Mostrar el registro sencillo del ítem

dc.contributor.advisorAlmario, Diego Fernandospa
dc.contributor.authorGutiérrez G., Jorge Eduardospa
dc.contributor.authorPeña Paz, Lydaspa
dc.date.accessioned2020-06-26T21:32:15Z
dc.date.available2020-06-26T21:32:15Z
dc.date.issued2005
dc.identifier.urihttp://hdl.handle.net/20.500.12749/3303
dc.description.abstractIntroducción: La interpretación de estudios electrofisiológicos es esencialmente una tarea de clasificación. Las redes neuronales artificiales (ANN) son herramientas adecuadas para la clasificación porque son basado en técnicas de reconocimiento de patrones. Objetivos: Desarrollar un sistema informático para la detección automatizada de neuropatías focales. utilizando ANN. Métodos: El estudio se basó en 300 conjuntos de estudios de conducción nerviosa (NCS) de tres diferentes laboratorios de medicina de electrodiagnóstico. Cada conjunto de datos de entrada estaba formado por 11 parámetros, incluyendo latencias motoras y sensoriales, amplitudes, duraciones y velocidades de un solo nervio. Los conjuntos de entrada se clasificaron en 4 subgrupos de neuropatía focal (distal desmielinización, desmielinización proximal, desmielinización generalizada, pérdida de axones) según sobre el tipo de daño nervioso más 1 adicional para hallazgos normales. Los datos fueron presentados a una ANN de retropropagación con 1 capa oculta. La estructura de la red se modificó para lograr el error cuadrático medio más bajo posible. Los resultados de estas redes de primer nivel se presentaron a una red de segundo nivel para detectar neuropatías generalizadas. Después entrenando a las ANN, la precisión de la clasificación se probó utilizando otro conjunto de datos que se desconocido para las redes. Resultados: Se alcanzó una precisión de clasificación del 99% para la detección de patologías patrones. La precisión para la clasificación de neuropatías focales fue del 95,2%. Conclusiones: las redes neuronales clasifican subgrupos de neuropatía focal con alta precisión (> 95%). Este método puede conducir a la detección automática de neuropatía focal.spa
dc.description.sponsorshipInstituto Tecnológico de Estudios Superiores de Monterrey ITESMspa
dc.description.tableofcontentsSUMMARY 11 INTRODUCCION 1 1 EL PROBLEMA 3 1.1 DESCRIPCIÓN DEL PROBLEMA 3 1.2 FORMULACIÓN DEL PROBLEMA 5 1.3 OBJETIVO GENERAL 5 1.4 OBJETIVOS ESPECIFICOS 5 1.5 JUSTIFICACIÓN 6 1.6 ALCANCES Y LIMITACIONES 7 2 MARCO DE REFERENCIA 9 2.1 ANTECEDENTES DE LA INVESTIGACIÓN 9 2.2 MARCO TEÓRICO CONCEPTUAL 11 2.2.1 Medicina Electrodiagnóstica 12 2.2.2 Inteligencia Artificial y Medicina 45 2.2.3 Redes Neuronales Artificiales 61 2.2.4 Aplicaciones de redes neuronales a Medicina 94 2.2.5 Aplicaciones de redes neuronales a electrodiagnóstico 104 3 METODOLOGÍA 106 3.1 DATOS 106 3.1.1 Salidas deseadas 106 3.1.2 Selección de los datos de entrada 107 3.1.3 Preprocesamiento de los datos de entrada 109 3.1.4 Datos Faltantes 110 3.1.5 Fuente de los datos 111 3.2 ARQUITECTURA DE LA RED 113 3.2.1 Tipo de red 114 3.2.2 Mejorar la Generalización 115 3.2.3 Arquitectura de la Red 1 116 3.2.4 Arquitectura de la Red 2 121 3.3 SOFTWARE 124 3.4 HARDWARE 125 3.5 ENTRENAMIENTO 125 3.6 VALIDACIÓN DE LA RED 126 4 RESULTADOS 127 4.1 RED 1 (ESTRUCTURA DE RED GENERAL) 127 4.2 RED 2 (RED NERVIO MEDIANO) 128 4.3 RED 3 (RED NERVIO ULNAR) 130 4.4 RED 4 (RED DE GENERALIZACIÓN) 132 4.5 VALIDACIÓN DE RESULTADOS 135 5 DISCUSIÓN 137 CONCLUSIONES 139 RECOMENDACIONES 141 BIBLIOGRAFIA 142 REFERENCIAS ELECTRONICASspa
