Abstract
In orthodontics, the increasing use of AI-generated smile images in patient communication raises ethical and practical concerns about user perception and misinterpretation of these visuals. This cross-sectional, non-probabilistic sample study evaluated the ability of dentists, dental students, and laypeople to distinguish between real and AI-generated orthodontic smile images, and their perceived attractiveness. The final sample consisted of 288 participants, (63.4% female; mean age = 32.4 years) including 76 dentists, 63 dental students, and 149 laypeople. Each participant was presented with three clinical scenarios, mild dental misalignment, midline diastema, and moderate anterior crowding, and viewed randomized sets of images depicting pre-treatment, real post-treatment, and AI-generated smiles. For each image, participants indicated whether they believed it was AI-generated or real and rated its aesthetic appeal using a visual analog scale ranging from 0 to 100. Data were analyzed using descriptive statistics and diagnostic performance metrics (accuracy, sensitivity, specificity, PPV, and NPV), with attractiveness ratings compared between AI-generated and real images. Sensitivity for identifying AI-generated images was low across all groups (< 50%), while specificity for recognizing real images was high (> 87%). Dental students achieved the highest overall accuracy (72.7%), followed by laypeople (66.3%) and dentists (62.6%). AI-generated smiles were consistently rated as significantly more attractive than real outcomes by all groups (mean VAS: 78.8 vs. 37.9; p < 0.001). AI-generated smile images were less accurately identified and more aesthetically pleasing than real clinical outcomes compared to real post-treatment outcomes, which were more consistently recognized across all participant groups, regardless of treatment type.
Similar content being viewed by others
Data availability
Data is provided within the manuscript or supplementary information file.
References
Bandi, R., Kumar, S. & Patel, M. Impact of AI-generated content in media industries. Media Technol. Rev. 28, 45–59 (2023).
Ramesh, A. et al. Zero-shot text-to-image generation. In Proceeding 38th International Conference on Machine Learning 8821–8831 (2021).
Struppek, L., Weng, M., Wang, Y., Schiele, B. & Akata, Z. Diffusion models: A comprehensive survey of methods and applications. arXiv:2303.08934 (2023).
Vimpari, M., Laaksonen, J. & Kannala, J. Text-to-image synthesis with deep generative models: A survey. Pattern Recognit. 136, 109379 (2023).
Wang, X., Liu, Y. & Zhang, Z. User-friendly interfaces for AI-generated image platforms. Comput. Graph Forum. 42, 67–78 (2023).
Liu, Y. & Chilton, L. B. Design guidelines for human-AI co-creation tools. In Proceeding CHI Conference on Human Factors in Computing Systems 1–13 (2022).
Oppenlaender, J. The rise of AI-generated images in digital art and marketing. J. Vis. Cult. 21, 345–359 (2022).
Samad, A. & Jamal, A. Transformative applications of ChatGPT: A comprehensive review of its impact across industries. Glob J. Multidiscip. Sci. Arts. 1, 26–48 (2024).
Patil, D., Rane, N. L., Rane, J. & Paramesha, M. Artificial intelligence and generative AI, such as ChatGPT, in transportation: Applications, technologies, challenges, and ethical considerations. In Trustworthy Artificial Intelligence in Industry and Society 185–232 (Deep Science Publishing, 2024).
Chang, H., Kim, S. & Lee, J. User perceptions of AI-generated art: A comparative study. Int. J. Hum. Comput. Stud. 170, 102997 (2023).
Ting, Y., Zhao, Q. & Wang, H. Evaluating aesthetic judgments of AI-generated images. Vis. Comput. 39, 1234–1245 (2023).
Samo, D. & Highhouse, S. Human vs. AI-generated art: Perception and value. Psychol. Aesthet. Creat Arts. 17, 215–225 (2023).
Meira, T. M. et al. The effects of images posted to social media by orthodontists on public perception of professional credibility and willingness to become a client. Prog. Orthod. 22, 1–8 (2021).
Mori, M. The uncanny valley. IEEE Robot Autom. Mag. 19, 98–100 (2012).
Go, E. & Sundar, S. S. Humanizing chatbots: The effects of anthropomorphism on user trust. Comput. Hum. Behav. 97, 304–316 (2019).
Rapp, A., Curti, L. & Boldi, A. The uncanny valley of AI-generated faces: A psychological perspective. Front. Psychol. 14, 1122334 (2023).
Wickham, H. ggplot2: Elegant Graphics for Data Analysis (Springer, Cham, 2016).
Turing, A. M. Computing machinery and intelligence. Mind 59, 433–460 (1950).
Fraser, K. C., Dawkins, H. & Kiritchenko, S. Detecting AI-generated text: Factors influencing detectability with current methods. J. Artif. Intell. Res. 82, 2233–2278 (2025).
