Data-driven approach to cardiovascular disease: deep phenotyping, omics and machine learning
Tipus de documentText en actes de congrés
Data publicació2020
EditorBarcelona Supercomputing Center
Condicions d'accésAccés obert
Tots els drets reservats. Aquesta obra està protegida pels drets de propietat intel·lectual i
industrial corresponents. Sense perjudici de les exempcions legals existents, queda prohibida la seva
reproducció, distribució, comunicació pública o transformació sense l'autorització del titular dels drets
Abstract
Most cardiovascular (CV) risk scores used in clinical practice predict the probability
of CV events using information on the seven traditional cardiovascular risk factors:
age, gender, hypertension, dyslipidemia, obesity, smoking and diabetes. These scores,
however, fail to identify young, healthy individuals potentially at risk based on their
extension or progression of subclinical atherosclerosis, mainly characterized using imaging
techniques. By means of deep phenotyping and omics data analyzed with machine
learning methods we aim to develop new risk scores to refine the prediction of 10-
year cardiovascular risk in young, asymptomatic individuals. Moreover, this data-driven
approach to CVD is improving our understanding about how the molecular profile and a
variety of psychosocial, lifestyle, dietary and demographic variables affects the genesis
of the disease and its progression and, eventually, how and when SA will lead to cardiovascular
events.
CitacióSánchez Cabo, F. Data-driven approach to cardiovascular disease: deep phenotyping, omics and machine learning. A: . Barcelona Supercomputing Center, 2020, p. 32-33.
Fitxers | Descripció | Mida | Format | Visualitza |
---|---|---|---|---|
BSC_SORS_2019-2 ... oach to cardiovascular.pdf | 314,4Kb | Visualitza/Obre | ||
license_rdf.rdf | 1,203Kb | application/rdf+xml; charset=utf-8 | Visualitza/Obre |