Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Dec 19;14(24):2857.
doi: 10.3390/diagnostics14242857.

Non-Invasive Ventilation Failure in Pediatric ICU: A Machine Learning Driven Prediction

Maria Vittoria Chiaruttini  1 , Giulia Lorenzoni  1 , Marco Daverio  2 , Luca Marchetto  2 , Francesca Izzo  3 , Giovanna Chidini  4 , Enzo Picconi  5 , Claudio Nettuno  6 , Elisa Zanonato  7 , Raffaella Sagredini  8 , Emanuele Rossetti  9 , Maria Cristina Mondardini  10 , Corrado Cecchetti  11 , Pasquale Vitale  12 , Nicola Alaimo  13 , Denise Colosimo  14 , Francesco Sacco  15 , Giulia Genoni  16 , Daniela Perrotta  17 , Camilla Micalizzi  18 , Silvia Moggia  19 , Giosuè Chisari  20 , Immacolata Rulli  21 , Andrea Wolfler  22 , Angela Amigoni  2 , Dario Gregori  1
Affiliations

Non-Invasive Ventilation Failure in Pediatric ICU: A Machine Learning Driven Prediction

Maria Vittoria Chiaruttini et al. Diagnostics (Basel). .

Abstract

Background/Objectives: Non-invasive ventilation (NIV) has emerged as a possible first-step treatment to avoid invasive intubation in pediatric intensive care units (PICUs) due to its advantages in reducing intubation-associated risks. However, the timely identification of NIV failure is crucial to prevent adverse outcomes. This study aims to identify predictors of first-attempt NIV failure in PICU patients by testing various machine learning techniques and comparing their predictive abilities. Methods: Data were sourced from the TIPNet registry, which comprised patients admitted to 23 Italian Paediatric Intensive Care Units (PICUs). We selected patients between January 2010 and January 2024 who received non-invasive ventilation (NIV) as their initial approach to respiratory support. The study aimed to develop a predictive model for NIV failure, selecting the best Machine Learning technique, including Generalized Linear Models, Random Forest, Extreme Gradient Boosting, and Neural Networks. Additionally, an ensemble approach was implemented. Model performances were measured using sensitivity, specificity, AUROC, and predictive values. Moreover, the model calibration was evaluated. Results: Out of 43,794 records, 1861 admissions met the inclusion criteria, with 678 complete cases and 97 NIV failures. The RF model demonstrated the highest AUROC and sensitivity equal to 0.83 (0.64, 0.94). Base excess, weight, age, systolic blood pressure, and fraction of inspired oxygen were identified as the most predictive features. A check for model calibration ensured the model's reliability in predicting NIV failure probabilities. Conclusions: This study identified highly sensitive models for predicting NIV failure in PICU patients, with RF as a robust option.

Keywords: NIV; NIV failure; PICU; TIPNet; machine learning; non-invasive ventilation; predictive models; random forest.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflicts of interest.

Figures

Figure 1
Figure 1
Bagging vs. boosting algorithm.
Figure 2
Figure 2
VIMP (%) calculated by the RF model for the top 10 ranked predictors. Each bar is colored according to its importance: dark blue (higher importance), light blue (lower importance).
Figure 3
Figure 3
Calibration plot using predicted probabilities by RF model.
See this image and copyright information in PMC

References

    1. Mortamet G., Emeriaud G., Jouvet P., Fauroux B., Essouri S. Intérêt de la ventilation non invasive en réanimation pédiatrique: Doit-on espérer un autre niveau de preuve ? Arch. De Pédiatrie. 2017;24:58–65. doi: 10.1016/j.arcped.2016.10.012. - DOI - PubMed
    1. Ganu S.S., Gautam A., Wilkins B., Egan J. Increase in use of non-invasive ventilation for infants with severe bronchiolitis is associated with decline in intubation rates over a decade. Intensive Care Med. 2012;38:1177–1183. doi: 10.1007/s00134-012-2566-4. - DOI - PubMed
    1. Al-Mukhaini K.S., Al-Rahbi N.M. Noninvasive Ventilation and High-Flow Nasal Cannulae Therapy for Children with Acute Respiratory Failure: An overview. Sultan Qaboos Univ. Med. J. 2018;18:278. doi: 10.18295/squmj.2018.18.03.003. - DOI - PMC - PubMed
    1. Al Sutari M.M., Abdalrahim M.S., Hamdan-Mansour A.M., Ayasrah S.M. Pain among mechanically ventilated patients in critical care units. J. Res. Med. Sci. 2014;19:726–732. - PMC - PubMed
    1. Ferreyro B.L., Angriman F., Munshi L., Del Sorbo L., Ferguson N.D., Rochwerg B., Ryu M.J., Saskin R., Wunsch H., da Costa B.R., et al. Association of Noninvasive Oxygenation Strategies With All-Cause Mortality in Adults With Acute Hypoxemic Respiratory Failure: A Systematic Review and Meta-analysis. JAMA. 2020;324:57. doi: 10.1001/jama.2020.9524. - DOI - PMC - PubMed

LinkOut - more resources