EUVIMEDEUVIMED entdecken
Crossref

Artificial intelligence and the phantom pneumothorax: Clinical reasoning still matters

Fulvio Cacciapuoti, Antonio Ruocco, Salvatore Crispo, Massimiliana Abbate, Giuseppina Dell'Aversano Orabona, Osvaldo Cuomo, Ciro Mauro

Emergency Radiology · 20.08.2026

DOI: 10.1007/s10140-026-02533-8 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Emergency Radiology, online erschienen am 20.08.2026. Verfasst von Fulvio Cacciapuoti und 6 weiteren Autor:innen. Beteiligte Einrichtung: Division of Cardiology "Antonio Cardarelli" Hospital, Via Antonio Cardarelli, 9, Naples, 80131, Italy. fulvio.cacciapuoti@aocardarelli.it. Die Arbeit nennt 14 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Artificial intelligence (AI) has become increasingly integrated into chest radiograph interpretation, demonstrating excellent diagnostic performance for several thoracic abnormalities, including pneumothorax. Nevertheless, current AI systems remain predominantly image-based and do not inherently incorporate procedural or clinical information into diagnostic interpretation. We report the case of an 81-year-old man who underwent uncomplicated left-sided dual-chamber permanent pacemaker implantation. Routine post-procedural chest radiography, analyzed by an AI-assisted interpretation system, generated a positive alert for a right apical pneumothorax, highlighting the suspected abnormality with automated visual annotation. The alert was immediately considered clinically discordant by the treating team, given the left-sided venous access, normal oxygen saturation, hemodynamic stability, and absence of respiratory symptoms. Because of this clinicoradiological discordance, chest computed tomography was performed and definitively excluded pneumothorax, confirming a false-positive AI interpretation. The patient required no additional intervention and experienced an uneventful recovery. This case highlights the importance of integrating AI-generated findings with procedural details, bedside clinical assessment, and, when clinically indicated, confirmatory imaging in the presence of clinicoradiological discordance. Although AI can accurately identify many radiographic abnormalities, accurate diagnosis ultimately depends on integrating imaging findings with procedural information, clinical presentation, and pre-test probability. This case also emphasizes that AI should be regarded as a clinical decision-support tool rather than an autonomous diagnostic system and highlights the continuing importance of physician oversight in ensuring patient safety during AI-assisted post-procedural imaging interpretation.

Schlagwörter

Stichwörter der Autor:innen

Artificial intelligenceAutomation biasChest radiographyClinical reasoningPacemaker implantationPatient safetyPneumothorax

Autor:innen und Institutionen

  • Division of Cardiology "Antonio Cardarelli" Hospital, Via Antonio Cardarelli, 9, Naples, 80131, Italy. fulvio.cacciapuoti@aocardarelli.it.
  • Division of Cardiology "Antonio Cardarelli" Hospital, Via Antonio Cardarelli, 9, Naples, 80131, Italy.
  • Division of Radiology "Antonio Cardarelli" Hospital, Naples, Italy.
  • Postgraduate School of Cardiology "Federico II" University, Naples, Italy.

Zitieren

APA

Cacciapuoti, F., Ruocco, A., Crispo, S., Abbate, M., Orabona, G. D., Cuomo, O., & Mauro, C. (2026). Artificial intelligence and the phantom pneumothorax: Clinical reasoning still matters. Emergency Radiology. https://doi.org/10.1007/s10140-026-02533-8

Vancouver

Cacciapuoti F, Ruocco A, Crispo S, Abbate M, Orabona GD, Cuomo O, et al. Artificial intelligence and the phantom pneumothorax: Clinical reasoning still matters. Emergency Radiology. 2026. doi:10.1007/s10140-026-02533-8

BibTeX
@article{Cacciapuoti2026,
  author = {Cacciapuoti, Fulvio and Ruocco, Antonio and Crispo, Salvatore and Abbate, Massimiliana and Orabona, Giuseppina Dell'Aversano and Cuomo, Osvaldo and Mauro, Ciro},
  title = {Artificial intelligence and the phantom pneumothorax: Clinical reasoning still matters},
  journal = {Emergency Radiology},
  year = {2026},
  doi = {10.1007/s10140-026-02533-8}
}
Kostenlos starten →