Στην παρούσα διπλωματική εργασία παρουσιάζονται τα ιατρικά συστήματα λήψης απόφασης (MDSS) και αρχιτεκτονικές ανάπτυξή τους. Πραγματεύεται τις έννοιες του ευφυούς ελέγχου και της ασάφειας για να καταλήξει στον όρο Ασαφή Γνωστικά Δίκτυα(FCΜ). Αφού περιγράφεται αναλυτικά η ανάπτυξή, ο καθορισμός των παραμέτρων και οι μεθοδολογίες εκμάθησης ενός Ασαφούς Γνωστικού Δικτύου, καταλήγει τελικά στην εφαρμογή τους στον χώρο της ιατρικής. Τέλος, ακολουθεί το μοντέλο ενός Ασαφούς Ελεγκτή για ιατρικές εφαρμογές και η ανάπτυξη ενός MDSS για την εύρεση Κάκωσης Γόνατος με αρχιτεκτονικές Ανταγωνιστικού Ασαφούς Γνωστικού Δικτύου (CFCΜ). / The thesis represents the medical decision support systems (MDSS) and their architecture. Starting with the concepts of intelligent control and Fuzzy Cognitive Maps (FCM), it describes in detail the development, the setting parameters, and the learning methods of FCMs, with the purpose of their application into the field of medicine. Finally, it illustrates the model of a Fuzzy Controller for medical applications and the development of an MDSS for finding knee injury with the architecture of Competitive FCMs (CFCM).

Made available in DSpace on 2015-05-14T12:36:36Z (GMT). No. of bitstreams: 1 ArquivoTotalRenata.pdf: 2638998 bytes, checksum: c2e2373b63cd157ac4705018a4e58468 (MD5) Previous issue date: 2013-02-19 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / In recent years, there was an increasing interest in the use of information technology in the medical field. In this way, several studies have been conducted regarding a large range of diseases, including cancer. For example, there are organizations that maintain databases, which record information about cases of cancer around the world, so that health personnel can investigate such bases and find possible classifications for an initial diagnostic according to the symptoms presented by their patients. However, these databases do not offer a proper support for this investigation. This dissertation discusses the use of the of case-based reasoning and rule-based reasoning technologies as a solution to support medical diagnosis via representations of actual patients and adaptations of these cases to define more specialized diagnoses, according to the peculiarities of each patient. The data collection was carried out in the Napoleao Laureano Hospital, at Joao Pessoa city, and the information inherent in the structure of the case, the rules and weights were defined in accordance with the specialized literature and conversations with health professionals. Despite the absence of a specialist, the small base of cases and presence of limited information on each of them, the results showed that the system is effective as a RBC system aimed at diagnosis about cancer. The focus of this project is on the main gastrointestinal cancer domain, but the ideas can be extended to other fields of cancer. / O tratamento de pacientes com câncer é um desafio para os hospitais e centros de saúde. O primeiro problema é classificar ou identificar o tipo específico de câncer. Em seguida, os médicos devem determinar um tratamento adequado para tal doença. Existem bancos de dados mundiais que registram informações sobre câncer, de modo que os médicos possam tentar achar uma classificação para a doença de acordo com os sintomas apresentados pelo paciente. Contudo eles não oferecem um bom suporte para a procura das doenças e, principalmente, para a identificação do tratamento. Este artigo propõe a utilização das tecnologias de raciocínio baseado em casos e raciocínio baseado em regras como solução para suportar estas duas atividades via representações de casos de pacientes e adaptações destes casos para a definição de diagnósticos mais especializados, de acordo com as peculiaridades de cada paciente. Nosso foco é sobre o câncer gastrointestinal, mas as idéias podem ser estendidas para outros domínios de câncer.

Introduction : Établir un diagnostic médical fiable requiert l’identification de la maladie d’un patient sur la base de l’observation de ses signes et symptômes. Par ailleurs, les ontologies constituent un formalisme adéquat et performant de représentation des connaissances biomédicales. Cependant, les ontologies classiques ne permettent pas de représenter les connaissances liées au processus du diagnostic médical : connaissances probabilistes et connaissances imprécises et vagues. Matériel et méthodes : Nous proposons des méthodes générales de représentation des connaissances afin de construire des ontologies adaptées au diagnostic médical. Ces méthodes permettent de représenter : (a) Les connaissances imprécises et vagues par la discrétisation des concepts (définition de plusieurs catégories distinctes à l’aide de valeurs seuils ou en représentant les différentes modalités possibles). (b) Les connaissances probabilistes (les sensibilités et les spécificités des signes pour les maladies, et les prévalences des maladies pour une population donnée) par la réification des relations ayant des arités supérieures à 2. (c) Les signes absents par des relations et (d) les connaissances liées au processus du diagnostic médical par des règles SWRL. Un moteur d’inférences abductif et probabiliste a été conçu et développé. Ces méthodes ont été testées à l’aide de dossiers patients réels. Résultats : Ces méthodes ont été appliquées à trois domaines (les maladies plasmocytaires, les urgences odontologiques et les lésions traumatiques du genou) pour lesquels des modèles ontologiques ont été élaborés. L’évaluation a permis de mesurer un taux moyen de 89,34% de résultats corrects. Discussion-Conclusion : Ces méthodes permettent d’avoir un modèle unique utilisable dans le cadre des raisonnements abductif et probabiliste, contrairement aux modèles proposés par : (a) Fenz qui n’intègre que le mode de raisonnement probabiliste et (b) García-crespo qui exprime les probabilités hors du modèle ontologique. L’utilisation d’un tel système nécessitera au préalable son intégration dans le système d’information hospitalier pour exploiter automatiquement les informations du dossier patient électronique. Cette intégration pourrait être facilitée par l’utilisation de l’ontologie du système. / Introduction: Making a reliable medical diagnosis requires the identification of the patient’s disease based on the observation of signs. Moreover, ontologies provide an adequate and efficient formalism for medical knowledge representation. However, classical ontologies do not allow representing knowledge associated with medical reasoning such as probabilistic, imprecise, or vague knowledge. Material and methods: In the current work, general knowledge representation methods are proposed. They aim at building ontologies fitting to medical diagnosis. They allow to represent: (a) imprecise or vague knowledge by discretizing concepts (definition of several distinct categories thanks to threshold values or by representing the various possible modalities), (b) probabilistic knowledge (sensitivity, specificity and prevalence) by reification of relations of arity greater than 2, (c) absent signs by relations and (d) medical reasoning and reasoning on the absent signs by SWRL rules. An abductive reasoning engine and a probabilistic reasoning engine were designed and implemented. The methods were evaluated by use of real patient records. Results: These methods were applied to three domains (the plasma cell diseases, the dental emergencies and traumatic knee injuries) for which the ontological models were developed. The average rate of correct diagnosis was 89.34 %. Discussion-Conclusion: In contrast with other methods proposed by Fenz and García-crespo, the proposed methods allow to have a unique model which can be used both for abductive and probabilistic reasoning. The use of such a system will require beforehand its integration in the hospital information system for the automatic exploitation of the electronic patient record. This integration might be made easier by the use of the ontology on which the system is based.