dc.format.mimetypeapplication/pdfspa
dc.language.isospaspa
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/2.5/co/*
dc.titleAplicaciones de redes neuronales artificiales a estudios neurofisiológicos en neuropatías periféricas focalesspa
dc.title.translatedApplications of artificial neural networks to neurophysiological studies in focal peripheral neuropathieseng
dc.degree.nameMagíster en Ciencias Computacionalesspa
dc.coverageBucaramanga (Colombia)spa
dc.publisher.grantorUniversidad Autónoma de Bucaramanga UNABspa
dc.rights.localAbierto (Texto Completo)spa
dc.publisher.facultyFacultad Ingenieríaspa
dc.publisher.programMaestría en Ciencias Computacionalesspa
dc.description.degreelevelMaestríaspa
dc.type.driverinfo:eu-repo/semantics/masterThesis
dc.type.localTesisspa
dc.type.coarhttp://purl.org/coar/resource_type/c_bdcc
dc.subject.keywordsArtificial neural networks (Computers)eng
dc.subject.keywordsNeuropathyeng
dc.subject.keywordsComputer scienceeng
dc.subject.keywordsDiseaseseng
dc.subject.keywordsDiagnosiseng
dc.subject.keywordsData processingeng
dc.subject.keywordsInvestigationseng
dc.subject.keywordsAnalysiseng
dc.subject.keywordsSystems engineeringeng
dc.subject.keywordsFocal neuropathyeng
dc.subject.keywordsAutomated detectioneng
dc.identifier.instnameinstname:Universidad Autónoma de Bucaramanga - UNABspa
dc.identifier.reponamereponame:Repositorio Institucional UNABspa
dc.type.hasversioninfo:eu-repo/semantics/acceptedVersion
dc.rights.accessrightsinfo:eu-repo/semantics/openAccessspa
dc.rights.accessrightshttp://purl.org/coar/access_right/c_abf2spa
dc.relation.referencesGutiérrez G., Jorge Eduardo, Peña Paz, Lyda (2005). Aplicaciones de redes neurales artificiales a estudios neurofisiológicos en neuropatías periféricas focales. Bucaramanga (Colombia) : Universidad Autónoma de Bucaramanga UNAB, Instituto Tecnológico y de Estudios Superiores de Monterrey ITESMspa
dc.relation.referencesAAEM: Glossary of terms in Electrodiagnostic Medicine. En: Muscle Nerve. No 10. 2001.spa
dc.relation.referencesPractice Parameter for Electrodiagnostic Studies in carpal tunnel syndrome: Summary statement. En Muscle Nerve. No 26. 2002.spa
dc.relation.referencesPractice Parameter for Electrodiagnostic Studies in Ulnar Neuropathy at the elbow: Summary statement. En Muscle Nerve. No 8. 1999.spa
dc.relation.referencesABREU-LIMA C. and DE SA, J.P. Automatic classifiers for the interpretation of electrocardiograms. Rev. Port. Cardiol. 17. 1998.spa
dc.relation.referencesACCORNERO N and CAPOZZA M OPTONET: neural network for visual field diagnosis. Med Biol Eng Comput, Vol 2. No 33. 1995spa
dc.relation.referencesAMINOFF MJ Electromyography in clinical practice, 3ed. New York, Churchill Livingstone. 1998.spa
dc.relation.referencesBAKER JA et al Breast cancer: prediction with artificial neural network based on BIRADS standardized lexicon. Radiology, 1995spa
dc.relation.referencesBAXT WG Analysis of the clinical variables driving decision in an artificial neural network trained to identify the presence of myocardial infarction. Ann Emerg Med, 1992.spa
dc.relation.referencesUse of an artificial neural network for the diagnosis of myocardial infarction. Ann Intern Med. 1991.spa
dc.relation.referencesBENESOVA O et al Perinatal pharmacotherapy and the risk of functional teratogenic defect]. Cesk Fysiol, 1995.spa
