Estimação do risco de morte de recém-nascidos utilizando logica fuzzy tipo-2 intervalar

• Main Author: Simioni, Giovani Bulian [UNESP]
• Publication Date: 2013
• Format: Bachelor thesis
• Language: por
• Source: Repositório Institucional da UNESP
• Download full: http://hdl.handle.net/11449/121323
• topic: Lógica difusa; Recem-nascidos - Mortalidade; Processo decisorio; Banco de dados; Intervalo entre nascimentos; Fuzzy logic

The main objective of the presented study is the development of a predictive interval type-2 fuzzy inference system in order to estimate the mortality risk for a newborn, to be used as an auxiliary tool for decision making in medical centers where there is a lack of professionals for this purpose and, afterwards, to compare its performance to a type-1 fuzzy system. The input variables were chosen due to their acquisition ‘simplicity, not involving any invasive tests, such as blood tests or other specific tests. The variables are easily obtained in the first few minutes of life: birth weight, gestational age at delivery, 5-minute Apgar score and previous report of stillbirth. Databases from the DATASUS were used to validate the model. 1351 records from the city of São José dos Campos, a mid-sized city in the São Paulo state’s countryside, were considered in this study. Finally, an analysis using the ROC curve was performed to estimate the model’s accuracy