UIO:RealArt: Real world ¨C artificial worlds: Improving causal inference in perinatal pharmaco-epidemiology using machine learning approaches on real-world and artificial data

We use linked data from the Norwegian health and education registries in combination with observational and biological data, including genetic and epigenetic data, from the large Norwegian birth cohort MoBa to study health outcomes, including language development, educational attainment, and psychological disorders from childhood until adolescence, in children exposed to psychotropics and pain relievers in utero. By systematically exploring a selected collection of artificial worlds, i.e., simulated datasets that reflect real-world perinatal epidemiology datasets, we will overcome fundamental challenges of understanding medication safety in pregnancy. We will apply novel approaches that will embed machine learning techniques within the causal inference framework.This convergence project will join scientists from the natural sciences, medicine, and social/educational sciences to improve our understanding of the safety of medications commonly used in pregnancy.

Read more about the project (mn.uio.no)