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

<b>Background/Objectives</b>: 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. <b>Methods</b>: 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. <b>Results</b>: 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. <b>Conclusions</b>: This study identified highly sensitive models for predicting NIV failure in PICU patients, with RF as a robust option.

Authors

Institutions

Publication Details

Journal
Diagnostics
Published
2024-12-19
DOI
https://doi.org/10.3390/diagnostics14242857
Citations
1
Primary Topic
Respiratory Support and Mechanisms
Type
article
Field-Weighted Citation Impact
0.42
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

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

Maria Vittoria Chiaruttini, Maria Cristina Mondardini, Luca Marchetto, Emanuele Rossetti et al.
1 citations
Diagnostics
Respiratory Support and Mechanisms
0.42
article

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

Maria Vittoria Chiaruttini, Maria Cristina Mondardini, Luca Marchetto, Emanuele Rossetti, Corrado Cecchetti, Enzo Picconi, Elisa Zanonato, Pasquale Vitale, Marco Daverio, Immacolata Rulli, Francesca Izzo, Darío Gregori, Giulia Genoni, Angela Amigoni, Giovanna Chidini, Camilla Micalizzi, Andrea Wolfler, Raffaella Sagredini, Giulia Lorenzoni, Nicola Alaimo, Daniela Perrotta, Denise Colosimo, Francesco Sacco, Claudio Nettuno, Silvia Moggia, Giosuè Chisari
article en
1 citations

Abstract

<b>Background/Objectives</b>: 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. <b>Methods</b>: 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. <b>Results</b>: 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. <b>Conclusions</b>: This study identified highly sensitive models for predicting NIV failure in PICU patients, with RF as a robust option.

DiagnosticsVol. 14(24)
University of Padua (IT), IRCCS Materno Infantile Burlo Garofolo (IT), Istituto Giannina Gaslini (IT), Agostino Gemelli University Polyclinic (IT), Fondazione IRCCS Ca' Granda Ospedale Maggiore Policlinico (IT), Magna Graecia University (IT), Azienda Ospedaliera Universitaria Integrata Verona (IT), Ospedale Garibaldi (IT), Meyer Children's Hospital (IT), Bambino Gesù Children's Hospital (IT), Ospedale Regina Margherita (IT), Ospedale dei Bambini Vittore Buzzi (IT), Ospedale Buon Consiglio Fatebenefratelli (IT), Ospedale San Bortolo (IT), Istituti di Ricovero e Cura a Carattere Scientifico (IT), Azienda Ospedaliera Nazionale SS. Antonio e Biagio e Cesare Arrigo (IT)
Openalex Percentile: Top 29%
Respiratory Support and Mechanisms
0.42
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.