1.
Dear Editor,
In recent years, the field of cosmetic dermatology has witnessed a remarkable transformation with the integration of Artificial Intelligence (AI) technologies. This groundbreaking shift has not only enhanced the precision and efficacy of cosmetic procedures but has also opened new avenues for personalized skincare. AI is driving a remarkable revolution in the rapidly evolving field of cosmetic dermatology through highly accurate visualization capabilities. This technological marvel is revolutionizing both the beauty and skincare industry, ushering a new era where accuracy and customization will reign supreme. From accurate skin analysis and diagnosis, to the creation of individualized treatment plans, AI has a far‐reaching impact on the field of cosmetic dermatology. 1 Further, it helps improve aesthetic procedures and early detection of skin cancer, in addition to predicting treatment outcomes and facilitating virtual consultations. The ability of AI to analyze and diagnose skin conditions with pinpoint accuracy is central to this shift. 2 , 3 Nowadays, dermatologists can make objective diagnoses of a wide range of skin conditions thanks to AI algorithms that have replaced subjective methods. There are several studies conducted and published that confirm the reliability of AI diagnostic systems in dermatology; as an instance, DIET‐AI. 4 , 5 , 6 The risks in cosmetic dermatological practice start with the unrealistic expectations within the pre‐treatment period. Untailored treatment plan is another risk that augments the probability of post‐treatment complications. Therefore, a tailored treatment plan with realistic expectations is the key to a successful treatment. During the treatment, there is always the risk of human error in performing the procedure. For the sake of the safety of the treatment process, minimizing errors is essential. AI‐based tools provide a detailed analysis of the skin texture, pigmentation, and subtle nuances for a more precise and effective diagnosis than that of the naked eye alone. In cosmetic dermatology, the true magic of AI emerges in its ability to personalize treatment plans to each patient. AI algorithms customize treatments for individual patients based on their skin type, concerns, and sensitivities. It does this through deep learning which continues updating and improving through accumulation of new patient data acquired with time. This feature not only benefits the doctor's perspective, but also helps patients see the potential results via virtual “try‐on” before committing to certain aesthetic procedures. The ability to predict treatment results through the use of AI resolves the unrealistic expectations issue to a great extent. In similar terms, AI enables patients to make informed decisions about cosmetic procedures which lead to having a tangible preview of what to expect. All the mentioned factors contribute to patient‐doctor confidence. Moreover, the transparency of this technology not only fosters confidence between doctor and patient, but also gives people the tools they need to take charge of their own beauty routines. Similarly, some researches indicate that most patients feel empowered by using teledermatological tools, thus are more likely to trust dermatologists. In turn, an era of convenience is expecting the field of dermatology as a result of AI‐based consultations and telemedicine. 7 , 8 Apart from reducing commuting time for the patients and the doctors, AI technology is not far from globalizing cosmetic dermatological procedures in terms of accessibility. To clarify, the traditional cosmetic dermatological procedures have been conducted in one‐on‐one sessions due to the risk of wrong diagnosis and the complications of virtual follow‐ups. However, the precision of the tools facilitated by AI (whether it is deep tissue analysis through images, suggesting individualized treatment plan, performing the treatment procedure or follow‐up using precise image analysis) can reduce the relevance of one‐on‐one sessions, making hybrid cosmetic dermatological procedures a reliable option. This change in the dynamics of cosmetic dermatological procedures promises a new order with new advantages and problems which we will discuss later in the ethics argument. Last but not least, the perks of using AI in dermatology goes beyond building confidence in the patient, as it also helps guide the treatment processes of injectables, laser treatments, and surgical procedures. 9 Doctors are able to achieve previously unimaginable results by leveraging artificial neural networks which make complex mappings between inputs (e.g., images) and outputs (e.g., diagnoses) reliably accurate. Well known studies such as the ones conducted by Young et al. and Brinker el al. have compared AI generated sensitivity and accuracy in skin condition diagnosis and analysis with human clinician performance. 