Global Excellence Seminar with Søren Brunak

  • 23 February 2018 |
  • Søren Brunak |
  • MR Conference Room |
  • Time 9:00 |

Global Excellence Seminar with Professor Søren Brunak entitled: "Big biomedical data analysis in support of precision medicine".

Improvement in more precise treatment of individual patients will, in part, be driven by the availability of novel data (e.g. genomes, cancer genomes, proteomes), but also by new analysis approaches extracting deep phenotyping signals from existing data. The latter work typically from highly heterogeneous data sources: patient record text, laboratory values, images, diagnoses and procedures. An important aspect will be better methods for analysis of longitudinal data, leading to better patient stratification. Multi-step disease trajectories are key to the understanding of human disease progression patterns and their underlying molecular level etiologies. The number of human protein coding genes is small and many genes are presumably impacting more than one disease, a fact that complicates the process of identifying actionable variation for use in precision medicine efforts.

We present approaches to the identification of frequent disease trajectories from population-wide healthcare data comprising millions of patients and corresponding strategies for linking disease co-occurrences to genomic individuality. An additional opportunity provided by redefining phenotypes as longitudinal patterns is to assess the validity of diagnoses (mis- and over-diagnosis), or alternatively suggest missing diagnoses (under-diagnosis), from their temporal context. We use COPD as a case and demonstrate how we can identify and impute likely under-diagnosed patients in this manner. Such a diagnosis “clean-up” step is also relevant in conventional case-control studies where false negative and false positive patients bring down the statistical power or the predictive performance of machine learning algorithms.

The Global Excellence Seminar will be held on Friday 23 February 2018 at 9 o'clock in the MR Conference Room.