| Abstract |
In this WAI, I will talk about an FP7 proposal called Depredictor. In
this project, the main goal is the development of individualized
predictive models based on a rich set of patient specific data, thereby
including environmental data. Such models will provide the biomedical
researcher
with insight into the relationships that are present between the
prominent factors related to depression. Furthermore, the models will
give the clinician a prediction of the onset and evolution (including
relapse, re-occurrence and deterioration) of depression. More
specifically, they will predict the occurrence of new depressive
episodes and the expected development of factors related to the severity
of depressive symptoms (activity patterns, course of mood, use of coping
skills, social involvement). The combination of both the predictive
capabilities as well as the interrelationships provides the clinician
with an empirical basis for deciding upon the most suitable therapeutic
intervention for the patient for reducing depressive symptoms. To come
to such predictive models, this project will contribute the following:
(1) a methodology to develop individualized predictive model for the
field of depression, and (2) a detailed dataset containing information
on an individual patient level. Furthermore, the usefulness of the
predictive models for clinician will be validated in a pilot study
whereby clinicians are provided with a software tool incorporating the
models. The project team consists of a combination of experts from
several disciplines within the ICT, psychology, and psychiatry domains. |