EP 231: From polygenic scores to AI-driven medicine with Andrea Ganna of the Institute for Molecular Medicine Finland
Episode Description
This week on The Genetics Podcast, Patrick is joined by Dr. Andrea Ganna, Associate Professor at the Institute for Molecular Medicine Finland (FIMM). They discuss the promise and limits of polygenic risk scores for disease prediction and clinical trials, how large-scale electronic health records and AI models could transform medical research and healthcare planning, what Finland’s national health data infrastructure enables for population-scale studies, and how genetics can be used to strengthen trial emulation in observational data.
Show Notes:
0:00 Intro to The Genetics Podcast
00:59 Welcome to Andrea
01:51 Andrea’s research focuses, including polygenic scores in biobanks and AI applications
03:02 Complementarity between polygenic scores and electronic health record–derived risk signals across biobanks
04:47 Using polygenic risk scores for prognostic versus predictive enrichment in clinical trials
10:28 Limitations and opportunities of using AI models on large-scale electronic health records
15:47 Legal, data infrastructure, and privacy barriers to building AI models on health records
18:04 Choosing model architectures for healthcare AI
19:47 Using AI and multi-omics data to integrate biological knowledge and the challenge of learning causality
21:43 How removing genetic effects from proteins improves disease prediction and highlights the role of environment
24:42 Finland’s health data ecosystem and national biobanks
28:11 Using genetics to improve trial emulation in biobank data and observational studies
33:42 Closing remarks
Find out more:
Please consider rating and reviewing us on your chosen podcast listening platform!