During Michaelmas Term, OxTalks will be moving to a new platform (full details are available on the Staff Gateway).
For now, continue using the current page and event submission process (freeze period dates to be advised).
If you have any questions, please contact halo@digital.ox.ac.uk
Utilising data from Finland, where genetic details of approximately 500,000 individuals are linked to a national health registry, this presentation will explore the use of polygenic scores and electronic health records (EHRs) to predict disease susceptibility. It will highlight the challenges and successes of employing polygenic scores for disease prediction. Additionally, the talk will discuss the application of machine learning algorithms to predict healthcare outcomes from EHRs, assessing their fairness and generalizability across different populations. The presentation will conclude with a direct comparison of genetic and EHR-based predictions to assess which approach is most predictive and generalizable across healthcare systems.