Deep learning for pediatric chest x-ray diagnosis: Repurposing a commercial tool developed for adults
PLOS One · 24.07.2025 · 20 (7) · e0328295
DOI: 10.1371/journal.pone.0328295 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 24.07.2025. Verfasst von Prerana Agarwal und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Diagnostic and Interventional Radiology, Medical Center - University of Freiburg, Freiburg, Germany. Hauptthemen laut MEDLINE: Deep Learning, Radiography, Thoracic, Radiographic Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Lunit.
Abstract (Originalsprache)
The number of commercially available artificial intelligence (AI) tools to support radiological workflows is constantly increasing, yet dedicated solutions for children are largely unavailable. Here, we repurposed an AI-tool developed for chest radiograph interpretation in adults (Lunit INSIGHT CXR) and investigated its diagnostic performance in a real-world pediatric clinical dataset. 958 consecutive frontal chest radiographs of children aged 2−14 years were included and analyzed with the commercially available AI-tool. The reference standard was determined in a dedicated reading session by a board-certified radiologist. The original reports validated by specialized pediatric radiologists, were considered as second readings. All discordant findings were reanalyzed in consensus. The diagnostic performance of the AI-tool was validated using standard measures of accuracy. For this, the continuous AI output (ranging from 0−100) was binarized using vendor recommended thresholds recommended for adults and optimized thresholds identified for children. Relevant findings were defined as consolidation, atelectasis, nodule, cardiomegaly, mediastinal widening due to mass, pleural effusion and pneumothorax. 200 radiographs [20.9%] demonstrated at least one relevant pathology. Using the adult threshold, the AI-tool showed a high performance for all relevant findings with an AUC 0.94 (95% CI: 0.92–0.95) and. In stratified analysis by age (2−7 vs. 7–14-years-old) a significantly higher performance (p < 0.001) was found for older children with an AUC of 0.96 (95% CI: 0.94–0.98) with a sensitivity and specificity of 87.5% and 82.3% respectively, which further increased using optimized thresholds for children. Repurposing existing AI-tools developed for adult application to pediatric patients could support clinical workflows until dedicated solutions become available.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Diagnostic and Interventional Radiology, Medical Center - University of Freiburg, Freiburg, Germany.
- Lunit, 7F, 374, Gangnam-daero, Gangnam-gu, Seoul, Korea.
ORCID-Profile: Prerana Agarwal, Alexander Rau, Elmar Kotter
Förderung
- Lunit
Zitieren
APA
Agarwal, P., Rau, A., Ngo, H., Seth, A., Bamberg, F., Kotter, E., & Weiss, J. (2025). Deep learning for pediatric chest x-ray diagnosis: Repurposing a commercial tool developed for adults. PLOS One, 20(7), e0328295. https://doi.org/10.1371/journal.pone.0328295
Vancouver
Agarwal P, Rau A, Ngo H, Seth A, Bamberg F, Kotter E, et al. Deep learning for pediatric chest x-ray diagnosis: Repurposing a commercial tool developed for adults. PLOS One. 2025;20(7):e0328295. doi:10.1371/journal.pone.0328295
BibTeX
@article{Agarwal2025,
author = {Agarwal, Prerana and Rau, Alexander and Ngo, Helen and Seth, Ambika and Bamberg, Fabian and Kotter, Elmar and Weiss, Jakob},
title = {Deep learning for pediatric chest x-ray diagnosis: Repurposing a commercial tool developed for adults},
journal = {PLOS One},
year = {2025},
volume = {20},
number = {7},
pages = {e0328295},
doi = {10.1371/journal.pone.0328295}
}
EUVIMED