Detección temprana de cáncer en población sintomática: desarrollo de un modelo multivariante y un modelo de aprendizaje de máquinas basados en bases de datos administrativas del sistema de salud colombiano y aplicados al cáncer gástrico

dc.contributor.advisorBuitrago Gutierrez, Giancarlospa
dc.contributor.advisorPatiño Guevara, Diego Alejandrospa
dc.contributor.authorMurillo Moreno, Raúl Hernandospa
dc.contributor.cvlacMurillo, Raúl Hernando [https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0000264474]spa
dc.contributor.orcidMurillo, Raúl [0000000171879946]spa
dc.contributor.researchgroupInvestigaciones Clínicas en Cáncerspa
dc.coverage.countryColombiaspa
dc.date.accessioned2025-01-15T16:34:03Z
dc.date.available2025-01-15T16:34:03Z
dc.date.issued2024-05
dc.descriptionilustraciones, diagramasspa
dc.description.abstractEn Colombia, el cáncer gástrico es la primera causa de muerte por cáncer. En el momento no existen estrategias de tamización con eficacia demostrada para esta enfermedad y mejorar la oportunidad diagnóstica en sintomáticos representaría menor esfuerzo para sistemas de salud y pacientes. Diversos modelos utilizan síntomas y factores de riesgo restringidos a variables con muy alto valor predictivo positivo. La inteligencia artificial posibilita la búsqueda de nuevas alternativas, pero los estudios en este campo se orientan a mejorar la interpretación de imágenes endoscópicas o a mejorar modelos epidemiológicos preexistentes. Adicionalmente, no se conocen trabajos desarrollados en Latinoamérica. Utilizando bases de datos del sistema de salud, este trabajo abordó la problemática descrita mediante el análisis de la asociación del diagnóstico de cáncer gástrico con diagnósticos y procedimientos registrados en todas las atenciones previas al diagnóstico de cáncer, sobre la idea de que el registro sistemático de todas las atenciones permite identificar el rastro que deja el paciente durante el desarrollo de la patología oncológica. Se realizó un estudio con dos componentes: modelo multivariado de predicción clínica (prospectivo) y modelos de predicción basados en aprendizaje de máquinas (retrospectivo). Se utilizó la base de datos para cálculo de la Unidad de Pago por Capitación en el régimen contributivo del sistema de salud y la información de defunciones del sistema de estadísticas vitales. Se seleccionaron periodos de análisis con base en la disponibilidad, suficiencia, comparabilidad y consistencia de los datos. Modelo multivariante: Se incluyeron pacientes de 40 a 90 años que usaron servicios en 2011. Se excluyeron pacientes con diagnóstico de cáncer o fallecidos ese año. Se utilizó regresión logística LASSO para seleccionar variables predictoras. Las anemias carenciales se definieron como variable de exposición, y el índice de comorbilidad de Charlson modificado como covariable. En total conformaron la cohorte 14.399 individuos con anemia (expuestos) y 44.961 sin anemia (no expuestos). Se analizó el riesgo de diagnóstico de cáncer gástrico mediante una función de incidencia acumulada. Posteriormente se utilizó un modelo de riesgos competitivos. Se observaron diferencias en edad, sexo y lugar de residencia entre expuestos y no expuestos. El riesgo relativo para el diagnóstico de cáncer gástrico fue 1,53 (IC95% 1,51-1,54), con fracción atribuible 47,1 y fracción atribuible poblacional 17,8. La mediana de tiempo al diagnóstico fue 28,2 y 36,7 meses para expuestos y no expuestos. La incidencia de cáncer gástrico a 60 meses con anemia fue 7,6 por 1.000 (IC95% 6,1-9,1) y sin anemia 2,4 por 1.000 (IC95% 1,9-2,8). En el modelo de riesgos competitivos la anemia mostró la mayor fuerza de asociación. Modelo de aprendizaje de máquinas: Se seleccionaron pacientes de 30 a 90 años con y sin diagnóstico de cáncer gástrico entre septiembre y diciembre de 2017. Se utilizaron dos periodos de análisis: próximo al desenlace (enero-agosto 2017) y dos años previos al desenlace (septiembre 2015-agosto 2017). En el último caso se dejó un periodo de lavado de seis meses para reducir el efecto de diagnósticos y procedimientos cercanos al desenlace. Se filtraron variables predictoras (CIE10 diagnósticos y CUPS procedimientos). Se incluyeron 1.426 y 1.462 variables para los análisis a uno y dos años, respectivamente. Se utilizaron tres modelos: regresión logística LASSO, bosques aleatorios y potenciación del gradiente. Se evaluó el desempeño mediante el área bajo la curva (AUROC), exactitud (accuracy), sensibilidad, especificidad, valor predictivo positivo (VPP) y valor predictivo negativo (VPN). Se calculó el número necesario a seguir (NNT) en función de la probabilidad de diagnóstico de cáncer. Se incluyeron 4.965.931 y 5.175.620 individuos para el seguimiento a uno y dos años, dentro de los cuales hubo 1.426 y 1.462 casos de cáncer gástrico, respectivamente. La mayoría fueron mujeres, la edad promedio 58 y 53 años en pacientes con y sin cáncer gástrico, el número de atenciones fue mayor en pacientes con cáncer gástrico. Los coeficientes para las variables predictivas fueron mayores en el análisis de un año. A su vez, los diagnósticos mostraron mayor capacidad predictiva en ambos periodos de análisis. El AUROC no mostró diferencias entre modelos en el análisis a dos años; sin embargo, al utilizar el mejor punto de corte de cada modelo, la sensibilidad para LASSO fue mayor que para bosques aleatorios y potenciación de gradiente (65,4%; 27,8% y 57,9%). La especificidad fue mayor en los bosques aleatorios. La mayor capacidad predictiva la tuvo la regresión logística LASSO en el año previo al diagnóstico. En todos los modelos, el desempeño se mejoró con el incremento del punto de corte (mayor probabilidad de predicción del desenlace), esencialmente por un incremento de la especificidad. Los VPP en todos los modelos fueron menores de 1% en razón a la baja prevalencia de la enfermedad. El AUROC no mostró diferencias entre el ejercicio de validación interno (entrenamiento) y la validación externa. Consistentemente, municipios ubicados en la zona de montaña estuvieron dentro de las variables con coeficientes más altos mientras que municipios de la Costa Atlántica