<link rel="stylesheet" href="styles.f3b1fba60ec7970c.css">

Exploración metodológica multivariada aplicada a seis registros poblacionales de cáncer en Colombia

dc.contributor.advisorPlazas Nossa, Leonardo
dc.contributor.authorGonzález Salguero, Jhonatan
dc.contributor.orcidPlazas Nossa, Leonardo [0000-0002-2223-9886]
dc.creator.emailicg.gonzalez@outlook.com
dc.creator.id20241695009
dc.date.accessioned2026-11-20T16:40:03Z
dc.date.created2026-10-05
dc.descriptionEsta investigación desarrolla y valida un marco metodológico multivariado para la caracterización de patrones y la estratificación del riesgo de cáncer en Colombia, utilizando datos de seis Registros Poblacionales de Cáncer (RPC) entre 2003 y 2019. El estudio aborda la complejidad y la incertidumbre de la información oncológica nacional mediante la convergencia de cuatro enfoques analíticos: aprendizaje no supervisado, análisis de supervivencia, series de tiempo e inteligencia computacional. A través del algoritmo K-Means, se identificaron clústeres poblacionales consistentes por rangos de edad y sexo, destacando la predominancia de patologías de alta incidencia. En el análisis de supervivencia, los modelos CART y RFSRC permitieron jerarquizar la importancia de las variables clínicas, alcanzando índices de concordancia de hasta 0,89 en regiones con alta densidad de datos. El análisis mediante regresión Joinpoint detectó puntos de quiebre estructurales en la captación de los registros, mientras que un sistema de inferencia difusa tipo Mamdani (configuración C3) logró una capacidad discriminativa de AUC 0,71 para el riesgo de mortalidad a tres años. Los resultados demuestran que la integración de estas técnicas permite una comprensión integral del fenómeno oncológico, superando las limitaciones de los análisis aislados. El marco propuesto se consolida como una herramienta reproducible y explicable que fortalece la gobernanza del dato y la vigilancia epidemiológica en salud pública, especialmente en escenarios con información clínica limitada.spa
dc.description.abstractThis research develops and validates a multivariate methodological framework for pattern characterization and cancer risk stratification in Colombia, utilizing data from six Population Cancer Registries (RPC) between 2003 and 2019. The study addresses the complexity and uncertainty of national oncological information through the convergence of four analytical approaches: unsupervised learning, survival analysis, time series, and computational intelligence. Through the K-Means algorithm, consistent population clusters were identified by age and sex ranges, highlighting the predominance of high-incidence pathologies. In the survival analysis, CART and RFSRC models enabled the ranking of clinical variable importance, reaching concordance indices (C-Index) of up to 0.89 in regions with high data density. Joinpoint regression analysis detected structural break points in registry reporting, while a Mamdani-type fuzzy inference system (C3 configuration) achieved a discriminative capacity of AUC 0.71 for three-year mortality risk. The results demonstrate that the integration of these techniques allows for a comprehensive understanding of the oncological phenomenon, overcoming the limitations of isolated analyses. The proposed framework is established as a reproducible and explainable tool that strengthens data governance and epidemiological surveillance in public health, especially in scenarios with limited clinical information.eng
dc.format.mimetypepdf
dc.identifier.urihttp://hdl.handle.net/11349/104501
dc.language.isospa
dc.publisherUniversidad Distrital Francisco José de Caldas
dc.relation.referencesAmin, R., Hendryx, M., Shull, M., & Bohnert, A. (2014). A Cluster Analysis of Pediatric Cancer Incidence Rates in Florida: 2000–2010. Statistics and Public Policy, 1(1), 69-77
dc.relation.referencesBanco Mundial. (2024). Esperanza de vida al nacer, total (años) – Colombia. World Bank Data: https://datos.bancomundial.org/indicador/SP.DYN.LE00.IN?locations=CO
