EUVIMEDOntdek EUVIMED
CrossrefInfokaart

Challenges and Limitations of Multimodal Large Language Models in Interpreting Pediatric Panoramic Radiographs

Yuichi Mine, Yuko Iwamoto, Shota Okazaki, Taku Nishimura, Eimi Tabata, Saori Takeda, Tzu‐Yu Peng, Ryota Nomura, Naoya Kakimoto, Takeshi Murayama

International Journal of Paediatric Dentistry · 2026-01 · 36 (1) · 74-80

DOI: 10.1111/ipd.70029 ↗
SamenvattingBibliografische gegevens

Samenvatting

ABSTRACT Background Multimodal large language models (LLMs) have potential for medical image analysis, yet their reliability for pediatric panoramic radiographs remains uncertain. Aim This study evaluated two multimodal LLMs (OpenAI o1, Claude 3.5 Sonnet) for detecting and counting teeth (including tooth germs) on pediatric panoramic radiographs. Design Eighty‐seven pediatric panoramic radiographs from an open‐source data set were analyzed. Two pediatric dentists annotated the presence or absence of each potential tooth position. Each image was processed five times by the LLMs using identical prompts, and the results were compared with the expert annotations. Standard performance metrics and Fleiss' kappa were calculated. Results Detailed examination revealed that subtle developmental stages and minor tooth loss were consistently misidentified. Claude 3.5 Sonnet had higher sensitivity but significantly lower specificity (29.8% ± 21.5%), resulting in many false positives. OpenAI o1 demonstrated superior specificity compared to Claude 3.5 Sonnet, but still failed to correctly detect subtle defects in certain mixed dentition cases. Both models showed large variability in repeated runs. Conclusion Both LLMs failed to achieve clinically acceptable performance and cannot reliably identify nuanced discrepancies critical for pediatric dentistry. Further refinements and consistency improvements are essential before routine clinical use.

Kennis die bij uw werk past.

Van een gratis start via persoonlijk literatuuronderzoek tot de volledige Research Suite.

Tarieven bekijken →

Zijn alle volledige uitgeversteksten inbegrepen?

Nee. Bibliografische records, abstracts en volledige teksten zijn verschillende inhoudstypen. Beschikbaarheid hangt af van bron, open access en bestaande licenties. Een EUVIMED-abonnement vervangt geen aanvullende uitgeversrechten.

Tarieven bekijken →