#PAGE_PARAMS# #ADS_HEAD_SCRIPTS# #MICRODATA#

Skin Cancer Diagnostics through a Mobile Applications Use


Authors: M. Arenbergerová 1;  L. Drlík 2;  O. Volný 3;  M. Pásek 1
Authors‘ workplace: Dermatovenerologická klinika 3. LF UK a FNKV Praha 1;  Dermatologická ordinace Mohelnice 2;  Neurologická klinika LF OU a FN Ostrava 3
Published in: Čes-slov Derm, 100, 2025, No. 6, p. 223-229
Category: New drugs, cosmetics, devices

Overview

Mobile applications for skin cancer diagnostics are available in an increasing frequency targeting either healthcare professionals or the general public. Among apps for general population, only SkinVision (and skinScan, not clinically validated) hold European certification. The first prospective study showed sensitivity of 73% and specificity of 83% compared to dermatologists (88% and 97%). Another study confirmed similar results with 80% sensitivity and 78% specificity. A retrospective study demonstrated very high sensitivity (95.1%) but lower specificity (78.3%). Next study reported a wide range: sensitivity 41–83% and specificity 60–83%, with a tendency toward overdiagnosis. The multicenter study found sensitivity of 86.9% and specificity of 70.4%. Overall, SkinVision shows sensitivity between 41–95% and specificity between 60–83%, depending on study design. Compared to dermatologists, the app remains less accurate –⁠ dermatologists with dermoscopy achieve up to 92% sensitivity and 95% specificity. The main advantage is the ability for patients to perform self-examinations, especially those unlikely to see a dermatologist. Without technology, self-exams detect only 21–57% of melanomas; with the app, detection rates improve significantly. However, the app tends to classify benign lesions as suspicious, leading to false positives. Greatest benefits may occur in at-risk groups who usually skip preventive check-ups. SkinVision is classified as a class IIa medical device since June 2025 (class I before this date) and can complement preventive strategies. Further clinical studies, especially in a general population, are needed to validate its real-world evidence.

Keywords:

Skin tumors – dermoscopy – Mobile apps – SkinVision


Sources
  1. AKSHAY, G., IRFAN, M., SRINIVAS, K. G., SINGH, A. Skin-Vision: An Innovative Mobile-Based Automated Skin Disease Detection Application. 2023, OCIT, doi: 10.1109/OCIT59427.2023.10430941.
  2. CLIMSTEIN, M., HUDSON, J., STAPELBERG, M., MILLER, I. J., ROSIC, N., COXON, P., FURRNESS, J., WALSH, J. Patients poorly recognize lesions of concern that are malignant melanomas: is self-screening the correct advice? PeerJ, 2024, 3(12), p. e17674.
  3. DAVIS, S., PIGGOTT, C., LYON, C., DESANTO, K. Effectiveness of dermoscopy in skin cancer diagnosis. Can Fam Physician, 2020, 66(10), p. 739–740.
  4. DEEKS, J. J., DINNES, J., WILLIAMS, H. C. Sensitivity and specificity of SkinVision are likely to have been overestimated. J Eur Acad Dermatol Venereol., 2020, 34(10), p. e582–e583.
  5. FERLAY, J. Global Cancer Observatory: Cancer Today. Lyon, France: International Agency for Research on Cancer [29. 11. 2019]. https://gco.iarc.fr/ today
  6. JAHN, A. S., NAVARINI, A. A., CERMINARA, S. E., KOSTNER, L., HUBER, S. M., KUNZ, M,, MAUL, J. T., DUMMER, R., SOMMER, S., NEUNER, A. D., LE-VESQUE, M. P., CHENG, P. F., MAUL, L. V. Over-Detection of Melanoma-Suspect Lesions by a CE-Certified Smartphone App: Performance in Comparison to Dermatologists, 2D and 3D Convolutional Neural Networks in a Prospective Data Set of 1204 Pigmented Skin Lesions Involving Patients‘ Perception. Cancers (Basel), 2022, 714(15), p. 3829.
  7. KREJČÍ, D. Portál epidemiologie novotvarů v ČR [online]. Masarykova univerzita, Brno, 2024. [cit. 202506-21]. Dostupné na www: https://www.svod.cz. Verze 8.0.1.
  8. KREJČÍ, D. Novotvary 2019–2021 ČR Cancer incidence 2019–2021 in the Czech Republic. Ústav zdravotnických informací a statistiky ČR, Praha, Česká republika, 2023. Dostupné na www: https:// www.uzis.cz/index.php?pg=aktuality&aid=8646.
  9. MAIER, T., KULICHOVA, D., SCHOTTEN, K., ASTRID, R., RUZICKA, T., BERKING, C., UDREA, A. Accuracy of a smartphone application using fractal image analysis of pigmented moles compared to clinical diagnosis and histological result. J Eur Acad Dermatol Venereol., 2015, 29, p. 663–667.
  10. MAR, V., ROBERTS, H., WOLFE, R., ENGLISH, D. R., KELLY, J. W. Nodular melanoma: a distinct clinical entity and the largest contributor to melanoma deaths in Victoria, Australia. J Am Acad Dermatol., 2013, 68(4), p. 568–575.
  11. SALAH, S., KEROB, D., EZZEDINE, K., KHURANA, P., BALAN, D., PASSERON, T. Analysis of global skin cancer epidemiology in 2022 and correlation with dermatologist density. J Eur Acad Dermatol Venereol., 2025, 30. doi: 10.1111/jdv.20883.
  12. SANGERS, T., REEDER, S., VAN DER VET, S., JHINGOER, S., MOOYAART, A., SIEGEL, D. M., NIJSTEN, T., WAKKEE, M. Validation of a Market-Approved Artificial Intelligence Mobile Health App for Skin Cancer Screening: A Prospective Multicenter Diagnostic Accuracy Study. Dermatology, 2022, 238(4), p. 649–656.
  13. SMAK GREGOOR, A. M. An artificial intelligence based app for skin cancer detection evaluated in a population based setting. Digital Medicine, 2023, 6(1), p. 1–24.
  14. THISSEN, M., UDREA, A., HACKING, M., VON BRAUNMUEHL, T., RUZICKA, T. mHealth App for Risk Assessment of Pigmented and Nonpigmented Skin Lesions –⁠ A Study on Sensitivity and Specificity in Detecting Malignancy. Telemed J E Health, 2017, 23(12), p. 948–954.
  15. UDREA, A., MITRA, G. D., COSTEA, D., NOELS, E. C., WAKKEE, M., SIEGEL, D. M., DE CARVALHO, T. M.,NIJSTEN, T. E. C. Accuracy of a smartphone application for triage of skin lesions based on machine learning algorithms. J Eur Acad Dermatol Venereol., 2020, 34(3), p. 648–655.

Do redakce došlo dne 11. 11. 2025.

Adresa pro korespondenci:
prof. MUDr. Monika Arenbergerová, Ph.D. D
ermatovenerologická
klinika 3. LF UK a FNKV
Šrobárova 50
100 34
Praha 10
e-mail: arenbergerova@email.cz

Labels
Dermatology & STDs Paediatric dermatology & STDs
Login
Forgotten password

Enter the email address that you registered with. We will send you instructions on how to set a new password.

Login

Don‘t have an account?  Create new account

#ADS_BOTTOM_SCRIPTS#