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

By Matthieu Komorowski, Leo Anthony Celi, O. Badawi, A. Gordon, Aldo A. Faisal. 2018

1,233 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Epidemiology, Health Informatics, Reinforcement Learning, Medical & Health AI

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Epidemiology

In Health Informatics

In Reinforcement Learning

In Medical & Health AI

Citations in the corpus

Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges (2021, background): “, 2017), treatment of sepsis (Komorowski et al., 2018), treatment of chronic disorders including epilepsy (Guez et al.”
Counterfactual Off-Policy Evaluation with Gumbel-Max Structural Causal Models (2019, methodology): “We give an illustrative example of this use case here, motivated by recent work examining the use of RL algorithms for treating sepsis among intensivecare unit (ICU) patients (Komorowski et al., 2018).”
Sepsis-induced immunosuppression: mechanisms, diagnosis and current treatment options (2022, methodology): “Rol ML, Venet F, Rimmele T, Moucadel V, Cortez P, Quemeneur L, et al. The REAnimation Low Immune Status Markers (REALISM) project: a protocol for broad characterisation and follow‑up of injury‑induced immunosuppression in intensive care unit (ICU) critically ill patients.”
Deep Reinforcement Learning for Closed-Loop Blood Glucose Control (2020, methodology): “In our experiments, we use the UVA/Padova model (Kovatchev et al., 2009). This simulator models the glucoregulatory system as a nonlinear multi-compartment system, where glucose is generated in the liver, absorbed through the gut, and controlled by external insulin. A more detailed explanation can b”
POPCORN: Partially Observed Prediction COnstrained ReiNforcement Learning (2020, methodology): “…implementation of POPCORN can be found online at https://github.com/dtak/POPCORN-POMDP, along with code to reproduce our experiments. sepsis (Komorowski et al., 2018; Raghu et al., 2017), mechanical ventilation (Prasad et al., 2017), HIV (Ernst et al., 2006), and dialysis (Martín-Guerrero…”
High-performance medicine: the convergence of human and artificial intelligence (2019, background): “Of the more than $3.5 trillion per year (and rising) expenditures for healthcare in the United States, almost a third is related to hospitals.”
Shifting machine learning for healthcare from development to deployment and from models to data (2022, methodology): “NLP has enabled the automated translation of doctor–patient interactions to notes 5,104,105 , the summarization of clinical notes 106 , the captioning of medical images 107,108 and the prediction of disease progression 6,7 .”
Interpretable Off-Policy Evaluation in Reinforcement Learning by Highlighting Influential Transitions (2020, methodology): “To construct vasopressors, we ﬁrst normalize vasopressor infusion rates across different drug types as follows, using the same normalization as in Komorowski et al. (2018): 1.”