IME - Artigos publicados em periódicos
URI Permanente para esta coleção
Navegar
Navegando IME - Artigos publicados em periódicos por Autor "Barros, Laécio Carvalho de"
Agora exibindo 1 - 2 de 2
Resultados por página
Opções de Ordenação
Item A metodologia ROC na avaliação de um modelo fuzzy de predição do estádio patológico do tumor de próstata(2010) Silveira, Graciele Paraguaia; Barros, Laécio Carvalho de; Vendite, Laércio Luis; Ferreira, Ubirajara; Billis, AthanaseIn recent years, the increase in the incidence of prostate cancer has become a major public health problem and a challenge for medical science. The goal of this work is assessing the performance of a mathematical model, developed by Silveira (2007) to predict the pathological stage of the prostate cancer, through ROC methodology (Receiver Operating Characteristic). The model is a fuzzy rulebased system, that combines pre-surgical data – clinical stage, PSA level and Gleason score – availing of a set of linguistic rules made with base on information of the existents nomograms. The output of the system provides the possibilities of the individual, with certain clinical features, be in each stage of the tumor extension: localized, advanced locally and metastatic. To analyze the discriminatory power of the fuzzy model as a diagnosis test, was constructed from the measures of sensitivity and specificity, the ROC curve and calculated the total area under the curve, as measure of performance. Moreover, were obtained (in two different ways) the cutoff points most “appropriate”, that is a threshold for deciding between the disease is fully localized within the prostate gland or not. Real data of patients from the Clinics Hospital of UNICAMP were used in the calculations and the surgery – radical prostatectomy – was used as gold standard. The results showed that the fuzzy model in question can be used to discriminate localized prostate cancer.Item Nomograma com Lógica Fuzzy para o Câncer de Próstata – NFCP(2010) Silveira, Graciele Paraguaia; Vendite, Laércio Luis; Barros, Laécio Carvalho deWe begin developing a fuzzy model aiming to predict the pathologic staging of prostate cancer (SILVEIRA-2007). The model (also known as cancer nomogram) is composed of a fuzzy rule-based system that combines the pre-surgery data of the patient - clinic stat, PSA level, Gleason score - keeping in mind a set of linguistic rules based on the already knwon cancer nomograms of Kattan (STEPHENSON-2006). The output is the odds of the patient to be in each one of the extension stages of the tumor. Several simulations were done with data from patients of UNICAMP's Hospital das Clínicas and the results have been compared with the Kattan probabilities. Next, we validate our results analising the (Receiver Operating Characteristic) curve, using the database of the same hospital. A paper about the construction of the ROC curve was written and will be on the Revista Brasileira de Engenharia Biomédica. A software, named NFCP - Nomograma com Lógica Fuzzy para o Câncer de Próstata, was developed using this model. It was written in JAVA and has a GUI (graphic user interface) that can interact with the calculating sub-routines. This software is iin process of acquiring the patent in the Instituto Nacional da Propriedade Industrial - INPI.