dc.relation.referencesBasavegowda, M., Kenkere Marulaiah, S., Vidyalakshmi, R., Marimuthu Prashanthi, D., Nagaralu Channabasappa, A., & Somanathan, B. (Abril de 2016). Spatio-Temporal Pattern of Breast Cancer - Case Study of Southern Karnataka, India. Journal of Clinical and Diagnostic Research, 10(4), LC20–LC24. https://doi.org/https://doi.org/10.7860/JCDR/2016/19042.7666
dc.relation.referencesBou-Hamad, I., Larocque, D., & Ben-Ameur, H. (2011). Tree-based methods for survival analysis and high-dimensional data. Statistics Surveys, 5, 44–71. https://doi.org/https://doi.org/10.1214/10-SS094
dc.relation.referencesBouzon Nagem Assad, D., Gomes Ferreira da Costa, P., Spiegel, T., Cara, J., Ortega-Mier, M., & Monteiro Scaff, A. (2024). Comparing the current short-term cancer incidence prediction models in Brazil with state-of-the-art time-series models. Scientific Reports, 14, 4566. https://doi.org/10.1038/s41598-024-55230-2
dc.relation.referencesBray, F., Ferlay, J., Soerjomataram, I., Siegel, R. L., Torre, L. A., & Jemal, A. (2018). Global Cancer Statistics 2018: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries. CA: A Cancer Journal for Clinicians, 68, 394-424.
dc.relation.referencesBreiman, L., Friedman, J. H., & Olshen, C. J. (1984). Classification and Regression Trees. California: Chapman & Hall / Wadsworth.
dc.relation.referencesBrockwell, P. J., & Davis, R. A. (2016). Introduction to Time Series and Forecasting (3 ed.). Springer. https://doi.org/10.1007/978-3-319-29854-2
dc.relation.referencesBruce, P., Bruce, A., & Gedeck, P. (2020). Practical Statistics for Data Scientists (Segunda ed.). Sebastopol, CA: O’Reilly Media, Inc.
dc.relation.referencesCheng, S.-F., Chen, J.-H., & Lee, T.-C. (2018). Evaluation of classification and regression tree (CART) model in weight loss prediction following head and neck cancer radiation therapy. PLOS ONE, 13(2), e0191856. https://doi.org/https://doi.org/10.1371/journal.pone.0191856
dc.relation.referencesCleveland, W. S., Grosse, E., & Shyu, W. M. (1992). Local regression models. En J. M. Chambers, & T. Hastie, Statistical Models in S. Wadsworth & Brooks/Cole.
dc.relation.referencesCox, D. (1972). Regression models and life-tables. Journal of the Royal Statistical Society: Series B (Methodological), 34(2), 187–220.
dc.relation.referencesDepartamento Administrativo Nacional de Estadística – DANE. (2025). Los hitos: Personas mayores de 100 años en Colombia. DANE: https://dane70.dane.gov.co/los-hitos/censos/personas-mayores-de-100-anos-en-colombia
dc.relation.referencesDíaz García, M. E., González Rodríguez, G., & Rico Martínez, R. (2014). Selecting variables for K-means cluster analysis by using a genetic algorithm that optimises the silhouettes. Analytica Chimica Acta, 130, 87-100. https://doi.org/10.1016/j.aca.2003.12.020
dc.relation.referencesFlorensa, D., Mateo-Fornés, J., Solsona, F., Pedrol Aige, T., Mesas Julió, M., Piñol, R., & Godoy, P. (19 de Julio de 2022). Use of Multiple Correspondence Analysis and K-means to Explore Associations Between Risk Factors and Likelihood of Colorectal Cancer: Cross-sectional Study. Journal of Medical Internet Research, 24(7), e29056. https://doi.org/https://doi.org/10.2196/29056
dc.relation.referencesGhiasi, M., & Zendehboudi, S. (2020). Application of decision tree-based ensemble learning in the classification of breast cancer. Health Informatics Journal, 26(4), 2536–2552. https://doi.org/https://doi.org/10.1177/1460458220902929
dc.relation.referencesGhizzardi, G., Maiandi, S., Vasaturo, D., Collemi, C., Laurano, A., Magon, A., . . . Caruso, R. (Febrero de 2025). Patient clusters based on demographics, clinical characteristics and cancer-related symptoms: A cross-sectional pilot study. European Journal of Oncology Nursing, 74, 102796. https://doi.org/https://doi.org/10.1016/j.ejon.2025.102796
dc.relation.referencesGoldberg, D. E. (1989). Genetic Algorithms in Search, Optimization, and Machine Learning. Reading: Addison-Wesley.
