ArticleClinical oral investigations2026
Human perception of AI-generated post-treatment orthodontic facial images: factors associated with misclassification.
Article in Clinical oral investigations, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Not yet cited in PubMed.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
0 citing papers in PubMed.
No citing paper in PubMed yet.
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
4 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
objectivesThis 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
methodsIn 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.
resultsA 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).
conclusionsIn 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.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.