SUMMARY
Selskyy P. R., Selskyy B. P. ???????? ???????? ??????? ??? ??????????? ??????????????? ???????? ??????????? ?? ????????? ?????? ? ??????????? ????????? ??????????? ?????????????? ??????? = The algorithm of decision-making to optimize the prediction of disease at the primary level with a complex phased application of information techniques. Journal of Education, Health and Sport. 2016;6(9):305-314. eISSN 2391-8306. DOI http://dx.doi.org/10.5281/zenodo.61842http://ojs.ukw.edu.pl/index.php/johs/article/view/3846 The journal has had 7 points in Ministry of Science and Higher Education parametric evaluation. Part B item 755 (23.12.2015).755 Journal of Education, Health and Sport eISSN 2391-8306 7© The Author (s) 2016;This article is published with open access at Licensee Open Journal Systems of Kazimierz Wielki University in Bydgoszcz, PolandOpen Access. This article is distributed under the terms of the Creative Commons Attribution Noncommercial License which permits any noncommercial use, distribution, and reproduction in any medium,provided the original author(s) and source are credited. This is an open access article licensed under the terms of the Creative Commons Attribution Non Commercial License(http://creativecommons.org/licenses/by-nc/4.0/) which permits unrestricted, non commercial use, distribution and reproduction in any medium, provided the work is properly cited.This is an open access article licensed under the terms of the Creative Commons Attribution Non Commercial License (http://creativecommons.org/licenses/by-nc/4.0/) which permits unrestricted, non commercialuse, distribution and reproduction in any medium, provided the work is properly cited.The authors declare that there is no conflict of interests regarding the publication of this paper.Received: 05.08.2016. Revised 25.08.2016. Accepted: 06.09.2016. The algorithm of decision-making to optimize the prediction of disease at the primary level with a complex phased application of information techniques P. R. Selskyy, B. P. Selskyy State Institution of Higher Education “I. Horbachevsky Ternopil State Medical University of the Ministry of Health of Ukraine”, Ternopil, Ukraine SummaryThe paper describes the algorithm of decision-making to optimize the prediction of disease at the primary health care level with a complex phased application of information techniques. The approach is based on analysis of the average values of indicators, correlation coefficients, using multi-parameter neural network clustering, ROC-analysis and decision tree.The data of 63 patients with arterial hypertension obtained at teaching and practical centers of primary health care were used for the analysis. The blood pressure at the first treatment of the patients was as follows: systolic – (154,76 ± 2,29) mm Hg, diastolic – (92,94 ± 1,04) mm Hg, pulse pressure – (61,83 ± 1,95) mm Hg. Indicators of the upper and lower blood pressure were significantly lower compared with those before the treatment: systolic – (145,86 ± 2,01) mm Hg (P <0,01), diastolic – (88,49 ± 1,08) mm Hg (p < 0,001). In 13 (19,40 %) patients we observed worsening of the health condition and the development of complications. Correlation analysis revealed a direct correlation between the indices of the heart rate (+ 0,5), the systolic (+ 0,1), the diastolic (+ 0,4) and the pulse (+ 0,1) pressure at the first pressure and re-examination.It has been established that neural network clasterization can effectively and objectively allocate patients into the appropriate categories according to the level of average indices of patient examination results. The cluster analysis data has revealed that the combination of high arterial tension measurement (during the first and repeated examination) provides a basis of the deteriorated patient condition, while the combination of high age and heart rate measurement (polycardia) also plays a significant, but not the primary role for the disease prognosis.Determination of the sensitivity and specificity of hemodynamic parameters, including blood pressure, and repeated during the initial survey conducted using ROC-analysis.In order to obtain the rules in decision-making and, corresponding algorithms of clinical thinking, we applied