dc.relation.referencesBENIGNI R. and RICHARD A.M. Quantitative structure-based modeling applied to characterization and prediction of chemical toxicity. Methods, 14, 1998spa
dc.relation.referencesBINDER M. et at. Epiluminiscence microscopy-based classification of pigmented skin lesions using computerirized image analysis and a n artificial neural network. Melanoma. 1998.spa
dc.relation.referencesBISHOP, Christopher M. Neural Network for Pattern Recognition. 1995spa
dc.relation.referencesBOON M.E. et al. Neural network processing of cervical smears can lead to a decrease in diagnostic variability and an increase in screening efficiacy: a study of 63 false-negative smears. Mod Pathol, 1994.spa
dc.relation.referencesBOUNDS D. and LLOYD P.J. A multi-layer perceptron network for the diagnosis of low back pain. Proc. IEEE Int. Conf. on Neural Networks. Vol.II. 1988. p. 481-489spa
dc.relation.referencesBRAUSE,R. and FRIEDRICH, F. A Neuro-Fuzzy Approach as Medical Diagnostic Interface. European Symposium on Artificial Neural networks. ESANN 2000spa
dc.relation.referencesBURSTEIN Z. A network model of developmental gene hierarchy. J Theor Biol 1995spa
dc.relation.referencesBURTIS CA. Technological trends in clinical laboratory science. Clin Biochem, 1995spa
dc.relation.referencesCHITTAJALLU SK and WONG D. Connectionist networks in auditory system modeling. Comput Biol Med, 1994spa
dc.relation.referencesCRISTODOULOU CU and PATTICHIS CS. A new technique for the classification and decomposition of EMG signals. Proceedings of the IEEE international conference on Neural Networks. Vol 5. 1995spa
dc.relation.referencesDAWSON AE; AUSTIN RE Jr and WEINBERG DS. Nuclear grading of breast carcinoma by image analysis. Classification by multivariate and neural network analysis. Am J Clin Pathol, 1991.spa
dc.relation.referencesDEFIGUEIREDO R et al. Neural-network-based classification of cognitively normal, demented, Alzheimer disease and vascular dementia from single photon emission with computed tomography image data from brain. Proc Natl Acad Sci USA, 1995.spa
dc.relation.referencesDESCATHA A et al. Incidence of ulnar nerve entrapment at the elbow in repetitive work. Scand J Work Environ Health. 2004. p.234-40.spa
dc.relation.referencesDOMINE D. et al. Nonlinear neural mapping analysis of the adverse effects of drugs. SAR QSAR Environ. Res., 8, 1998spa
dc.relation.referencesDONOFRIO PD and ALBERS JW. Polyneuropathy: Classification by nerve conduction studies and electromyography. En Muscle Nerve. No 13. 1990.spa
dc.relation.referencesDUMITRI D. Electrodiagnostic Medicine. Williams and Wilkins, Philadelphia, 1995spa
dc.relation.referencesDUMITRU D.; AMATO AA and ZWARTS MJ: Electrodiagnostic Medicine 2ed. Philadelphia, Hanley & Belfus. 2001.spa
dc.relation.referencesDYBOWSKI R, Gant V (Eds): Clinical applications of neural networks. Cambridge University Press, United Kingdom, 2001.spa
dc.relation.referencesEKLUND P and FORSSTROM JJ. Computational intelligence for laboratory information systems. Scand J Clin Lab Invest Suppl, 1995. p.222spa
dc.relation.referencesENGEL AG and FRANZINI-ARMSTRONG C, eds. Myology. New York, McGraw-Hill. 1994.spa
dc.relation.referencesERRINGTON PA and GRAHAM J. Application of artificial neural networks to chromosome classification. Cytometry. 1993spa
