Titulo Estágio
Algorithms for short-term Cardiovascular event risk predicttion
Área Tecnológica
Informática Médica
Local do Estágio
DEI
Enquadramento
Several risk score tools are available in literature to predict cardiovascular events. In particular, this work addresses death/myocardial infarction events for coronary artery disease (CAD) patients, within a short period of time.
However, the choice of the most adequate tool is not straightforward since there might not be a consensus about the best model to use in clinical practice. Moreover, each individual tool considers a reduced number of risk factors and is rigid, in the sense that does not permit the incorporation of new risk factors or additional clinical knowledge. Additionally, these tools present difficulties in coping with missing risk factors.
Objetivo
The main goal is to develop a strategy able to combine several known and validated short-term risk tools (available in the medical community) into a multi-model approach.
The combination of these individual risk tools will eliminate the need of a consensus on the best model to use in the clinical practice; it will enable to increase the number of risk factors to compute the risk; it will improve the capability to deal with missing risk factors and will allow the incorporation of additional clinical knowledge.
One of the key aspects to be addressed is related to clinical knowledge representation and to group personalization, i.e., the developing of specific risk models to be applicable for each target patient group
Computational intelligence methodologies, such as fuzzy systems, Bayesian networks and decision trees, in order to represent/combine and to introduce clinical know-how will be investigated.
Plano de Trabalhos - Semestre 1
1. Clinical context
2. State of the art: modeling techniques and knowledge representation and stratification
3. Clinical data base analysis
4. Dissertation intermediate documentation
Plano de Trabalhos - Semestre 2
1. Development of personalized algorithms for CV risk
2. Validation
3. Integration into the clinical framework
4. Writing of dissertation
Condições
A realizar no DEI.
Orientador
Jorge Henriques
jh@dei.uc.pt 📩