Neural network model for meta-analysis of medical and ecological data
- 1 Head of Research, South-West State University (Kursk)
- 2 Post-graduate Student, Chair of Biomedical Engineering, South-West State University (Kursk)
- 3 Dr. Sc. (Eng.), Professor, Chair of Biomedical Engineering, South-West State University (Kursk)
- 4 Ph. D. (Phys.-Math.), Deputy Head, Institute for Studies, Voronezh Institute of the State Fire Service (Voronezh)
Abstract
The purpose of these researches is development of models and algorithm meta-analysis, which assess the effectiveness of prescribing or the effect of environmental factors on the incidence of industrial cluster or segment.
To estimates of efficiency of medicinal appointments or assessment of influence of an ecological factor on incidence the scheme meta-analysis is submitted. Meta-analysis allows the selection of medical and biological parameters, having the greatest sensitivity to the drug or environmental factors, and collection of clinical or epidemiological indicators, allowing to estimate health level in experimental group or an industrial cluster.
To assess the impact of environmental factors on public health the neural network models of meta-analysis are proposed. Also the neural network models of meta-analysis allow to make forecast the incidence of a certain period (periods) in a known history and the level of environmental hazards.
To assess the impact of environmental factors on disease the system of automatic neural network is proposed. The structure of a matrix of data for their training is offered.
The neural networks of counter distribution have been used for overcoming of the difficulties connected with the narrow range of a variation the size of an ecological factor or a dose of medicinal appointment.
How to cite
Курочкин А.Г., Протасова В.В., Филист С.А., Шуткин А.Н. Нейросетевые модели для мета-анализа медико-экологических данных // Нейрокомпьютеры: разработка, применение. 2015. № 6. С. 48–53.
References
- Fletcher R., Fletcher S., Vagner EH. Klinicheskaja ehpidemiologija. M.: MediaSfera. 2008. 350 s.
- Sipe T. A., Curlette W. L. A meta-synthesis of factors related to educational chievement //Int J Educ Res. 2011. P. 598.
- gorban A. N., Dunin-Barkovskijj V. L., Kirdin A. N. i dr. Nejjroinformatika. Novosibirsk: Nauka. 1998.
- Filist S.A., Emeljanov S. g., Rybochkin A. F. Nejjrosetevojj reshajushhijj modul dlja issledovanija zhivykh sistem // Izv. Kurskogo gosudarstvennogo tekhnicheskogo universiteta. 2008. № 2 (23). S. 77-82.
- Filist, S.A., shatalova O. v., efremov M. A. Gibridnaja nejjronnaja set s makroslojami dlja medicinskikh prilozhenijj// Nejjrokompjutery: razrabotka, primenenie. 2014. № 6. S. 35-39.
- Rutkovskaja D., Pilinskijj M., Rutkovskijj L. Nejjronnye seti, geneticheskie algoritmy i nechetkie sistemy: Per. s polsk. I.D. Rudinskogo. M.: Gorjachaja linija «Telekom». 2004. 452 s.
- KHajjkin S.Nejjronnye seti: polnyjj kurs. M.: Viljams. 2006. 1104 s.