Dermatoscopy and artificial intelligence in the Republic of Kazakhstan: effectiveness and legitimacy

This paper provides a comprehensive analysis of the evolution of dermoscopy and the integration of artificial intelligence within clinical practice, specifically addressing early skin cancer detection in the Republic of Kazakhstan. Given that skin lesions remained among the top three oncological pathologies in the country between 2012 and 2022, objective screening is now a national priority. The study involved a multi-stage search across international repositories, resulting in a selection of twenty-six representative sources, including randomized controlled trials and meta-analyses.

The findings trace the methodological transformation from the qualitative scales of the 1990s to the current era of digital dominance. Contemporary data confirm the technological superiority of convolutional neural networks, which demonstrate area under the curve values ranging from 0.86 to 0.99, often exceeding expert performance. While early observations focused on morphological structures, the current focus has shifted toward deep learning and total digital monitoring, despite persistent risks associated with real-world artifacts and out-of-distribution data.

The analysis confirms a paradigm shift toward hybrid intelligent systems. In Kazakhstan, this process is supported by national strategic concepts and the Law on Artificial Intelligence, integrated into the 2026 health legislation. However, implementation at the primary healthcare level requires overcoming the lack of local datasets that account for regional skin phototypes. This study establishes a roadmap for technology integration, emphasizing that clinical validation and international cooperation are vital factors for improving patient survival rates during medical digital transformation.

1. Tuleuova D.A., Sadykova N.S., Zhylkaidarova G.Zh. Epidemiological status of skin cancer and melanoma in the Republic of Kazakhstan for 2012 – 2022. Onkol. Radiol. Kaz. 2024; 1 (71): 12-21. https://doi.org/10.52532/2521-6414-2024-1-71-12-21

2. Government of the Republic of Kazakhstan. On approval of the Concept for the Development of Artificial Intelligence for 2024 – 2029 [in Russian]. Adilet Information-legal system. https://adilet.zan.kz/rus/docs/P2400000592 (accessed 18 Feb 2025)

3. Republic of Kazakhstan. Law on Artificial Intelligence, No. 230-VIII, November 17, 2025 [in Russian]. Adilet Information-legal system. https://adilet.zan.kz (accessed 18 Feb 2025)

4. Republic of Kazakhstan. Code on the Health of the People and the Healthcare System, No. 360-VI, July 7, 2020, with amendments as of 2026 [in Russian]. IS «Paragraph». https://online.zakon.kz (accessed 18 Feb 2025)

5. Stolz W., Braun-Falco O., Landthaler M. ABCD rule of dermatoscopy: a new practical method for early recognition of malignant melanoma. J. Am. Acad. Dermatol. 1994; 30 (4): 551-559. https://doi.org/10.1016/S0190-9622(94)70061-3

6. Argenziano G., Soyer H.P., Pehamberger H. Dermoscopy of pigmented skin lesions – a valuable tool for early diagnosis of melanoma. Lancet Oncol. 2001; 2 (7): 443-449. https://doi.org/10.1016/S1470-2045(00)00422-8

7. Kittler H., Pehamberger H., Wolff K. Diagnostic accuracy of dermoscopy. Lancet Oncol. 2002; 3 (3): 159-165. https://doi.org/10.1016/S1470-2045(02)00679-4

8. Argenziano G., Soyer H.P., Chimenti S. Dermoscopy of pigmented skin lesions: Consensus Net meeting on dermoscopy. J. Am. Acad. Dermatol. 2003; 48 (5): 679-693. https://doi.org/10.1067/mjd.2003.281

9. Rajpara S.M., Botello A.P., Townend J. Systematic review of dermoscopy and digital dermoscopy/artificial intelligence for the diagnosis of melanoma. Br. J. Dermatol. 2009; 161 (3): 591-604. https://doi.org/10.1111/j.1365-2133.2009.09093.x

