Personalized Multimorbidity Management for Patients with Type 2 Diabetes Using Reinforcement Learning of Electronic Health Records
This work addresses personalized treatment for patients with type 2 diabetes and multiple chronic conditions, representing an incremental advance in applying AI to healthcare.
The researchers tackled personalized management of type 2 diabetes and comorbidities by developing a reinforcement learning algorithm using electronic health records, which demonstrated high concordance with clinician prescriptions and substantial improvements in health outcomes such as glycemia, blood pressure, and cardiovascular disease risk.
Comorbid chronic conditions are common among people with type 2 diabetes. We developed an Artificial Intelligence algorithm, based on Reinforcement Learning (RL), for personalized diabetes and multi-morbidity management with strong potential to improve health outcomes relative to current clinical practice. In this paper, we modeled glycemia, blood pressure and cardiovascular disease (CVD) risk as health outcomes using a retrospective cohort of 16,665 patients with type 2 diabetes from New York University Langone Health ambulatory care electronic health records in 2009 to 2017. We trained a RL prescription algorithm that recommends a treatment regimen optimizing patients' cumulative health outcomes using their individual characteristics and medical history at each encounter. The RL recommendations were evaluated on an independent subset of patients. The results demonstrate that the proposed personalized reinforcement learning prescriptive framework for type 2 diabetes yielded high concordance with clinicians' prescriptions and substantial improvements in glycemia, blood pressure, cardiovascular disease risk outcomes.