dc.relation.referencesHarrell, F. E., Lee, K. L., & Mark, D. B. (1996). Multivariable prognostic models: Issues in developing models, evaluating assumptions and adequacy, and measuring and reducing errors. Statistics in Medicine, 15(4), 361-387. https://doi.org/10.1002/(SICI)1097-0258(19960229)15:4<361::AID-SIM168>3.0.CO;2-4
dc.relation.referencesHolland, J. H. (1975). Adaptation in Natural and Artificial Systems. University of Michigan Press.
dc.relation.referencesHyndman, R. J., & Athanasopoulos, G. (2018). Forecasting: Principles and Practice. OTexts.
dc.relation.referencesİncekırık, A., İşçi Güneri, Ö., & Durmuş, B. (Junio de 2021). Classification of Cancer Types by Cluster Analysis Methods. Alphanumeric Journal, 9(1), 125–142. https://doi.org/http://dx.doi.org/10.17093/alphanumeric.949958
dc.relation.referencesInstituto Nacional de Cancerología. (s.f.). Retrieved 13 de Noviembre de 2023, from Información de cáncer en Colombia: https://www.infocancer.co/portal/#!/FAQ/
dc.relation.referencesInstituto Nacional de Cancerología. (2017). Guía metodológica para el análisis de la situación del cáncer en Colombia. Bogotá: Instituto Nacional de Cancerología.
dc.relation.referencesIshwaran, H., Kogalur, U., Blackstone, E., & Lauer, M. (2008). Random survival forests. Annals of Applied Statistics, 2(3), 841–860. https://doi.org/https://doi.org/10.1214/08-AOAS169
dc.relation.referencesItriago G., L., Silva L., N., & Cortés E., G. (2013). Cancer en Chile y el mundo: Una mirada epidemiologica, presente y futuro. Revista Médica Clínica Las Condes, 24(4): 531-552.
dc.relation.referencesJain, A. K. (2010). Data clustering: 50 years beyond K-means. Pattern Recognition Letters, 31(8), 651–666. https://doi.org/10.1016/j.patrec.2009.09.011
dc.relation.referencesJaiswal, V., Saurabh, P., Lilhore, U. K., Pathakd, M., Simaiya, S., & Dalale, S. (2023). A breast cancer risk predication and classification model with ensemble learning and big data fusion. Decision Analytics Journal.
dc.relation.referencesKaplan, E., & Meier, P. (1958). Nonparametric estimation from incomplete observations. Journal of the American Statistical Association, 53(282), 457–481. https://doi.org/https://doi.org/10.1080/01621459.1958.10501452
dc.relation.referencesKassambara, A. (2017). Practical Guide to Cluster Analysis in R: Unsupervised Machine Learning (1 ed.). STHDA.
