Predictive models for complex diseases
The Non Communicable Complex Disease (NCCD) are the leading causes of death in the world, causing more deaths each year than all other combined causes. The approximately 80% of deaths were caused by NCCD and occured in low and middle income countries. However, NCCD deaths could be avoided by prevent...
Guardado en:
Autores principales: | , |
---|---|
Formato: | Artículo revista |
Lenguaje: | Español |
Publicado: |
Universidad Nacional Cba. Facultad de Ciencias Médicas. Secretaria de Ciencia y Tecnología
2012
|
Acceso en línea: | https://revistas.unc.edu.ar/index.php/med/article/view/21360 |
Aporte de: |
id |
I10-R10-article-21360 |
---|---|
record_format |
ojs |
spelling |
I10-R10-article-213602019-05-10T12:42:03Z Predictive models for complex diseases Modelos predictivos para enfermedades complejas Brunotto, Mabel Zarate, Ana María The Non Communicable Complex Disease (NCCD) are the leading causes of death in the world, causing more deaths each year than all other combined causes. The approximately 80% of deaths were caused by NCCD and occured in low and middle income countries. However, NCCD deaths could be avoided by prevention programs and early diagnosis. The challenge of the multifactorial phenotypes is to achieve a valid strategy for identifying risk individuals at the population. These strategies may be addressed to screening population or generating causal predictive models for early detection, interpreting the root causes that create the condition. The aim of this paper is to describe the characteristic of complex chronic diseases and some of the current methods of study of these in the health area . Conclusions: Interdisciplinary work, a team of health professionals belonging to different areas allows for an adequate management of complex diseases. The application of graph models, such asDAG’s, is a valuable tool for a better adjustment of the statistical model, which allows an appropriate correspondence with the actual health model of these illnesses. And the best methodological strategy for complex diseases is the early diagnosis and the monitoring of risk groups and therapy monitoring of patients diagnosed. Las Enfermedades Complejas No Transmisibles (ECNT) son las principales causas de muerte en el mundo, produciendo más muertes cada año que todas las otras causas combinadas. De acuerdo a los datos disponibles aproximadamente el 80% de las muertes por ECNT se producen en países de bajos y medianos ingresos. Sin embargo, las muertes causadas por ECNT podrían evitarse si se implementaran programas de prevención y diagnóstico temprano. El desafío que representan los fenotipos multifactoriales es lograr una estrategia válida de identificación de individuos de riesgo en la población. Estas estrategias pueden estar orientadas al monitoreo poblacional o a la generación de modelos predictivos causales para detección temprana, interpretando las causas primordiales que generan la patología. El objetivo de este trabajo es describir las caracterísitcas de las enfermedades crónicas complejas y algunos de los métodos actuales de estudio de éstas en el área de la salud. Conclusiones. El trabajo interdisciplinario, de un equipo de profesionales de la salud pertenecientes a diversas áreas permite un adecuado abordaje de las patologías complejas. La aplicación de modelos como los gráficos de causalidad resulta una herramienta invalorable para lograr un adecuado ajuste del modelo estadístico, permitiendo introducir todos los componentes que intervienen en la dinámica salud-enfermedad. Y la mejor estrategia metodológica para las enfermedades complejas es el diagnóstico temprano y el monitoreo de grupos de riesgo y el seguimiento de terapias de pacientes diagnosticados. Universidad Nacional Cba. Facultad de Ciencias Médicas. Secretaria de Ciencia y Tecnología 2012-03-27 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://revistas.unc.edu.ar/index.php/med/article/view/21360 Revista de la Facultad de Ciencias Médicas de Córdoba.; Vol. 69 No. 1 (2012); 33-41 Revista de la Facultad de Ciencias Médicas de Córdoba; Vol. 69 Núm. 1 (2012); 33-41 Revista da Faculdade de Ciências Médicas de Córdoba; v. 69 n. 1 (2012); 33-41 1853-0605 0014-6722 10.31053/1853.0605.v69.n1 spa https://revistas.unc.edu.ar/index.php/med/article/view/21360/20876 Derechos de autor 2018 Universidad Nacional de Córdoba |
institution |
Universidad Nacional de Córdoba |
institution_str |
I-10 |
repository_str |
R-10 |
container_title_str |
Revistas de la UNC |
language |
Español |
format |
Artículo revista |
author |
Brunotto, Mabel Zarate, Ana María |
spellingShingle |
Brunotto, Mabel Zarate, Ana María Predictive models for complex diseases |
author_facet |
Brunotto, Mabel Zarate, Ana María |
author_sort |
Brunotto, Mabel |
title |
Predictive models for complex diseases |
title_short |
Predictive models for complex diseases |
title_full |
Predictive models for complex diseases |
title_fullStr |
Predictive models for complex diseases |
title_full_unstemmed |
Predictive models for complex diseases |
title_sort |
predictive models for complex diseases |
description |
The Non Communicable Complex Disease (NCCD) are the leading causes of death in the world, causing more deaths each year than all other combined causes. The approximately 80% of deaths were caused by NCCD and occured in low and middle income countries. However, NCCD deaths could be avoided by prevention programs and early diagnosis. The challenge of the multifactorial phenotypes is to achieve a valid strategy for identifying risk individuals at the population. These strategies may be addressed to screening population or generating causal predictive models for early detection, interpreting the root causes that create the condition. The aim of this paper is to describe the characteristic of complex chronic diseases and some of the current methods of study of these in the health area . Conclusions: Interdisciplinary work, a team of health professionals belonging to different areas allows for an adequate management of complex diseases. The application of graph models, such asDAG’s, is a valuable tool for a better adjustment of the statistical model, which allows an appropriate correspondence with the actual health model of these illnesses. And the best methodological strategy for complex diseases is the early diagnosis and the monitoring of risk groups and therapy monitoring of patients diagnosed. |
publisher |
Universidad Nacional Cba. Facultad de Ciencias Médicas. Secretaria de Ciencia y Tecnología |
publishDate |
2012 |
url |
https://revistas.unc.edu.ar/index.php/med/article/view/21360 |
work_keys_str_mv |
AT brunottomabel predictivemodelsforcomplexdiseases AT zarateanamaria predictivemodelsforcomplexdiseases AT brunottomabel modelospredictivosparaenfermedadescomplejas AT zarateanamaria modelospredictivosparaenfermedadescomplejas |
first_indexed |
2022-08-20T01:25:51Z |
last_indexed |
2022-08-20T01:25:51Z |
_version_ |
1770718952351072256 |