Photograph-Based Visual Classification of Gingival Recession Using Multimodal Large Language Models: A Comparative Study

Purpose: This study aimed to evaluate the photograph-based visual classification performance of contemporary multimodal large language models for gingival recession defects according to Miller’s classification.Material and Methods: A dataset of 100 standardized intraoral photographs showing gingival recession was used. Five periodontists independently classified each photograph according to Miller’s classification using only the visual information available in the image. In cases of disagreement, a panel discussion was performed to establish a final periodontist visual consensus classification, which served as the reference comparator. Then photographs were submitted once to ChatGPT 5, Gemini 2.5 Pro, Grok 3, and Copilot GPT-5. Model outputs were compared with the periodontist panel consensus classification using overall accuracy, class-wise precision, sensitivity/recall, F1-score, Cohen’s kappa, and weighted kappa.Results: The periodontist panel showed almost perfect inter-rater agreement (Fleiss’ κ = 0.885; bootstrap 95% CI: 0.827–0.934). Overall classification accuracy differed significantly among the evaluated models (p < 0.001). Gemini showed the highest accuracy, correctly classifying 49% of photographs, followed by ChatGPT 5 with 32%, Grok 3 with 26%, and Copilot GPT-5 with 24%. Conclusion: Under standardized single-prompt and photograph-only conditions, the evaluated multimodal large language models showed limited and inconsistent agreement with the periodontist panel visual consensus classification.