Encouraging Physical Activity in Diabetes Patients Through Automatic Personalized Feedback Via Reinforcement Learning Improves Glycemic Control

Despite the clear benefit of regular physical activity, most patients with diabetes type 2 are sedentary. We provided 27 sedentary diabetes type 2 patients with a smartphone-based pedometer and a personal plan for physical activity. Patients were sent SMS messages to encourage physical activity between once a day to once a week. Messages were personalized through a Reinforcement Learning algorithm which optimized messages to improve each participant’s compliance with the activity regimen. The reinforcement learning algorithm was compared to a static policy for sending messages and to weekly reminders.

Our results show that participants who received messages generated by the learning algorithm increased the amount of activity and pace of walking, while the control group patients did not. Patients assigned to the reinforcement learning algorithm group experienced a superior reduction in blood glucose levels (HbA1c). The learning algorithm improved gradually in predicting which messages would lead participants to exercise.

Our results suggest that a mobile phone application coupled with a learning algorithm can improve adherence to exercise in diabetic patients. As a learning algorithm is automated, and delivers personalized messages, it could be used in large populations of diabetic patients to improve health and glycemic control. Our results can be expanded to other areas where computer-led health coaching of humans may have a positive impact.