TY - JOUR
T1 - Regression analysis for solving diagnosis problem of children's health
AU - Cherkashina, Yu A.
AU - Gerget, O. M.
N1 - Publisher Copyright:
© Published under licence by IOP Publishing Ltd.
Copyright:
Copyright 2017 Elsevier B.V., All rights reserved.
PY - 2016/6/2
Y1 - 2016/6/2
N2 - The paper includes results of scientific researches. These researches are devoted to the application of statistical techniques, namely, regression analysis, to assess the health status of children in the neonatal period based on medical data (hemostatic parameters, parameters of blood tests, the gestational age, vascular-endothelial growth factor) measured at 3-5 days of children's life. In this paper a detailed description of the studied medical data is given. A binary logistic regression procedure is discussed in the paper. Basic results of the research are presented. A classification table of predicted values and factual observed values is shown, the overall percentage of correct recognition is determined. Regression equation coefficients are calculated, the general regression equation is written based on them. Based on the results of logistic regression, ROC analysis was performed, sensitivity and specificity of the model are calculated and ROC curves are constructed. These mathematical techniques allow carrying out diagnostics of health of children providing a high quality of recognition. The results make a significant contribution to the development of evidence-based medicine and have a high practical importance in the professional activity of the author.
AB - The paper includes results of scientific researches. These researches are devoted to the application of statistical techniques, namely, regression analysis, to assess the health status of children in the neonatal period based on medical data (hemostatic parameters, parameters of blood tests, the gestational age, vascular-endothelial growth factor) measured at 3-5 days of children's life. In this paper a detailed description of the studied medical data is given. A binary logistic regression procedure is discussed in the paper. Basic results of the research are presented. A classification table of predicted values and factual observed values is shown, the overall percentage of correct recognition is determined. Regression equation coefficients are calculated, the general regression equation is written based on them. Based on the results of logistic regression, ROC analysis was performed, sensitivity and specificity of the model are calculated and ROC curves are constructed. These mathematical techniques allow carrying out diagnostics of health of children providing a high quality of recognition. The results make a significant contribution to the development of evidence-based medicine and have a high practical importance in the professional activity of the author.
UR - http://www.scopus.com/inward/record.url?scp=84975744279&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84975744279&partnerID=8YFLogxK
U2 - 10.1088/1757-899X/124/1/012047
DO - 10.1088/1757-899X/124/1/012047
M3 - Conference article
AN - SCOPUS:84975744279
VL - 124
JO - IOP Conference Series: Materials Science and Engineering
JF - IOP Conference Series: Materials Science and Engineering
SN - 1757-8981
IS - 1
M1 - 012047
T2 - International Conference on Mechanical Engineering, Automation and Control Systems 2015, MEACS 2015
Y2 - 1 December 2015 through 4 December 2015
ER -