Prototipo de sistema experto en diagnóstico médico basado en síntomas de los pacientes. Caso de estudio: esclerosis múltiple

Expert system prototype on medical diagnosis based on patients’ symptoms. Case study: multiple sclerosis

  • Juan Guillermo Rivera Berrío Institución Universitaria Pascual Bravo
  • Héctor Aníbal Tabares Ospina Institución Universitaria Pascual Bravo

Resumen (es_ES)

Se presenta en este artículo un modelo de sistema experto para el diagnóstico de la esclerosis múltiple. Esta labor no es una tarea trivial, debido a la subjetividad que puede presentarse en su evaluación. Este proceso se puede complementar usando un sistema de apoyo a la toma de decisiones. El sistema desarrollado se dividió en cuatro fases: toma de requisitos, diseño, implementación y puesta en marcha. Con el prototipo software se logró modelar el conocimiento específico del experto neurólogo, lo que permitió obtener un diagnóstico de la esclerosis múltiple.

Resumen (en_US)

This paper presents a model of expert system for the diagnosis of multiple sclerosis. This task is not a trivial task, due to the subjectivity that may occur in their evaluation. This process can be supplemented using a system to support decision making. The developed system was divided into four phases: making requirements, design and implementation, and its set-up. With the software prototype, it was possible to model the specific knowledge of the expert neurologist, allowing a diagnosis of multiple sclerosis.

Descargas

La descarga de datos todavía no está disponible.

Biografía del autor/a

Juan Guillermo Rivera Berrío, Institución Universitaria Pascual Bravo
Ingeniero civil, especialista en estructuras, doctor en estudios de ciencia y tecnología. Vicerrector académico, Institución Universitaria Pascual Bravo. Medellin.
Héctor Aníbal Tabares Ospina, Institución Universitaria Pascual Bravo
Ingeniero electricista, especialista en ingeniería del software, magíster en ingeniería de sistemas, estudiante de doctorado en sistemas energéticos. Docente, Institución Universitaria Pascual Bravo. Medellín

Referencias

AMERICAN ACADEMIC OF NEUROLOGY, C. (10 de 5 de 2011). Lifelong learning in neurology. Recuperado el 20 de 2 de 2012, de Lifelong learning in neurology: http://www.aan.com/elibrary/continuum/?event=home.showIssue&issue=ovid.com:/issue/ovftdb/00132979-200412000-00000.

Astion, M., Wener, M., Thomas, R., Hunder, G., & Bloch, D. (1994). Application of neural networks to the classification of giant cell arteritis. Arthritis and Rheumatism , 760-770.

Bartosh, A., Andersson, B., & Nilsson, J. (2008). Artificial neural networks in pancreatic disease. British journal of surgery , 817-826.

Bizios, D., Heij, A., & Bengtsson, B. (2007). Trained artificial neural network for galucoma diagnosis using visual field data: un comparison with conventional algorithms . Journal of glaucoma , 20-28.

Borges, K., Moura, R., & Steiner, A. (2010). Diagnosis of headache using artificial neural network. IJCSNS International Journal of Computer Science and NetworkSecurity , 128-142.

Bourdes, V., Bonnevay, S., Bachelot, T., & Perol, D. (2007). Breast cancer predictions by neural netwroks analysis: a comparison with logistic regression. Engineering in medicine and and biological society. 29th anuual international conference of the IEEE , 5424-5427.

Buarque, F. (2000). Multiple sclerosis plaque: computer model and simulations. Internal report. Imperial college of science technology and medicine, EEE Departure , 12, 51.

Celona, A., Grasso, G., & Puccio, L. (2009). Artificial neural network. Morphological classification by euclidean distance histograms for prognostic evaluation of magnetic resonance imaging in multiple sclerosis. SIMAI Congress , 283-292.

Chiou, Y., & Lure, Y. (1994). Hybrid lung module detection (HLND) system. Cancer Letters , 119-126.