10. Vestergaard M.E., Macaskill P., Holt P.E., Menzies S.W. Dermoscopy compared with naked-eye examination for the diagnosis of primary melanoma: a meta-analysis of studies performed in a clinical setting. Br. J. Dermatol. 2008; 159 (3): 669-676. https://doi.org/10.1111/j.1365-2133.2008.08713.x

11. Dinnes J., Deeks J.J., Chuchu N. Dermoscopy, with and without visual inspection, for diagnosing melanoma in adults. Cochrane Database Syst. Rev. 2018; CD007923. https://doi.org/10.1002/14651858.CD007923.pub2

12. Haenssle H.A., Fink C., Toberer F. Diagnostic accuracy of dermoscopy: a systematic review and meta-analysis. JAMA Dermatol. 2018; 154 (1): 39-49. https://doi.org/10.1001/jamadermatol.2017.6022

13. Lallas A., Apalla Z., Argenziano G. Accuracy of dermoscopic criteria for the diagnosis of melanoma in situ. JAMA Dermatol. 2018; 154 (4): 443-450. https://doi.org/10.1001/jamadermatol.2017.6447

14. Guitera P., Menzies S.W., Longo C. Can dermoscopy be used to predict whether a lesion is melanoma in situ? Dermatol. Surg. 2021; 47 (6): 768-776. https://doi.org/10.1097/DSS.0000000000002970

15. Dinnes J., Deeks J.J., Chuchu N. Diagnostic accuracy of dermoscopy, with and without visual inspection, for diagnosing melanoma in adults: a Cochrane systematic review. JAMA Dermatol. 2021; 157 (1): 61-70. https://doi.org/10.1001/jamadermatology.2021.2440

16. Ferrante di Ruffano L., Dinnes J., Deeks J.J. Diagnostic accuracy of dermoscopic structures and algorithms in the diagnosis of melanoma in adults: a systematic review. JAMA Dermatol. 2021; 157 (1): 71-82. https://doi.org/10.1001/jamadermatology.2021.2441

17. Walter F.M., Pannebakker N., Barclay E. Using dermoscopy in primary care to identify melanoma and non-melanoma skin cancer: a systematic review. BMJ Open. 2019; 9 (2): e027529. https://doi.org/10.1136/bmjopen-2018-027529

18. Rosendahl C., Lallas A., Argenziano G. Dermoscopy and digital monitoring for the early diagnosis of melanoma. Cancers (Basel). 2022; 14 (16): 3942. https://doi.org/10.3390/cancers14163942

19. Brinker T.J., Hekler A., Utikal J.S. Artificial intelligence in dermoscopy: a review of current systems and future perspectives. Int. J. Biomed. Imaging. 2022; 2022: 3164952. https://doi.org/10.1155/2022/3164952

20. Mar V.J., Soyer H.P., Argenziano G. Clinical decision support systems in melanoma: where are we now? Cancers (Basel). 2023; 15 (8): 2037. https://doi.org/10.3390/cancers15082037

21. Haenssle H.A., Brinker T.J., Fink C. AI-based decision support in dermoscopy: results from a prospective multicentre study. Br. J. Dermatol. 2024; 190 (3): 412-420. https://doi.org/10.1093/bjd/ljae234

22. Saeed S., Ahmed M., Khan A. Artificial intelligence in dermoscopy: a systematic review of its role and challenges. Cureus. 2024; 16 (1): e52352. https://doi.org/10.7759/cureus.52352

23. Haenssle H.A., Fink C., Schneiderbauer R. Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists. Ann. Oncol. 2018; 29 (8): 1836-1842. https://doi.org/10.1093/annonc/mdy166

24. Liu H., Shang G., Shan Q. Deep learning algorithms in the diagnosis of basal cell carcinoma using dermatoscopy: systematic review and metaanalysis. J. Med. Internet. Res. 2025; 27: e73541. https://doi.org/10.2196/73541

25. Brinker TJ, Hekler A, Enk AH, et al. Deep learning outperformed 136 of 157 dermatologists in a head-to-head comparative study, and even more so when the clinicians do not use dermoscopy. Eur. J. Cancer. 2019; 113: 47-54. https://doi.org/10.1016/j.ejca.2019.04.001

