Human perception of AI-generated post-treatment orthodontic facial images: factors associated with misclassification.

چکیده اصلی

OBJECTIVES: This study evaluated participants' ability to differentiate AI-enhanced orthodontic outcome images from real post-treatment images, and examined the demographic and behavioral factors associated with detection accuracy and with perceived attractiveness. MATERIALS AND METHODS: In a cross-sectional online survey (N = 252), participants viewed three sets of smile images-pre-treatment, real post-treatment, and AI-enhanced outcomes generated via ChatGPT with DALL·E 3-and rated each image's authenticity and attractiveness using a Visual Analogue Scale (VAS). A custom seven-item questionnaire assessed AI use and trust across daily and professional contexts. Generalized estimating equations were used to account for repeated image evaluations within participants, with logistic GEE models for misclassification outcomes and Gaussian GEE models for attractiveness ratings. RESULTS: A total of 63.2% of participants misclassified AI-enhanced images as real, whereas 18.5% misclassified real images as AI-generated. AI-enhanced images received significantly higher attractiveness ratings (mean VAS = 69.2; 95% CI: 67.5-70.9) than actual post-treatment results (mean VAS = 53.9; 95% CI: 51.9-56.0; p < 0.001). Greater trust in AI-generated content was associated with higher odds of misclassifying AI-enhanced images as real (OR = 1.38; 95% CI: 1.13-1.69), and older age showed a small association in the same direction (OR = 1.02; 95% CI: 1.00-1.05). CONCLUSIONS: In this sample, AI-generated orthodontic images were frequently misclassified as real and were perceived as more attractive than real post-treatment photographs. As generative AI tools become more accessible, understanding how demographic and behavioral factors affect human trust and perception is critical for developing responsible AI policies and digital literacy interventions. CLINICAL RELEVANCE: Clinicians should be aware that AI-generated smile simulations may create unrealistic patient expectations. This study provides empirical evidence supporting the need for transparent patient communication regarding the limitations of AI-generated content in orthodontic practice.

متن کامل اصلی