Cook, D. (2005). Artificial neural network to predict mortality in critial care patients. An applocation of supervised machine learning. Australasian anaesthesia , 205-224.

Doyle, H., Dvorchik, I., Mitchell, S., Marino, I., Ebert, F., McMichael, J., y otros. (1994). Predicting outcomes after liver transplantations. A connectionist approach. Annals of surgery , 408-415.

Ebell, M. (1993). Artificial neural netwokrs for predicting failure to survive following hospital cardiopulmonary resuscitation. Journal of family practice , 297-303.

Esposito, M., & De Pietro, G. (2011). An ontology-based fuzzy decision support system for multiple sclerosis. Elsevier. Engineering applications of artificial intelligence , 1340-1354.

Gannous, A., & Elhaddad, R. (2011). Improving an artificial neural network model to predict thyroid bending protein diagnosis using preprocessing techniques. World academic of science, engineering and technology , 132-141.

Gaspari, M., Roveda, G., Scandellari, C., & Stecchi, S. (2012). An expert system for the evaluation of EDSS in multiple sclerosis. Elsevier. Artificial intelligence in medicine , 187-210.

Giarratano, J., & Riley, G. (2001). Sistemas experto. Principios y programacion. Mexico D.F.: International Thompson Editors.

Gil, D., Johnsson, M., Garcia, J., & Soriano, A. (2009). Applications of artificial neural networks int the diagnosis of urological dysfunctions. Expert systems with applications , 5754-5760.

Gutierrez, A., Gonzalez, J., Lopez, P., Ojeda, E., Sanchez, J., & Toro, J. (2001). Esclerosisi Multiple. Consensos en Neurologia: guias de practica clinica , 1-13.

Harrison, R., & Kennedy, L. (2005). Artificial neural network models for prediction of acute coronary syndromes using clinical data from de time of presentation. Annals of emergency medicine. American collage of emergency , 228-251.
Ingeniería del software2005Pearson Addison-Wesley

Kasmierczak, C., Catrou, G., & Van Lente, F. (1998). Diagnostic accuracy of pancreatic enzymes evaluated by use of multivariate data analysis. Clinical chemestry , 817-826.

Primorac, C., & Mariño, S. (4 de 12 de 2010). Un sistema experto para asistir decisiones turisticas. Diseño de un prototipo basado en la web. Recuperado el 9 de 5 de 1012, de Un sistema experto para asistir decisiones turisticas. Diseño de un prototipo basado en la web: http://www.eumed.net/rev/turydes/10/index.htm

Sharpe, P., Solberg, H., Rootwelt, K., & Yearworth, M. (1993). Artificial neural networks in diagnosis of thyroid function from in vitro laboratory tests. Clinical chemestry , 2248-2253.

Shin, S., Tolum, M., & Hassanpour, R. (2012). Hybrid expert system: A survey of current approachesand applications. Elsevier. Expert systems with applications , 4609-4617.

Tabares, H., Monsalve, D., & Diez, D. (2013). Modelo de sistema experto para la seleccion de personal docente universitario. Tecnologicas , 35-54.

Wang, Y., & Shiun, J. (2009). Artificial neural network to predict skeletal metastaisis in patients with prostate cancer. Spreniger science, Med Syst , 91-100.

Xu, C., Brown, D., Breit, S., & Nakamura, T. (2006). Three new serum markers for prostate cancer detection within a percent free PSA-based artificial neural network. Prostate , 651-659.
Cómo citar
Rivera Berrío, J. G., & Tabares Ospina, H. A. (2014). Prototipo de sistema experto en diagnóstico médico basado en síntomas de los pacientes. Caso de estudio: esclerosis múltiple. Tecnura, 18, 205-216. https://doi.org/10.14483/udistrital.jour.tecnura.2014.SE1.a15
Publicado: 2014-12-01
Sección
Estudio de caso