dc.relation.referencesFARRUGGIA S; YEE H and NICKOLLS P. Implantable cardiverter defibrillator electrogram recognition with a multilayer perceptron. PACE Pacing Clin Electrophysiol. 1993.spa
dc.relation.referencesFOGEL DB; WASSON EC 3rd and BOUGHTON EM. Evolving neural networks for detecting breast cancer. Cancer Lett. 1995.spa
dc.relation.referencesFORINA M. et al. Zupan.s descriptors in QSAR applied to the study of a new class of cardiotonic agents. Farmaco, 52, 1997.spa
dc.relation.referencesFU, L.M. Neural networks in computer intelligence. McGrawHill, Singapore. 1994.spa
dc.relation.referencesGABOR AJ and SEYAL M: Automated interictal EEG spike detection using artificial neural networks. Electroencephalogr Clin Neurophysiol. 1992spa
dc.relation.referencesGIACOMETTI A et al. A Hybrid approach to computer-aided diagnosis in electromyography. Proceedings of the Annual International conference of the IEEE Engineering in Medicine and Biology Society. vol. 14. 1992spa
dc.relation.referencesGUIGON E et al. Neural correlates of learning in the prefrontal cortex of the monkey: a predictive model. Cereb Cortex, 1995.spa
dc.relation.referencesGURNEY JW and SWENSEN SJ. Solitary pulmonary nodules: determining the likelihood of malignancy with neural network analysis. Radiology. 1995spa
dc.relation.referencesGUTIERREZ, JE. Electroagnostico en PEDROZA A (Ed). Compendio de Neurocirugia. Bogota, Quebecor Impreandes, 2002spa
dc.relation.referencesGUYTON AC: Textbook of Medical Physiology, 8 ed. Philadelphia, W.B. Saunders, 1991spa
dc.relation.referencesHAMAMOTO I. et al. Prediction of the early prognosis of the hepatectomized patient with hepatocellular carcinoma with a neural network. ComputBiol Med. 1995spa
dc.relation.referencesHECHT-NIELSEN R. Neurocomputing. Addison-Wesley. 1991.spa
dc.relation.referencesHOYER D; SCHMIDT K and ZWIENER U: Principles and experiences for modeling chaotic attractors of heart rate fluctuations with artificial neural networks. Biomed Tech Berl, 1995spa
dc.relation.referencesHUDSON, Donna and COHEN, Maurice. Neural Networks and Artificial Intelligence for Biomedical Engineering. 2000.spa
dc.relation.referencesINSIGNARES, Víctor Manuel. Redes Neuronales. Principios y aplicaciones en el campo biológicospa
dc.relation.referencesJAKUS V. The concept and applications of artificial neural networks in Medicine. Bratisl Lek Listy. 1999.spa
dc.relation.referencesJAND. G et al. Pattern recognition of the electroencephalogram by artificial neural networks. Electroencephalogr Clin Neurophysiol. 1993spa
dc.relation.referencesJERVIS BW. The application of Neural Networks to interpret Evoked Potential waveforms. In LISBOA PJG (eds): Artificial Neural networks in Biomedicine. Springer, London, 2001spa
dc.relation.referencesJUHOLA M et al. Neural network recognition of otoneurogical vertigo diseases. In HORN W (eds): Artificial Intelligence in Medicine, Springer, Berlin, 1999spa
dc.relation.referencesKANDEL ER; SCHWARTZ JH and JESSELL TM: Principles of Neural Science, 4 ed. New York, Mc Graw-Hill, 2000spa
dc.relation.referencesKANGAS LJ and KELLER, PE. Neurometric assessment of adequacy of intraoperative anesthetic. In LISBOA PJG…(eds): Artificial Neural networks in Biomedicine. Springer, London, 2001spa
dc.relation.referencesKOKOL P et al. Some Ideas About Intelligent Medical System Design. Proceedings of the 12th IEEE Symposium on Computer-based Medical Systems CBMS’99 Stamford, CN, June 1999spa
