MULTIMODAL ARTIFICIAL INTELLIGENCE IN AESTHETIC DERMATOLOGY: CURRENT APPLICATIONS, CHALLENGES, AND FUTURE PERSPECTIVES – A NARRATIVE REVIEW
DOI:
https://doi.org/10.31435/ijitss.3(51).2026.6064Keywords:
Artificial Intelligence, Aesthetic Dermatology, Aesthetic Medicine, Machine Learning, Skin Analysis, Diagnostic Accuracy, Personalized MedicineAbstract
Background The rapid evolution of artificial intelligence (AI) technologies has transformed many areas of medicine, including dermatology, where AI-assisted diagnostic systems have demonstrated considerable effectiveness in identifying skin diseases. In contrast, aesthetic dermatology presents additional challenges due to the subjective nature of cosmetic assessments and the absence of universally accepted evaluation standards.
Objective This review aims to examine the current role of artificial intelligence in dermatology, with particular emphasis on its application in aesthetic medicine. Furthermore, it evaluates the shortcomings of conventional assessment methods and discusses future opportunities for integrating AI-driven solutions into clinical practice.
Methods A narrative review of the literature was conducted to assess the implementation of AI technologies in both medical and aesthetic dermatology. Traditional evaluation approaches, including patient-reported outcome measures and instrument-based skin analysis systems, were reviewed and compared with emerging AI-supported methodologies. Particular attention was given to the limitations of current AI models, dataset quality, and the lack of standardized assessment frameworks.
Results Artificial intelligence has achieved notable success in dermatological diagnostics, especially in the detection and classification of skin cancers. Nevertheless, aesthetic dermatology continues to rely heavily on subjective evaluation techniques that often lack reproducibility and standardization. Although AI-based tools are increasingly being introduced into this field, their clinical utility remains constrained by limited dataset diversity, potential algorithmic bias, and variability in assessment protocols.
Conclusions The successful implementation of AI in aesthetic dermatology requires the development of standardized evaluation criteria, the creation of comprehensive and ethnically diverse datasets, and improved education of healthcare professionals regarding both the capabilities and limitations of AI technologies. Addressing these challenges may enhance diagnostic consistency, optimize treatment outcomes, and facilitate the broader adoption of AI-driven solutions in aesthetic practice.
References
Esteva, A., Kuprel, B., Novoa, R. A., et al. (2017). Dermatologist-level classification of skin cancer with deep neural networks. Nature, 542(7639), 115–118.
Escalé-Besa, A., Yélamos, O., Vidal-Alaball, J., et al. (2023). Exploring the potential of artificial intelligence in improving skin lesion diagnosis in primary care. Sci Rep, 13(1), 4293.
Smak Gregoor, A. M., Sangers, T. E., Eekhof, J. A. H., et al. (2023). Artificial intelligence in mobile health for skin cancer diagnostics at home (AIM HIGH): A pilot feasibility study. eClinicalMedicine, 60, 102019.
Smak Gregoor, A. M., Sangers, T. E., Bakker, L. J., et al. (2023). An artificial intelligence based app for skin cancer detection evaluated in a population based setting. NPJ Digit Med, 6(1), 83.
Cassalia, F., Han, S. S., Cazzaniga, S., & Naldi, L. (2024). Melanoma detection: Evaluating the classification performance of a deep convolutional neural network and dermatologist assessment via a mobile app in an Italian real-world setting. J Eur Acad Dermatol Venereol, 38(9), e782–e784.
Han, S. S., Park, I., Chang, S. E., et al. (2020). Augmented intelligence dermatology: Deep neural networks empower medical professionals in diagnosing skin cancer and predicting treatment options for 134 skin disorders. J Invest Dermatol, 140(9), 1753–1761.
Melarkode, N., Srinivasan, K., Qaisar, S. M., & Plawiak, P. (2023). AI-Powered diagnosis of skin cancer: A contemporary review, open challenges and future research directions. Cancers, 15(4), 1183.
Huang, L., Tang, W. H., Attar, R., et al. (2024). Remote assessment of eczema severity via AI-Powered skin image analytics: A systematic review. Artif Intell Med, 156, 102968.
Goessinger EV, Gottfrois P, Mueller AM, Cerminara SE, Navarini AA. Image-Based Artificial Intelligence in Psoriasis Assessment: The Beginning of a New Diagnostic Era? Am J Clin Dermatol. 2024;25:1–12.
