On the problem of extracting information from medical data

Gelman V. Ya.
Doctor of Technical Sciences, Professor, Department of Medical Informatics and Physics¹

1North-West State Medical University named after I.I. Mechnikov, 191015, St. Petersburg

Gelman Viktor; e-mail: Viktor.Gelman@szgmu.ru

None declared.

The study had no sponsorship.

This paper analyzes and compares approaches to extracting information and knowledge from medical data. The paper examines the key principles for selecting analytical methods, statistical methods, and the use of neural networks, and compares them. It demonstrates that each approach has its own scope of application, advantages, and disadvantages. For medical data analysis, in cases where the structure of the object model is known, relatively simple, or can be reasonably assumed, standard statistical methods are appropriate. In complex cases, the use of more labor-intensive neural network methods is justified. Furthermore, the use of neural networks significantly expands the capabilities of medical data analysis, improving the accuracy of diagnostics and predictions.

medical data, information extraction, statistical methods, neural networks, method’s selection, validation

10.29234/2308-9113-2026-14-1-80-89

1. Narkevich A.N., Vinogradov K.A. Selecting a Method for Statistical Analysis of Medical Data and a Method for Graphical Presentation of Results. Social Aspects of Population Health [online publication] 2019; 65(4): 1-19. DOI: 10.21045/2071-5021-2019-65-4-9. (In Russ.)

2. Bavrina A.P., Borisov I.B. Modern Rules for Applying Correlation Analysis. Medical Almanac 2021; 68 (3): 70-79. (In Russ.)

3. Dmitrieva E.S., Zaitseva K.A., Gelman V.Ya. Age and Gender Peculiarities of Perception of Emotional Characteristics of Speech Under the Influence of Noise. Human Physiology 1999; 25(3): 57-64. (In Russ.)

4. Dmitrieva E.S., Gelman V.Ya., Zaitseva K.A., Orlov A.M. Dependence of the perception of emotional information in speech on the acoustic parameters of the stimulus in children of different ages. Human Physiology 2008; 34(4): 149-153. (In Russ.)

5. Ponomarev V.P., Beloglazov I.Yu. Application of factor and cluster statistical analysis in medicine. Int. sci.-tech. conf. Advanced Information Technologies (PIT 2016). 2016. Рp. 26-28. (In Russ.)

6. Kholmatova K.K., Grzhibovsky A.M. Panel studies and trend studies in medicine and public health. Human Ecology 2016; (10): 57-64. (In Russ.)

7. Molchanova E.V., Kruchek M.M. Mathematical methods for assessing factors influencing the health of the population in the regions of Russia (panel analysis). Social Aspects of Population Health 2013; 33(5): 1-10. (In Russ.)

8. Lebedeva T.V. Modeling indicators of natural population change based on panel data. Int. scientific-practical. conf., February 5-7, 2020, St. Petersburg «Data Science». 2020. pp. 175-177. (In Russ.)

9. Natsun L.N. Assessing the impact of medical, demographic, and economic factors on the dynamics of infant mortality in the regions of Russia. Economic and social changes: facts, trends, forecast. 2023; 16(3): 265-283. DOI: 10.15838/esc.2023.3.87.14. (In Russ.)

10. Askarov R.A. et al. Identification of life expectancy factors: a panel data analysis. Russian Federation Healthcare. 2019; 63(6): 313–321. (In Russ.)

11. Gerget O. M., Ignatishina F. A. Application of neural network models for processing and analyzing medical data. Automation and Modeling in Design and Management. 2022; 17(3): 24–33. (In Russ.)

12. Almukhametov A. A. et al. Application of recurrent neural networks for predicting events associated with diseases of the circulatory system. Bulletin of the Higher School of Public Health. 2025; 11(3): 120–132. (In Russ.)

13. Volchek Yu. A. et al. Position of the artificial neural network model in medical expert systems. Juvenis scientia. 2017; (9): 4–9. (In Russ.)

14. Madan S. et al. Transformer models in biomedicine. BMC medical informatics and decision making. 2024; 24(1): 214-233.

15. Kotov D. A. Comparative analysis of machine learning models for use in an information system for augmenting medical image sets using generative neural networks. Science and Technologies. Collection of scientific papers. Petrozavodsk, 2025. Pp. 62-71. (In Russ.)

16. Narkevich A. N. et al. Intelligent methods of data analysis in biomedical research: convolutional neural networks. Human ecology. 2021; (5): 53-64. (In Russ.)

17. Andrikov D. A. et al. Neural network graph architecture of transparent artificial intelligence in medicine. Doctor and information technologies. 2025; (2): 70-83. (In Russ.)