dc.relation.referencesKOLLES H et al. Automated grading of astrocytomas based on histomorphometric analysis. Classification results of neuronal networks and discriminant analysis. Anal Cell Pathol, 1995.spa
dc.relation.referencesLAPEER RJ et al. Application of neural networks to the ranking of perinatal variables influencing birth weight. Scand J Clin Lab Invest Supplspa
dc.relation.referencesLUNDBORG G et al. Motor control of tomorrow’s artificial hand: Based on the combined use of artificial neural networks and a data glove. ASSH 56th|annual Meeting, 2001, paper #1.spa
dc.relation.referencesMACFARLANE PW. Recent developments in computer analysis of ECGs. Clin Physiol 1992.spa
dc.relation.referencesMAEDA N; KLYCE SD and SMOLEK MK. Neural network classification of corneal topography. Preliminary demonstration. Invest Ophthalmol Vis Sci, 1995.spa
dc.relation.referencesMARTIN DEL BRIO, Bonifacio y SANZ MOLINA, Alfredo. Redes Neuronales y Sistemas Difusos (2ª Ed). 2002.spa
dc.relation.referencesMATWORKS. Documentación de MatLab.spa
dc.relation.referencesMcGONIGAL M. A New Technique for Survival Prediction in Trauma Care Using a Neural Network. Proc. World Conference on Neural Networks. 1994.spa
dc.relation.referencesMICHALEWIS Z. Genetic Algorithms + Data Structures = Evolution programs, 3 ed. Berlin, Springer, 1996.spa
dc.relation.referencesMINSKY, Marvin and PAPERT, Seymour. Perceptron: An Introduction to Computational Geometry. MIT Press. 1969spa
dc.relation.referencesMOLNAR B et al. Application of multivariate, fuzzy set and neural network analysis in quantitative cytological examinations. Anal Cell Pathol. 1993.spa
dc.relation.referencesMYLREA KC; ORR JA and WESTENSKOW DR: Integration of monitoring intelligent alarm anesthesia: neural networks - can they help? J Clin Monit. 1993.spa
dc.relation.referencesNIKOVSKY Daniel. Constructing Bayesian Networks for Medical Diagnosis from Incomplete and Partially Correct Statistics. IEEE Transactions on Knowledge and Data Engineering. Vol 12 (4), 2000spa
dc.relation.referencesNORDSTROM D. et al. Incidence of diagnosed carpal tunnel syndrome in a general population. Epidemiology 1998spa
dc.relation.referencesOH, SJ. Clinical Electromyography: case studies. Baltimore, Lippincott Williams & Wilkins. 1998.spa
dc.relation.referencesOÕLEARY TJ; MIKEL UV and BECKER RL: Computer-assisted image interpretation: use of a neural network to differentiate tubular carcinoma from sclerosing adenosis. Mod Pathol, 1992.spa
dc.relation.referencesORTIZ J. et al. Use of artificial neural networks in survival evaluation in heart failure. Arq Bras Cardiol, 1995spa
dc.relation.referencesPAPADOPOULOS A; FOTIADIS DI and LIKAS A: A automatic microcalcification detection system based on a hybrid neural network classifier. Artificial Intelligence in Medicine, 2002.spa
dc.relation.referencesPAPIK K et al: Application of neural networks in medicine-a review. Med Sci Monit 1988spa
dc.relation.referencesPATTICHIS CS; SCHIZAS CN and MIDDLETON L. Neural Networks models in EMG diagnosis. IEEE transactions on biomedical Engineering, 1995.spa
dc.relation.referencesGenetics-Based Machine Learning for the assessment of certain neuro-muscular disorders. IEE Transactions on Neural Networks. Vol 7(2), 1996.spa
dc.relation.referencesGenetics-Based Machine Learning for the assessment of certain neuro-muscular disorders. IEE Transactions on Neural Networks. Vol 7(2), 1996.spa
