A talk on the topic of MLOps for Health AI that I presented as a guest speaker for the AWS AI Learning Path, organized by Amazon Web Services (AWS) in collaboration with Women in AI (WAI) Finland

Velmio is a startup that I co-founded with the aim of advancing personalised health for underrepresented patient groups. We built digital health apps integrating data from wearables and other sources with AI technologies to provide timely, accurate and tailored health analyses.

Our new software tool developed in collaboration with the INTERVENE consortium creates biobank-scale synthetic data that resembles real genetics data. We publicly released a large dataset of genotypes and phenotypes to aid with computational genetics research

We developed a geometric deep learning approach to model the shared genetic, environment and lifestyle factors that influence disease risk in families. In collaboration with the Institute of Molecular Medicine Finland we studied a connected network of over 7 million patients

Meta-learning and multi-task learning are often used for learning from related tasks. Motivated by medical/biological data, we present a new meta-learning approach (formulated as Bayesian hierarchical modelling) for settings where tasks are generated by different causal models.