estuvieron dentro de las variables con coeficientes más bajos. En el análisis a dos años, la proporción de individuos que requieren seguimiento para detectar al menos el 70% de los casos de cáncer gástrico es 16,1%; 16,5%; y 20,4% según LASSO, bosques aleatorios y potenciación del gradiente, respectivamente; esto equivale a un NNT de 1.170, 1.230, y 1.498. La regresión logística LASSO a un año muestra que se debe seguir el 10,6% de la población para detectar al menos el 70% de los casos de cáncer gástrico (NNT 790). Conclusiones: El presente estudio representa un abordaje innovador del aprendizaje de máquinas al utilizar información no sesgada de toda expresión sintomática de la enfermedad en su fase previa al diagnóstico. La regresión logística LASSO mostró mejor desempeño que los modelos restantes incluido el modelo multivariante. El desempeño observado puede mejorarse en población de mayor riesgo como los residentes en los municipios de alta montaña. Los resultados tienen potencial de uso en la práctica clínica dada su capacidad discriminativa y el NNT, pero su uso en la rutina de los servicios debe estar precedido de su correcta validación clínica (Texto tomado de la fuente).spa
dc.description.abstractStomach cancer is the leading cause of cancer death in Colombia. There is no evidence-based screening available for this condition and early diagnosis in symptomatic patients is a more suitable alternative for low- and middle-income countries given the lower burden for health systems and patients. Predictive models have been developed but restricted to variables with very high positive predictive value. Artificial intelligence makes possible the search for new alternatives for stomach cancer early detection; however, most studies on this topic focus on endoscopic images or improvement of pre-existing epidemiological models. In addition, we found no studies from Latin America. Using databases from the Colombian health system, this study analyzes the association of stomach cancer diagnosis with previous clinical diagnoses and procedures, based on the idea that the systematic recording of all clinical conditions allows us to identify the patient’s footprint during the carcinogenic process. A study with two components was developed: a multivariate clinical prediction model (prospective) and a prediction model based on machine learning (retrospective). We used the database for the definition of the Capitation Payment Unit in the contributory regime of the Colombian health system (BDUPC given its Spanish acronym) and the country's death information from the vital statistics system. The period of analysis was defined based on data availability completeness, comparability (coding), and consistency. Multivariate model (prospective analysis): Subjects aged 40 to 90 years old who attended health services in 2011 were included. Patients with cancer diagnosis and patients reported in the mortality database for the year 2011 were excluded. LASSO logistic regression was used to select predictive variables. Non-hemolytic anemia was defined as the exposure variable and the Charlson comorbidity index a covariate (17 diagnoses). In total, 14,399 individuals with anemia and 44,961 without anemia made up the follow-up cohort. The risk of stomach cancer diagnosis was estimated using a cumulative incidence function, and subsequently a competing risks model. The groups showed differences in age, sex and place of residence. The average number of visits to health services was 1.8; 23.0 and 40.3 for patients without anemia, with anemia and with gastric cancer, respectively. The relative risk for stomach cancer diagnosis was 1.53 (95% CI 1.51-1.54), with attributable fraction 47.1 and a population attributable fraction 17.8. The median time to diagnosis for subjects with anemia was 28.2 months (IQR 17.2-40.9) and for subjects without anemia 36.7 months (IQR 23.8-48.0). The cumulative incidence of gastric cancer at 60 months in subjects with anemia was 7.6 per 1,000 (95% CI 6.1-9.1) and in subjects without anemia 2.4 per 1,000 (95% CI 1.9-2 ,8). In the competing risks model, anemia showed the greatest strength of association followed by male sex. Machine Learning Model (retrospective Analysis): A sample of patients with and without gastric cancer attending health services between September 1st and December 31st/2017 was selected. We included patients 30 to 90 years old. We analyzed the predictive capacity of the models close to the outcome (January-August 2017), and in a two-year period prior to the outcome (September 2015-August 2017). In the latter case, a washout period of six months prior to the outcome was allowed in order to reduce the effect of diagnoses and procedures close to the outcome. Predictive variables (diagnoses by CIE10 codes and procedures by CUPS codes) were filtered using LASSO logistic regression. In total 1,426 and 1,462 variables were included for the one-year and two-year periods of analysis, respectively. Three machine learning models were used: LASSO logistic regression, random forests, and gradient boosting. The accuracy of the models was evaluated by determining the area under the curve (AUROC), accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Additionally, the number needed to follow-up was calculated (NNT). After filtering by data quality, 4,965,931 and 5,175,620 individuals were included for the one-year and two-year periods of analysis, respectively. There were 1,426 and 1,462 cases of stomach cancer, respectively. Most patients were women, the average age was 58 years in patients with gastric cancer and 53 years in controls. The rate of health service attendance was higher in patients with gastric. The coefficients for diagnoses and procedures were higher for the one-year period. Diagnostic codes showed greater predictive capacity than procedures codes. The machine learning models showed no difference in AUROC; however, when using the best cutoff point for each model, the sensitivity for LASSO was higher than in random forests and gradient boosting (65.4%; 27.8% and 57. 