dc.relation.referencesKaufman, L., & Rousseeuw, P. (1990). Finding groups in data: An introduction to cluster analysis. John Wiley & Sons. https://doi.org/https://doi.org/10.1002/9780470316801
dc.relation.referencesKaviani, E., & Passi, K. (2025). Forecasting Cancer Incidence in Canada by Age, Sex, and Region Until 2026 Using Machine Learning Techniques. Algorithms, 18. https://doi.org/10.3390/a18050265
dc.relation.referencesKhalis, M., Elbadisy, I., Bouaddi, O., Luo, A., Bendriouich, A., Addahri, B., . . . Huybrechts, I. (2024). Cluster analysis of cancer knowledge, attitudes and behaviors in the Moroccan population. BMC Cancer, 669. https://doi.org/https://doi.org/10.1186/s12885-024-12226-5
dc.relation.referencesKim, H. J., Chen, H.-C. S., Midthune, D., & Fay, M. P. (2023). Data-driven choice of a model selection method in joinpoint regression. Journal of Applied Statistics, 50(9-10), 1992–2013.
dc.relation.referencesKomorowski, M., Marshall, D. C., Salciccioli, J. D., & Crutain, Y. (2016). Secondary analysis of electronic health records. Springer. https://doi.org/https://doi.org/10.1007/978-3-319-43742-2_15
dc.relation.referencesLi, J., Chan, N. B., Xue, J., & Tsoi, K. K. (2022). Time series models show comparable projection performance with joinpoint regression: A comparison using historical cancer data from World Health Organization. Frontiers in Public Health, 10, 1003162. https://doi.org/10.3389/fpubh.2022.1003162
dc.relation.referencesLi, S., Yi, H., Leng, Q., Wu, Y., & Mao, Y. (2024). New perspectives on cancer clinical research in the era of big data and machine learning. Surgical Oncology.
dc.relation.referencesLiu, K., Iyer, H., Lu, Y., Laden, F., Song, M., & Roscoe, C. (2025). Neighborhood socioeconomic disparities in cancer incidence following a hypothetical intervention to increase residential greenspace cover in the UK Biobank cohort. Environmental Research, 266, 120387. https://doi.org/https://doi.org/10.1016/j.envres.2024.120387
dc.relation.referencesMacias Muro, A., Martinez Trinidad, T., Valdez Lazalde, J. R., Romero Sánchez, M. E., & Vaquera Huerta, H. (2022). Evaluación de la salud del arbolado urbano a través de imágenes satelitales en Guadalajara, México. Entreciencias: Diálogos en la Sociedad del Conocimiento(24).
dc.relation.referencesMamdani, E. H. (1975). An experiment in linguistic synthesis with a fuzzy logic controller. International Journal of Man-Machine Studies, 7(1), 1–13.
dc.relation.referencesMartínez Toro, G. M., Rico Bautista, D., & Romero Riaño, E. (2019). Análisis comparativo de predicción dentro de bases de datos de cáncer: una aplicación de aprendizaje automático. Revista Iberica de Sistemas e Tecnologias de Informacao, 113-122.
dc.relation.referencesMeyers, A. L., Dowty, J. G., Mahmood, K., Macrae, F. A., Rosty, C., Buchanan, D. D., & Jenkins, M. A. (2024). Age-specific trends in colorectal, appendiceal, and anal tumour incidence by histological subtype in Australia from 1990 to 2020: a population-based time-series analysis. The Lancet Regional Health – Western Pacific, 64. https://doi.org/10.1016/j.lanwpc.2025.101728
dc.relation.referencesMinisterio de Salud y Protección Social - Instituto Nacional de Cancerología, E. (2012). Plan Decenal para el Control del Cáncer en Colombia, 2012 – 2021. Bogotá, D.C.
dc.relation.referencesMinisterio de Salud y Protección Social. (2018). Guía metodológica del Observatorio Nacional de Cáncer. Bogotá, Colombia: Ministerio de Salud y Protección Social.
dc.relation.referencesMinisterio de Salud y Protección Social. (s.f.). Ciclo de vida. Retrieved 17 de Enero de 2026, from Ministerio de Salud y Protección Social: https://www.minsalud.gov.co/proteccionsocial/paginas/ciclovida.aspx
dc.relation.referencesNavarro, E., Caballero, H., Cortés, A., Arias, N., Casas, H., de Vries, E., . . . Pardo, C. (2024). Sistema de información de cáncer en Colombia - SICC (Versión 1.0). Retrieved 4 de Marzo de 2024, from https://www.infocancer.co
dc.relation.referencesNilashi, M., Ibrahim, O., Ahmadi, H., & Shahmoradi, L. (2017). A knowledge-based system for breast cancer classification using fuzzy logic method. Telematics and Informatics, 133-144.
