regularization technique for Db and L2 regularization for Dp) and following a leave-one-out (LOO) cross-validation methods is represented.
Fig. 3: Relevance of each variable in the model in predicting dopamine treatment success (LR with L2 penalty and C = 0.1).
Fig. 4: Relevance of each variable in predicting dobutamine treatment success (LR with L1 penalty and C = 0.5).

Similar content being viewed by others

Data availability

Data for this study are not publicly available as they contain information that could compromise the privacy of the research participants; however, they may be requested upon signing a data access agreement.

References

  1. Aldana-Aguirre, J. C., Deshpande, P., Jain, A. & Weisz, D. E. Physiology of low blood pressure during the first day after birth among extremely preterm neonates. J. Pediatr. 236, 40–46.e3 (2021).

    Article  PubMed  Google Scholar 

  2. Deshpande, P., Baczynski, M., McNamara, P. J. & Jain, A. Patent ductus arteriosus: the physiology of transition. Semin. Fetal Neonatal Med. 23, 225–231 (2018).

    Article  PubMed  Google Scholar 

  3. Gephart, S. M. et al. Discrimination of GutCheck NEC: a clinical risk index for necrotizing enterocolitis. J. Perinatol. 34, 468–475 (2014).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  4. Bravo, M. C. et al. Randomized, placebo-controlled trial of dobutamine for low superior vena cava flow in infants. J. Pediatr. 167, 572–8.e1-2 (2015).

    Article  CAS  PubMed  Google Scholar 

  5. Osborn, D. A., Evans, N. & Kluckow, M. Haemodynamic and antecedent risk factors of early and late periventricular/intraventricular hemorrhage in premature infants. Pediatrics 112, 33–39 (2003).

    Article  PubMed  Google Scholar 

  6. Plomgaard, A. M. et al. The SafeBoosC II randomized trial: treatment guided by near-infrared spectroscopy reduces cerebral hypoxia without changing early biomarkers of brain injury. Pediatr. Res 79, 528–535 (2016).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  7. Baske, K., Saini, S. S., Dutta, S. & Sundaram, V. Epinephrine versus dopamine in neonatal septic shock: a double-blind randomized controlled trial. Eur. J. Pediatr. 177, 1335–1342 (2018).

    Article  CAS  PubMed  Google Scholar 

  8. Dempsey, E. M. et al. Hypotension in Preterm Infants (HIP) randomised trial. Arch. Dis. Child Fetal Neonatal Ed. 106, F398–F403 (2021).

    Article  Google Scholar 

  9. Ismail, R. et al. Methylene blue versus vasopressin analog for refractory septic shock in the preterm neonate: A randomized controlled trial. J. Neonatal Perinat. Med. 15, 265–273 (2022).

    Article  CAS  Google Scholar 

  10. Giesinger, R. E. & McNamara, P. J. Haemodynamic instability in the critically ill neonate: an approach to cardiovascular support based on disease pathophysiology. Semin. Perinatol. 40, 174–188 (2016).

    Article  PubMed  Google Scholar 

  11. Giesinger, R. E., Hobson, A. A., Bischoff, A. R., Klein, J. M. & McNamara, P. J. Impact of early screening echocardiography and targeted PDA treatment on neonatal outcomes in “22-23” week and “24-26” infants. Semin. Perinatol. 47, 151721 (2023).

    Article  CAS  PubMed  Google Scholar 

  12. Miletin, J., Pichova, K. & Dempsey, E. M. Bedside detection of low systemic flow in the very low birth weight infant on day 1 of life. Eur. J. Pediatr. 168, 809–813 (2009).

    Article  CAS  PubMed  Google Scholar 

  13. de Boode, W. P. et al. The role of Neonatologist Performed Echocardiography in the assessment and management of neonatal shock. Pediatr. Res. 84, 78–88 (2018).

    Article  PubMed  PubMed Central  Google Scholar 

  14. Burns, M. L. et al. Inotropic therapy in newborns, A Population-Based National Registry Study. Pediatr. Crit. Care Med. 17, 948–956 (2016).