4 , 10 , 11 The results of these studies show a significant higher accuracy in AI generated analyses and diagnoses. However, AI is in the end a service produced for humans through machines; as simple as it may look, even the most accurate machines may go through glitches and malfunctioning. Even if the percentage of such incidents is low, as human life is at stake, human doctors are indispensable from medical procedures. Moreover, pre‐consultation workflow and post‐operative management can both be automated with the help of AI. By training on a large dataset, including responses to various treatments for various skin types, generative AI can simulate the effects of topical treatments and potential outcomes of the given skin condition. Facial aging and the exposome impact simulations are made possible through the use of AI and augmented reality. 3 , 12 , 13 , 14 The simulations are able to provide a visual representation of the aging process by training AI models on various datasets, taking into account factors such as environmental influences and genetic conditions. Furthermore, generative AI for personalized surgical procedures, including the pre‐operative preparation, surgical, and postoperative recovery period, use advanced algorithms to allow for the creation of unique surgical plans for each patient. However, in order to ensure the accuracy and suitability of these AI‐generated plans for surgical implementation, it is crucial that they be subject to a thorough assessment and approval by trained medical experts. 15 , 16 , 17 Additionally, as AI is becoming an essential part of our daily lives, it is vital for consumers to have trust in these applications and processes. 18 The ability of AI to learn from its users’ input, and providing precise, accurate and reliable results, as well as data security and privacy, are important contributors to earning the trust of the consumer. Accuracy is of the utmost importance, and the use of AI technologies drastically decreases the risk for error, however, it does not eliminate the risk. Therefore, it is crucial to eradicate any biases that may exist in the underlying algorithms. Another element to consider is whether the guarantee for the benefits of AI technology is widely available and fairly distributed. Although for practitioners, the medical practices seem likely to be augmented rather than only automated by AI, the cost‐effectiveness of AI tools stays a concern which will inevitably affect the fair availability of this technology. 19 To prove this point, an economic evaluation by Rossi et al. showed that the cost‐effectiveness of AI as a decision system is, at this stage, limited and case‐specific, despite the fact that further improvements will also boost its cost‐effectiveness. 20 Alongside economic perspectives, the ethical aspect of AI‐based dermatology involves meticulous integration processes. Through stakeholder taxonomy, responsible and effective integration of AI in dermatology is ensured, taking into account the perspectives and needs of all stakeholders (payers, patients, physicians). In the light of ethical concerns, protecting patients' privacy and personal information remains a top priority. The philosopher Nick Bostrom stresses the serious ethical concerns raised by the advancement of AI. He reiterates the importance of control and oversight, warning against the dangers of developing super‐intelligent systems that could outshine humanity. 21 In order to tone down the potential malicious effects of AI integration in our clinical practice, it is necessary that we raise innovation, encourage collaboration, and enact effective regulations. 22 The future of AI in cosmetic dermatology holds exciting promises for practitioners and patients alike, from refining existing practices to possibly uncovering entirely new horizons. The use of AI in cosmetic dermatology represents a quantum leap rather than a small step forward. In dermatology, AI has shown to be extremely beneficial, much as it has in other medical specialties. AI can help dermatologists with a variety of tasks, from diagnosing different dermatological conditions to detecting skin cancer, by analyzing large datasets and complex algorithms. It can enhance the speed, accuracy and efficiency of the diagnostic process, which predictably meliorate patient outcomes. 23 AI‐powered solutions can also make telemedicine consultations easier and provide patients with useful information about their skin condition. The quality of care in this significant medical area could be greatly improved by the synergistic collaboration between AI and dermatology. In consideration of the above‐mentioned arguments, the future of cosmetic dermatology is brighter than ever.
CONFLICT OF INTEREST STATEMENT
The authors declare no conflicts of interest.
Haykal D, Garibyan L, Flament F, Cartier H. Hybrid cosmetic dermatology: AI generated horizon. Skin Res Technol. 2024;30:e13721. 10.1111/srt.13721
DATA AVAILABILITY STATEMENT
The data that support the findings of this study are available on references' part.
REFERENCES
- 1. Haykal D, Cartier H, du Crest D, Galadari H, Landau M, Haddad A. What happens when simulations get real and cosmetic dermatology goes virtual? J Cosmet Dermatol. 2023;22(10):2682‐2684. Accessed July 11, 2023. https://onlinelibrary.wiley.com/doi/abs/10.1111/jocd.15888 [DOI] [PubMed] [Google Scholar]
- 2. Yoon H, Kim S, Lee J, Yoo S. Deep‐learning‐based morphological feature segmentation for facial skin image analysis. Diagn Basel Switz. 2023;13(11):1894. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 3. Flament F, Zhang Y, Yu Z, et al. Developing an Artificial Intelligence (A.I)‐based descriptor of facial appearance that fits with the assessments of makeup experts. Skin Res Technol. 2021;27(6):1081‐1091. [DOI] [PubMed] [Google Scholar]