dc.relation.referencesPENNY, Hill and FROST, Davis. Neural Networks in Clinical Medicine.spa
dc.relation.referencesPEÑA-REYES C.A. and SIPPER M. Evolutionary computation in medicine: an overview. Artificial Intelligence in Medicine. Vol 19 (1), 2000spa
dc.relation.referencesA fuzzy-genetic approach to breast cancer diagnosis. Artif Intell Med.spa
dc.relation.referencesPESONEN, E.; ESKELINEN, M. and JUHOLA, M. Comparision of different neural networks algorithm in the diagnosis of acute apendicitis. Int. J Bio-Med. Comput. 40. 1996.spa
dc.relation.referencesPETAJAN J: AAEM Minimonograph # 3: Motor unit recruitment. Muscle Nerve. No 14. 1991.spa
dc.relation.referencesPFURTSCHELLER G; FLOTZINGER D and MATUSCHIK K: Sleep classification in infants based on artificial neural networks. Biomed Tech Berlin. 1992.spa
dc.relation.referencesPODGOLEREC, V. and KOKOL, P. Medical diagnosis using Genetic Programming. Proceedings of the 12th IEEE Symposium on Computer-based Medical Systems CBMS’99 Stamford, CN, June 1999.spa
dc.relation.referencesPREHCELT, Lutz. Early Stopping – but when?spa
dc.relation.referencesRAVDIN PM et al.: A demonstration that breast cancer recurrence can be predicted by neural network analysis. Breast Cancer Res Treat. 1992.spa
dc.relation.referencesSCHIZAS C et al: Unsupervised learning in computer aided macro Electromyography. In Computer-based Medical Systems, IEEE Computer Society Press, Los Alamitos, CA, USA. 1991.spa
dc.relation.referencesNeural Networks is Computer Aided Clinical Electromyography, Proceedings of the 13th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Ed. By J.H. Nagel and W.M. Smith, 13. 1991. p. 1458-1459spa
dc.relation.referencesSILVERSTEIN B et al. Claims incidence of work-related disorders of the upper extremities: Washington State, 1987 through 1995. Am J Public Health 1998. p 1827-33.spa
dc.relation.referencesSTEWART JD. Focal Peripheral neuropathies, 3 ed. New York, Lippincott Williams & Wilkins. 1999.spa
dc.relation.referencesSTOTZKA R. et al. A hybrid neural and statistical classifier system for histopathologic grading of prostatic lesions. Anal Quant Cytol Histol, 1995.spa
dc.relation.referencesSWINGLER, K. Applying neural networks. Academic Press. London. 1996.spa
dc.relation.referencesSZOLOVITS P. Artificial Intelligence in Medicine. Westview Press, Boluder, CO, 1982.spa
dc.relation.referencesTONG, K and GRANAT MH. Artificial Neural Network control on functional electrical stimulation assisted gait for persons with spinal cord injury. In Lisboa PJG…(eds): Artificial Neural networks in Biomedicine. Springer, London. 2001.spa
dc.relation.referencesTOURASSI GD et al. Artificial neural network for diagnosis of acute pulmonary embolism: effect of case and observer selection. Radiology, 1995.spa
dc.relation.referencesWANG RJ and JABRI MA. Artificial neural network-based channel selection and loudness mapping. Ann Otol Rhinol Laryngol Suppl, 1995spa
dc.relation.referencesWILBOURN AJ: AAEM Case Report # 12: Common Peroneal Mononeuropathy at the Fibular Head. Muscle Nerve. 1986.spa
dc.relation.referencesWINSTON, P. W. Artificial Intelligence. Addison-Wesley, Reading, Mass. 1977.spa
dc.relation.referencesWU C et al: Protein classification artificial neural system. Protein Sci, 1992.spa
dc.relation.referencesYAGER RR and ZADEH LA. Fuzzy Sets, Neural Networks, and Soft Computing. New York: Van Nostrand Reinhold, 1994spa
