The Artificial Intelligence Clinician learns optimal treatment strategies for sepsis in intensive care

• Published in: Nature medicine Vol. 24; no. 11; pp. 1716 - 1720
• Main Authors: Komorowski, Matthieu, Celi, Leo A., Badawi, Omar, Gordon, Anthony C., Faisal, A. Aldo
• Format: Journal Article
• Language: English
• Published: New York Nature Publishing Group US 01.11.2018; Nature Publishing Group
• Subjects: 631/114/1305; 631/114/2397; 639/166/985; 692/308/409; Administration, Intravenous - adverse effects; Artificial intelligence; Artificial Intelligence - standards; Artificial Intelligence - trends; Biomedical and Life Sciences; Biomedicine; Cancer Research; Clinical Decision-Making; Cohort Studies; Computational fluid dynamics; Critical Care - methods; Decision analysis; Decision making; Decisions; Female; Humans; Infectious Diseases; Intravenous administration; Learning; Male; Metabolic Diseases; Molecular Medicine; Mortality; Neurosciences; Patients; Sepsis; Sepsis - drug therapy; Sepsis - mortality; Sepsis - pathology; Software; Vasoconstrictor Agents - adverse effects; Vasoconstrictor Agents - therapeutic use
• ISSN: 1078-8956; 1546-170X
• DOI: 10.1038/s41591-018-0213-5

Sepsis is the third leading cause of death worldwide and the main cause of mortality in hospitals 1 – 3 , but the best treatment strategy remains uncertain. In particular, evidence suggests that current practices in the administration of intravenous fluids and vasopressors are suboptimal and likely induce harm in a proportion of patients 1 , 4 – 6 . To tackle this sequential decision-making problem, we developed a reinforcement learning agent, the Artificial Intelligence (AI) Clinician, which extracted implicit knowledge from an amount of patient data that exceeds by many-fold the life-time experience of human clinicians and learned optimal treatment by analyzing a myriad of (mostly suboptimal) treatment decisions. We demonstrate that the value of the AI Clinician’s selected treatment is on average reliably higher than human clinicians. In a large validation cohort independent of the training data, mortality was lowest in patients for whom clinicians’ actual doses matched the AI decisions. Our model provides individualized and clinically interpretable treatment decisions for sepsis that could improve patient outcomes. A reinforcement learning agent, the AI Clinician, can assist physicians by providing individualized and clinically interpretable treatment decisions to improve patient outcomes.