    Article  PubMed  Google Scholar 

  15. Pellicer, A. et al. Cardiovascular support for low birth weight infants and cerebral haemodynamics: arandomized, blinded, clinical trial. Pediatrics 115, 1501–1512 (2005)

    Article  PubMed  Google Scholar 

  16. Pellicer, A. et al. Early systemic hypotension and vasopressor support in low birth weight infants: Impact on neurodevelopment. Pediatrics 123, 1369–1376 (2009).

    Article  PubMed  Google Scholar 

  17. Ergenekon, E. et al. Cardiovascular drug therapy for human newborn: review of pharmacodynamic data. Curr. Pharm. Des. 23, 5850–5860 (2017).

    Article  CAS  PubMed  Google Scholar 

  18. Osborn, D. A., Evans, N., Kluckow, M., Bowen, J. R. & Rieger, I. Low superior vena cava flow and effect of inotropes on neurodevelopment to 3 years in preterm infants. Pediatrics 120, 372–380 (2007).

    Article  PubMed  Google Scholar 

  19. Jain, A. et al. Use of targeted neonatal echocardiography to prevent postoperative cardiorespiratory instability after patent ductus arteriosus ligation. J. Pediatr. 160, 584–589 (2012).

    Article  PubMed  Google Scholar 

  20. Kharrat, A. & Jain, A. Haemodynamic dysfunction in neonatal sepsis. Pediatr. Res. 91, 413–424 (2022).

    Article  PubMed  Google Scholar 

  21. Kalfa, D., Agrawal, S., Goldshtrom, N., LaPar, D. & Bacha, E. Wireless monitoring and artificial intelligence: A bright future in cardiothoracic surgery. J. Thorac. Cardiovasc Surg. 160, 809–812 (2020).

    Article  PubMed  Google Scholar 

  22. Krittanawong, C. et al. Future direction for using artificial intelligence to predict and manage hypertension. Curr. Hypertens. Rep. 20, 75 (2018).

    Article  PubMed  Google Scholar 

  23. Obermeyer, Z. & Emanuel, E. J. Predicting the future — big data, machine learning, and clinical medicine. N. Engl. J. Med. 375, 1216–1219 (2016).

    Article  PubMed  PubMed Central  Google Scholar 

  24. Challen, R. et al. Artificial intelligence, bias and clinical safety. BMJ Qual. Saf. 28, 231–237 (2019).

    Article  PubMed  PubMed Central  Google Scholar 

  25. Yoon Na, J. et al. Artificial intelligence model comparison for risk factor analysis of patent ductus arteriosus in nationwide very low birth weight infants cohort. Sci. Rep. 11, 22353 (2021).

    Article  ADS  Google Scholar 

  26. Huang, B. et al. A neonatal dataset and benchmark for non-contact neonatal heart rate monitoring based on spatio-temporal neural networks. Eng. Appl. Artif. Intell. 106, 104447 (2021).

    Article  Google Scholar 

  27. Ghazal S., et al. Using machine learning models to predict oxygen saturation following ventilator support adjustment in critically ill children: a single center pilot study. PLoS ONE 14, e0198921 (2019).

  28. Lin, A. et al. Artificial intelligence: improving the efficiency of cardiovascular imaging. Expert Rev. Med. Devices 17, 565–577 (2020).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  29. Jayakumar, P. et al. Comparison of an artificial intelligence-enabled patient decision aid vs educational material on decision quality, shared decision-making, patient experience, and functional outcomes in adults with knee osteoarthritis: a randomized clinical trial. JAMA Netw. Open 4, e2037107 (2021).

    Article  PubMed  PubMed Central  Google Scholar 

  30. Bravo, M. C. et al. Validity of biomarkers of early circulatory impairment to predict outcome: A retrospective analysis. Front. Pediatr. 7, 212 (2019).

    Article  PubMed  PubMed Central  Google Scholar 

  31. Dempsey, E. M. et al. Hypotension in Preterm Infants (HIP) randomised trial On behalf of the HIP consortium. Arch. Dis. Child Fetal Neonatal Ed. 106, 398–403 (2021).

    Article  PubMed  Google Scholar 

  32. Agut, T. et al. Preterm white matter injury: ultrasound diagnosis and classification. Pediatr. Res. 87, 37–49 (2020).