- 4. Young AT, Xiong M, Pfau J, Keiser MJ, Wei ML. Artificial intelligence in dermatology: a primer. J Invest Dermatol. 2020;140(8):1504‐1512. [DOI] [PubMed] [Google Scholar]
- 5. Liu Y, Jain A, Eng C, et al. A deep learning system for differential diagnosis of skin diseases. Nat Med. 2019;26(6):900‐908. Accessed November 5, 2023. http://arxiv.org/abs/1909.05382 [DOI] [PubMed] [Google Scholar]
- 6. Li H, Zhang P, Wei Z, et al. Deep skin diseases diagnostic system with Dual‐channel Image and Extracted Text. Front Artif Intell. 2023;6:1213620. Accessed November 5, 2023. https://www.frontiersin.org/articles/10.3389/frai.2023.1213620 [DOI] [PMC free article] [PubMed] [Google Scholar]
- 7. Tuknayat A, Bhalla M, Dogar K, Thami GP, Sandhu JK. Clinical profile and diagnostic accuracy of patient‐submitted photographs in teledermatology. J Clin Aesthetic Dermatol. 2023;16(4):21‐25. [PMC free article] [PubMed] [Google Scholar]
- 8. Haykal D, Cartier H, Rossi A, Margara A, du Crest D. The art of a successful cosmetic consultation in 2023. J Eur Acad Dermatol Venereol JEADV. 2023;37(9):e1166‐e1167. [DOI] [PubMed] [Google Scholar]
- 9. Kapoor KM, Kapoor A, Bertossi D. Role of robotics in neuromodulator and filler injections of face. Indian J Plast Surg. 2023;56(5):470‐473. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 10. Brinker TJ, Hekler A, Enk AH, Klode J, Hauschild A, Berking C, et al. A convolutional neural network trained with dermoscopic images performed on par with 145 dermatologists in a clinical melanoma image classification task. Eur J Cancer Oxf Engl 1990. 2019;111:148‐154. [DOI] [PubMed] [Google Scholar]
- 11. Brinker TJ, Hekler A, Enk AH, Klode J, Hauschild A, Berking C, et al. Deep learning outperformed 136 of 157 dermatologists in a head‐to‐head dermoscopic melanoma image classification task. Eur J Cancer. 2019;113:47‐54. [DOI] [PubMed] [Google Scholar]
- 12. Flament F, Zhang Y, Jiang R, et al. Objective and automatic grading system of facial signs from selfie pictures of South African women: characterization of changes with age and sun‐exposures. Skin Res Technol. 2022;28(4):596‐603. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 13. Flament F, Velleman D, Yamashita E, et al. Japanese experiment of a complete and objective automatic grading system of facial signs from selfie pictures: validation with dermatologists and characterization of changes due to age and sun exposures. Skin Res Technol. 2021;27(4):544‐553. [DOI] [PubMed] [Google Scholar]
- 14. Zhang Y, Jiang R, Kezele I, et al. A new procedure, free from human assessment, that automatically grades some facial skin signs in men from selfie pictures. Application to changes induced by a severe aerial chronic urban pollution. Int J Cosmet Sci. 2020;42(2):185‐197. [DOI] [PubMed] [Google Scholar]
- 15. Hashimoto DA, Rosman G, Rus D, Meireles OR. Artificial intelligence in surgery: promises and perils. Ann Surg. 2018;268(1):70‐76. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 16. Rokhshad R, Keyhan SO, Yousefi P. Artificial intelligence applications and ethical challenges in oral and maxillo‐facial cosmetic surgery: a narrative review. Maxillofac Plast Reconstr Surg. 2023;45(1):14. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 17. Liu PR, Lu L, Zhang JY, Huo TT, Liu SX, Ye ZW. Application of artificial intelligence in medicine: an overview. Curr Med Sci. 2021;41(6):1105‐1115. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 18. Wang G, Meng X, Zhang F. Past, present, and future of global research on artificial intelligence applications in dermatology: a bibliometric analysis. Medicine. 2023;102(45):e35993. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 19. Karako K, Song P, Chen Y, Tang W. Realizing 5G‐ and AI‐based doctor‐to‐doctor remote diagnosis: opportunities, challenges, and prospects. Biosci Trends. 2020;14(5):314‐317. [DOI] [PubMed] [Google Scholar]
- 20. Rossi JG, Rojas‐Perilla N, Krois J, Schwendickle F. Cost‐effectiveness of artificial intelligence as a decision‐support system applied to the detection and grading of melanoma, dental caries, and diabetic retinopathy. JAMA Network Open. 2022;5(3):e220269. Accessed September 20, 2023. https://jamanetwork.com/journals/jamanetworkopen/fullarticle/2790106 [DOI] [PMC free article] [PubMed] [Google Scholar]
- 21. Bostrom N. The vulnerable world hypothesis. Glob Policy. 2019;10(4):455‐476. [Google Scholar]
- 22. Sangers TE, Kittler H, Blum A, et al. Position statement of the EADV Artificial Intelligence (AI) Task Force on AI‐assisted smartphone apps and web‐based services for skin disease. J Eur Acad Dermatol Venereol JEADV. 2023;38(1):22‐30. Accessed September 27, 2023. [DOI] [PubMed] [Google Scholar]
- 23. Goh CL. Will digitization, big data and artificial intelligence– and deep learning–based algorithm govern the practice of medicine? J Eur Acad Dermatol Venereol. 2022;36(7):947‐947. [DOI] [PubMed] [Google Scholar]
Associated Data
This section collects any data citations, data availability statements, or supplementary materials included in this article.
Data Availability Statement
The data that support the findings of this study are available on references' part.