Applications of Data Science Techniques in Predicting Mortality among Pediatric ARDS Patients: A Medico-Statistical Approach

Authors

  • Peddapalegani Palavardhan
  • M. Bhupathi Naidu
  • Akkyam Vani
  • Mohammad Reshma

Keywords:

N\A

Abstract

This study explores the application of data science techniques in identifying key predictors of mortality among pediatric patients with Acute Respiratory Distress Syndrome (ARDS). A retrospective analysis was conducted on 200 mechanically ventilated patients admitted to the Pediatric Intensive Care Unit (PICU) of the Department of Pediatrics, Malla Reddy Narayana Multispeciality Hospital. Clinical and ventilatory variables at 0 and 24 hours were analyzed using Python. Statistical methods included descriptive statistics, paired t-tests, point-biserial correlation, and multivariable logistic regression. Variance Inflation Factor (VIF) was applied to address multicollinearity, and ROC curve analysis was used to assess model performance. The Sequential Organ Failure Assessment (SOFA) score and Pediatric Risk of Mortality (PRISM) score emerged as significant independent predictors of mortality. The final logistic model achieved an AUC of 0.85, with a sensitivity of 77.3% and specificity of 84.4%. These findings highlight the potential of integrating data science techniques into clinical prediction modeling to improve early risk stratification in pediatric ARDS.

Downloads

Download data is not yet available.

References

Amini, M., Ebrahimzadeh, S., & Azizi, R. (2021). Machine learning approaches in ICU outcome prediction: A systematic review. Journal of Biomedical Informatics, 119, 103792. https://doi.org/10.1016/j.jbi.2021.103792

Bellani, G., Laffey, J. G., Pham, T., et al. (2016). Epidemiology, patterns of care, and mortality for patients with acute respiratory distress syndrome in intensive care units in 50 countries. JAMA, 315(8), 788–800. https://doi.org/10.1001/jama.2016.0291

Bhakta, P., & Saluja, M. (2020). Paediatric ARDS: Review of current concepts. Indian Journal of Pediatrics, 87(10), 792–798. https://doi.org/10.1007/s12098-020-03264-7

Flori, H. R., Spaeder, M. C., Brady, P. W., et al. (2020). Time-dependent factors associated with mortality in pediatric acute respiratory distress syndrome. Pediatric Critical Care Medicine, 21(4), 335–343.

Goh, A. Y., Lum, L. C., & Chan, P. W. (2022). Predictive value of PRISM and SOFA scores in pediatric intensive care. Journal of Pediatric Intensive Care, 11(3), 211–218.

Gupta, R. G., Hartigan, S. M., Kashiouris, M. G., et al. (2021). Role of mechanical power in ventilator-induced lung injury: Recent evidence. Critical Care Clinics, 37(4), 849–866.

Hager, D. N., Krishnan, J. A., Hayden, D. L., Brower, R. G., & ARDS Network. (2005). Tidal volume reduction in ARDS: A multicentre trial. Chest, 128(1), 394–403.

Helviz, Y., & Einav, S. (2018). A systematic review of adult and pediatric high-flow nasal cannula oxygen therapy.

Journal of Clinical Monitoring and Computing, 32(4), 687–703.

Hulley, S. B., Cummings, S. R., Browner, W. S., Grady, D. G., & Newman, T. B. (2013). Designing clinical research

(4th ed.). Lippincott Williams & Wilkins.

Khemani, R. G., Smith, L. S., Zimmerman, J. J., & Erickson, S. (2015). Pediatric acute respiratory distress syndrome: definition, incidence, and epidemiology. Pediatric Critical Care Medicine, 16(5_suppl), S23–S40.

Kuhn, M., & Johnson, K. (2013). Applied predictive modeling. Springer.

Liu, Y., Zhang, Z., Wang, Y., & Wang, H. (2023). Vasoactive-inotropic score and outcomes in pediatric critical care: A review. Frontiers in Pediatrics, 11, 1132450. https://doi.org/10.3389/fped.2023.1132450

Lundberg, S. M., & Lee, S. I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30, 4765–4774.

Marini, J. J., & Gattinoni, L. (2020). Management of COVID-19 respiratory distress. JAMA, 323(22), 2329–2330. https://doi.org/10.1001/jama.2020.6825

Mehta, N. M., & Turner, D. A. (2018). Acute lung injury and ARDS in children: Updates and controversies. Critical Care Clinics, 34(2), 377–398.

Modesto i Alapont, V., & Medina, A. (2020). Predicting pediatric ARDS outcomes using AI-based models: New directions. Frontiers in Pediatrics, 8, 578147. https://doi.org/10.3389/fped.2020.578147

Panwar, R., Hardie, M., Bellomo, R., et al. (2016). Conservative vs. liberal oxygen therapy in ARDS: A meta-analysis.

The Lancet Respiratory Medicine, 4(11), 938–946.

Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., ... & Duchesnay, É. (2011). Scikit- learn: Machine learning in Python. Journal of Machine Learning Research, 12, 2825–2830.

Pollack, M. M., Ruttimann, U. E., & Getson, P. R. (1988). Pediatric risk of mortality (PRISM) score. Critical Care Medicine, 16(11), 1110–1116.

Rajpurkar, P., Chen, E., Banerjee, O., & Topol, E. J. (2022). AI in health and medicine. Nature Medicine, 28(1), 31– 38. https://doi.org/10.1038/s41591-021-01614-0

Rimensberger, P. C. (2017). The open lung concept in pediatric ARDS. Pediatric Pulmonology, 52(S48), S34–S40.

Riviello, E. D., Kiviri, W., Fowler, R. A., et al. (2016). Predicting mortality in resource-limited ARDS settings. Critical Care, 20(1), 257.

Sauthier, M., & Jouvet, P. (2019). Sedation practices in pediatric intensive care: An evolving science. Pediatric Critical Care Medicine, 20(7), 669–678.

Sweeney, T. E., & Khatri, P. (2017). Benchmarking machine learning methods for mortality prediction. Nature Communications, 8, 13721. https://doi.org/10.1038/ncomms13721

Topol, E. J. (2019). High-performance medicine: the convergence of human and artificial intelligence. Nature Medicine, 25(1), 44–56.

Vincent, J. L., Moreno, R., Takala, J., et al. (1996). The SOFA score to describe organ dysfunction/failure. Intensive Care Medicine, 22(7), 707–710.

Yehya, N., & Thomas, N. J. (2017). Disassociating lung mechanics and oxygenation in pediatric ARDS. Critical Care Medicine, 45(7), 1232–1239.

Zimmerman, J. J., & Akhtar, S. (2020). Machine learning in pediatric intensive care. Current Opinion in Pediatrics, 32(3), 360–366.

Downloads

Published

2025-06-03

How to Cite

1.
Palavardhan P, Naidu MB, Vani A, Reshma M. Applications of Data Science Techniques in Predicting Mortality among Pediatric ARDS Patients: A Medico-Statistical Approach. J Neonatal Surg [Internet]. 2025 Jun. 3 [cited 2025 Dec. 13];14(7):1118-31. Available from: https://www.jneonatalsurg.com/index.php/jns/article/view/6994

Issue

Vol. 14 No. 7 (2025): Journal of Neonatal Surgery

Section

Original Article

License

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

You are free to:

  • Adapt — remix, transform, and build upon the material for any purpose, even commercially.

Terms:

  • Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
  • No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.