9%, respectively). Specificity was higher in the random forest at the cost of a significant reduction in sensitivity. The predictive capacity of the LASSO model for the one-year period was the highest. In all cases, the accuracy improved with a higher cut-off point (greater probability of predicting the outcome), essentially due to an increase in specificity. Due to the low prevalence of the disease (approximately 0.02%), the PPV in all models was lower than 1%. The AUROC did not show relevant differences between training and test datasets. In all models, municipalities located in the Colombian mountains reported higher coefficients, and municipalities located in the Atlantic Coast lower coefficients. The detect at least 70% of stomach cancer cases, we need to follow-up 16.1%; 16.5%; and 20.4% of the population during two years according to LASSO, random forests and gradient boosting, respectively. Such numbers are equivalent to a NNT 1,170, 1,230, and 1,498, respectively. The LASSO logistic regression at one-year reports that 10.6% of the population requires follow-up to detect at least 70% of stomach cancer cases (NNT 790). Conclusions: The machine learning models developed in this study represent an innovative approach by using all available data related to the symptomatic expression of the disease in the pre-diagnostic phase. LASSO showed better performance than other models (including the multivariate model). The observed performance might improve in a higher risk population such as residents in high mountain municipalities. The results have potential for use in clinical practice given their discriminative capacity and the NNT, but their use in routine services must be preceded by their correct clinical validation.eng
dc.description.degreelevelDoctoradospa
dc.description.degreenameDoctor en Oncologíaspa
dc.description.methodsSe utilizó la base de datos para cálculo de la Unidad de Pago por Capitación en el régimen contributivo del sistema de salud y la información de defunciones del sistema de estadísticas vitales. Se seleccionaron periodos de análisis con base en la disponibilidad, suficiencia, comparabilidad y consistencia de los datos. Modelo multivariante: Se incluyeron pacientes de 40 a 90 años que usaron servicios en 2011. Se excluyeron pacientes con diagnóstico de cáncer o fallecidos ese año. Se utilizó regresión logística LASSO para seleccionar variables predictoras. Las anemias carenciales se definieron como variable de exposición, y el índice de comorbilidad de Charlson modificado como covariable. En total conformaron la cohorte 14.399 individuos con anemia (expuestos) y 44.961 sin anemia (no expuestos). Se analizó el riesgo de diagnóstico de cáncer gástrico mediante una función de incidencia acumulada. Posteriormente se utilizó un modelo de riesgos competitivos. Se observaron diferencias en edad, sexo y lugar de residencia entre expuestos y no expuestos. El riesgo relativo para el diagnóstico de cáncer gástrico fue 1,53 (IC95% 1,51-1,54), con fracción atribuible 47,1 y fracción atribuible poblacional 17,8. La mediana de tiempo al diagnóstico fue 28,2 y 36,7 meses para expuestos y no expuestos. La incidencia de cáncer gástrico a 60 meses con anemia fue 7,6 por 1.000 (IC95% 6,1-9,1) y sin anemia 2,4 por 1.000 (IC95% 1,9-2,8). En el modelo de riesgos competitivos la anemia mostró la mayor fuerza de asociación. Modelo de aprendizaje de máquinas: Se seleccionaron pacientes de 30 a 90 años con y sin diagnóstico de cáncer gástrico entre septiembre y diciembre de 2017. Se utilizaron dos periodos de análisis: próximo al desenlace (enero-agosto 2017) y dos años previos al desenlace (septiembre 2015-agosto 2017). En el último caso se dejó un periodo de lavado de seis meses para reducir el efecto de diagnósticos y procedimientos cercanos al desenlace. Se filtraron variables predictoras (CIE10 diagnósticos y CUPS procedimientos). Se incluyeron 1.426 y 1.462 variables para los análisis a uno y dos años, respectivamente. Se utilizaron tres modelos: regresión logística LASSO, bosques aleatorios y potenciación del gradiente. Se evaluó el desempeño mediante el área bajo la curva (AUROC), exactitud (accuracy), sensibilidad, especificidad, valor predictivo positivo (VPP) y valor predictivo negativo (VPN). Se calculó el número necesario a seguir (NNT) en función de la probabilidad de diagnóstico de cáncer.spa
dc.format.extent99 páginasspa
dc.format.mimetypeapplication/pdfspa
dc.identifier.instnameUniversidad Nacional de Colombiaspa
dc.identifier.reponameRepositorio Institucional Universidad Nacional de Colombiaspa
dc.identifier.repourlhttps://repositorio.unal.edu.co/spa
dc.identifier.urihttps://repositorio.unal.edu.co/handle/unal/87310
dc.language.isospaspa
dc.publisherUniversidad Nacional de Colombiaspa
dc.publisher.branchUniversidad Nacional de Colombia - Sede Bogotáspa
dc.publisher.facultyFacultad de Medicinaspa
dc.publisher.placeBogotá, Colombiaspa
dc.publisher.programBogotá - Medicina - Doctorado en Oncologíaspa
dc.relation.referencesBray F, Laversanne M, Sung H, Ferlay J, Siegel RL, Soerjomataram I, et al. Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin. 2024;74(3):229-63.spa
dc.relation.referencesBray F, Ferlay J, Soerjomataram I, Siegel RL, Torre LA, Jemal A. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: a cancer journal for clinicians. 2018;68(6):394-424.spa
dc.relation.referencesFondo Colombiano de Enfermedades de Alto Costo. Situación del cáncer en la población adulta atendida en el SGSSS en Colombia. 2022. Bogotá DC, Cuenta de Alto Costo (CAC); 2023.spa
dc.relation.referencesAllemani C, Matsuda T, Di Carlo V, Harewood R, Matz M, Niksic M, et al. Global surveillance of trends in cancer survival 2000-14 (CONCORD-3): analysis of individual records for 37 513 025 patients diagnosed with one of 18 cancers from 322 population-based registries in 71 countries. Lancet. 2018;391(10125):1023-75.spa
dc.relation.referencesLangton JM, Blanch B, Drew AK, Haas M, Ingham JM, Pearson SA. Retrospective studies of end-of-life resource utilization and costs in cancer care using health administrative data: a systematic review. Palliat Med. 2014;28(10):1167-96.spa
