Diagnostic Accuracy of Large Language Models for Pediatric Chest Radiograph: Comparison With Pediatricians and Radiologists
Pediatric Pulmonology · 2026-11 · 61 (11)
DOI: 10.1002/ppul.71916 ↗Kurz gefasst
Beobachtungsstudie in der Zeitschrift Pediatric Pulmonology, online erschienen am 14.11.2026. Verfasst von Luis Bachiller Carnicero und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pediatrics, Segovia General Hospital, Segovia, Spain. Hauptthemen laut MEDLINE: Large Language Models, Radiography, Thoracic, Radiologists, Pediatricians. Die Arbeit nennt 39 Literaturangaben.
Abstract (Originalsprache)
Introduction
Chest radiography (CR) is the most widely used radiological test in pediatrics, yet its interpretation remains heterogeneous. Although large language models (LLMs) such as ChatGPT and Perplexity are not designed for medical use, their widespread use justifies evaluating their performance in healthcare. We compared ChatGPT and Perplexity with radiologists and pediatricians, assessing both their screening performance between pathological or non‐pathological CR and diagnostic accuracy for specific pathologies. Material and Methods We conducted a cross‐sectional, observational and analytical study including all CRs obtained from pediatric patients between November 2023 and April 2024 at a secondary hospital. The screening performance and the diagnostic accuracy of the observers (ChatGPT, Perplexity and pediatricians) compared to the reference standard (a consensus of three radiologists) were evaluated using Phi coefficient and Cohen's Kappa.
Results
The study included 502 radiographs from 444 patients. Pediatricians showed better sensitivity, specificity and positive predictive value than ChatGPT and Perplexity, whereas Perplexity obtained a higher negative predictive value. ChatGPT demonstrated higher sensitivity for pneumonia than for the overall sample (0.81 vs. 0.67). Inter‐observer agreement was highest between pediatricians and radiologists (Phi = 0.80; Kappa = 0.69). ChatGPT showed higher concordance with radiologists than Perplexity did (Phi = 0.56; Kappa = 0.34 vs. Phi = 0.33; Kappa = 0.32, respectively). Inter‐observer agreement was lower for pneumonia cases and within the neonatal population.
Discussion
General‐purpose LLMs, both ChatGPT and Perplexity provide fair screening capability for pediatric CR, although their diagnostic accuracy drops significantly for specific conditions. The findings suggest that LLMs cannot replace specialists and highlight the need to develop pediatric‐specific AI models.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Pediatrics, Segovia General Hospital, Segovia, Spain.
- Department of Medicine, Francisco de Vitoria University, Pozuelo de Alarcón (Madrid), Spain.
- Department of Radiology, Segovia General Hospital, Segovia, Spain.
ORCID-Profile: Luis Bachiller Carnicero, Cristina Antón Rodríguez
Zitieren
APA
Bachiller Carnicero, L., Serón Luna, J. M., Antón Rodríguez, C., Pérez Yagüe, G., Bartolomé Calvo, G., & Rodríguez Ramos, A. (2026). Diagnostic Accuracy of Large Language Models for Pediatric Chest Radiograph: Comparison With Pediatricians and Radiologists. Pediatric Pulmonology, 61(11). https://doi.org/10.1002/ppul.71916
Vancouver
Bachiller Carnicero L, Serón Luna JM, Antón Rodríguez C, Pérez Yagüe G, Bartolomé Calvo G, Rodríguez Ramos A. Diagnostic Accuracy of Large Language Models for Pediatric Chest Radiograph: Comparison With Pediatricians and Radiologists. Pediatric Pulmonology. 2026;61(11). doi:10.1002/ppul.71916
BibTeX
@article{BachillerCarnicero2026,
author = {Bachiller Carnicero, Luis and Serón Luna, Juan Manuel and Antón Rodríguez, Cristina and Pérez Yagüe, Gema and Bartolomé Calvo, Gloria and Rodríguez Ramos, Ana},
title = {Diagnostic Accuracy of Large Language Models for Pediatric Chest Radiograph: Comparison With Pediatricians and Radiologists},
journal = {Pediatric Pulmonology},
year = {2026},
volume = {61},
number = {11},
doi = {10.1002/ppul.71916}
}
EUVIMED