Combining artificial intelligence and conventional statistics to predict bronchopulmonary dysplasia in very preterm infants using routinely collected clinical variables
Pediatric Pulmonology · 2024-12 · 59 (12) · 3400-3409
DOI: 10.1002/ppul.27216 ↗Kurz gefasst
Fachartikel in der Zeitschrift Pediatric Pulmonology, online erschienen am 16.08.2024. Verfasst von Sara Montagna und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pure and Applied Sciences (DiSPeA), University of Urbino Carlo Bo, Urbino, Italy. Hauptthemen laut MEDLINE: Bronchopulmonary Dysplasia, Artificial Intelligence, Infant, Premature. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: None.
Abstract (Originalsprache)
Background
Prematurity is the strongest predictor of bronchopulmonary dysplasia (BPD). Most previous studies investigated additional risk factors by conventional statistics, while the few studies applying artificial intelligence, and specifically machine learning (ML), for this purpose were mainly targeted to the predictive ability of specific interventions. This study aimed to apply ML to identify, among routinely collected data, variables predictive of BPD, and to compare these variables with those identified through conventional statistics.
Methods
Very preterm infants were recruited; antenatal, perinatal, and postnatal clinical data were collected. A BPD prediction model was built using conventional statistics, and nine supervised ML algorithms were applied for the same purpose: the results of the best‐performing model were described and compared with those of conventional statistics.
Results
Both conventional statistics and ML identified the degree of immaturity (low gestational age and/or birth weight), need for mechanical ventilation, and absent or reversed end diastolic flow (AREDF) in the umbilical arteries as risk factors for BPD. Each of the two approaches also identified additional potentially predictive clinical variables.
Conclusion
ML algorithms might be useful to integrate conventional statistics in identifying novel risk factors, in addition to prematurity, for the development of BPD in very preterm infants. Specifically, the identification of AREDF status as an independent risk factor for BPD by both conventional statistics and ML highlights the opportunity to include detailed antenatal information in clinical predictive models for neonatal diseases.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Pure and Applied Sciences (DiSPeA), University of Urbino Carlo Bo, Urbino, Italy.
- Department of Medical and Surgical Sciences, University of Bologna, Bologna, Italy.
- Neonatal Intensive Care Unit, IRCCS AOU BO, Bologna, Italy.
- Department of Computer Science and Engineering, University of Bologna, Bologna, Italy.
- Obstetric Unit, IRCCS AOU BO, Bologna, Italy.
ORCID-Profile: Arianna Aceti
Förderung
- None
Zitieren
APA
Montagna, S., Magno, D., Ferretti, S., Stelluti, M., Gona, A., Dionisi, C., Simonazzi, G., Martini, S., Corvaglia, L., & Aceti, A. (2024). Combining artificial intelligence and conventional statistics to predict bronchopulmonary dysplasia in very preterm infants using routinely collected clinical variables. Pediatric Pulmonology, 59(12), 3400-3409. https://doi.org/10.1002/ppul.27216
Vancouver
Montagna S, Magno D, Ferretti S, Stelluti M, Gona A, Dionisi C, et al. Combining artificial intelligence and conventional statistics to predict bronchopulmonary dysplasia in very preterm infants using routinely collected clinical variables. Pediatric Pulmonology. 2024;59(12):3400-3409. doi:10.1002/ppul.27216
BibTeX
@article{Montagna2024,
author = {Montagna, Sara and Magno, Dalila and Ferretti, Stefano and Stelluti, Michele and Gona, Andrea and Dionisi, Camilla and Simonazzi, Giuliana and Martini, Silvia and Corvaglia, Luigi and Aceti, Arianna},
title = {Combining artificial intelligence and conventional statistics to predict bronchopulmonary dysplasia in very preterm infants using routinely collected clinical variables},
journal = {Pediatric Pulmonology},
year = {2024},
volume = {59},
number = {12},
pages = {3400--3409},
doi = {10.1002/ppul.27216}
}
EUVIMED