Most reinforcement learning studies for sepsis treatment use the MIMIC database.
Reinforcement learning for treatment decision-making in sepsis: a scoping review.
Ziyi Tang et al. · NPJ digital medicine · 2026
Background
This scoping review summarizes the progress of reinforcement learning (RL) in clinical decision-making for sepsis at the intersection of medicine and artificial intelligence (AI).
Methods
All 72 included studies were retrospective, with the majority using the Medical Information Mart for Intensive Care (MIMIC) database (58 studies [80.6%]), and relatively few employing private datasets (10 studies [13.9%]).
n = 58 studies
Results
most reinforcement learning studies for sepsis treatment used the MIMIC database
n = 58 studies
More results
Study designs varied widely, especially in state representation, action space, reward definition, and choice of algorithms.
Most research focused on vasopressor and intravenous fluid management, while fewer studies addressed antibiotics, corticosteroids, mechanical ventilation, heparin, or vasopressin.
“
Conclusion
Ultimately, advancing interpretability, generalizability, and safety will be critical to effectively integrating RL into routine clinical practice.