Patients with T1DM require long-term exogenous insulin therapy to regulate blood glucose levels and prevent the long-term complications of the disease.
Currently, there are no effective algorithms that consider the unique characteristics of T1DM patients to automatically recommend personalized insulin dosage levels.
On the basis of the result of a treatment action at time step t, the RL agent receives a numeric reward, positive or negative.
The reward is calculated as a function of the difference between the actual blood glucose level achieved in response to the insulin dose and the targeted Hb A1c level.
JMIR Diabetes focuses on technologies, medical devices, apps, engineering, informatics and patient education for diabetes prevention, self-management, care, and cure, to help people with diabetes.
As open access journal JD is read by clinicians and patients alike and have (as all JMIR journals) a focus on readable and applied science reporting the design and evaluation of health innovations and emerging technologies, as well as on diabetes prevention and epidemiology.
Diabetes is caused due to the lack of production of Insulin by the pancreas or due to the cells of the body not responding properly towards the insulin produced.
IOD journal publishes a variety of contributions, including original articles, focused reviews and rapid communications that include brief articles of particular interest and apparent novelty.
Methods: This research presents a model-free data-driven RL algorithm, namely Q-learning, that recommends insulin doses to regulate the blood glucose level of a T1DM patient, considering his or her state defined by glycated hemoglobin (Hb A1c) levels, body mass index, engagement in physical activity, and alcohol usage.
In this approach, the RL agent identifies the different states of the patient by exploring the patient’s responses when he or she is subjected to varying insulin doses.