Epizootic situation on bovine leukosis in the Omsk region and a short- term forecast of its development

   The analysis of the epizootic situation on bovine leukosis in the Omsk region from 2018 to 2022 was carried out on the basis of the received data on the results of diagnostic tests in the immune diffusion reaction (IDR) and the hematological method. Despite the widespread viral infection, there was a slight downward trend in the number of positive samples from 16.8% in 2018 to 14% in 2022, nevertheless, the seroprevalence rate exceeded 5% in the predominant part of the region. The percentage of animals with leukosis during this period, on the contrary, increased 1.5 times. Several modifications of artificial neural networks (ANN) with nonlinear dependence on the Wolf numbers (W), harmonics of the Fourier spectral model, as well as the additionally introduced factor “Sigma”, which takes the value of 1 at W ≥ 110 at the input, were created at the next stage of the research in order to predict the further development of the epizootic situation in bovine leukosis. Three approaches of the ANN research were used: with spectral analysis from the beginning of the known period (from 1994); with spectral analysis from the end of the known period (from 2022); with construction of the ANN from the 1st to the 9th layers with odd-numbered acceleration. A total of 9 packages including more than 40 neural networks were created. The research was carried out in the direction of increasing the number of layers of the neural network and changing the harmonic composition. In some ANNs, a significant variation in the expected number of bovine leukosis virus infections was observed when the number of the layers was increased. In others, on the contrary, the forecast spread was minimal. Application of these approaches makes it possible to consider different scenarios of epizootic situation development in bovine leukosis and to choose the most optimal models when new data on the spread of infection become available.

1. Haredasht S.A., Vidal G., Edmondson A., Moore D., Del-Rio N.S., Lopez B.M. Characterization of the temporal trends in the rate of cattle carcass condemnations in the US and dynamic modeling of the condemnation reasons in California with a seasonal component. Frontiers in Veterinary Science, 2018, vol. 5, no. 87. DOI: 10.3389/fvets.2018.00087.

2. Bartlett P.C., Ruggiero V.J., Hutchinson H.C., Droscha C.J. Current developments in the epidemiology and control of enzootic bovine leukosis as caused by bovine leukemia virus. Pathogens, 2020, vol. 9 (12), no. 1058. DOI: 10.3390/pathogens9121058.

3. John E.E., Keefe G., Cameron M., Stryhn H., McClure J.T. Development and implementation of a risk assessment and management program for enzootic bovine leukosis in Atlantic Canada. Journal of Dairy Science. 2020. Vol. 103 (9). P. 8398–8406. DOI: 10.3168/jds.2019-17434.

4. Donnik I.M., Gulyukin M.I., Busol V.A., Kovalenko L.V., Kovalenko A.M. Bovine leukemia virus infection – diagnostics, eradication and anthropozoonotic potential (back-ground review). Sel'skohozyajstvennaya biologiya = Agricultural Biology, 2021, vol. 56, no. 2, pp. 230–244. (In Russian). DOI: 10.15389/agrobiology.2021.2.230rus.

5. Gulyukin M.I., Gulyukin A.M., Donchenko A.S., Donchenko N.A. Analysis of the episootic situation of cattle leukemia in the Siberian Federal District. Sibirskii vestnik sel'skokhozyaistvennoi nauki = Siberian Herald of Agricultural Science, 2021, vol. 51, no. 4, pp. 67–75. (In Russian). DOI: 10.26898/0370-8799-2021-4-8.

6. Borisevich M.N., Krasochko P.A., Prishchepa I.M. Model mathematic functions in practical biology. Vesnik VDU = Vestnik VSU, 2018, no. 3, pp. 29–34. (In Russian).

7. Cedeno-Mieles W., Hu Z., Ren Y., Deng H., Contractor N., Ekanayake S. Data mining and pipeline modeling for controlled network experiments in the social sciences. PLoS One, 2020, vol. 15 (11), P. E0242453. DOI: 10.1371/journal.pone.0242453.

8. Datilo P.M., Ismail Z., Dare J. A review of epidemic forecasting using artificial neural networks. International Journal of Epidemiologic Research, 2019, vol. 6, pp. 132–143. DOI: 10.15171/ijer.2019.24.

9. Wu J.T., Cowling B.J. Real-time forecasting of infectious disease epidemics. Hong Kong Medical Journal, 2018, vol. 24, suppl. 6 (5), pp. 26–29.

10. Manliura Datilo P., Ismail Z., Dare J. A review of epidemic forecasting using artificial neural networks. International Journal of Epidemiological Research, 2019, vol. 6 (3), pp. 132–143. DOI: 10.15171/ijer.2019.24.

11. Saba A.I., Elsheikh A.H. Forecasting the prevalence of COVID-19 outbreak in Egypt using nonlinear autoregressive artificial neural networks. Process Saf Environ Prot, 2020, vol. 141, pp. 1–8. DOI: 10.1016/j.psep.2020.05.029.

12. Hong Y., Hou B., Jiang H., Zhang J. Machine learning and artificial neural network accelerated computational discoveries in materials science. Wiley Interdisciplinary Reviews Computational Molecular Science, 2020, vol. 10, no. e1450. DOI: 10.1002/wcms.1450.

13. Cogollo M.R., González-Parra G., Arenas A.J. Modeling and forecasting cases of RSV using artificial neural networks. Mathematics, 2021, vol. 9, no. 2958. DOI: 10.3390/math9222958.

14. Vlasenko V.S., Borisov E.S. Artificial neural network in forecasting of the epizootic situation on the leukosis of cattle. Veterinariya i kormlenie = Veterinaria i kormlenie, 2023, no. 1, pp. 26–29. (In Russian). DOI: 10.30917/ATTVK-1814-9588-2023-1-6.