Pharmacoepidemiology and ML to improve medication safety of polypharmacy in pregnancy

Our research

We combine pharmacoepidemiological methods with machine learning to address medication safety in pregnancy by describing patterns of polypharmacy use, including over-the-counter, prescription, and hospital-administered medications. 

We study medication use patterns and drug combinations and assess their associations with adverse maternal and fetal outcomes, while also investigating opportunities for drug repurposing and identifying potential new drug effects. 

In addition, we develop and validate predictive models of adverse maternal and fetal outcomes among women exposed to polypharmacy during pregnancy, using Nordic healthcare data.

Projects​

• Optimal Classification And improved Prevention of Intrauterine growth restriction (OCAPI)

Funding​

• DFF-Forskningsprojekt2 (tematisk forskning), 2024

Collaborations ​

• Dr. Zeyan Liew, Assistant Professor of Epidemiology (Environmental Health), Yale School og Public Health,
• Adam Hulman, Associate Professor & Senior Data Scientist, Steno Diabetes Center Aarhus, Denmark