Review of the results of a survey of users of the “ProRodinki” mobile application used to detect malignant skin tumors on the territory of the Nizhny Novgorod region

• Natalia A. Sivоdedova
• Nikolay N. Karyakin
• Sergey V. Gamayunov
• Kseniia A. Uskova

Abstract

In Russia, more than 600,000 new cases of malignant skin tumors (hereinafter referred to as MST) are diagnosed annually. MST is in first place in the structure of oncological diseases of the male and female population in the Russian Federation. Currently, an increase of MST is observed throughout the world.

Nowadays, Russian and foreign researchers continue to develop information systems based on automatic analysis of images of neoplasms aimed at diagnosing malignant neoplasms.

In the Russian Federation, the “ProRodinki” mobile application is used. The application was developed by employees of the Department of Skin and Venereal Diseases of the Federal State Budgetary Educational Institution of Higher Education “Privolzhsky Research Medical University” of the Ministry of Health of the Russian Federation and specialists in the field of IT technologies of AIMED LLC with the support of the Nizhny Novgorod Regional Clinical Oncological Dispensary.

The purpose of this stage of the study is to present and evaluate the results of the use of the ProRodinki mobile application by users in the detection of malignant skin tumors.

Material and methods. The work used a telephone survey of application users who received a referral to a doctor in the near future. The telephone survey was conducted by volunteer students of the Volga Research Medical University. The survey questionnaire was developed jointly with the Department of General and Clinical Psychology of the Volga Research Medical University.

The mobile application “ProRodinki” is an application that determines the probability of having MNV based on a photograph of nevi (moles) and the data sent, on the basis of which it forms and issues a recommendation to the user about the need to visit a doctor.

Results. On the territory of the Nizhny Novgorod region, 37 022 images were uploaded from 18,544 users of the “ProRodinki” mobile application. 659 people (3.5% of users) received a notification about the need for an urgent visit to a doctor at a specialized center. As a result of a telephone survey of 343 (52%) users who were advised on the need for an urgent visit to a doctor of a specialized center, 178 (52%) people consulted a doctor, in 105 (59%) of them, after consultation, the need for a biopsy was confirmed, which is a marker of the diagnostic value of artificial intelligence, equal to the diagnostic accuracy of an examination by a dermatovenereologist. According to the biopsy results, 73 (78%) patients were confirmed to have a malignant neoplasm of the skin.

Of those who did not see a doctor, 45.4% of the surveyed users did not see a notification to see a doctor. 39% of users who received a notification with a suspected MST did not respond to a telephone survey. The data obtained speak in favor of finding active solutions to inform the patient, who is included in the high-risk group for MST. It is expedient to transfer the function of informing patients with a high risk of MST to a specialized medical organization for the subsequent accelerated routing of the patient to a specialized medical institution.

Keywords:malignant neoplasms of the skin; early detection; telemedicine technologies; mobile applications; mobile application “ProRodinki”

References

1. Malignant neoplasms in Russia in 2021 (morbidity and mortality). In: A.D. Kaprin, V.V. Starinsky, A.O. Shakhzadova (eds). Moscow: MNIOI im. P.A. Gertsena – filial FGBU «NMITs radiologii» Minzdrava Rossii, 2022: 252 p. (in Russian)

2. Marinina A.O., Stepanova Ya.L., Uskova K.A. Analysis of the structure of primary referral to a specialized office of a dermatologist-oncologist. In: Federal State Budgetary Educational Institution of Higher Education «Volga Region Research Medical University» of the Ministry of Health of the Russian Federation. VolgaMedScience: Collection of abstracts of the VIII All-Russian Scientific and Practical Conference of Young Scientists and students with international participation, Nizhny Novgorod, March 17–18, 2022. Nizhny Novgorod, 2022: 150–2. (in Russian)

3. Maqsood S., Damaševičius R. Multiclass skin lesion localization and classification using deep learning based features fusion and selection framework for smart healthcare. Neural Netw. 2023; 160: 238–58. DOI: https://doi.org/10.1016/j.neunet.2023.01.022 Epub 2023 Jan 24. PMID: 36701878.

4. Combalia M., Codella N., Rotemberg V., Carrera C., Dusza S., Gutman D., et al. Validation of artificial intelligence prediction models for skin cancer diagnosis using dermoscopy images: the 2019 International Skin Imaging Collaboration Grand Challenge. Lancet Digit Health. 2022; 4 (5): e330–9. DOI: https://doi.org/10.1016/S2589-7500(22)00021-8 PMID: 35461690; PMCID: PMC9295694.

5. Felmingham C., MacNamara S., Cranwell W., Williams N., Wada M., Adler N.R., et al. Improving Skin cancer Management with ARTificial Intelligence (SMARTI): protocol for a preintervention/postintervention trial of an artificial intelligence system used as a diagnostic aid for skin cancer management in a specialist dermatology setting. BMJ Open. 2022; 12 (1): e050203. DOI: https://doi.org/10.1136/bmjopen-2021-050203 PMID: 34983756; PMCID: PMC8728443.

6. Esteva A., Kuprel B., Novoa R.A., Ko J., Swetter S.M., Blau H.M., et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017; 542 (7639): 115–8. DOI: https://doi.org/10.1038/nature21056.nature21056

7. Shlivko I.L., Garanina O.E., Klemenova I.A., et al. Artificial intelligence: how it works and evaluation criteria. Consilium Medicum. 2021; 23 (8): 626–32. DOI: https://doi.org/10.26442/20751753.2021.8.201148 (in Russian)

8. Haenssle H.A., Fink C., Schneiderbauer R., Toberer F., Buhl T., Blum A., et al. 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): 1836–42.

9. Marchetti M.A., Codella N.C.F., Dusza S.W., Gutman D.A., Helba B., Kalloo A., et al. Results of the 2016 international skin imaging collaboration international symposium on biomedical imaging challenge: comparison of the accuracy of computer algorithms to dermatologists for the diagnosis of melanoma from dermoscopic images. J Am Acad Dermatol. 2018; 78 (2): 270–7.e1.

10. Fink C., Blum A., Buhl T., Mitteldorf C., Hofmann-Wellenhof R., Deinlein T., et al. Diagnostic performance of a deep learning convolutional neural network in the differentiation of combined naevi and melanomas. J Eur Acad Dermatol Venereol. 2020; 34 (6): 1355–61. DOI: https://doi.org/10.1111/jdv.16165 Epub 2020 Jan 21. PMID: 31856342.

All articles in our journal are distributed under the Creative Commons Attribution 4.0 International License (CC BY 4.0 license)