Diagnostic performance and short-interval reproducibility of multimodal large language models in differentiating cholesteatoma from chronic otitis media using key-image temporal bone high-resolution computed tomography.

The radiologist achieved an accuracy of 96.0% (95% CI: 90.3-98.4) with almost perfect agreement with the reference standard (κ: 0.921).

Both models combined high sensitivity (83.3%-97.9%) with low specificity (1.9%-13.2%), and balanced accuracy ranged from 0.45 to 0.52.

Between-session reproducibility was fair for GPT-5 (κ: 0.360) and moderate for Gemini 2.5 Pro (κ: 0.485), and inter-model agreement was slight at both sessions (κ: 0.035 at S1 and κ: 0.086 at S2).

Accuracy did not differ significantly between the two models ( P = 0.211).