Saraswathi, C., & Pushpa, B. (2022). Computer imaging of alopecia areata and scalp detection: A survey. Int J Eng Trends Technol, 70(8), 347–358.
Chakraborty, A. (2023). Disease severity scores in dermatology: An update of the various indices. Indian J Dermatol Venereol Leprol, 89, 1–15.
Humphrey, S., Brown, S. M., Cross, S. J., & Mehta, R. (2021). Defining skin quality: Clinical relevance, terminology, and assessment. Dermatol Surg, 47(7), 974–981.
Kania, B., Montecinos, K., & Goldberg, D. J. (2024). Artificial intelligence in cosmetic dermatology. J Cosmet Dermatol, 23(10), 3305–3311.
Baumann, L. (2008). Understanding and treating various skin types: The Baumann skin type indicator. Dermatol Clin, 26(3), 359–373.
Hersant, B., Abbou, R., SidAhmed-Mezi, M., & Meningaud, J. P. (2016). Assessment tools for facial rejuvenation treatment: A review. Aesthet Plast Surg, 40(4), 556–565.
Modasia, K. H., & Kaliyadan, F. (2022). Digital tools for assessing disease severity in dermatology. Indian Dermatol Online J, 13(2), 190–198.
Vashi, N. A., de Castro Maymone, M. B., & Kundu, R. V. (2016). Aging differences in ethnic skin. J Clin Aesthet Dermatol, 9(1), 31–38.
Fink, C., Fuchs, T., Enk, A., & Haenssle, H. A. (2018). Design of an algorithm for automated, computer-guided PASI measurements by digital image analysis. J Med Syst, 42(12), 248.
FotoFinder Systems. (n.d.). Artificial intelligence in dermatology. https://www.fotofinder.de/en/technology/artificial-intelligence
Haenssle, H. A., Fink, C., Schneiderbauer, R., et al. (2018). Man against machine: Diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists. Ann Oncol, 29(8), 1836–1842.
Thomsen, K., Iversen, L., Titlestad, T. L., & Winther, O. (2020). Systematic review of machine learning for diagnosis and prognosis in dermatology. J Dermatolog Treat, 31(5), 496–510.
Kim, B. R., Won, S. H., Kim, J. W., et al. (2023). Development of a new classification and scoring system for scalp conditions: Scalp photographic index (SPI). J Dermatolog Treat, 34(1), 2181655.
Kim, B. R., Kim, M. J., Koo, J., et al. (2024). Artificial intelligence-based prescription of personalized scalp cosmetics improved the scalp condition: Efficacy results from 100 participants. J Dermatolog Treat, 35(1), 2337908.
Ou, C., Zhou, S., Yang, R., et al. (2022). A deep learning based multimodal fusion model for skin lesion diagnosis using smartphone collected clinical images and metadata. Front Surg, 9, 1029991.
Soenksen, L. R., Ma, Y., Zeng, C., et al. (2022). Integrated multimodal artificial intelligence framework for healthcare applications. NPJ Digit Med, 5(1), 149.
Acosta, J. N., Falcone, G. J., Rajpurkar, P., & Topol, E. J. (2022). Multimodal biomedical AI. Nat Med, 28(9), 1773–1784.
Chan, S., Reddy, V., Myers, B., Thibodeaux, Q., Brownstone, N., & Liao, W. (2020). Machine learning in dermatology: Current applications, opportunities, and limitations. Dermatol Ther, 10(3), 365–386.
Boehm, K. M., Aherne, E. A., Ellenson, L., et al. (2022). Multimodal data integration using machine learning improves risk stratification of high-grade serous ovarian cancer. Nat Cancer, 3(6), 723–733.
Fassi, S. C. E., Abdullah, A., Fang, Y., et al. (2024). Not all AI health tools with regulatory authorization are clinically validated. Nat Med, 30, 1–3.
Salminen, A. T., Manga, P., & Camacho, L. (2023). Race, pigmentation, and the human skin barrier—considerations for dermal absorption studies. Front Toxicol, 5, 1271833.
Menzies, S. W., Sinz, C., Menzies, M., et al. (2023). Comparison of humans versus mobile phone-powered artificial intelligence for the diagnosis and management of pigmented skin cancer in secondary care. Lancet Digit Health, 5(10), e679–e691.