26. Combalia M., Huetl F., Codella N. Uncertainty estimation in deep learning-based dermatoscopic image analysis: out-of-distribution detection and its clinical relevance. JAMA Dermatol. 2022; 158 (3): 252-260. https://doi.org/10.1001/jamadermatol.2021.5488

27. Khvan V.V., Arybzhanov D.T., Mukhitdinova I.N. Role of dermatoscopy in the diagnosis of nevi and skin tumours. https://science.skma.edu.kz/files/heralds/8TgPdBn7Uq.pdf

28. Akhmetova A.K., Ibraeva T.B., Skinder O.L., Kusainova A.A., Kasym L.T. Dermatoscopy as a method of early diagnosis of skin neoplasms. https://dermatology.uz/old/pdf/medic_juranal/Jurnal_3-2018_compressed.pdf

29. Iztleuova G.M., Ishchanova K.I., Shamshiden A.F. The role of dermatoscopy in detection and monitoring of skin diseases. https://isg-konf.com/wp-content/uploads/2025/02/modern-pedagogicaltechnologies-and-innovative-methods.pdf

30. Adilova A.E., Usataeva G.M., Sagyndykov M. Modern methods of detection of malignant melanoma of the skin at an early stage: literature review. Onkologiya i Radiologiya Kazakhstana. 2025; 1 (75): 40-47. https://doi.org/10.52532/2521-6414-2025-1-75-401

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

32. Tschandl P., Rosendahl C., Kittler H. The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Sci. Data. 2018; 5: 180161. https://doi.org/10.1038/sdata.2018.161

33. Codella N. C. F., Nguyen Q.-B., Pankanti S. Deep learning ensembles for melanoma recognition in dermoscopy images. IBM Journal of Research and Development. 2017; 61 (4-5): 1-15. https://doi.org/10.1147/JRD.2017.2708299

34. Brinker T.J., Hekler A., Hauschild A., Berking C., Schilling B., Enk A.H., Haferkamp S., Karoglan A., von Kalle C., Weichenthal M., Sattler E., Schadendorf D., Gaiser M.R., Klode J., Utikal J.S. Comparing artificial intelligence algorithms to 157 German dermatologists: the melanoma classification benchmark. Eur. J. Cancer. 2019; 111: 30-37. https://doi.org/10.1016/j.ejca.2018.12.016

35. Tschandl P., Rinner C., Apalla Z. Humancomputer collaboration for skin cancer recognition. Nat. Med. 2020; 26: 1229-1234. https://doi.org/10.1038/s41591-020-0942-0

36. Winkler J.K., Fink C., Toberer F., Enk A., Deinlein T., Hofmann-Wellenhof R., Thomas L., Lallas A., Blum A., Stolz W., Haenssle H.A. Association Between Surgical Skin Markings in Dermoscopic Images and Diagnostic Performance of a Deep Learning Convolutional Neural Network for Melanoma Recognition. JAMA Dermatol. 2019; 155 (10): 1135-1141. https://doi.org/10.1001/jamadermatol.2019.1735

37. Daneshjou R., Smith M.P., Sun M.D., Rotemberg V., Zou J. Lack of Transparency and Potential Bias in Artificial Intelligence Data Sets and Algorithms: A Scoping Review. JAMA Dermatol. 2021; 157 (11): 1362-1369. https://doi.org/10.1001/jamadermatol.2021.3129

38. Phillips M., Marsden H., Jaffe W., Matin R.N., Wali G.N., Greenhalgh J., McGrath E., James R., Ladoyanni E., Bewley A., Argenziano G., Palamaras I. Assessment of Accuracy of an Artificial Intelligence Algorithm to Detect Melanoma in Images of Skin Lesions. JAMA Netw. Open. 2019; 2 (10): e1913436. https://doi.org/10.1001/jamanetworkopen.2019.13436