Diagnostic Performance of ChatGPT‐4o and DeepSeek‐3 Differential Diagnosis of Complex Oral Lesions: A Multimodal Imaging and Case Difficulty Analysis
Remarkably, the text-only DeepSeek-3 model exceeded the diagnostic performance of the multimodal ChatGPT-4o model for complex oral lesions, highlighting its structured reasoning capabilities and reduced hallucination rate. These findings underscore the potential of non-vision LLMs in diagnostic support, emphasizing the critical need for expert oversight in complex scenarios.
Authors
- Asmaa Abou‐Bakr (ORCID: https://orcid.org/0000-0001-5069-8257)
- Susan Sarhan
- Radwa R. Hussein
- Yousra Ahmed (ORCID: https://orcid.org/0000-0002-5404-7248)
- Ahmed El Barbary (ORCID: https://orcid.org/0009-0007-0992-8322)
- Fatma E. A. Hassanein (ORCID: https://orcid.org/0009-0000-8010-9265)
- Jylan El‐Guindy
Institutions
- Ain Shams University (EG)
- Suez University (EG)
- Cairo University (EG)
- Galala University
Publication Details
- Journal
- Oral Diseases
- Published
- 2025-07-01
- DOI
- https://doi.org/10.1111/odi.70007
- Citations
- 20
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 13.09