During the COVID-19 outbreak, one-size-fits-all treatments have been demonstrably ineffective in terms of both patient outcomes and use of limited resources. By quickly analyzing data, AI-based models help to save lives. They can mediate and accelerate the development of management and treatment plans that are personalized for each patient, depending on their unique characteristics and needs, including the best policies for employing mechanical ventilation and/or experimental treatments. Dynamic Machine Learning modelling can predict the evolution of a patient’s health state over time during hospitalization and medical care, allowing the efficient deployment of resources.