the method of decision tree that can be used to predict the flow of other pathology. The recursive procedure is taken as a basis for research. The method is implemented in Netbeans development environment using Java programming language. Base training data are deployed on the MySQL server.The algorithm of decision-making to optimize the prediction of disease at the primary level in order to adjust examination procedures and treatment based on the analysis of indicators of patient examination with a complex, gradual application of information procedures. The proposed algorithm can be used to determine the risk of developing health complications of various diseases that are most prevalent in a given region. The suggested methodology is easy to use and does not require large financial investments, which is important for the organization of primary health care in rural areas. Keywords: the primary health care level, hypertension, information methods decision algorithm, neural network clustering, ROC-analysis, decision tree. ???????? ???????? ??????? ??? ??????????? ??????????????? ???????? ??????????? ?? ????????? ?????? ? ??????????? ????????? ??????????? ?????????????? ??????? ?. ?. ?????????, ?. ?. ????????? ??????????????? ?????? ??????? ????????? “????????????? ??????????????? ??????????? ??????????? ????? ?.?. ????????????? ??? ???????”, ?????????, ??????? ??????? ?????? ????????? ???????? ???????? ??????? ??? ??????????? ??????????????? ???????? ??????????? ?? ????????? ?????? ?????????????? ??????-?????????? ?????? ? ??????????? ????????? ??????????? ?????????????? ???????. ?????? ??????? ?? ??????? ??????? ???????? ???????????, ????????????? ??????????, ????????????? ???????????????????? ???????????? ?????????????, ROC-??????? ? ?????? ???????.? ???????? ?????? ??? ??????? ???????????? ?????????? ???????????? 63 ????????? ? ???????????? ???????????? ? ??????-???????????? ??????? ????????? ??????-?????????? ??????. ?????????? ????????????? ???????? ??? ?????? ????????? ????????? ???? ??????????: ????????????? ? (154,76 ± 2,29) ??. ??. ??., ?????????????? ? (92,94 ± 1,04) ??. ??. ??., ????????? ???????? - (61,83 ± 1,95) ??. ??. ??. ?????????? ???????? ? ??????? ????????????? ???????? ???? ??????????? ???? ?? ????????? ? ???????????? ???????????? ?? ???????: ????????????? ? (145,86 ± 2,01) ??. ??. ??. (p < 0,01), ?????????????? ? (88,49 ± 1,08) ??. ??. ??. (p < 0,001). ? 13 (19,40 %) ????????? ??????????? ????????? ????????? ? ???????? ??????????. ??? ?????????????? ??????? ?????????? ?????? ?????????????? ????? ????? ???????????? ?????? (+ 0,5), ???????? (+ 0,1), ??????? (+ 0,4) ? ?????????? (+ 0,1) ???????? ??? ?????? ? ????????? ????????????.???????????, ??? ???????????? ????????????? ????????? ?????????? ? ?????????? ???????????? ????????? ? ??????????????? ????????? ?? ?????? ??????? ??????????? ??????????? ????????????. ? ?????????? ??????? ?????????? ????????? ??????????, ??? ?????? ????????? ??????? ??????????? ????????????? ???????? (??? ?????? ? ????????? ????????????) ???? ????????? ?????????????? ????????? ????????? ?????????, ? ????????? ??????? ??????????? ???????? ? ?????? (??????????) ????? ????????????, ?????? ?? ?????????????? ???????? ??? ????????.??????????? ???????????????? ? ????????????? ??????????? ????????????, ? ????????? ????????????? ????????, ??? ????????? ? ????????? ???????????? ????????? ? ??????? ROC-???????.? ????? ????????? ?????? ? ???????? ???????? ???????, ?????????? ?????????? ???????????? ????????, ????????? ???????? ?????? ???????, ??????? ????? ???? ???????????? ? ??? ??????????????? ??????? ?????? ?????????. ?? ?????? ????? ??????????? ????????? ??????. ????? ?????????? ? ????? ?????????? Netbeans ?? ????? ???????????????? Java. ???? ??????? ?????? ?????????? ?? ??????? MySQL.?????????? ???????? ???????? ??????? ??? ??????????? ??????????????? ???????? ??????????? ?? ????????? ?????? ? ????? ????????? ???????????? ? ??????? ?? ?????? ??????? ??????????? ???????????? ??????? ? ???????????, ????????? ??????????? ?????????????? ???????. ???????? ?????: ????????? ??????? ??????-?????????? ??????, ???????????? ???????????, ?????????????? ????????, ???????? ???????? ???????, ???????????? ?????????????, ROC-??????, ?????? ???????.