Agrupamiento de K-medias para estimación de insulino-resistencia en adultos mayores de Cuenca
Abstract
ABSTRACT
Insulin resistance (IR) is a prediabetic condition that requires early diagnosis. However, there is no consensus regarding the estimation method according to the population studied. In this paper, we analyze five methods of IR estimation using a K-means clustering algorithm on a population of 119 older adults from Cuenca who underwent an Oral Test of Tolerance to the Glucose (OTTG) of two points. The K-means clustering algorithm, with K = 2, was applied in one-dimensional experiments for the Homa-IR, Quicki, Avignon, Matsuda and a multidimensional experiment using the four observations of the OGTT (fasting and postprandial values of glucose and insulin). The population was divided into two clusters: C-N, with normal values and C-RI with IR. Clinical cutoff points for Homa-IR and Quicki were validated. The number of individuals classified in each C-IR was very different according to each method. Methods using fasting and postprandial values (Avignon and Matsuda) identify a larger population with IR and this group corresponds to the Elderly with a high abdominal circumference. The multidimensional method seems to provide less information than one-dimensional methods that include postprandial values. The variety of clusters obtained according to the IR estimation method indicate that it is necessary to carefully analyze these results from the clinical point of view to establish strategies for early diagnosis of IR in the Elderly population of Cuenca.
Keywords: K-means, unsupervided learning, insulin resistance, elderly, Homa-IR, Quicki.
RESUMEN
La Resistencia a la Insulina (RI) es una condición prediabética que requiere ser diagnosticada de forma temprana. Sin embargo, no existe consenso en cuanto al método de estimación según la población estudiada. En este trabajo se analizan cinco métodos de estimación de RI usando una clasificación de K-medias sobre una población de 119 Adultos Mayores de la ciudad de Cuenca quienes se sometieron a una Prueba Oral de Tolerancia a la Glucosa (POTG) de dos puntos. El algoritmo de K-medias, con K=2, fue aplicado en experimentos unidimensionales para los métodos Homa-IR, Quicki, Avignon, Matsuda y se realizó un experimento multidimensional usando las cuatro observaciones de la POTG (valores de glucosa e insulina basal y postprandial). La población se dividió en dos clústeres: C-N, con valores normales y C-RI con RI. Se validaron los puntos de corte clínicos para Homa-IR y Quicki. La cantidad de individuos clasificados en cada C-RI fue muy diferente según cada método. Los métodos que usan valores basales y postprandiales (Avignon y Matsuda) identificaron una mayor cantidad de población con RI y este grupo correspondió a los Adultos Mayores con una circunferencia abdominal elevada. El método multidimensional parece aportar menos información que los métodos unidimensionales que incluyen valores postprandiales. La pluralidad de los clústeres obtenidos según el método de estimación de RI, revelan que es necesario analizar detenidamente estos resultados desde el punto de vista clínico para establecer estrategias de diagnóstico precoz de RI en la población de Adultos Mayores cuencana.
Palabras clave: K-medias, aprendizaje no supervisado, resistencia a la insulina, adulto mayor, Homa-IR, Quicki.
Downloads
Metrics
References
Andreopoulos, B., An, A., Wang, X., & Schroeder, M. (2009). A roadmap of clustering algorithms: finding a match for a biomedical application. Briefings in Bioinformatics, 10(3), 297-314. https://doi.org/10.1093/bib/bbn058
Brown, R. J., & Yanovski, J. A. (2014). Estimation of insulin sensitivity in children: methods, measures and controversies. Pediatric Diabetes, 15(3), 151-161. https://doi.org/10.1111/pedi.12146
Friedrich, N., Thuesen, B., Jørgensen, T., Juul, A., Spielhagen, C., Wallaschofksi, H., & Linneberg, A. (2012). The association between IGF-I and insulin resistance. Diabetes Care, 35(4), 768-773. https://doi.org/10.2337/dc11-1833
Kahn, C. R. (1978). Insulin resistance, insulin insensitivity, and insulin unresponsiveness: A necessary distinction. Metabolism, 27(12), 1893-1902. https://doi.org/10.1016/S0026-0495(78)80007-9
Kahn, C. R. (2003). Knockout mice challenge our concepts of glucose homeostasis and pathogenesis of diabetes. Experimental Diabetes Research, 4(3), 169-182.
Kawada, T., Andou, T., & Fukumitsu, M. (2016). Waist circumference, visceral abdominal fat thickness and three components of metabolic syndrome. Diabetes & Metabolic Syndrome: Clinical Research & Reviews, 10(1), 4-6. https://doi.org/10.1016/j.dsx.2015.08.013
Morales, E., & Fornieri, M. (2007). Consideraciones clínicas sobre la importancia de la sensibilidad a la insulina, su resistencia y la intolerancia a la glucosa. Revistaalad.com. Retrieved from http://www.revistaalad.com/pdfs/0702revinsl.pdf
Motamed, N., Miresmail, S. J. H., Rabiee, B., Keyvani, H., Farahani, B., Maadi, M., & Zamani, F. (2016). Optimal cutoff points for HOMA-IR and QUICKI in the diagnosis of metabolic syndrome and non-alcoholic fatty liver disease: A population based study. Journal of Diabetes and Its Complications, 30(2), 269-274. https://doi.org/10.1016/j.jdiacomp.2015.11.019
Parra, F., Andrade, D., Cruz, J., Solano-Quinde, L., Palacio-Baus, K., Encalada, L., & Wong, S. (2015). Plataforma basada en ecgML para el estudio de las complicaciones cardiovasculares en el adulto mayor con síndrome metabólico. Maskana, 6(Supl.), 157-164. Retrieved from https://www.ucuenca.edu.ec/ojs/index.php/maskana/article/view/709
Severeyn, E., Wong, S., Passariello, G., Cevallos, J. L., & Almeida, D. (2012). Methodology for the study of metabolic syndrome by heart rate variability and insulin sensitivity. Revista Brasileira de Engenharia Biomédica, 28(3), 272-277. https://doi.org/10.4322/rbeb.2012.026
Velásquez, J., Severeyn, E., Herrera, H., Encalada, L., & Wong, S. (2017). Anthropometric index for insulin sensitivity assessment in older adults from Ecuadorian highlands. In E. Romero, N. Lepore, J. Brieva, & I. Larrabide (Eds.) (p. 101600S). International Society for Optics and Photonics. https://doi.org/10.1117/12.2257207
Vintimilla, C., Wong, S., Astudillo-Salinas, F., Encalada, L., & Severeyn, E. (2017). An aide diagnosis system based on k-means for insulin resistance assesment in eldery people from the Ecuadorian highlands. Enviado a http://sites.ieee.org/etcm-2017/
Downloads
Published
How to Cite
Issue
Section
License
Copyright © Autors. Creative Commons Attribution 4.0 License. for any article submitted from 6 June 2017 onwards. For manuscripts submitted before, the CC BY 3.0 License was used.
You are free to:
 |
Share — copy and redistribute the material in any medium or format |
 |
Adapt — remix, transform, and build upon the material for any purpose, even commercially. |
Under the following conditions:
 |
Attribution — You must give appropriate credit, provide a link to the licence, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licenser endorses you or your use. |
| No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the licence permits. |
