ARTIFICIAL INTELLIGENCE AS A DECISION TOOL FOR SKIN LESIONS TRIAGE IN PRIMARY CARE: A NARRATIVE REVIEW

Zuzanna Pietruk; Michał Kozicki; Przemysław Siemiątkowski; Agnieszka Kiedik; Sylwia Skraińska; Julia Kozłowska; Jakub Chamier-Gliszczyński; Dominik Ryszard Płaza; Kacper Zima

doi:10.31435/ijitss.1(49).2026.4806

Authors

Zuzanna Pietruk Florian Ceynowa Specialist Hospital, Wejherowo, Poland https://orcid.org/0009-0007-1360-3248
Michał Kozicki Florian Ceynowa Specialist Hospital, Wejherowo, Poland https://orcid.org/0009-0006-5539-6825
Przemysław Siemiątkowski 7th Navy Hospital in Gdańsk, Gdańsk, Poland https://orcid.org/0000-0003-2120-6051
Agnieszka Kiedik Medical University of Gdańsk, Gdańsk, Poland https://orcid.org/0009-0002-1507-8479
Sylwia Skraińska Szpital Specjalistyczny w Kościerzynie, Kościerzyna, Poland https://orcid.org/0009-0002-7644-5340
Julia Kozłowska Szpital Specjalistyczny w Kościerzynie, Kościerzyna, Poland https://orcid.org/0009-0005-1814-4437
Jakub Chamier-Gliszczyński Neurosurgery Department, 10th Military Research Hospital and PolyClinic SPZOZ, Bydgoszcz, Poland; Scientific Circle of Neurotraumatology, Department of Emergency Medicine, Medical University of Gdańsk, Gdańsk, Poland https://orcid.org/0009-0006-8971-9864
Dominik Ryszard Płaza Scientific Circle of Neurotraumatology, Department of Emergency Medicine, Medical University of Gdańsk, Gdańsk, Poland https://orcid.org/0009-0000-6251-3969
Kacper Zima Szpital Specjalistyczny w Kościerzynie, Kościerzyna, Poland https://orcid.org/0009-0006-0679-6435

DOI:

https://doi.org/10.31435/ijitss.1(49).2026.4806

Keywords:

Artificial Intelligence, Primary Care, Skin Lesions, Skin Cancer, Dermoscopy, Melanoma

Abstract

Background: Skin lesions are one of the common reasons for consultations in primary care (PC). Among them, skin cancers are a key clinical challenge, where early detection is crucial for the patient’s prognosis. Primary care physicians (PCPs) are responsible for the initial classification of skin conditions, determining which cases require referral to a specialist. In recent years, solutions using artificial intelligence (AI) have been gaining growing interest in medicine, offering new possibilities for diagnostic support, including in the field of dermatology.

Objectives: The aim of this narrative review is to analyze the literature on whether and how artificial intelligence (AI) can support primary care physicians in the initial classification of skin lesions.

Methods: A comprehensive review of the literature regarding the application of artificial intelligence in skin cancer diagnosis was conducted. The analysis covered results from clinical trials and reviews identifying implementation barriers.

Key findings: Results from recent multicenter clinical trials demonstrate that Artificial Intelligence algorithms achieve high diagnostic sensitivity for melanoma, as well as robust accuracy for non-melanoma skin cancers. Comparative studies indicate that while AI performance is comparable to that of board-certified dermatologists, it statistically outperforms less experienced physicians.

Conclusion: The conclusions from the study indicate that artificial intelligence can support primary care physicians by increasing their diagnostic effectiveness in the triage of skin lesions. As a support tool, it has the potential to reduce the risk of missing cancers while reducing the number of unreasonable referrals to specialists. However, a key condition for introducing these technologies into everyday clinical practice is to resolve identified ethical and technological barriers.

