Perfiles genéticos en la hipertensión
Loading...
Download
Official URL
Full text at PDC
Publication date
2025
Defense date
06/11/2024
Authors
Advisors (or tutors)
Editors
Journal Title
Journal ISSN
Volume Title
Publisher
Universidad Complutense de Madrid
Citation
Abstract
En los últimos años ha habido un aumento sustancial en la cantidad de datos epigenéticos, como por ejemplo datos de metilación del ADN, y su relación con varias enfermedades. En esta tesis utilizamos datos de metilación del ADN en el contexto de la hipertensión, que es una de las principales causas de mortalidad en todo el mundo. Según estimaciones de la Organización Mundial de la Salud actualmente hay más de mil millones de personas con hipertensión. Un porcentaje sustancial de esas personas no son conscientes de que tienen hipertensión. Se encontraron firmas epigenéticas claras en pacientes hipertensos y prehipertensos utilizando datos de metilación del ADN y un algoritmo de clasificación (redes neuronales). Se muestra cómo al seleccionar un subconjunto apropiado de CpG es posible lograr una clasificación de precisión media del 86% para distinguir pacientes control e hipertensos (y prehipertensos). Además, también es posible obtener un modelo estadísticamente comparable que logra una precisión media del 83% utilizando solo 22 CpGs. Ambos enfoques representan una mejora sustancial sobre el uso de toda la cantidad de CpG disponibles, lo que resultó en que la red neuronal no generara clasificaciones precisas...
In recent years there has been a substantial increase in the amount of epigenetic data, such as DNA methylation data, and its link to several illness. In this dissertation we use DNA methylation data in the context of hypertension, which is a major mortality cause across the world. According to estimates from the World Health Organization there are currently more than one billion individuals with hypertension. A substantial amount of those individuals are unaware that they have hypertension. Clear epigenetic signatures were found in hypertensive and pre-hypertensive patients using DNA methylation data and neural networks in a classification algorithm. It is shown how by selecting an appropriate subset of CpGs it is possible to achieve a mean accuracy classification of 86% for distinguishing control and hypertensive (and pre-hypertensive) patients. Furthermore, it is also possible to obtain a statistically comparable model achieving an 83% mean accuracy using only 22 CpGs. Both of these approaches represent a substantial improvement over using the entire amount of available CpGs, which resulted in the neural network not generating accurate classifications...
In recent years there has been a substantial increase in the amount of epigenetic data, such as DNA methylation data, and its link to several illness. In this dissertation we use DNA methylation data in the context of hypertension, which is a major mortality cause across the world. According to estimates from the World Health Organization there are currently more than one billion individuals with hypertension. A substantial amount of those individuals are unaware that they have hypertension. Clear epigenetic signatures were found in hypertensive and pre-hypertensive patients using DNA methylation data and neural networks in a classification algorithm. It is shown how by selecting an appropriate subset of CpGs it is possible to achieve a mean accuracy classification of 86% for distinguishing control and hypertensive (and pre-hypertensive) patients. Furthermore, it is also possible to obtain a statistically comparable model achieving an 83% mean accuracy using only 22 CpGs. Both of these approaches represent a substantial improvement over using the entire amount of available CpGs, which resulted in the neural network not generating accurate classifications...
Description
Tesis inédita de la Universidad Complutense de Madrid, Facultad de Medicina, leída el 06-11-2024












