The development of Artificial Intelligence for clinical decision cannot be achieved without hybrid approaches, to learn from a limited number of heterogeneous cases, with complex phenotypes, and complex underlying biological mechanisms. Solutions based on deep phenotyping are being investigated to solve a diagnostic or a therapeutic problem of a new patient by recalling previous cases that exhibited similar characteristics in rare disease clinical data warehouses. Future directions consist in developing digital twins solutions that integrate the precision medicine paradigm. Such approaches combine different methodologies, using holistic omics data, and existing data from clinical trials and routine care. Because of data complexity, multi-scale knowledge, and fast changing models, AI in medicine raises lots of issues that require multidisciplinary research at the highest level.




