Translation of interdisciplinary artificial intelligence methods into medical diagnostics: Socioeconomic effects assessment

Aim. The work aimed to determine the applicability of interdisciplinary artificial intelligence (AI) methods, developed and tested by the authors in various domains, to objectives of modern medical diagnostics, as well as to identify the potential for translating these methods into clinical practice, taking into account the methodological, ethical, regulatory, and managerial aspects of their implementation. It also work aimed to highlight the key socioeconomic effects of using AI technologies in medical diagnostics in the context of the national healthcare system.
Methods. A literature review on the integration of AI into management and healthcare was conducted, including the authors’ research and a number of relevant international and Russian sources on the use of AI in medical diagnostics. A systems approach and risk-based analysis were used, allowing for a comprehensive consideration of technical and socioeconomic aspects.
Objectives. The work seeks to summarize and systematize the interdisciplinary AI methods developed and tested in related fields (public administration, data processing, neurotechnology, ontological decision support systems) in terms of their potential for translation to medical diagnostics. It also seeks to analyze the methodological, ethical, regulatory, and managerial aspects of implementing AI technologies in healthcare diagnostic processes; to assess the potential socioeconomic impact of interdisciplinary AI approaches, including their impact on the accessibility, quality, and effectiveness of medical diagnostics; and to draw generalized conclusions about the prospects and limitations of scaling AI solutions in modern high-tech medical diagnostics.
Results. Interdisciplinary AI technologies demonstrate high potential for improving the accuracy and speed of diagnostics, streamlining workflows, and reducing costs in healthcare. It was demonstrated that the use of AI can improve clinical outcomes (e.g., through earlier disease detection) and save resources by reducing unnecessary procedures. However, limitations and risks have been identified, namely ethical and legal obstacles, data confidentiality issues, the need for significant investments in infrastructure and personnel training, and the potential for algorithmic bias.
Conclusions. Successful translation of AI methods into medical diagnostics requires a comprehensive interdisciplinary approach that takes into account ethical standards and the development of a regulatory framework. Maximization of positive socioeconomic impacts (improving the quality and accessibility of medical care, reducing costs, and developing technological potential) is possible through risk management, ensuring transparency and trust in AI systems, as well as development of intellectual capital in the AI field during its implementation in medical diagnostics.

1. Fedorov M.V., Repin D.A., Ignatev S.A. The future of artificial intelligence in public administration: Finding the paradigm of the reasonable (self)limitation. Izvestiya Sankt-Peterburgskogo gosudarstvennogo ekonomicheskogo universiteta. 2024;(5):46-53. (In Russ.).

2. Repin D.A., Ignatyev S.A. “Implementation impossible to refuse”: The influence of ethics on using artificial intelligence in socio-economic management. Ekonomika i upravlenie = Economics and Management. 2024;30(12):1503-1509. (In Russ.). https://doi.org/10.35854/1998-1627-2024-12-1503-1509

3. Repin D.A., Ignatev S.A. Neurotechnologies in managerial communication: The case of neurointerfaces. Izvestiya Sankt-Peterburgskogo gosudarstvennogo ekonomicheskogo universiteta. 2025;(1):84-90. (In Russ.).

4. Fedorov M.V., Repin D.A., Ignatev S.A. Intellectual capital in artificial intelligence as a driver of technological potential in Russia. Ekonomika i upravlenie = Economics and Management. 2025;31(9):1105-1120. (In Russ.). https://doi.org/10.35854/1998-1627-2025-9-1105-1120

5. Klevtsova O.Yu., Repin D.A. Proposals for improving the methodology of selecting options for financial support of innovative defense projects if there are alternatives. Vestnik Voennoi akademii material’no-tekhnicheskogo obespecheniya. 2025;(2):96-108. (In Russ.).

6. El Arab R.A., Al Moosa O.A. Systematic review of cost effectiveness and budget impact of artificial intelligence in healthcare. NPJ Digital Medicine. 2025;8:548. https://doi.org/10.1038/s41746-025-01722-y

7. Yanishevsky I.M., Arlazarov V.V. Training a convolutional neural network with automatic consideration of input distortion. Izvestiya Tul’skogo gosudarstvennogo universiteta. Tekhnicheskie nauki = News of the Tula State University. Technical Sciences. 2022;(9): 52-56. (In Russ.). https://doi.org/10.24412/2071-6168-2022-9-52-56

8. Repin D.A. Artificial intelligence technologies as a factor in improving public administration: Challenges and threats. Ekonomika i upravlenie = Economics and Management. 2025;31(2):139-148. (In Russ.). https://doi.org/10.35854/1998-1627-2025-2-139-148

9. Tkachenko V.T., Fedorov M.V., Fedorova V.V., et al. New methods for pathogen risk assessment: Machine learning in the analysis of toxicity spectrum of Albifimbria verrucaria. Vestnik voisk RKhB zashchity = Journal of NBC Protection Corps. 2025;9(1):57-73. (In Russ.). https://doi.org/10.35825/2587-5728-2025-9-1-57-73

10. Nikitin I., Morgunov I., Safronov V., Kalyuzhnaya A., Fedorov M. Towards explainable computational toxicology: Linking antitargets to rodent acute toxicity. Pharmaceutics. 2025;17(12):1573. https://doi.org/10.3390/pharmaceutics17121573

11. Rassabina A.E., Fedorov M.V. Analysis of the toxicological profile of Heracleum sosnowskyi Manden. Metabolites using in Silico methods. Plants. 2025;14(21):3253. https://doi.org/10.3390/plants14213253

12. Repin D.A. AI-driven socio-technological instruments for public administration. Sotsiologiya i pravo = Sociology and Law. 2025;17(2):150-161. (In Russ.). https://doi.org/10.35854/2219-6242-2025-2-150-161

13. Gribova V.V., Okun D.B., Shalfeeva E.A. Medical decision support model for diagnosing and rehabilitating patients with disabilities. Real’naya klinicheskaya praktika: dannye i dokazatel’stva = Real-World Data & Evidence. 2025;5(4):81-96. (In Russ.). https://doi.org/10.37489/2782-3784-myrwd-091

14. Khokhlov A.L., Sychev D.A. The concept of patient-oriented medicine and pharmacy. Patsientoorientirovannaya meditsina i farmatsiya = Patient-Oriented Medicine and Pharmacy. 2023;1(1):1-4. (In Russ.). https://doi.org/10.37489/2949-1924-0001

15. Khokhlov A.L., Belousov D.Yu. Ethical issues of using artificial intelligence in drug development. Kachestvennaya klinicheskaya praktika = Good Clinical Practice. 2025;(3):111-117. (In Russ.). https://doi.org/10.37489/2588-0519-2025-3-111-117