dc.relation.referencesOrganización Mundial de la Salud. (2013). Clasificación Internacional de Enfermedades para Oncología (CIE-O) (3ª ed., 1ª revisión ed.). Madrid, España: Ministerio de Sanidad, Servicios Sociales e Igualdad.
dc.relation.referencesPapachristou, N., Kotronoulas, G., Dikaios, N., Allison, S. J., Eleftherochorinou, H., Rai, T., . . . Bamidis, P. D. (2023). Digital Transformation of Cancer Care in the Era of Big Data, Artificial Intelligence, and Data-Driven Interventions: Navigating the Field. Seminars in Oncology Nursing, 39.
dc.relation.referencesPardo, C., De Vries, E., Buitrago, L., & Gamboa, O. (2017). Atlas de mortalidad por cáncer en Colombia (Cuarta ed., Vol. 1). Bogotá, D.C.: Instituto Nacional de Cancerología.
dc.relation.referencesPencina, M. J., & D’Agostino, R. B. (2004). Overall C as a measure of discrimination in survival analysis: Model-specific population value and confidence interval estimation. Statistics in Medicine, 23(13), 2109–2123. https://doi.org/10.1002/sim.1802
dc.relation.referencesPeralta Hernández, A. E. (2025). Pronóstico de la esperanza de vida para la población de Colombia utilizando machine learning. Universidad Distrital Francisco José de Caldas. http://hdl.handle.net/11349/95509
dc.relation.referencesRawat, M., Pathak, P., & Vats, P. (2024). An approach to diagnosis of prostate cancer using fuzzy logic. International Journal of Reconfigurable and Embedded Systems, 13(1), 192-200. https://doi.org/10.11591/ijres.v13.i1.pp192-200
dc.relation.referencesRivera Gómez, F. A. (2023). Clasificación de series de tiempo con datos funcionales y técnicas de Machine Learning: una aproximación para el Índice de Desarrollo Humano. Bogotá, D.C.: Universidad Santo Tomás.
dc.relation.referencesRodriguez Villamizar, L., Valbuena Garcia, A., Moreno Corzo, F., Jaimes Reyes, M., Brome Bohorquez, M., & García García, H. (2022). Cluster analysis of childhood cancer and its relationship with proximity to sources of industrial pollution in the Valle de Aburrá Metropolitan Area, 2000-2015. Revista Facultad Nacional de Salud Pública, 40(2), e346065. https://doi.org/https://doi.org/10.17533/udea.rfnsp.e346065
dc.relation.referencesRousseeuw, P. (1987). Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. Journal of Computational and Applied Mathematics, 20, 53-65. https://doi.org/https://doi.org/10.1016/0377-0427(87)90125-7
dc.relation.referencesSalcedo Sanz, S., Prado Cumplido, M., Pérez Cruz, F., & Bousoño Calzón, C. (2002). Feature Selection via Genetic Optimization. Artificial Neural Networks, 547-552.
dc.relation.referencesSavitha, S., & Umadevi, V. (2025). Fuzzy modelling approach for accurate and explainable breast cancer prediction. ICTACT Journal on Soft Computing, 15(1), 3763–3768. https://doi.org/10.21917/ijsc.2025.0521
dc.relation.referencesSimon, G. J., & Aliferis, C. (2024). Artificial Intelligence and Machine Learning in Health Care and Medical Sciences: Best Practices and Pitfalls. Cham: Springer.
