RESUMO

The determination of the optimal time of the patients in weaning trial process from mechanical ventilation, between patients capable of maintaining spontaneous breathing and patients that fail to maintain spontaneous breathing, is a very important task in intensive care unit. Wavelet Transform (WT) and Neural Networks (NN) techniques were applied in order to develop a classifier for the study of patients on weaning trial process. The respiratory pattern of each patient was characterized through different time series. Genetic Algorithms (GA) and Forward Selection were used as feature selection techniques. A classification performance of 77.00±0.06% of well classified patients, was obtained using a NN and GA combination, with only 6 variables of the 14 initials.

Assuntos

Diagnóstico por Computador/métodos , Redes Neurais de Computação , Insuficiência Respiratória/diagnóstico , Insuficiência Respiratória/radioterapia , Terapia Assistida por Computador/métodos , Desmame do Respirador/métodos , Humanos , Reconhecimento Automatizado de Padrão/métodos , Reprodutibilidade dos Testes , Testes de Função Respiratória/métodos , Insuficiência Respiratória/reabilitação , Sensibilidade e Especificidade , Análise de Ondaletas