dc.relation.referencesBravo LE, Hernández Vargas JA, Collazos P, García LS, Valbuena AM, Acuña L. Survival in stomach cancer: analysis of a national cancer information system and a population-based cancer registry in Colombia. Colombia Médica. 2022;53(4).spa
dc.relation.referencesZhang X, Li M, Chen S, Hu J, Guo Q, Liu R, et al. Endoscopic Screening in Asian Countries Is Associated With Reduced Gastric Cancer Mortality: A Meta-analysis and Systematic Review. Gastroenterology. 2018;155(2):347-54 e9.spa
dc.relation.referencesSung H, Ferlay J, Siegel RL, Laversanne M, Soerjomataram I, Jemal A, et al. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: a cancer journal for clinicians. 2021;71(3):209-49.spa
dc.relation.referencesMurillo R. Cancer screening: from biology to public health. World Cancer Report: Cancer Research for Cancer Prevention. Lyon, France: International Agency for Research on Cancer; 2020. p. 540-9.spa
dc.relation.referencesMalfertheiner P, Camargo MC, El-Omar E, Liou JM, Peek R, Schulz C, et al. Helicobacter pylori infection. Nat Rev Dis Primers. 2023;9(1):19.spa
dc.relation.referencesIARC Helicobacter pylori Working Group 2014. Helicobacter pylori Eradication as a Strategy for Preventing Gastric Cancer. Lyon: International Agency for research on Cancer; 2014 Dec 2013.spa
dc.relation.referencesCharvat H, Sasazuki S, Inoue M, Iwasaki M, Sawada N, Shimazu T, et al. Prediction of the 10-year probability of gastric cancer occurrence in the Japanese population: the JPHC study cohort II. Int J Cancer. 2016;138(2):320-31.spa
dc.relation.referencesEom BW, Joo J, Kim S, Shin A, Yang HR, Park J, et al. Prediction Model for Gastric Cancer Incidence in Korean Population. PLoS One. 2015;10(7):e0132613.spa
dc.relation.referencesHamilton W. The CAPER studies: five case-control studies aimed at identifying and quantifying the risk of cancer in symptomatic primary care patients. British journal of cancer. 2009;101(2):S80-S6.spa
dc.relation.referencesNiu PH, Zhao LL, Wu HL, Zhao DB, Chen YT. Artificial intelligence in gastric cancer: Application and future perspectives. World J Gastroenterol. 2020;26(36):5408-19.spa
dc.relation.referencesCao R, Tang L, Fang M, Zhong L, Wang S, Gong L, et al. Artificial intelligence in gastric cancer: applications and challenges. Gastroenterol Rep (Oxf). 2022;10:goac064.spa
dc.relation.referencesFan Z, He Z, Miao W, Huang R. Critical Analysis of Risk Factors and Machine-Learning-Based Gastric Cancer Risk Prediction Models: A Systematic Review. Processes. 2023;11(8):2324.spa
dc.relation.referencesAfrash MR, Shafiee M, Kazemi-Arpanahi H. Establishing machine learning models to predict the early risk of gastric cancer based on lifestyle factors. BMC Gastroenterol. 2023;23(1):6.spa
dc.relation.referencesBriggs E, de Kamps M, Hamilton W, Johnson O, McInerney CD, Neal RD. Machine Learning for Risk Prediction of Oesophago-Gastric Cancer in Primary Care: Comparison with Existing Risk-Assessment Tools. Cancers (Basel). 2022;14(20).spa
dc.relation.referencesMohammadnezhad K, Sahebi MR, Alatab S, Sadjadi A. Modeling Epidemiology Data with Machine Learning Technique to Detect Risk Factors for Gastric Cancer. J Gastrointest Cancer. 2023.spa
dc.relation.referencesHuang RJ, Kwon NS, Tomizawa Y, Choi AY, Hernandez-Boussard T, Hwang JH. A Comparison of Logistic Regression Against Machine Learning Algorithms for Gastric Cancer Risk Prediction Within Real-World Clinical Data Streams. JCO Clin Cancer Inform. 2022;6:e2200039.spa
dc.relation.referencesInternational Agency for Reseach on Cancer-World Health Organization. Global Cancer Observatory 2022. Available from: http://gco.iarc.fr.spa
dc.relation.referencesRose G. Sick individuals and sick populations. International journal of epidemiology. 2001;30(3):427-32.spa
dc.relation.referencesHu B, El Hajj N, Sittler S, Lammert N, Barnes R, Meloni-Ehrig A. Gastric cancer: Classification, histology and application of molecular pathology. Journal of gastrointestinal oncology. 2012;3(3):251.spa
dc.relation.referencesSierra MS, Cueva P, Bravo LE, Forman D. Stomach cancer burden in Central and South America. Cancer epidemiology. 2016;44:S62-S73.spa
dc.relation.referencesMalnick SDH, Melzer E, Attali M, Duek G, Yahav J. Helicobacter pylori: friend or foe? World journal of gastroenterology: WJG. 2014;20(27):8979.spa
dc.relation.referencesBravo LE, Cortés A, Carrascal E, Jaramillo R, García LS, Bravo PE, et al. Helicobacter pylori: patología y prevalencia en biopsias gástricas en Colombia. Colombia médica. 2003;34(3):124-31.spa
dc.relation.referencesKandulski A, Malfertheiner P, Wex T. Role of regulatory T-cells in H. pylori-induced gastritis and gastric cancer. Anticancer research. 2010;30(4):1093-103.spa
dc.relation.referencesKayali S, Manfredi M, Gaiani F, Bianchi L, Bizzarri B, Leandro G, et al. Helicobacter pylori, transmission routes and recurrence of infection: state of the art. Acta Biomed. 2018;89(8-S):72-6.spa
dc.relation.referencesArévalo A, Trespalacios AA, Otero W. The importance of CagA protein in Helicobacter Pylori infection. Revista colombiana de Gastroenterología. 2009;24(4):388-95.spa
dc.relation.referencesTempera PJ, Michael M, Tageldin O, Hasak S. Gastric cancer due to chronic H. pylori infection: what we know and where we are going. Diseases. 2022;10(3):57.spa
dc.relation.referencesDincă AL, Meliț LE, Mărginean CO. Old and new aspects of H. pylori-associated Inflammation and gastric cancer. Children. 2022;9(7):1083.spa
dc.relation.referencesFielding J, Ellis D, Jones B, Paterson J, Powell D, Waterhouse J, et al. Natural history of" early" gastric cancer: results of a 10-year regional survey. Br Med J. 1980;281(6246):965-7.spa
dc.relation.referencesTsukuma H, Oshima A, Narahara H, Morii T. Natural history of early gastric cancer: a non-concurrent, long term, follow up study. Gut. 2000;47(5):618-21.spa
dc.relation.referencesNadler DL, Zurbenko IG. Estimating cancer latency times using a Weibull model. Advances in Epidemiology. 2014;2014.spa
dc.relation.referencesIida T, Yamashita K, Ohwada S, Ohkubo Y, Hirano T, Miyake T, et al. Natural history of gastric cancer from a retrospective review of endoscopic images of older patients with interval gastric cancer. Geriatrics & Gerontology International. 2018;18(7):997-1002.spa