dc.relation.referencesSoleimani, A., Bahrami, M., & Vali, M. (2025). Survival prediction from imbalanced colorectal cancer dataset using hybrid sampling methods and tree-based classifiers. Computers in Biology and Medicine, 109578. https://doi.org/https://doi.org/10.1016/j.compbiomed.2025.109578
dc.relation.referencesSteyerberg, E. W. (2008). Clinical prediction models: A practical approach to development, validation, and updatin. New York: Springer.
dc.relation.referencesTherneau, T., & Atkinson, E. (2019). An introduction to recursive partitioning using the rpart routines. Mayo Clinic. https://cran.r-project.org/web/packages/rpart/vignettes/longintro.pdf
dc.relation.referencesTibshirani, R., Walther, G., & Hastie, T. (2001). Estimating the number of clusters in a data set via the gap statistic. Journal of the Royal Statistical Society: Series B, 63(2), 411-423.
dc.relation.referencesTsai, C.-F. (2014). Combining cluster analysis with classifier ensembles to predict financial distress. Information Fusion, 16, 45-58.
dc.relation.referencesVargas Moranth, R., & Navarro Lechuga, E. (2018). Incidencia y mortalidad por cáncer en Barranquilla, Colombia. 2008-2012. Colombia Médica, 49, 55-62.
dc.relation.referencesVischioni, C., Bove, F., Mandreoli, F., Martoglia, R., Pisi, V., & Taccioli, C. (2022). Visual exploratory data analysis for copy number variation studies in biomedical research. Big Data Research.
dc.relation.referencesWitten, D., Hastie, T., Tibshirani, R., & James, G. (2021). An Introduction to Statistical Learning: with Applications in R. New York: Springer.
dc.relation.referencesYılmaz, A., & Ayan, K. (2013). Cancer risk analysis by fuzzy logic approach and performance status of the model. Turkish Journal of Electrical Engineering and Computer Sciences, 21(3), 897–912. https://doi.org/10.3906/elk-1108-22
dc.relation.referencesZadeh, L. A. (1965). Fuzzy sets. Information and Control, 8(3), 338–353.
dc.relation.referencesZamar, R., & Raymaekers, J. (Junio de 2020). Pooled variable scaling for cluster analysis. Bioinformatics, 36(12), 3849–3855. https://doi.org/10.1093/bioinformatics/btaa243
dc.rights.accesoAbierto (Texto Completo)
dc.rights.accessrightsOpenAccess
dc.subjectCáncer
dc.subjectRegistros poblacionales de cáncerspa
dc.subjectAprendizaje automáticospa
dc.subjectRegresión Joinpointspa
dc.subjectÁrboles de decisiónspa
dc.subjectLógica difusaspa
dc.subjectCancerspa
dc.subjectPopulation-based cancer registrieseng
dc.subjectMachine learningeng
dc.subjectJoinpoint regressioneng
dc.subjectDecision treeseng
dc.subjectFuzzy logiceng
dc.subject.lembMaestría en Ciencias de la Información y las Comunicaciones Metodología Profundización -- Tesis y disertaciones académicas
dc.subject.lembCáncer — Estadísticas — Colombia
dc.subject.lembRegistros de enfermedades — Análisis de datos
dc.subject.lembAnálisis multivariante — Aplicaciones médicas
dc.titleExploración metodológica multivariada aplicada a seis registros poblacionales de cáncer en Colombiaspa
dc.title.titleenglishMultivariate methodological exploration applied to six population-based cancer registries in Colombia
dc.typemasterThesis
dc.type.coarhttp://purl.org/coar/resource_type/c_bdcc
dc.type.degreeMonografíaspa
dc.type.driverinfo:eu-repo/semantics/masterThesis

Archivos

Bloque original

Mostrando 1 - 2 de 2
Cargando...
Miniatura
Nombre:
trabajodegrado.pdf
Tamaño:
6,48 MB
Formato:
Adobe Portable Document Format
Cargando...
Miniatura
Nombre:
Licencia de uso y publicacion.pdf
Tamaño:
305,68 KB
Formato:
Adobe Portable Document Format