Neural Networks in Forecasting Disease Dynamics

Introduction.In recent years, computer technologies are more and more widely used in medicine. Thus, medical neuro‑ informatics solves diagnostic and forecasting tasks using neural networks.

Materials and methods. Using the example of erysipelas, the possibility of forecasting the course and outcome of the dis‑ ease is demonstrated. A retrospective study of the medical histories of patients treated for erysipelas at the Ufa Clinical Hospital No.8 during 2006–2015 was carried out. Modern statistical packages and the MATLAB environment were used.

Results and discussion.The conducted comparative analysis showed a 3-layer recurring network of direct distribution to be the most suitable neural network architecture. The optimal structure of the neural network was found to be: 27–6–1 (i.e. 27 neurons are used at the entrance; 6 — in a hidden layer; 1 — in the output layer). The best convergence of the network learning process is provided by the quasi-Newton and conjugated gradient algorithms. In order to assess the effectiveness of the proposed neural network in predicting the dynamics of inflammation, a comparative analysis was carried out using a number of conventional methods, such as exponential smoothing, moving average, least squares and group data handling.

Conclusion.The proposed neural network based on approximation and extrapolation of variations in the patient’s medi‑ cal history over fixed time window segments (within the ‘sliding time window’) can be successfully used for forecasting the development and outcome of erysipelas. 

1. Kravchenko V.O. Methods of using of artificial neural networks in medicine. Sustainable development of science and education. 2018;6:266–70 (In Russ.).

2. Glukhov A.A., Brazhnik E.A. Modern approach to the comprehensive treatment of erysipelas. Fundamental research. 2014;10:411–5 (In Russ.).

3. Yakheva G.E. Fuzzy sets and neural networks. Moscow: BINOM; 2012 (In Russ.). 4 Aggarwal C.C. Neural networks and deep learning: a textbook. Springer; 2018. DOI 10.1007/978-3-319-94463-0 ISBN 978-3-319- 94462-3

4. Ayvazyan S.A., Enyukov I.S., Meshalkin L.D. Practical statistics. Classification and dimensionality reduction. Moscow: Finansy i statistika; 1989 (In Russ.).

5. Cherkasov V.L. Erysipelas. Leningrad: Meditcina; 1986 (In Russ.).

6. Tsvil M.M. The time series analysis and forecasting. Rostov-on-Don; 2016 (In Russ.).

7. Seybold U., Stubbe H., Draenert R., Bogner J.R. Erysipelas. MMW Fortschr Med. 2018;160(10):37–40. DOI: 10.1007/s15006-018-0580-3

8. Karakonstantis S. Is coverage of S. aureus necessary in cellulitis/ erysipelas? A literature review. Infection. 2020;48(2):183–91. DOI: 10.1007/s15010-019-01382-7

9. Zhernakov S.V., Shaibakov D.G. Prediction of erysipelas development based on neural networks. In: Neurocomputers and their use: abstracts of the XVII All-Russian scientific conference. Moscow; 2019:297–9 (In Russ.).

10. Kriegeskorte N., Golan T. Neural network models and deep learning. Curr Biol. 2019;29(7):R231–6. DOI: 10.1016/j.cub.2019.02.034

11. Faustova K.I. Neural networks: use today and future development. Territoriya nauki. 2017;4:83–7 (In Russ.).

12. Mustafaev A.G. Neural network technology in tasks of medical diagnostics. Vestnik komp’iuternykh i informatsionnykh tekhnologii. 2019;6:32–8 (In Russ.). DOI: 10.14489/vkit.2019.06.pp.032-038

13. Volchek Y.A., Shyshko V.M., Spiridonova O.S., Mokhort Т.V. Position of the model of the artificial neural network in medical expert systems. Juvenis Scientia. 2017;9:4–9 (In Russ.). DOI: 10.15643/jscientia.2017.9.001

14. Pérez J., Cabrera J.A., Castillo J.J., Velasco J.M. Bio-inspired spiking neural network for nonlinear systems control. Neural Netw. 2018;104:15–25. DOI: 10.1016/j.neunet.2018.04.002

15. Haykin S. Neural Networks: A Comprehensive Foundation. Moscow: Williams; 2016 (In Russ.).