Regression analysis for solving diagnosis problem of children's health

Yu A. Cherkashina, O. M. Gerget

Research output: Contribution to journalConference articlepeer-review

1 Citation (Scopus)

Abstract

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.

Original languageEnglish
Article number012047
JournalIOP Conference Series: Materials Science and Engineering
Volume124
Issue number1
DOIs
Publication statusPublished - 2 Jun 2016
EventInternational Conference on Mechanical Engineering, Automation and Control Systems 2015, MEACS 2015 - Tomsk, Russian Federation
Duration: 1 Dec 20154 Dec 2015

ASJC Scopus subject areas

  • Materials Science(all)
  • Engineering(all)

Fingerprint Dive into the research topics of 'Regression analysis for solving diagnosis problem of children's health'. Together they form a unique fingerprint.

Cite this