Razonador basado en casos para la inferencia de hipótesis diagnósticas, basado en la teoría de los conjuntos aproximados
Archivos
Fecha
2018-03-19
Autores
Nodarse Morales, Katterine
Título de la revista
ISSN de la revista
Título del volumen
Editor
Resumen
La Historia Clínica Electrónica (HCE) constituye el documento esencial de los sistemas de informa-ción hospitalarios (SIH). La proliferación de la HCE como consecuencia del incremento de los SIH en las instituciones hospitalarias representa enormes ventajas, debido a la riqueza de información y experiencias que en ella se recogen. Garantizar su uso productivo demanda de nuevos métodos capaces de procesar la información y extraer conocimiento en un tiempo razonable, que permita guiar a los especialistas en el proceso de admisión de nuevos pacientes. En este trabajo se presenta una propuesta novedosa que contribuye al diagnóstico clínico basado en el análisis de información textual y estructurada. La combinación del agrupamiento como base para la organización de la base de casos y la propuesta Rough Text, para enfrentar diversas tareas de la minería de textos basada en la Teoría de Conjuntos Aproximados (RST), favorece la inferencia de hipótesis diagnósticas a la llegada un nuevo paciente. El sistema CDARS implementado contribuye a asistir el proceso de toma de decisiones en la práctica del método clínico.
The Electronical Medical Record (EMC) is an essential document of the hospital information sys-tems (HIS). The proliferation of the EMC as a result of the HIS increasing in hospitals has numerous advantages because of the abundance of information and experiences we can find in them. New methods able to process information and extract knowledge at a reasonable time are needed to help specialists in the admission process of new patients. In this paper, a new proposal that contributes to the clinical diagnosis based on the analysis of textual and structured information is presented. The combination of clustering as the foundation for the case base organization, and the proposal Rough Text to deal with several tasks of text mining based on Rough Sets Theory (RST), contributes to infer diagnosis hypothesis when a new patient arrives. The system CDARS, a result of the model implementation, contributes to assist the decision making process while practicing the clinical method.
The Electronical Medical Record (EMC) is an essential document of the hospital information sys-tems (HIS). The proliferation of the EMC as a result of the HIS increasing in hospitals has numerous advantages because of the abundance of information and experiences we can find in them. New methods able to process information and extract knowledge at a reasonable time are needed to help specialists in the admission process of new patients. In this paper, a new proposal that contributes to the clinical diagnosis based on the analysis of textual and structured information is presented. The combination of clustering as the foundation for the case base organization, and the proposal Rough Text to deal with several tasks of text mining based on Rough Sets Theory (RST), contributes to infer diagnosis hypothesis when a new patient arrives. The system CDARS, a result of the model implementation, contributes to assist the decision making process while practicing the clinical method.
Descripción
Palabras clave
Razonamiento Basado en Casos, Agrupamiento, Toma de Decisiones, Historia Clínica Electrónica (HCE), Teoría de Conjuntos Aproximados, Case Based Reasoning, Clustering, Decision Making, Electronical Medical Record (EMC), Rough Sets Theory
Citación
Citar según la fuente original:
1. Visval, A. and M. Sara, La gestión docu-mental, de información y el conocimiento en la empresa. El caso de Cuba. Acimed, 2009. 19(5). 2. Fiks, A.G., et al., Electronic medical rec-ord use in pediatric primary care. Journal of the American Medical Informatics As-sociation, 2010. 18(1): p. 38-44. 3. Fernández-Alemán, J.L., et al., Analysis of health professional security behaviors in a real clinical setting: An empirical study. International journal of medical informa-tics, 2015. 84(6): p. 454-467. 4. Martınez, I.G. and R.E.B. Pérez, Making decision in case-based systems using prob-abilities and rough sets. Knowledge-Based Systems, 2003. 16(4): p. 205-213. 5. Lorenzo, M.M.G. and R.E.B. Pérez, A model and its different applications to case-based reasoning. Knowledge-based systems, 1996. 9(7): p. 465-473. 6. Fuentes, I., Valdés, B., García, M., Arco, L., Herrera, M., Fuentes, R. (2017). A Case-Based Reasoning Framework for Clinical Decision Making. 16th Mexican International Conference on Artificial In-telligence MICAI 2017. Vol. 10062. 2017: Springer. 7. Pawlak, Z., Rough sets. International Jour-nal of Computer & Information Sciences, 1982. 11(5): p. 341-356. 8. Arco, L., et al., Rough Text Assisting Text Mining: Focus on Document Clustering Validity. Granular Computing: At the Junction of Rough Sets and Fuzzy Sets, 2008: p. 229-248. 9. Dolin, R.H., et al., HL7 clinical document architecture, release 2. Journal of the Ame-rican Medical Informatics Association, 2006. 13(1): p. 30-39. 10. García Lorenzo, M.M., Monografía de re-conocimiento de patrones. 1999. 8(1). 11. Pawlak, Z., Rough sets. International Jour-nal of Parallel Programming, 1982. 11(5): p. 341-356. 12. Cruañes Vilas, J., M.T. Romá Ferri, and E. Lloret, Análisis del uso de métodos de si-militud léxica con conocimiento semántico superficial para mapear la información de enfermería en español. 2012. 13. Magdaleno, D., et al., Comparative Study of Clustering Algorithms using Over-allSimSUX Similarity Function for XML Documents. Inteligencia Artificial. Revista Iberoamericana de Inteligencia Artificial, 2015. 18(55). 14. Fuentes, I. E., Magdaleno, D., & García, M. M. (2015a). Methodology for discov-ery of implicit knowledge in Medical Rec-ords. Paper presented at the Fifth interna-tional workshop on Knowledge Discovery, Knowledge Management and Decision Support, EUREKA 2015, Universidad Autónoma Metropolitana.Ciudad México. Fuentes 15. Fuentes, I., Valdés, B., García, M., Arco, L., Herrera, M., Fuentes, R. (2017). Clini-cal Diagnostic based-on Textual and Struc-tured Information Analysis. Published in: Memorias del evento International Confer-ence of Processing Information CIPI 2017, ISBN: 978-959-312-258-0. 16. Salton, G., A. Wong, and C.-S. Yang, A vector space model for automatic indexing. Communications of the ACM, 1975. 18(11): p. 613-620. 17. Guevara, D.M., Y. Miranda, and I. Fuentes, Comparative Study of Clustering Algorithms using OverallSimSUX Simi-larity Function for XML Documents. Inte-ligencia Artificial, 2015. 19(57): p. 69-80. 18. Jurgens, D. and K. Stevens. The S-Space package: an open source package for word space models. in Proceedings of the ACL 2010 System Demonstrations. 2010. Asso-ciation for Computational Linguistics. 19. Magdaleno, D., Refinamiento, evaluación y etiquetamiento de grupos textuales basa- dos en la teoría de los conjuntos aproxima-dos, in Ciencias de la Computación. 2008, Universidad Central "Marta Abreu" de Las Villas: Santa Clara, Villa Clara. 20. Cawley, G.C. Leave-one-out cross-valida-tion based model selection criteria for weighted LS-SVMs. in Neural Networks, 2006. IJCNN'06. International Joint Con-ference on. 2006. IEEE. 21. Wess, S., K.-D. Althoff, and G. Derwand. Using kd trees to improve the retrieval step in case-based reasoning. in European Workshop on Case-Based Reasoning. 1993. Springer.
Institución propietaria: Universidad Central "Marta Abreu" de Las Villas