AI for Health

🇬🇧 Machine learning for predictive analytics and decision support in the intensive care unit

Nov 17 15:55 - 16:20

Présentée par


Resuscitation and critical care have always been seen as a typical application of curative medicine. Patients must have symptoms and signs of severity to be admitted to resuscitation. However, at this stage, some damage is already established and it becomes complicated to reverse it. This probably explains the plateau observed in the evolution of the mortality in intensive care. We propose a change of paradigm in which resuscitation would integrate a preventive aspect in order to act upstream of these damages. To do this, we must have tools that allow us to predict a certain number of critical events in order to prevent them and improve the prognosis of our patients.