References

Arnold, M., Singh, D., Laversanne, M., Vignat, J., Vaccarella, S., Meheus, F., Cust, A. E., De Vries, E., Whiteman, D. C., & Bray, F. (2022). Global burden of cutaneous melanoma in 2020 and projections to 2040. JAMA Dermatology, 158(5), 495–503. https://doi.org/10.1001/jamadermatol.2022.0160

Bray, F., Laversanne, M., Sung, H., Ferlay, J., Siegel, R. L., Soerjomataram, I., & Jemal, A. (2024). Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: A Cancer Journal for Clinicians, 74(3), 229–263. https://doi.org/10.3322/caac.21834

Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017). Dermatologist-level classification of skin cancer with deep neural networks. Nature, 542(7639), 115–118. https://doi.org/10.1038/nature21056

Freeman, K., Dinnes, J., Chuchu, N., Takwoingi, Y., Bayliss, S. E., Matin, R. N., Jain, A., Walter, F. M., Williams, H. C., & Deeks, J. J. (2020). Algorithm based smartphone apps to assess risk of skin cancer in adults: Systematic review of diagnostic accuracy studies. BMJ, 368, Article m127. https://doi.org/10.1136/bmj.m127

Goyal, M., Knackstedt, T., Yan, S., & Hassanpour, S. (2020). Artificial intelligence-based image classification methods for diagnosis of skin cancer: Challenges and opportunities. Computers in Biology and Medicine, 127, Article 104065. https://doi.org/10.1016/j.compbiomed.2020.104065

Jones, O. T., Jurascheck, L. C., Van Melle, M. A., Hickman, S., Burrows, N. P., Hall, P. N., Emery, J., & Walter, F. M. (2019). Dermoscopy for melanoma detection and triage in primary care: A systematic review. BMJ Open, 9(8), Article e027529. https://doi.org/10.1136/bmjopen-2018-027529

Liopyris, K., Gregoriou, S., Dias, J., & Stratigos, A. J. (2022). Artificial intelligence in dermatology: Challenges and perspectives. Dermatology and Therapy, 12(12), 2637–2651. https://doi.org/10.1007/s13555-022-00833-8

Marques, M., Almeida, A., & Pereira, H. (2024). The medicine revolution through artificial intelligence: Ethical challenges of machine learning algorithms in decision-making. Cureus, 16(9), Article e69405. https://doi.org/10.7759/cureus.69405

Marsden, H., Morgan, C., Austin, S., DeGiovanni, C., Venzi, M., Kemos, P., Greenhalgh, J., Mullarkey, D., & Palamaras, I. (2023). Effectiveness of an image analyzing AI-based digital health technology to identify non-melanoma skin cancer and other skin lesions: Results of the DERM-003 study. Frontiers in Medicine, 10, Article 1288521. https://doi.org/10.3389/fmed.2023.1288521

Menzies, S. W., Sinz, C., Menzies, M., Lo, S. N., Yolland, W., Lingohr, J., Razmara, M., Tschandl, P., Guitera, P., Scolyer, R. A., Boltz, F., Borik-Heil, L., Herbert Chan, H., Chromy, D., Coker, D. J., Collgros, H., Eghtedari, M., Corral Forteza, M., Forward, E., et al. (2023). Comparison of humans versus mobile phone-powered artificial intelligence for the diagnosis and management of pigmented skin cancer in secondary care: A multicentre, prospective, diagnostic, clinical trial. The Lancet Digital Health, 5(10), e679–e691. https://doi.org/10.1016/s2589-7500(23)00130-9

Narla, A., Kuprel, B., Sarin, K., Novoa, R., & Ko, J. (2018). Automated classification of skin lesions: From pixels to practice. Journal of Investigative Dermatology, 138(10), 2108–2110. https://doi.org/10.1016/j.jid.2018.06.175

Okobi, O. E., Abreo, E., Sams, N. P., Chukwuebuni, O. H., Tweneboa Amoako, L. A., Wiredu, B., Uboh, E. E., Ekechi, V. C., & Okafor, A. A. (2024). Trends in melanoma incidence, prevalence, stage at diagnosis, and survival: An analysis of the United States Cancer Statistics (USCS) database. Cureus, 16(10), Article e70697. https://doi.org/10.7759/cureus.70697

Papachristou, P., Söderholm, M., Pallon, J., Taloyan, M., Polesie, S., Paoli, J., Anderson, C. D., & Falk, M. (2024). Evaluation of an artificial intelligence-based decision support for the detection of cutaneous melanoma in primary care: A prospective real-life clinical trial. British Journal of Dermatology, 191(1), 125–133. https://doi.org/10.1093/bjd/ljae021

Urban, K., Mehrmal, S., Uppal, P., Giesey, R. L., & Delost, G. R. (2021). The global burden of skin cancer: A longitudinal analysis from the Global Burden of Disease Study, 1990–2017. JAAD International, 2, 98–108. https://doi.org/10.1016/j.jdin.2020.10.013