Hosted by the School of Medicine at Cardiff University

Analysis of disease progression patterns of multimorbid patients typically try to find systematic patterns of risk factors, diseases and complications. Such analyses are made difficult by the fact that certain risk factors also can present as complications, thus representing “promiscuous” diseases that appear in quite different contexts. Another problem is that similar outcomes can be caused by different mechanisms, mixed etiologies, that can be difficult to disentangle longitudinally. The talk will discuss approaches to patient stratification in such situations, including deep learning frameworks that can be trained across all diseases by data from millions of patients at population scale.

Register for your free place on Eventbrite or join online via Zoom, https://cardiff.zoom.us/j/81835753222?pwd=tvkmYeN8S4wSbAS4jOACxo8abaCMRv.1, Meeting ID: 818 3575 3222, Password: 773431

Søren Brunak is a professor of Disease Systems Biology and Research Director in the Novo Nordisk Foundation Center for Protein Research at University of Copenhagen. His program combines molecular level systems biology data with analysis of healthcare sector phenotypic data (electronic patient records, registry information and biobank questionnaires) to understand multimorbidities and discriminate between treatment related disease correlations. This stratifies patients not only from their genotype, but also based on the clinical descriptions in their medical records and is particularly relevant in the context of the precision medicine agenda. He has been a Member of the Royal Swedish Academy of Sciences since 2016, a Member of the European Molecular Biology Organization since 2009, and a Member of the Royal Danish Academy of Sciences and Letters since 2004.