Zero-shot detection of apical periodontitis on periapical radiographs using multimodal large language models: diagnostic accuracy and error patterns.

BACKGROUND

The present study evaluated the diagnostic performance of three general-purpose multimodal large language models (MLLMs)-Claude 4.5 Sonnet, GPT-5.2 Thinking, and Gemini 3.0 Pro-in detecting apical periodontitis on periapical radiographs.

METHODS

One hundred twenty periapical radiographs were included (60 apical periodontitis-positive and 60 healthy), retrieved from routine clinical records at a university dental clinic. Teeth with root canal fillings and radiographs showing metallic artifacts were excluded to minimize superimposition in the apical region. Two experienced clinicians independently assessed all images to establish the reference standard based on two-dimensional periapical radiographic interpretation without CBCT confirmation. Disagreements were resolved by consensus, and interobserver agreement was high (Cohen's κ = 0.88). The same coded images were subsequently evaluated by the three MLLMs in separate sessions using a standardized prompt, without any example or training images. Model outputs were restricted to binary "present/absent" responses. Accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated. Differences among models were analyzed using Cochran's Q test (α = 0.05), followed by Bonferroni-adjusted McNemar tests.

RESULTS

Gemini 3.0 Pro achieved the highest overall accuracy (71.67%). This performance was significantly superior to that of Claude 4.5 Sonnet (Bonferroni-adjusted p = 0.0015). Claude 4.5 Sonnet demonstrated very high sensitivity (95.00%) but low specificity (13.33%), reflecting a strong false-positive tendency. In contrast, GPT-5.2 Thinking showed high specificity (98.33%) with markedly reduced sensitivity (20.00%). Gemini 3.0 Pro maintained high sensitivity (95.00%) while achieving moderate specificity (48.33%). Positive and negative predictive values (PPV/NPV) were 52.29%/72.73% for Claude, 92.31%/55.14% for GPT-5.2 Thinking, and 64.77%/90.62% for Gemini 3.0 Pro.

CONCLUSIONS

Under zero-shot conditions, the evaluated MLLMs did not demonstrate sufficient reliability to replace clinical judgment in the detection of apical periodontitis on periapical radiographs. Although diagnostic performance varied among models, none achieved a level of diagnostic performance sufficient for independent clinical use. At present, these systems appear more suitable as clinician-supervised decision-support tools. Further research is needed to improve diagnostic reliability and validate performance across diverse clinical settings.