dc.relation.referencesHuang RJ, Laszkowska M, In H, Hwang JH, Epplein M. Controlling Gastric Cancer in a World of Heterogeneous Risk. Gastroenterology. 2023;164(5):736-51.spa
dc.relation.referencesJanuszewicz W, Turkot MH, Malfertheiner P, Regula J. A Global Perspective on Gastric Cancer Screening: Which Concepts Are Feasible, and When? Cancers. 2023;15(3):664.spa
dc.relation.referencesHibino M, Hamashima C, Iwata M, Terasawa T. Radiographic and endoscopic screening to reduce gastric cancer mortality: a systematic review and meta-analysis. The Lancet Regional Health–Western Pacific. 2023.spa
dc.relation.referencesTerasawa T, Nishida H, Kato K, Miyashiro I, Yoshikawa T, Takaku R, et al. Prediction of gastric cancer development by serum pepsinogen test and Helicobacter pylori seropositivity in Eastern Asians: a systematic review and meta-analysis. PloS one. 2014;9(10):e109783.spa
dc.relation.referencesZagari RM, Rabitti S, Greenwood DC, Eusebi LH, Vestito A, Bazzoli F. Systematic review with meta‐analysis: diagnostic performance of the combination of pepsinogen, gastrin‐17 and anti‐Helicobacter pylori antibodies serum assays for the diagnosis of atrophic gastritis. Alimentary pharmacology & therapeutics. 2017;46(7):657-67.spa
dc.relation.referencesRobles C, Rudzite D, Polaka I, Sjomina O, Tzivian L, Kikuste I, et al. Assessment of serum pepsinogens with and without co-testing with gastrin-17 in gastric cancer risk assessment—Results from the GISTAR pilot study. Diagnostics. 2022;12(7):1746.spa
dc.relation.referencesNecula L, Matei L, Dragu D, Neagu AI, Mambet C, Nedeianu S, et al. Recent advances in gastric cancer early diagnosis. World journal of gastroenterology. 2019;25(17):2029.spa
dc.relation.referencesCalanzani N, Druce PE, Snudden C, Milley KM, Boscott R, Behiyat D, et al. Identifying Novel Biomarkers Ready for Evaluation in Low-Prevalence Populations for the Early Detection of Upper Gastrointestinal Cancers: A Systematic Review. Adv Ther. 2021;38(2):793-834.spa
dc.relation.referencesOliveros-Wilches R, Grillo-Ardila CF, Vallejo-Ortega M, Gil-Parada F, Cardona-Tobón M, Páramo-Hernández D, et al. Guía de práctica clínica para la prevención primaria y secundaria y diagnóstico temprano de cáncer gástrico. Revista Colombiana de Cancerología. 2022;26(1):39-96.spa
dc.relation.referencesGu J, Chen R, Wang S-M, Li M, Fan Z, Li X, et al. Prediction models for gastric cancer risk in the general population: a systematic review. Cancer Prevention Research. 2022;15(5):309-18.spa
dc.relation.referencesTaninaga J, Nishiyama Y, Fujibayashi K, Gunji T, Sasabe N, Iijima K, et al. Prediction of future gastric cancer risk using a machine learning algorithm and comprehensive medical check-up data: A case-control study. Scientific reports. 2019;9(1):12384.spa
dc.relation.referencesLeung WK, Cheung KS, Li B, Law SY, Lui TK. Applications of machine learning models in the prediction of gastric cancer risk in patients after Helicobacter pylori eradication. Alimentary pharmacology & therapeutics. 2021;53(8):864-72.spa
dc.relation.referencesHamilton W, Walter FM, Rubin G, Neal RD. Improving early diagnosis of symptomatic cancer. Nature Reviews Clinical Oncology. 2016;13(12):740-9.spa
dc.relation.referencesHippisley-Cox J, Coupland C. Development and validation of risk prediction algorithms to estimate future risk of common cancers in men and women: prospective cohort study. BMJ open. 2015;5(3):e007825.spa
dc.relation.referencesForster AS, Renzi C, Lyratzopoulos G. Diagnosing cancer in patients with ‘non-alarm’symptoms: Learning from diagnostic care innovations in Denmark. Cancer epidemiology. 2018;54:101.spa
dc.relation.referencesVan Es N, Le Gal G, Otten H-M, Robin P, Piccioli A, Lecumberri R, et al. Screening for occult cancer in patients with unprovoked venous thromboembolism: a systematic review and meta-analysis of individual patient data. Annals of internal medicine. 2017;167(6):410-7.spa
dc.relation.referencesKoo MM, Hamilton W, Walter FM, Rubin GP, Lyratzopoulos G. Symptom signatures and diagnostic timeliness in cancer patients: a review of current evidence. Neoplasia. 2018;20(2):165-74.spa
dc.relation.referencesJutte DP, Roos LL, Brownell MD. Administrative record linkage as a tool for public health research. Annual review of public health. 2011;32:91-108.spa
dc.relation.referencesSmith M, Lix LM, Azimaee M, Enns JE, Orr J, Hong S, et al. Assessing the quality of administrative data for research: a framework from the Manitoba Centre for Health Policy. Journal of the American Medical Informatics Association. 2018;25(3):224-9.spa
dc.relation.referencesBenchimol EI. Epidemiology and health administrative data: Focus on methodology and transparency. Oxford University Press Oxford, UK; 2014. p. 1780-1.spa
dc.relation.referencesMoons KG, Kengne AP, Woodward M, Royston P, Vergouwe Y, Altman DG, et al. Risk prediction models: I. Development, internal validation, and assessing the incremental value of a new (bio) marker. Heart. 2012;98(9):683-90.spa
dc.relation.referencesRanstam J, Cook J, Collins G. Clinical prediction models. Journal of British Surgery. 2016;103(13):1886spa
dc.relation.referencesLee Y-h, Bang H, Kim DJ. How to establish clinical prediction models. Endocrinology and Metabolism. 2016;31(1):38-44.spa
dc.relation.referencesShipe ME, Deppen SA, Farjah F, Grogan EL. Developing prediction models for clinical use using logistic regression: an overview. Journal of thoracic disease. 2019;11(Suppl 4):S574.spa
dc.relation.referencesMoons KG, Kengne AP, Grobbee DE, Royston P, Vergouwe Y, Altman DG, et al. Risk prediction models: II. External validation, model updating, and impact assessment. Heart. 2012;98(9):691-8.spa
dc.relation.referencesVickers AJ. Prediction models in cancer care. CA: a cancer journal for clinicians. 2011;61(5):315-26.spa
dc.relation.referencesUsher-Smith J, Emery J, Hamilton W, Griffin SJ, Walter FM. Risk prediction tools for cancer in primary care. British journal of cancer. 2015;113(12):1645-50.spa
