{"id":14096,"date":"2026-05-07T17:44:06","date_gmt":"2026-05-07T15:44:06","guid":{"rendered":"https:\/\/www.uni.lu\/lcsb-en\/?post_type=events&p=14096"},"modified":"2026-05-19T16:22:49","modified_gmt":"2026-05-19T14:22:49","slug":"artificial-intelligence-for-bioscientific-research-prof-laura-azzimonti","status":"publish","type":"events","link":"https:\/\/www.uni.lu\/lcsb-en\/events\/artificial-intelligence-for-bioscientific-research-prof-laura-azzimonti\/","title":{"rendered":"Artificial Intelligence for Bioscientific Research – Prof. Laura Azzimonti"},"content":{"rendered":"\n
<\/div>\n\n\n

This is an online event<\/strong>, tune in via Webex here<\/a>.<\/p>\n\n\n

<\/div>\n\n\n

\nPhysics-informed machine learning and causal artificial intelligence for personalized diabetes prevention<\/h2>\n\n\n\n

Personalised medicine requires tools capable of integrating heterogeneous expert knowledge, from mechanistic models to causal relationships, with real-world clinical data. Physics-Informed Machine Learning (PIML) and Causal Artificial Intelligence (Causal AI) represent two complementary methodological frameworks that address this challenge: PIML embeds domain knowledge encoded in differential equations directly into the learning process, while Causal AI enables the estimation of intervention effects from real-world data. Together, they offer a principled way to move beyond black-box predictions towards interpretable, mechanistically grounded models that can inform individualised clinical decisions. This talk illustrates both approaches through applications to type 2 diabetes prevention, developed within the Horizon Europe project PRAESIIDIUM. Specifically, we show how PIML and Causal AI can jointly support clinicians by enabling physics-grounded personalised predictions and guiding prevention strategies across heterogeneous patient populations.<\/p>\n\n\n

<\/div>\n\n\n
\n
\n

\nAbout the speaker<\/h3>\n\n\n\n

Laura Azzimonti is a senior researcher and lecturer at the Dalle Molle Institute for Artificial Intelligence <\/a>(SUPSI-IDSIA) in Lugano, Switzerland, and a SIB Group Leader. She develops machine learning methods for personalised medicine, focusing on physics-informed machine learning, causal AI, federated learning and Bayesian modelling, with applications in bioinformatics, clinical decision support and biomedical modelling<\/p>\n\n\n

<\/div>\n\n\n