SP5 - COMMITMENT
Subgroup and comorbidity analysis
Patients are treated largely by a “one-fits-all” approach, despite substantial clinical heterogeneity in course, treatment response and presence of somatic comorbidities that include type 2 diabetes, cardiovascular diseases and neurodegenerative processes. There is a strong need to identify biological means to stratify patients with psychotic disorders and identify the biological basis of somatic comorbidity. This will allow improved clinical delineation of psychotic illnesses and facilitate novel intervention strategies targeted at the minimization of comorbidity risk, reducing mortality and morbidity. The primary objective of SP5 is the integrative application of algorithms developed as part of the COMMITMENT project to disentangle biologically-defined subgroups of patients with psychotic disorders and identify biological dimensions shared with somatic comorbidities. For this, we will combine the mechanistic cause-effect models identified in SP3 with the extensively tested multitask-learning algorithms developed in SP4, and coordinate the application of these algorithms on the distributed data resource in close collaboration with SP2 and SP3. We will make specific use of strategies to map incomplete multi-OMICs data to the same dataspace, for example in form of biological pathway features, such that analysis is not restricted to data subsets with overlapping modalities. This will identify biological profiles that index subgroups of psychosis patients, which we will then predict into existing cross-sectional and longitudinal data to explore associations with clinical course and treatment response, as well as the occurrence of early comorbidity signs (SP2). Secondly, we will collaborate closely with SP6, to (I) map multivariate symptom domains across the COMMITMENT database and identify associations with comorbidity profiles and (II) facilitate the lifespan trajectory analysis of psychosis stratification and comorbidity profiles.