Large-scale evaluation of multimodal large language models for pneumothorax detection
Automated systems capable of high specificity but low sensitivity should not be relied upon to exclude pneumothorax. However, they may serve as valuable assistants for confirming positive findings and prioritizing urgent cases in busy clinical workflows.
Authors
- Ali Murat Koç (ORCID: https://orcid.org/0000-0001-6824-4990)
- Cemre Özenbaş (ORCID: https://orcid.org/0000-0002-6688-5003)
- Hamza Eren Güzel
Institutions
- Izmir University (TR)
- Izmir Kâtip Çelebi University (TR)
- Sağlık Bilimleri Üniversitesi (TR)
Publication Details
- Journal
- Diagnostic and Interventional Radiology
- Published
- 2026-02-12
- DOI
- https://doi.org/10.4274/dir.2026.263696
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 0.00