Cao, Y. et al. A comprehensive survey of AI-generated content (AIGC): A history of generative AI from GAN to ChatGPT. arXiv:2303.04226 (2023).
Tanaka, O. M. et al. Assessing the reliability of ChatGPT: A content analysis of self-generated and self-answered questions on clear aligners, TADs and digital imaging. Dent. Press. J. Orthod. 28, e2323183 (2023).
Makowski, D. et al. Too beautiful to be fake: Attractive faces are less likely to be judged as artificially generated. Acta Psychol. 252, 104670 (2025).
Liu, Y. & Sundar, S. S. Anthropomorphism in human–robot interactions: A multidimensional conceptualization. Comput. Hum. Behav. 86, 191–198 (2018).
Liu, Y. AI in journalism: Opportunities and challenges. Digit. J. 10, 512–528 (2022).
Ruan, F., Wang, Y., Li, J. & Zhang, X. Perception of AI-generated images: A psychological perspective. J. Vis. Commun. Image Represent. 58, 1–9 (2019).
Bird, J., Smith, L. & Thompson, R. The impact of AI-generated images on aesthetic expectations. Comput. Hum. Behav. 139, 107513 (2023).
Sanny, L., Hartono, P. & Nugroho, Y. The influence of AI-generated content on social media engagement. J. Theor. Appl. Electron. Commer. Res. 15, 1–12 (2020).
Lu, Z. et al. Seeing is not always believing: A quantitative study on human perception of AI-generated images. In Proceedings of the Neural Information Processing Systems (NeurIPS, 2023).
Huang, L. Personal content creation with AI: A new era. New Media Soc. 25, 289–306 (2023).
Li, J. et al. ChatGPT in healthcare: A taxonomy and systematic review. Comput. Methods Programs Biomed. 245, 108013 (2024).
Huang, J., Kim, I. J. & Yoon, D. Mirror to companion: Exploring roles, values, and risks of AI self-clones through story completion. In Proceeding CHI Conference on Human Factors in Computing Systems 1–15 (2025).
Nadarzynski, T., Miles, O., Cowie, A. & Ridge, D. Acceptability of artificial intelligence (AI)-led chatbot services in healthcare: A mixed-methods study. Digit. Health. 5, 2055207619871808 (2019).
Fitzpatrick, K. K., Darcy, A. & Vierhile, M. Delivering cognitive behavior therapy to young adults with symptoms of depression and anxiety using a fully automated conversational agent (Woebot): A randomized controlled trial. JMIR Ment Health. 4, e19 (2017).
Bradley, M. M. & Lang, P. J. The international affective picture system (IAPS) in the study of emotion and attention. In Handbook of Emotion Elicitation and Assessment (eds Coan, J. A. & Allen, J. J. B.) 29–46 (Oxford University Press, 2007).
Tanaka, O. M. et al. Effectiveness of AI-generated orthodontic treatment plans compared to expert orthodontist recommendations: A cross-sectional pilot study. Dent. Press. J. Orthod. 30, e2524186 (2025).
Funding
This study did not receive any specific grants from funding agencies in the public, commercial, or not-for-profit sectors.
Author information
Authors and Affiliations
Contributions
Otso Tirkkonen, Gil Guilherme Gasparello, Sergio Luiz Mota-Júnior, and Matheus Melo Pithon conceptualized and designed the study. Gil Guilherme Gasparello and Sergio Luiz Mota-Júnior were responsible for the preparation and formatting of figures. Gil Guilherme Gasparello, Sergio Luiz Mota-Júnior, and Claudia Trindade Mattos participated in the development and refinement of the questionnaire. Gil Guilherme Gasparello and Sergio Luiz Mota-Júnior conducted the statistical analyses. Otso Tirkkonen, Marco Antonio Dias da Silva, and Matheus Melo Pithon drafted the manuscript. All authors contributed to the translation and back-translation process and critically reviewed and approved the final version of the manuscript.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Ethical approval and consent to participate
This study was approved by the Ethics Committee of the Pontifícia Universidade Católica do Paraná (PUCPR), Brazil (2235302). Participation was entirely voluntary and anonymous, with no collection of personally identifiable information. Informed consent was obtained from every participant, including individuals whose de-identified smile images were utilized, permitting their use for both research and educational objectives. The research was conducted in strict accordance with the principles outlined in the Declaration of Helsinki and its subsequent revisions.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
About this article
Cite this article
Tirkkonen, O., Gasparello, G.G., Mota-Júnior, S.L. et al. Perception of AI-generated smile versus real orthodontic treatment outcomes among dentists, students, and laypeople. Sci Rep (2026). https://doi.org/10.1038/s41598-026-41744-4
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-41744-4
