Fiche de DA CAMARA RIBEIRO DANTAS Marcel

Titre : Learning interpretable causal networks from very large datasets, application to 400,000 medical records of breast cancer patients
Date : 4 juillet 2022
Heure: 14:00
Résumé : Discovering causal effects is at the core of scientific investigation but remains challenging when only observational data is available. In practice, causal networks are difficult to learn and interpret and limited to relatively small datasets. This thesis proposes a more reliable and scalable causal discovery method (iMIIC), that can learn interpretable causal networks for a wide range of biological, biomedical, and presumably other complex heterogeneous data. It is based on a general mutual information supremum principle, which greatly improves the precision of inferred causal relations while distinguishing genuine causes from putative and latent causal effects. We showcase iMIIC on synthetic and real-life healthcare data from 396,179 breast cancer patients (US Surveillance, Epidemiology, and End Results program).
Lieu : Amphithéâtre Curie