EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Immediate postnatal prediction of death or bronchopulmonary dysplasia among very preterm and very low birth weight infants based on gradient boosting decision trees algorithm: A nationwide database study in Japan

Kota Yoneda iD, Tomohisa Seki, Yoshimasa Kawazoe iD, Kazuhiko Ohe, Naoto Takahashi, Neonatal Research Network of Japan

PLOS ONE · 27.03.2024 · 19 (3) · e0300817

DOI: 10.1371/journal.pone.0300817 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 27.03.2024. Verfasst von Kota Yoneda und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pediatrics, The University of Tokyo Hospital, Tokyo, Japan. Hauptthemen laut MEDLINE: Bronchopulmonary Dysplasia, Hypertension, Pulmonary, Premature Birth. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Bronchopulmonary dysplasia (BPD) poses a substantial global health burden. Individualized treatment strategies based on early prediction of the development of BPD can mitigate preterm birth complications; however, previously suggested predictive models lack early postnatal applicability. We aimed to develop predictive models for BPD and mortality based on immediate postnatal clinical data.

Methods

Clinical information on very preterm and very low birth weight infants born between 2008 and 2018 was extracted from a nationwide Japanese database. The gradient boosting decision trees (GBDT) algorithm was adopted to predict BPD and mortality, using predictors within the first 6 h postpartum. We assessed the temporal validity and evaluated model adequacy using Shapley additive explanations (SHAP) values.

Results

We developed three predictive models using data from 39,488, 39,096, and 40,291 infants to predict “death or BPD,” “death or severe BPD,” and “death before discharge,” respectively. These well-calibrated models achieved areas under the receiver operating characteristic curve of 0.828 (95% CI: 0.828–0.828), 0.873 (0.873–0.873), and 0.887 (0.887–0.888), respectively, outperforming the multivariable logistic regression models. SHAP value analysis identified predictors of BPD, including gestational age, size at birth, male sex, and persistent pulmonary hypertension. In SHAP value-based case clustering, the “death or BPD” prediction model stratified infants by gestational age and persistent pulmonary hypertension, whereas the other models for “death or severe BPD” and “death before discharge” commonly formed clusters of low mortality, extreme prematurity, low Apgar scores, and persistent pulmonary hypertension of the newborn.

Conclusions

GBDT models for predicting BPD and mortality, designed for use within 6 h postpartum, demonstrated superior prognostic performance. SHAP value-based clustering, a data-driven approach, formed clusters of clinical relevance. These findings suggest the efficacy of a GBDT algorithm for the early postnatal prediction of BPD.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Bronchopulmonary DysplasiaHypertension, PulmonaryPremature BirthInfantFemaleHumansInfant, NewbornPregnancyJapanInfant, Extremely PrematureInfant, Very Low Birth WeightGestational AgeDecision Trees

Autor:innen und Institutionen

  • Department of Pediatrics, The University of Tokyo Hospital, Tokyo, Japan.
  • Department of Healthcare Information Management, The University of Tokyo Hospital, Tokyo, Japan.
  • Artificial Intelligence and Digital Twin in Healthcare, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan.
  • Department of Biomedical Informatics, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan.

ORCID-Profile: Kota Yoneda, Yoshimasa Kawazoe

Zitieren

APA

Yoneda, K., Seki, T., Kawazoe, Y., Ohe, K., Takahashi, N., & Neonatal Research Network of Japan (2024). Immediate postnatal prediction of death or bronchopulmonary dysplasia among very preterm and very low birth weight infants based on gradient boosting decision trees algorithm: A nationwide database study in Japan. PLOS ONE, 19(3), e0300817. https://doi.org/10.1371/journal.pone.0300817

Vancouver

Yoneda K, Seki T, Kawazoe Y, Ohe K, Takahashi N, Neonatal Research Network of Japan. Immediate postnatal prediction of death or bronchopulmonary dysplasia among very preterm and very low birth weight infants based on gradient boosting decision trees algorithm: A nationwide database study in Japan. PLOS ONE. 2024;19(3):e0300817. doi:10.1371/journal.pone.0300817

BibTeX
@article{Yoneda2024,
  author = {Yoneda, Kota and Seki, Tomohisa and Kawazoe, Yoshimasa and Ohe, Kazuhiko and Takahashi, Naoto and Neonatal Research Network of Japan, Neonatal Research Network of Japan},
  title = {Immediate postnatal prediction of death or bronchopulmonary dysplasia among very preterm and very low birth weight infants based on gradient boosting decision trees algorithm: A nationwide database study in Japan},
  journal = {PLOS ONE},
  year = {2024},
  volume = {19},
  number = {3},
  pages = {e0300817},
  doi = {10.1371/journal.pone.0300817}
}
Kostenlos starten →