dc.relation.referencesZAKARIA D. et al. Work-related cumulative trauma disorders of the upper extremity: Navigating the epidemiologic literature. Am J Ind Med. 2002.spa
dc.relation.referencesZAZULA D; KOROSEC D and SOSTARIC A. Computer-Assisted Decomposition of the Electromyograms . Proceedings of the 11th IEEE Symposium on Computer-based Medical Systems CBMS’98 Lubbock, TX. 1998.spa
dc.relation.referencesZIGMOND MJ; BLOOM FE and LANDIS SC, eds: Fundamental Neuroscience. San Diego, Academic Press. 1998spa
dc.relation.referencesZORMAN M et al. Decisión Tree´s Induction Strategies on a Hard Real World Problem. Proceedings of the 13rd IEEE Symposium on Computer-based Medical Systems CBMS’00, Houston TX. 2000.spa
dc.contributor.cvlachttps://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0000196606*
dc.subject.lembRedes neuronales artificiales (Computadores)spa
dc.subject.lembNeuropatíaspa
dc.subject.lembIngeniería de sistemasspa
dc.subject.lembCiencias computacionalesspa
dc.subject.lembEnfermedadesspa
dc.subject.lembDiagnósticospa
dc.subject.lembProcesamiento de datosspa
dc.subject.lembInvestigacionesspa
dc.subject.lembAnálisisspa
dc.contributor.corporatenameInstituto Tecnológico y de Estudios Superiores de Monterrey (ITESM)spa
dc.description.abstractenglishIntroduction: Interpreting electrophysiological studies is essentially a classification task. Artificial neural networks (ANNs) are suitable tools for classification because they are based on pattern recognition techniques. Objectives: To develop a computer system for automated detection of focal neuropathies using ANNs. Methods: The study was based on 300 sets of nerve conduction studies (NCSs) from three different electrodiagnostic medicine laboratories. Each input data set was formed by 11 parameters, including motor and sensory latencies, amplitudes, durations, and velocities of a single nerve. The input sets were classified into 4 focal neuropathy subgroups (distal demyelination, proximal demyelination, generalized demyelination, axon loss) depending on the type of nerve damage plus 1 additional for normal findings. The data were presented to a backpropagation ANN with 1 hidden layer. The network structure was modified to achieve the lowest possible mean square error. The outputs from these first-level networks were presented to a second-level network in order to detect generalized neuropathies. After training the ANNs, the classification accuracy was tested using another data set that was unknown to the networks. Results: A classification accuracy of 99% was reached for the detection of pathologic patterns. The accuracy for focal neuropathies classification was 95.2%.Conclusions: Neural networks classify focal neuropathy subgroups with high accuracy (>95%). This method may lead to automated focal neuropathy detection.eng
dc.subject.proposalNeuropatía focal
dc.subject.proposalDetección automatizada
dc.type.redcolhttp://purl.org/redcol/resource_type/TM
dc.rights.creativecommonsAtribución-NoComercial-SinDerivadas 2.5 Colombia*
dc.coverage.campusUNAB Campus Bucaramangaspa
dc.description.learningmodalityModalidad Presencialspa


Ficheros en el ítem

Thumbnail

Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem

Atribución-NoComercial-SinDerivadas 2.5 Colombia
Excepto si se señala otra cosa, la licencia del ítem se describe como Atribución-NoComercial-SinDerivadas 2.5 Colombia