Model Based Reinforcement Learning for Personalized Heparin Dosing
This work addresses the challenge of safe and personalized heparin dosing for patients in medical settings, representing an incremental improvement by applying known model-based methods to a specific domain.
The paper tackles the problem of optimizing personalized heparin dosing under partial information about both patient states and dynamics, proposing a model-based reinforcement learning framework that uses patient-specific predictive models and scenario generation to ensure safety, and validates it with numerical experiments showing predictive capabilities and simulated ICU treatment.
A key challenge in sequential decision making is optimizing systems safely under partial information. While much of the literature has focused on the cases of either partially known states or partially known dynamics, it is further exacerbated in cases where both states and dynamics are partially known. Computing heparin doses for patients fits this paradigm since the concentration of heparin in the patient cannot be measured directly and the rates at which patients metabolize heparin vary greatly between individuals. While many proposed solutions are model free, they require complex models and have difficulty ensuring safety. However, if some of the structure of the dynamics is known, a model based approach can be leveraged to provide safe policies. In this paper we propose such a framework to address the challenge of optimizing personalized heparin doses. We use a predictive model parameterized individually by patient to predict future therapeutic effects. We then leverage this model using a scenario generation based approach that is capable of ensuring patient safety. We validate our models with numerical experiments by comparing the predictive capabilities of our model against existing machine learning techniques and demonstrating how our dosing algorithm can treat patients in a simulated ICU environment.