Performance of an artificial intelligence–based software in detecting pneumothorax on supine chest radiographs: a retrospective study
Emergency Radiology · 11.03.2026 · 33 (2) · 281-290
DOI: 10.1007/s10140-026-02448-4 ↗Kurz gefasst
Fachartikel in der Zeitschrift Emergency Radiology, online erschienen am 11.03.2026. Verfasst von Hitomi Nakamura und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Emergency and Critical Care Medicine, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-Ku, Tokyo, 113-0033, Japan. Hauptthemen laut MEDLINE: Pneumothorax, Radiography, Thoracic, Artificial Intelligence, Radiographic Image Interpretation, Computer-Assisted. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The University of Tokyo.
Abstract (Originalsprache)
Purpose
To evaluate the diagnostic performance of artificial intelligence (AI)-based software for pneumothorax detection on supine radiographs and its impact on physicians’ interpretation.
Methods
This single-center retrospective study analyzed 114 hemithoraces with pneumothorax and 340 without, using computed tomography as the reference standard. We evaluated the performance of CXR-AID, an AI-based software, for pneumothorax detection on supine chest radiographs, and conducted a reader study to assess the utility of AI assistance. Sensitivities and specificities were adjusted for clustering within patients.
Results
Sensitivity and specificity of the AI in detecting overall pneumothorax on a supine chest radiograph were 61.0% (95% confidence interval [CI], 50.6%–70.4%) and 94.3% (95% CI, 90.8%–96.5%), respectively. Sensitivity of the AI in detecting a large pneumothorax with a maximum radial interpleural distance > 35 mm was 97.4% (95% CI, 83.6%–99.6%). Sensitivity was significantly higher in the upper lung zone than in the lower lung zone (69.5% [95% CI, 59.3%–78.1%] vs. 37.5% [95% CI, 27.3%–48.8%]). In the reader study, the AI significantly improved resident sensitivity (46.8% to 57.3%, P < 0.001). For experts, the AI did not improve sensitivity significantly ( P = 0.32) but significantly improved specificity (90.9% to 95.6%, P = 0.02).
Conclusions
The AI demonstrated high sensitivity for detecting large pneumothoraces on supine radiographs, helping identify patients requiring tube thoracotomy. It may serve as a diagnostic safety net for residents by increasing sensitivity and enhances experts’ diagnostic confidence by improving specificity. However, pneumothorax detection in the lower lung zone remains challenging.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Emergency and Critical Care Medicine, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-Ku, Tokyo, 113-0033, Japan.
- Department of Emergency and Critical Care Medicine, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-Ku, Tokyo, 113-0033, Japan. towada-tky@umin.ac.jp.
- Department of Radiology, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-Ku, Tokyo, 113-0033, Japan.
Förderung
- The University of Tokyo
Zitieren
APA
Nakamura, H., Wada, T., Inokuchi, R., Hanaoka, S., Sakamoto, N., & Doi, K. (2026). Performance of an artificial intelligence–based software in detecting pneumothorax on supine chest radiographs: a retrospective study. Emergency Radiology, 33(2), 281-290. https://doi.org/10.1007/s10140-026-02448-4
Vancouver
Nakamura H, Wada T, Inokuchi R, Hanaoka S, Sakamoto N, Doi K. Performance of an artificial intelligence–based software in detecting pneumothorax on supine chest radiographs: a retrospective study. Emergency Radiology. 2026;33(2):281-290. doi:10.1007/s10140-026-02448-4
BibTeX
@article{Nakamura2026,
author = {Nakamura, Hitomi and Wada, Tomoki and Inokuchi, Ryota and Hanaoka, Shouhei and Sakamoto, Naoya and Doi, Kent},
title = {Performance of an artificial intelligence–based software in detecting pneumothorax on supine chest radiographs: a retrospective study},
journal = {Emergency Radiology},
year = {2026},
volume = {33},
number = {2},
pages = {281--290},
doi = {10.1007/s10140-026-02448-4}
}
EUVIMED