Chanda, T., Hauser, K., Hobelsberger, S., et al. (2024). Dermatologist-like explainable AI enhances trust and confidence in diagnosing melanoma. Nat Commun, 15(1), 1–17.
Clarys, P., Alewaeters, K., Lambrecht, R., & Barel, A. O. (2000). Skin color measurements: Comparison between three instruments: The chromameter, the DermaSpectrometer and the Mexameter. Skin Res Technol, 6(4), 230–238.
Abràmoff, M. D., Tarver, M. E., Loyo-Berrios, N., et al. (2023). Considerations for addressing bias in artificial intelligence for health equity. NPJ Digit Med, 6(1), 170.
Daneshjou, R., Vodrahalli, K., Novoa, R. A., et al. (2022). Disparities in dermatology AI performance on a diverse, curated clinical image set. Sci Adv, 8(32), abq6147.
Mei, X., Liu, Z., Robson, P. M., et al. (2022). RadImageNet: An open radiologic deep learning research dataset for effective transfer learning. Radiol Artif Intell, 4(5), e210315.
Haggenmüller, S., Schmitt, M., Krieghoff-Henning, E., et al. (2024). Federated learning for decentralized artificial intelligence in melanoma diagnostics. JAMA Dermatol, 160(3), 303–311.
Rieke, N., Hancox, J., Li, W., et al. (2020). The future of digital health with federated learning. NPJ Digit Med, 3, 119.
Cho, S. I., Navarrete-Dechent, C., Daneshjou, R., et al. (2023). Generation of a melanoma and nevus dataset from unstandardized clinical photographs on the internet. JAMA Dermatol, 159(11), 1223–1231.
Charalambides, M., Flohr, C., Bahadoran, P., & Matin, R. N. (2021). New international reporting guidelines for clinical trials evaluating effectiveness of artificial intelligence interventions in dermatology. Br J Dermatol, 184(3), 381–383.
Daneshjou, R., Barata, C., Betz-Stablein, B., et al. (2022). Checklist for evaluation of image-based artificial intelligence reports in dermatology. JAMA Dermatol, 158(1), 90–96.
Bommasani, R., Hudson, D. A., Adeli, E., et al. (2022). On the opportunities and risks of foundation models. Stanford Center for Research on Foundation Models.
Moor, M., Banerjee, O., Abad, Z. S. H., et al. (2024). Foundation models for generalist medical artificial intelligence. Nature, 616, 259–265.
Singhal, K., Tu, T., Gottweis, J., et al. (2025). Towards expert-level medical question answering with large language models. Nature, 637, 842–850.
Topol, E. J. (2024). The creative destruction of medicine by generative AI. Nat Med, 30(1), 14–22.
Ghassemi, M., Naumann, T., Schulam, P., et al. (2024). Practical guidance on artificial intelligence for health-care data. Lancet Digit Health, 6, e206–e214.
Cho, S. I., Navarrete-Dechent, C., Daneshjou, R., et al. (2023). Generation of a melanoma and nevus dataset from unstandardized clinical photographs on the internet. JAMA Dermatol, 159(11), 1223–1231.
Acosta, J. N., Falcone, G. J., Rajpurkar, P., & Topol, E. J. (2022). Multimodal biomedical AI. Nat Med, 28(9), 1773–1784.
Meskó, B., & Topol, E. J. (2024). The imperative for regulatory oversight of generative artificial intelligence in health care. NPJ Digit Med, 7, 46.
Benjamens, S., Dhunnoo, P., & Meskó, B. (2024). The state of artificial intelligence-based FDA-approved medical devices and clinical validation. NPJ Digit Med, 7, 12.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Anna Kropiwnicka, Krzysztof Sebastian Habirek, Maja Maria Porażko, Anna Katarzyna Żurakowska-Zadrożna, Adrianna Krupska, Julia Anna Czarnecka, Zuzanna Marta Marcinkowska, Joanna Zuzanna Gugulska, Michał Kieres, Klaudia Karolina Wójcik, Aleksander Kacper Kierys, Michał Mieczysław Parus
This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles are published in open-access and licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0). Hence, authors retain copyright to the content of the articles.
CC BY 4.0 License allows content to be copied, adapted, displayed, distributed, re-published or otherwise re-used for any purpose including for adaptation and commercial use provided the content is attributed.
