Objectives: This study assessed the ability of ChatGPT, an artificial intelligence(AI) language model, to determine the stage, grade, and extent of periodontitis based on the 2018 classification. Materials and methods: This study used baseline digital data of 200 untreated periodontitis patients to compare standardized reference diagnoses (RDs) with ChatGPT findings and determine the best criteria for assessing stage and grade. RDs were provided by four experts who examined each case. Standardized texts containing the relevant information for each situation were constructed to query ChatGPT. RDs were compared to ChatGPT's responses. Variables influencing the responses of ChatGPT were evaluated. Results: ChatGPT successfully identified the periodontitis stage, grade, and extent in 59.5%, 50.5%, and 84.0% of cases, respectively. Cohen’s kappa values for stage, grade and extent were respectively 0.447, 0.284, and 0.652. A multiple correspondence analysis showed high variance between ChatGPT’s staging and the variables affecting the stage (64.08%) and low variance between ChatGPT’s grading and the variables affecting the grade (42.71%). Conclusions: The present performance of ChatGPT in the classification of periodontitis exhibited a reasonable level. However, it is expected that additional improvements would increase its effectiveness and broaden its range of functionalities (NCT05926999). Clinical relevance: Despite ChatGPT's current limitations in accurately classifying periodontitis, it is important to note that the model has not been specifically trained for this task. However, it is expected that with additional improvements, the effectiveness and capabilities of ChatGPT might be enhanced.

It is very difficult to objectively evaluate the negative changes in bone structure due to periodontitis. The present study was aimed to evaluate the trabecular bone structure between healthy individuals and periodontitis patients by fractal analysis (FA) on digital panoramic radiographs. The study included 50 periodontally healthy individuals (control group), 50 individuals with Stage 1 periodontitis (S1-P group), 50 individuals with Stage 2 periodontitis (S2-P), and 50 individuals with Stage 3 periodontitis (S3-P), a total of 200 individuals were included. The fractal dimension (FD) value of the trabecular bone in the interdental space between mandibular first molar and second premolar tooth roots was evaluated using Image J program. The mean FD values of the two regions were calculated by box counting method. There was a statistically significant difference between the groups in terms of all periodontal parameter values (p<0.05). The mean FD values of individuals diagnosed with periodontitis were 1.36±0.08 in the S1-P group, 1.35±0.07 in the S2-P group, 1.28±0.15 in the S3-P group, and 1.44±0.06 in the control group. When the FD values between the groups were examined, it was seen that there was a statistically significant difference between the control and individuals with periodontitis, and the mean FD values were significantly higher in the healthy group (p<0.05). The best receiver operator curve was identified for periodontitis at the ≤1.409 cut-off FD value (area under the curve: 0.828; 95% CI: 0.758-0.899); p=0.000, p<0.001). FD evaluation can give an objective result about the effect of periodontitis on alveolar bone. The FD values of trabecular bone are different in healthy individuals and individuals with different stages of periodontitis. The findings suggested that a negative correlation between the periodontal data with the sites in which FD was measured and as the periodontitis stage progresses, FD decreases. Key words:Diagnosis, Periodontal Diseases, Radiographic Evaluation.

Keywords Saliva; Stress; Gingivitis; Pregnancy