Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 10, 2025Open Access

Evaluation of the Effectiveness of the ChatGPT Artificial Intelligence Application in the Diagnosis of Pneumothorax on Chest Radiograph Interpretation

View Full Paper
Ask AI
Bookmark
Share

Authors

OAOnur AkçayAOA. OzelÖÖÖzgür Öztürk

Discussion

Loading...

Member takes

Overview

Retrospective analysis showed ChatGPT's diagnostic accuracy of 83.7% for identifying pneumothorax, suggesting potential in clinical settings.

Key Points

  • ChatGPT achieved 83.7% diagnostic accuracy for pneumothorax detection on chest radiographs.
  • Sensitivity was 70.9% while specificity reached 96.4%, highlighting potential clinical utility in certain cases.
  • Large pneumothoraces had a better AUC of 0.894, indicating improved detection capability compared to small ones.
  • Cohen's kappa coefficient showed substantial agreement with expert evaluations, emphasizing trustworthiness but caution needed.

Cite This Study

Akçay et al. (2025) studied this question.

synapsesocial.com/papers/68c24317b210217d647a634fhttps://doi.org/10.21203/rs.3.rs-7297832/v1
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1New frontiers in radiologic interpretation: evaluating the effectiveness of large language models in pneumothorax diagnosis.2025
  2. 2Diagnostic performance of ChatGPT in detecting gastrointestinal tract perforation on chest radiographs: a comparative study2025
  3. 3ChatGPT: A Useful Tool for Medical Students in Radiology Education?2025
  4. 4Performance of ChatGPT-4o in thoracic trauma: A comparative evaluation with guidelines2025
  5. 5Diagnostic Accuracy of a Large Language Model (ChatGPT-4) for Patients Admitted to a Community Hospital Medical Intensive Care Unit: A Retrospective Case Study2025 · 2 citations