Optimal medication dosing from suboptimal clinical examples: A deep reinforcement learning approach
- 18 October 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2016, 2978-2981
Abstract
Misdosing medications with sensitive therapeutic windows, such as heparin, can place patients at unnecessary risk, increase length of hospital stay, and lead to wasted hospital resources. In this work, we present a clinician-in-the-loop sequential decision making framework, which provides an individualized dosing policy adapted to each patient's evolving clinical phenotype. We employed retrospective data from the publicly available MIMIC II intensive care unit database, and developed a deep reinforcement learning algorithm that learns an optimal heparin dosing policy from sample dosing trails and their associated outcomes in large electronic medical records. Using separate training and testing datasets, our model was observed to be effective in proposing heparin doses that resulted in better expected outcomes than the clinical guidelines. Our results demonstrate that a sequential modeling approach, learned from retrospective data, could potentially be used at the bedside to derive individualized patient dosing policies.Keywords
This publication has 12 references indexed in Scilit:
- Human-level control through deep reinforcement learningNature, 2015
- A data-driven approach to optimized medication dosing: a focus on heparinIntensive Care Medicine, 2014
- Dynamic Treatment RegimesAnnual Review of Statistics and Its Application, 2014
- The use of reinforcement learning algorithms to meet the challenges of an artificial pancreasExpert Review of Medical Devices, 2013
- A New, Evidence-based Estimate of Patient Harms Associated with Hospital CareJournal of Patient Safety, 2013
- Adverse Effects of Heparin2011
- Achieving a Nationwide Learning Health SystemScience Translational Medicine, 2010
- Neural Fitted Q Iteration – First Experiences with a Data Efficient Neural Reinforcement Learning Method2005
- Q-learningMachine Learning, 1992
- Identification and preliminary validation of predictors of major bleeding in hospitalized patients starting anticoagulant therapyThe American Journal of Medicine, 1987