Advances in Periodontal Diagnostics: Application of MultiModal Language Models in Visual Interpretation of Panoramic...

Background: Periodontitis is a multifactorial disease leading to the loss of clinical attachment and alveolar bone. The diagnosis of periodontitis involves a clinical examination and radiographic evaluation, including panoramic images. Panoramic radiographs are cost-effective methods widely used in periodontitis classification. The remaining bone height (RBH) is a parameter used to assess the alveolar bone level. Large language models are widely utilized in the medical sciences. ChatGPT, the leading conversational model, has recently been extended to process visual data. The aim of this study was to assess the effectiveness of the ChatGPT models 4.5, o1, o3 and o4-mini-high in RBH measurement and tooth counts in relation to dental professionals' evaluations. Methods: The analysis was based on 10 panoramic images, from which 252, 251, 246 and 271 approximal sites were qualified for the RBH measurement (using the models 4.5, o1, o3 and o4-mini-high, respectively). Three examiners were asked to independently evaluate the RBH in approximal sites, while the tooth count was achieved by consensus. Subsequently, the results were compared with the ChatGPT outputs. Results: ChatGPT 4.5, ChatGPT o3 and ChatGPT o4-mini-high achieved substantial agreement with clinicians in the assessment of tooth counts (κ = 0.65, κ = 0.66, κ = 0.69, respectively), while ChatGPT o1 achieved moderate agreement (κ = 0.52). In the context of RBH values, the ChatGPT models consistently exhibited a positive mean bias compared with the clinicians. ChatGPT 4.5 was reported to provide the lowest bias (+12 percentage points (pp) for the distal surfaces, width of the 95% CI for limits of agreement (LoAs) ~60 pp; +11 pp for the mesial surfaces, LoA width ~54 pp). Conclusions: ChatGPT 4.5 and ChatGPT o3 show potential in the assessment of tooth counts on a panoramic radiograph; however, their present level of accuracy is insufficient for clinical use. In the current stage of development, the ChatGPT models substantially overestimated the RBH values; therefore, they are not applicable for classifying periodontal disease.