dc.relation.referencesKourou K, Exarchos TP, Exarchos KP, Karamouzis MV, Fotiadis DI. Machine learning applications in cancer prognosis and prediction. Computational and structural biotechnology journal. 2015;13:8-17.spa
dc.relation.referencesGéron A. Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow: "O'Reilly Media, Inc."; 2022.spa
dc.relation.referencesTibshirani R. Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society Series B: Statistical Methodology. 1996;58(1):267-88.spa
dc.relation.referencesRamos Castillo L. Regresión Lasso. 2018. Disponible en: https://idus.us.es/items/5a8cceef-1a26-4f46-b38c-009430551db6spa
dc.relation.referencesBentéjac C, Csörgő A, Martínez-Muñoz G. A comparative analysis of gradient boosting algorithms. Artificial Intelligence Review. 2021;54:1937-67.spa
dc.relation.referencesMartínez Celda B. Gradient boosting (Potenciación del gradiente) en aprendizaje estadístico. 2021. Disponible en: https://uvadoc.uva.es/handle/10324/50607spa
dc.relation.referencesAgrawal S, Agrawal J. Neural network techniques for cancer prediction: A survey. Procedia Computer Science. 2015;60:769-74.spa
dc.relation.referencesShell J, Gregory WD. Efficient cancer detection using multiple neural networks. IEEE journal of translational engineering in health and medicine. 2017;5:1-7.spa
dc.relation.referencesSteiner MC. Solving cancer: The use of artificial neural networks in cancer diagnosis and treatment. Journal of Young Investigators. 2017;33(5):122-4.spa
dc.relation.referencesUniversidad Autónoma de Bucaramanga. Registro poblacional de cancer del área metropolitana de Bucaramanga. Vigencia 2021 2021 Disponible en: https://apolo.unab.edu.co/es/projects/registro-poblacional-de-cancer-del-area-metropolitana-de-bucarama.spa
dc.relation.referencesGuerrero R, Gallego AI, Becerril-Montekio V, Vásquez J. Sistema de salud de Colombia. Salud pública de México. 2011;53:s144-s55.spa
dc.relation.referencesMinisterio de Salud y Protección Social. Serie Anual de Afiliación a Nivel Nacional 1995-2022. In: Subdirección de la Operación del Aseguramiento en Salud, editor. República de Colombia2023.spa
dc.relation.referencesMinisterio de Salud y Protección Social. Solicitud de información a Entidades Promotoras de Salud para el Estudio de Suficiencia y de los mecanismos de ajuste de riesgo para el cálculo de la UPC recursos para garantizar la financiación de los servicios y tecnologías en salud año 2022. Periodo de estudio 2020. . Bogotá, Colombia: Minsalud; 2020.spa
dc.relation.referencesMinisterio de Salud y ¨Protección Social. Resolución 1896 de 2001: Por la cual se sustituye el anexo técnico de la Resolución 02333 de 2000, 1896 (2001). Bogotá, Colombia: Minsalud; 2001spa
dc.relation.referencesMinisterio de Salud y Protección Social. Resolución 0255 DE 2007: Por la cual se adopta el Código Único Nacional de Medicamentos, CUM, 0255 (2007). Bogotá, Colombia: Minsalud; 2007spa
dc.relation.referencesWorld Health Organization. ATC/DDD classification (temporary). WHO Drug Information. 2019;33(2):226-32.spa
dc.relation.referencesMinisterio de Salud y Protección Social. Portal SISPRO: RUAFND – Módulo de nacimientos y defunciones. Minsalud; Disponible en: https://www.sispro.gov.co/central-prestadores-de-servicios/Pages/RUAFND.aspx.spa
dc.relation.referencesAjani JA, Bentrem DJ, Besh S, D’Amico TA, Das P, Denlinger C, et al. Gastric cancer, version 2.2013. Journal of the national comprehensive cancer network. 2013;11(5):531-46.spa
dc.relation.referencesWinkler WE. String comparator metrics and enhanced decision rules in the Fellegi-Sunter model of record linkage. U.S. Bureau of the Census - Stat. Research Div. Washington DC; 1990.spa
dc.relation.referencesDamerau FJ. A technique for computer detection and correction of spelling errors. Communications of the ACM. 1964;7(3):171-6spa
dc.relation.referencesMeng X-L, Rubin DB. Maximum likelihood estimation via the ECM algorithm: A general framework. Biometrika. 1993;80(2):267-78.spa
dc.relation.referencesHarron KL, Doidge JC, Knight HE, Gilbert RE, Goldstein H, Cromwell DA, et al. A guide to evaluating linkage quality for the analysis of linked data. International journal of epidemiology. 2017;46(5):1699-710.spa
dc.relation.referencesInternational Agency for Reseach on Cancer. CI5 – Cancer Incidence in Five Continents. Disponible en: http://ci5.iarc.fr/.spa
dc.relation.referencesPisani P, Bray F, Parkin DM. Estimates of the world‐wide prevalence of cancer for 25 sites in the adult population. International journal of cancer. 2002;97(1):72-81.spa
dc.relation.referencesFiteni F, Westeel V, Pivot X, Borg C, Vernerey D, Bonnetain F. Endpoints in cancer clinical trials. Journal of visceral surgery. 2014;151(1):17-22.spa
dc.relation.referencesPardo C, Cendales R. Incidencia, mortalidad y prevalencia de cáncer en Colombia, 2012-2016. . Bogotá, Colombia: Instituto Nacional de Cancerología; 2022.spa
dc.relation.referencesPoveda Amaya MC. Prioritizing patients for stomach cancer screening programs: a machine learning approach. Disponible en: https://repository.javeriana.edu.co/handle/10554/62019spa
dc.relation.referencesLeone P, Vacca A, Dammacco F, Racanelli V. Common variable immunodeficiency and gastric malignancies. International journal of molecular sciences. 2018;19(2):451.spa
dc.relation.referencesCharlson M, Szatrowski TP, Peterson J, Gold J. Validation of a combined comorbidity index. Journal of clinical epidemiology. 1994;47(11):1245-51.spa
dc.relation.referencesCharan J, Biswas T. How to calculate sample size for different study designs in medical research? Indian journal of psychological medicine. 2013;35(2):121-6.spa
dc.relation.referencesPintilie M. Análisis de riesgos competitivos. Revista Española de Cardiología. 2011;64(7):599-605.spa
dc.relation.referencesLazcano-Ponce E, Martínez ME. Latin America: ripe for cutting-edge research proposals for prevention and control of Helicobacter pylori. Cancer Causes & Control. 2013;24:207-8.spa
dc.relation.referencesStephens M, Lewis W, White S, Blackshaw G, Edwards P, Barry J, et al. Prognostic significance of alarm symptoms in patients with gastric cancer. Journal of British Surgery. 2005;92(7):840-6.spa
