Development and internal validation of a nomogram for identifying severe neonatal pneumonia during early admission: a retrospective cohort study
Translational Pediatrics · 2026-11 · 15 (11) · 455-455
DOI: 10.21037/tp-2026-0920 ↗Kurz gefasst
Kohortenstudie in der Zeitschrift Translational Pediatrics, 2026-11. Verfasst von Yushui Fu und 5 weiteren Autor:innen.
Abstract (Originalsprache)
Background
Neonatal pneumonia is a major cause of neonatal morbidity and mortality worldwide, yet quantitative tools for standardized severity assessment during early admission remain limited. This study aimed to develop and internally validate a nomogram for identifying severe neonatal pneumonia during early admission using routinely available clinical and laboratory indicators.
Methods
This retrospective cohort study included 1,157 hospitalized neonates diagnosed with pneumonia at Hainan Women and Children's Medical Center between January 2021 and December 2025. Pneumonia severity was assessed during early admission. Participants were randomly divided into a training cohort and an internal validation cohort at a ratio of 7:3. Candidate variables were selected using least absolute shrinkage and selection operator (LASSO) regression, followed by multivariable logistic regression to construct the nomogram. Model performance was assessed in terms of discrimination, calibration, and clinical net benefit using receiver operating characteristic analysis, calibration curves, and decision curve analysis.
Results
Severe pneumonia occurred in 409 of 1,157 neonates (35.4%). The training cohort included 290 severe and 522 mild-to-moderate cases, whereas the internal validation cohort included 119 and 226 cases, respectively. LASSO regression selected 12 candidate variables. The final model retained respiratory rate, partial pressure of carbon dioxide (PCO2), lymphocyte count (LYM), monocyte count (MON), eosinophil count (EOS), C-reactive protein (CRP), total protein (TP), albumin (ALB), and blood urea nitrogen (BUN). The area under the receiver operating characteristic curve was 0.785 [95% confidence interval (CI): 0.751–0.818] in the training cohort and 0.789 (95% CI: 0.736–0.841) in the internal validation cohort, indicating acceptable discriminatory ability. Calibration curves showed good agreement between predicted and observed risks, and decision curve analysis suggested potential clinical utility. In a sensitivity analysis excluding respiratory rate, the AUC decreased from 0.785 to 0.738 in the training cohort and from 0.789 to 0.734 in the internal validation cohort (both P
Zitieren
APA
Fu, Y., Chang, M., Zhou, L., Chen, A., Yang, L., & Li, Z. (2026). Development and internal validation of a nomogram for identifying severe neonatal pneumonia during early admission: a retrospective cohort study. Translational Pediatrics, 15(11), 455-455. https://doi.org/10.21037/tp-2026-0920
Vancouver
Fu Y, Chang M, Zhou L, Chen A, Yang L, Li Z. Development and internal validation of a nomogram for identifying severe neonatal pneumonia during early admission: a retrospective cohort study. Translational Pediatrics. 2026;15(11):455-455. doi:10.21037/tp-2026-0920
BibTeX
@article{Fu2026,
author = {Fu, Yushui and Chang, Meng and Zhou, Lijiang and Chen, Aruan and Yang, Ling and Li, Zhihua},
title = {Development and internal validation of a nomogram for identifying severe neonatal pneumonia during early admission: a retrospective cohort study},
journal = {Translational Pediatrics},
year = {2026},
volume = {15},
number = {11},
pages = {455--455},
doi = {10.21037/tp-2026-0920}
}
EUVIMED