350 rub
Journal Biomedical Radioelectronics №10 for 2013 г.
Article in number:
Architecture of an expert system for analysis of the epidemiological situation
Authors:
Vladimir Vladimirovich Kotin - Ph.D. (Phys.-Math.), Assistant Professor, Chair «Medical and technical information technologies», Faculty «Biomedical Engineering», Bauman Moscow State Technical University. Е-mail: v.kotin@gmail.com
Victor Vladimirovich Chiganashkin - Diploma student, Chair «Medical and technical information technologies», Faculty «Biomedical Engineering», Bauman Moscow State Technical University. E-mail: chiganashkin@mail.ru
Abstract:
This article is devoted to the problem of developing a prototype expert system for monitoring the epidemiological situation. The basic components of expert systems are described. The main role in the prototype of expert system is assigned to the inference engine and knowledge base. Various methods of constructing of expert systems can be based on the strong and weak artificial intelligence. Method based on rules with the possibility of adding a Bayesian network was chosen for the implementation of the prototype. Examples of various medical expert systems are given and their advantages and disadvantages are described. The most well-known expert system that applied to medical problems is MYCIN. However at the moment there are a lot of rapidly developing commercial expert systems, for example GIDEON. This system is used for the diagnosis of infectious diseases, as well as developed prototype. The problem of the spread of infectious diseases includes both timely diagnosis and prediction of epidemics. Method used in the system MYCIN is modified for individual diagnosis. Prediction of epidemics is carried out using a modified indicator of technical analysis of stock markets. The analysis of the advantages and disadvantages of creating expert systems applied to the analysis of epidemiological situation is conducted. A comparative analysis of existing programming languages of expert systems specialized on medical tasks and unspecialized languages is carried out. CLIPS was selected of several considered options for knowledge representation and inference machine. According to this analysis the prototype of expert system with graphical interface, modules of individual diagnosis, prognosis, collection and processing of expert knowledge is developed. A demo-prototype allows to diagnose relatively small set of infectious diseases and conduct trend analysis of SIR model of the spread of infectious diseases.
Pages: 48-54
References

 

  1. http://www.aiportal.ru
  2. Dzharratano Dzh., Gari R. E'kspertny'e sistemy'. Princzipy' razrabotki i programmirovaniya. SPb.: Izd-vo. VIL'JaMS. 2007. 215 s.
  3. Oded M., Lior R. The Data Mining and Knowledge Discovery Handbook. Springer Science+Business Media, Inc. 2005.
  4. Adamenko A.N., Kuchukov A.M. Logicheskoe programmirovanie i Visual Prolog. SPb.: BXV-Peterburg. 2003. 992 s.
  5. http://www.openclinical.org
  6. http://www.gideononline.com
  7. Boev B.V., Semenenko T.A., Bondarenko V.M., Ginczburg A.L. Aktual'ny'e problemy' sozdaniya informaczionno-analiticheskoj sistemy' dlya operativnogo protivodejstviya e'pidemiyam infekczionny'x zabolevanij // Mikrobiologiya. 2011. № 6. S. 37-42.
  8. Bogomolov A.V., Gridin L.A., Kukushkin Ju.A., Ushakov I.B. Diagnostika sostoyaniya cheloveka: matematicheskie podxody'. M.: Mediczina. 2003. 204 s.
  9. Pankaskie M.C., Wagner M.M. Use of CLIPS for representation and inference in a clinical event monitor. Proc AMIA Annu Fall Symp. 1997. P. 193-197.
  10. Briko N.I., Kotin V.V., Jary'nkina T.A. Analiz periodichnosti i persistentnosti vremenny'x ryadov zabolevaemosti / Sb. dokladov 13-j nauchno-texnich. konf. «Medtex-2011» Mediko-texnicheskie texnologii na strazhe zdorov'ya. M.: Izd-vo: MGTU im. N.E'. Baumana. 2011. S. 20-27.
  11. Anderson R., Me'j R. Infekczionny'e bolezni cheloveka. Dinamika i kontrol'. Mir: Nauchny'j mir. 2004. 784 s.
  12. Bratus' A.S., Novozhilov A.S., Platonov A.P. Dinamicheskie sistemy' i modeli biologii. M.: Fizmatlit. 2010. 146 s.
  13. Cy'lakov A. Vvedenie v prognozirovanie v klassicheskix modelyax vremenny'x ryadov // Kvantil'. 2006. № 10. S. 3-19.
  14. http://www-formal.stanford.edu/jmc/someneed/someneed.html
  15. http://www.openclinical.org/aisp_germalert.html)
  16. http://ej.kubagro.ru/2013/05/pdf/38.pdf
  17. Dmitriev A.N., Kotin V.V. Modelirovanie vremenny'x ryadov zabolevaemosti s ispol'zovaniem iskusstvenny'x nejronny'x setej // Mediczinskaya texnika. 2013. № 1. C. 35-38.
  18. Rutkovskaya D., Pilin'skij M., Rutkovskij L. Nejronny'e seti, geneticheskie algoritmy' i nechetkie sistemy': per. s pol'sk. I.D. Rudinskogo. M.: Goryachaya liniya-Telekom. 2006. 124 s.