dc.relation.referencesLee T-Y, Chiang E-P, Shih Y-T, Lane H-Y, Lin J-T, Wu C-Y. Lower serum folate is associated with development and invasiveness of gastric cancer. World Journal of Gastroenterology: WJG. 2014;20(32):11313spa
dc.relation.referencesAlkan A, Mızrak D, Utkan G. Lower folate levels in gastric cancer: Is it a cause or a result? World journal of gastroenterology. 2015;21(13):4101-2.spa
dc.relation.referencesZohora F, Bidad K, Pourpak Z, Moin M. Biological and immunological aspects of iron deficiency anemia in cancer development: a narrative review. Nutrition and cancer. 2018;70(4):546-56.spa
dc.relation.referencesCook MB, Kamangar F, Weinstein SJ, Albanes D, Virtamo J, Taylor PR, et al. Iron in relation to gastric cancer in the Alpha-tocopherol, Beta-carotene Cancer Prevention Study. Cancer epidemiology, biomarkers & prevention. 2012;21(11):2033-42.spa
dc.relation.referencesRodriguez-Castro KI, Franceschi M, Noto A, Miraglia C, Nouvenne A, Leandro G, et al. Clinical manifestations of chronic atrophic gastritis. Acta Biomed. 2018;89(8-S):88-92.spa
dc.relation.referencesTang GH, Hart R, Sholzberg M, Brezden-Masley C. Iron deficiency anemia in gastric cancer: a Canadian retrospective review. European journal of gastroenterology & hepatology. 2018;30(12):1497-501.spa
dc.relation.referencesFord AC, Marwaha A, Sood R, Moayyedi P. Global prevalence of, and risk factors for, uninvestigated dyspepsia: a meta-analysis. Gut. 2015;64(7):1049-57.spa
dc.relation.referencesCarmona-Sánchez R, Gómez-Escudero O, Zavala-Solares M, Bielsa-Fernández M, Coss-Adame E, Hernández-Guerrero A, et al. Consenso mexicano sobre la dispepsia. Revista de Gastroenterología de México. 2017;82(4):309-27.spa
dc.relation.referencesMahadeva S, Goh K-L. Epidemiology of functional dyspepsia: a global perspective. World journal of gastroenterology: WJG. 2006;12(17):2661.spa
dc.relation.referencesMahmoodi SA, Mirzaie K, Mahmoodi MS, Mahmoudi SM. A medical decision support system to assess risk factors for gastric cancer based on fuzzy cognitive map. Computational and Mathematical Methods in Medicine. 2020;2020.spa
dc.relation.referencesSo JBY, Kapoor R, Zhu F, Koh C, Zhou L, Zou R, et al. Development and validation of a serum microRNA biomarker panel for detecting gastric cancer in a high-risk population. Gut. 2021;70(5):829-37.spa
dc.relation.referencesRockhill B. The privatization of risk. American journal of public health. 2001;91(3):365.spa
dc.relation.referencesXie SH, Lagergren J. A model for predicting individuals’ absolute risk of esophageal adenocarcinoma: moving toward tailored screening and prevention. International Journal of Cancer. 2016;138(12):2813-9.spa
dc.relation.referencesLin Z, Wang R, Zhou Y, Wang Q, Yang C-Y, Hao B-C, et al. Prediction of distant metastasis and survival prediction of gastric cancer patients with metastasis to the liver, lung, bone, and brain: Research based on the SEER database. Annals of Translational Medicine. 2022;10(1).spa
dc.relation.referencesvan den Boorn HG, Abu-Hanna A, Ter Veer E, van Kleef JJ, Lordick F, Stahl M, et al. SOURCE: a registry-based prediction model for overall survival in patients with metastatic oesophageal or gastric cancer. Cancers. 2019;11(2):187.spa
dc.relation.referencesPietrantonio F, Miceli R, Raimondi A, Kim YW, Kang WK, Langley RE, et al. Individual patient data meta-analysis of the value of microsatellite instability as a biomarker in gastric cancer. Journal of Clinical Oncology. 2019;37(35):3392-400.spa
dc.relation.referencesZhu M, Ma Z, Zhang X, Hang D, Yin R, Feng J, et al. C-reactive protein and cancer risk: a pan-cancer study of prospective cohort and Mendelian randomization analysis. BMC medicine. 2022;20(1):1-13.spa
dc.relation.referencesIn H, Langdon-Embry M, Gordon L, Schechter CB, Wylie-Rosett J, Castle PE, et al. Can a gastric cancer risk survey identify high-risk patients for endoscopic screening? A pilot study. Journal of Surgical Research. 2018;227:246-56.spa
dc.relation.referencesStapley S, Peters TJ, Neal RD, Rose P, Walter F, Hamilton W. The risk of oesophago-gastric cancer in symptomatic patients in primary care: a large case–control study using electronic records. British journal of cancer. 2013;108(1):25-31.spa
dc.relation.referencesPourshams A, Khademi H, Malekshah AF, Islami F, Nouraei M, Sadjadi AR, et al. Cohort profile: the Golestan Cohort Study—a prospective study of oesophageal cancer in northern Iran. International journal of epidemiology. 2010;39(1):52-9.spa
dc.relation.referencesKim TJ, Pyo JH, Lee H, Baek S-Y, Ahn SH, Min YW, et al. Lack of association between helicobacter pylori infection and various markers of systemic inflammation in asymptomatic adults. The Korean Journal of Gastroenterology. 2018;72(1):21-7.spa
dc.relation.referencesYoussefi M, Tafaghodi M, Farsiani H, Ghazvini K, Keikha M. Helicobacter pylori infection and autoimmune diseases; Is there an association with systemic lupus erythematosus, rheumatoid arthritis, autoimmune atrophy gastritis and autoimmune pancreatitis? A systematic review and meta-analysis study. Journal of Microbiology, Immunology and Infection. 2021;54(3):359-69.spa
dc.relation.referencesTong L, Wang B-B, Li F-H, Lv S-P, Pan F-F, Dong X-J. An updated meta-analysis of the relationship between Helicobacter pylori infection and the risk of coronary heart disease. Frontiers in Cardiovascular Medicine. 2022;9:794445.spa
dc.relation.referencesYue L, Zhang R, Chen S, Duan G. Relationship between Helicobacter pylori and incident hypertension as well as blood pressure: a systematic review and meta-analysis. Digestive Diseases. 2023;41(1):124-37.spa
dc.relation.referencesEzzati Amini E, Moradi Y. Association between helicobacter pylori infection and primary open-angle glaucoma: a systematic review and meta-analysis. BMC ophthalmology. 2023;23(1):374.spa
dc.relation.referencesHaber R, El Gemayel M. Comorbidities in rosacea: a systematic review and update. Journal of the American Academy of Dermatology. 2018;78(4):786-92. e8.spa
dc.relation.referencesStasi R, Sarpatwari A, Segal JB, Osborn J, Evangelista ML, Cooper N, et al. Effects of eradication of Helicobacter pylori infection in patients with immune thrombocytopenic purpura: a systematic review. Blood, The Journal of the American Society of Hematology. 2009;113(6):1231-40.spa
