SISCTG-um sistema inteligente para classificação de sinais cardiotocográficos para auxílio ao diagnóstico médico

Abstract

The accurate analysis of the fetal heart rate (FHR) and its correlation with uterine contractions (UC) allows the diagnostic and the anticipation of many problems related to fetal distress and the preservation of his life. This dissertation presents the results of an hibrid system based on a set of deterministic rules and fuzzy inference system developed to analyze FHR and UC signals collected by cardiotocography (CTG) exams. The studied variables are basal FHR, short and long term FHR variability, transitory accelerations and decelerations, these lasts classified by their type and number of ocurrencies. The system output is a first level diagnostics based on those input variables. The SISCTG system is developed using the Matlab version 7 script language. Tests and modeling issues used the Matlab Fuzzy Toolbox. The project also supports a multi-institutional agreement between Brazil and Germany, among the DETI - Departamento de Engenharia de Teleinform´atica of the UFC – Universidade Federal do Cear´a, the MEAC - Maternidade-Escola Assis Chateaubriand), the TUM - Technische Universität München, the Bundeswehr Universität München and the Trium Analysis Online GmbH. The SISCTG results are very promising, correctly classifying all normal exams. This is the expected behavior, once CTG exams are classified as of low specificity, with the most interest focused in finding pathologies aspects, but not precisely identifying them. These results allow the projection of improvements to the proposed system, inserting new input variables, for example. The system validation methodology was based on the knowledge of Brazilian and German obstetricians.