The clinical decision support systems (CDS) are generally limited to thresholds and variance detection in the case of anesthesia monitoring, this project aims at exploiting the potentialities of control, optimization and learning methods in order to propose generic and explainable approaches allowing to merge the different measured data, and to design advanced systems for critical and complex events detection. Furthermore, this project will help to tackle highly challenging problems related to anesthesia dynamics, such as, complex dynamics modeling and estimation, in order to better characterize patients’ reactions to drugs, as well as monitoring in presence of uncertainties and critical events. The particular asset being the availability of large open-source data-bases, as well as annotated data from other projects, allowing to better characterize the widely used models, and thereby to achieve an effective and personalized monitoring.