    Article  PubMed  PubMed Central  Google Scholar 

  33. Parodi, A. et al. Cranial ultrasound findings in preterm germinal matrix haemorrhage, sequelae and outcome. Pediatr. Res. 87, 13–24 (2020).

    Article  PubMed  PubMed Central  Google Scholar 

  34. 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 

  35. Troyanskaya, O. et al. Missing value estimation methods for DNA microarrays. Bioinformatics 17, 520–525 (2001).

    Article  CAS  PubMed  Google Scholar 

  36. de Boode, W. P. Advanced haemodynamic monitoring in the neonatal intensive care unit. Clin. Perinatol. 47, 423–434 (2020).

    Article  PubMed  Google Scholar 

  37. Pellicer, A. et al. The SafeBoosC phase II randomised clinical trial: a treatment guideline for targeted near-infrared-derived cerebral tissue oxygenation versus standard treatment in extremely preterm infants. Neonatology 104, 171–178 (2013).

    Article  CAS  PubMed  Google Scholar 

  38. Osborn, D., Evans, N. & Kluckow, M. Randomized trial of dobutamine versus dopamine in preterm infants with low systemic blood flow. J. Pediatr. 140, 183–191 (2002).

    Article  CAS  PubMed  Google Scholar 

  39. Repici, A. et al. Artificial intelligence and colonoscopy experience: Lessons from two randomised trials. Gut 71, 757–765 (2022).

    Article  PubMed  Google Scholar 

  40. Batton, B. et al. Use of antihypotensive therapies in extremely preterm infants. Pediatrics 131, e1865–e1873 (2013).

    Article  PubMed  PubMed Central  Google Scholar 

  41. Dempsey, E. & Rabe, H. The use of cardiotonic drugs in neonates. Clin. Perinatol. 46, 273–290 (2019).

    Article  PubMed  Google Scholar 

  42. Paradisis, M., Evans, N., Kluckow, M., Osborn, D. & McLachlan, A. J. Pilot study of milrinone for low systemic blood flow in very preterm infants. J. Pediatr. 148, 306–313 (2006).

    Article  CAS  PubMed  Google Scholar 

Download references

Funding

The authors have no potential conflict of interest. The first author, who wrote the first draft, did not receive a fee for producing the manuscript. The corresponding author acknowledges the financial support of the Spanish Health Research Fund (Fondo de Investigación Sanitaria), grant PI22/00567. EP-H acknowledges the support from the Spanish State Research Agency (AEI), project PID2020-115363RB-I00.

Author information

Authors and Affiliations

  1. Department of Neonatology, La Paz University Hospital and IdiPaz (La Paz Hospital Institute for Health Research), Madrid, Spain

    María Carmen Bravo, Raquel Jiménez & Adelina Pellicer

  2. Department of Signal Theory and Communications, Carlos III University, Madrid, Spain

    Raquel Jiménez

  3. Navarra University, Madrid, Spain

    Emilio Parrado-Hernández & Juan José Fernández

Authors
  1. María Carmen Bravo
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Raquel Jiménez
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Emilio Parrado-Hernández
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Juan José Fernández
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Adelina Pellicer
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

MCB conceptualized and designed the study, drafted the initial manuscript, performed the initial analyses and approved the final manuscript as submitted. RJ collected the patient data, completed the electronic dataset and approved the final manuscript as submitted. EPH designed the data collection instruments, analyzed the data, reviewed the manuscript and approved the final manuscript as submitted. JJF designed the data collection instruments, analyzed the data, reviewed the manuscript and approved the final manuscript as submitted. AP conceptualized and designed the study, drafted the initial manuscript, performed the initial analyses and approved the final manuscript as submitted.

Corresponding author

Correspondence to María Carmen Bravo.

Ethics declarations

Competing interests

The authors declare no competing interests.

Ethics approval and consent to participate

This project received ethical approval from the La Paz University Hospital Ethics Committee. Because it was a retrospective study, patient consent to participate was not necessary.

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

Bravo, M.C., Jiménez, R., Parrado-Hernández, E. et al. Predicting the effectiveness of drugs used for treating cardiovascular conditions in newborn infants. Pediatr Res 95, 1124–1131 (2024). https://doi.org/10.1038/s41390-023-02964-w

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s41390-023-02964-w

Search

Advanced search

Quick links