dc.relation.referencesWang X, Jiang D, Li T, Zhang X, Wang R, Gao S, et al. Association between microbiological risk factors and neurodegenerative disorders: An umbrella review of systematic reviews and meta-analyses. Frontiers in psychiatry. 2022;13:991085.spa
dc.relation.referencesShindler-Itskovitch T, Ravona-Springer R, Leibovitz A, Muhsen K. A systematic review and meta-analysis of the association between Helicobacter pylori infection and dementia. Journal of Alzheimer's Disease. 2016;52(4):1431-42.spa
dc.relation.referencesDabo B, Pelucchi C, Rota M, Jain H, Bertuccio P, Bonzi R, et al. The association between diabetes and gastric cancer: results from the Stomach Cancer Pooling Project Consortium. European Journal of Cancer Prevention. 2022;31(3):260.spa
dc.relation.referencesTseng C-H. The relationship between diabetes mellitus and gastric cancer and the potential benefits of metformin: An extensive review of the literature. Biomolecules. 2021;11(7):1022.spa
dc.relation.referencesSwanton C, Bernard E, Abbosh C, Andre F, Auwerx J, Balmain A, et al. Embracing cancer complexity: Hallmarks of systemic disease. Cell. 2024;187(7):1589-616.spa
dc.relation.referencesHasan S. An Overview of Promising Biomarkers in Cancer Screening and Detection. Curr Cancer Drug Targets. 2020;20(11):831-52.spa
dc.relation.referencesWeigt J, Malfertheiner P. Metastatic disease in the stomach. Gastrointestinal tumors. 2015;2(2):61-4.spa
dc.relation.referencesCampoli PMdO, Ejima FH, Cardoso DMM, Silva OQd, Santana Filho JB, Queiroz Barreto PAd, et al. Metastatic cancer to the stomach. Gastric Cancer. 2006;9:19-25.spa
dc.relation.referencesNamikawa T, Marui A, Yokota K, Kawanishi Y, Munekage M, Uemura S, et al. Frequency and therapeutic strategy for patients with ovarian metastasis from gastric cancer. Langenbeck's Archives of Surgery. 2022;407(6):2301-8.spa
dc.relation.referencesPardo Ramos C, De Vries E, Buitrago L, Gamboa O. Atlas de mortalidad por cáncer en colombia. Cuarta edición ed: Instituto Nacional de Cancerología; 2017.spa
dc.relation.referencesSmith RA. The value of modern mammography screening in the control of breast cancer: understanding the underpinnings of the current debates. Cancer epidemiology, biomarkers & prevention. 2014;23(7):1139-46.spa
dc.relation.referencesMizota Y, Yamamoto S. How long should we continue gastric cancer screening? From an epidemiological point of view. Gastric Cancer. 2019;22:456-62.spa
dc.relation.referencesYang Y, Long Z, Zhong Z, Liu Q, Yang X. Construction and Evaluation of Gastric Cancer Risk Prediction Model. Indian Journal of Pharmaceutical Sciences. 2021;83:112-8.spa
dc.relation.referencesZhu X, Lv J, Zhu M, Yan C, Deng B, Yu C, et al. Development, validation, and evaluation of a risk assessment tool for personalized screening of gastric cancer in Chinese populations. BMC medicine. 2023;21(1):159.spa
dc.relation.referencesCao M, Li H, Sun D, Lei L, Ren J, Shi J, et al. Classifying risk level of gastric cancer: Evaluation of questionnaire-based prediction model. Chinese Journal of Cancer Research. 2020;32(5):605.spa
dc.relation.referencesWatanabe J, Kotani K. The effect of Helicobacter pylori eradication on C-reactive protein: results from a meta-analysis. Archives of Medical Science: AMS. 2022;18(4):958.spa
dc.relation.referencesKrawczyk B. Learning from imbalanced data: open challenges and future directions. Progress in Artificial Intelligence. 2016;5(4):221-32.spa
dc.relation.referencesSteinberg DM, Fine J, Chappell R. Sample size for positive and negative predictive value in diagnostic research using case-control designs. Biostatistics. 2009;10(1):94-105.spa
dc.rights.accessrightsinfo:eu-repo/semantics/openAccessspa
dc.rights.licenseAtribución-NoComercial-SinDerivadas 4.0 Internacionalspa
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/spa
dc.subject.ddc610 - Medicina y salud::615 - Farmacología y terapéuticaspa
dc.subject.ddc610 - Medicina y salud::616 - Enfermedadesspa
dc.subject.decsNeoplasias Gástricasspa
dc.subject.decsDetección Precoz del Cáncerspa
dc.subject.decsEarly Detection of Cancereng
dc.subject.decsStomach Neoplasmseng
dc.subject.decsBases de Datos Estadísticosspa
dc.subject.decsStatistical Databaseseng
dc.subject.decsMortalidadspa
dc.subject.decsMortalityeng
dc.subject.decsAprendizaje Automático Supervisadospa
dc.subject.decsSupervised Machine Learningeng
dc.subject.proposalMachine learningeng
dc.subject.proposalBig dataeng
dc.subject.proposalRoutinely collected health dataeng
dc.subject.proposalColombiaspa
dc.subject.proposalAprendizaje de máquinasspa
dc.subject.proposalDatos masivosspa
dc.subject.proposalDatos de salud recolectados rutinariamentespa
dc.titleDetección temprana de cáncer en población sintomática: desarrollo de un modelo multivariante y un modelo de aprendizaje de máquinas basados en bases de datos administrativas del sistema de salud colombiano y aplicados al cáncer gástricospa
dc.title.translatedCancer early detection in symptomatic patients: development of multivariate and machine learning models based on administrative health data of the Colombian health system and applied to gastric cancereng
dc.typeTrabajo de grado - Doctoradospa
dc.type.coarhttp://purl.org/coar/resource_type/c_db06spa
dc.type.coarversionhttp://purl.org/coar/version/c_ab4af688f83e57aaspa
dc.type.contentTextspa
dc.type.driverinfo:eu-repo/semantics/doctoralThesisspa
dc.type.redcolhttp://purl.org/redcol/resource_type/TDspa
dc.type.versioninfo:eu-repo/semantics/acceptedVersionspa
dcterms.audience.professionaldevelopmentInvestigadoresspa
oaire.accessrightshttp://purl.org/coar/access_right/c_abf2spa

Archivos

Bloque original

Mostrando 1 - 1 de 1
Cargando...
Miniatura
Nombre:
98494191.2024.pdf
Tamaño:
2.03 MB
Formato:
Adobe Portable Document Format
Descripción:
Tesis de Doctorado en Oncología

Bloque de licencias

Mostrando 1 - 1 de 1
No hay miniatura disponible
Nombre:
license.txt
Tamaño:
5.74 KB
Formato:
Item-specific license agreed upon to submission
Descripción: