Patients with diabetes are often worried about having low blood glucose because of the unpleasant feeling and possible dangerous situations this can lead to. This can make patients consume more carbohydrates than necessary. Ad-hoc carbohydrate estimation and dosing by the patients can be unreliable and may produce unwanted periods of high blood glucose. In this paper we present a system that automatically estimates and dispenses the amount of juice (or similar) according to the current patients' blood glucose values. The system is remotely accessible and customizable from a chatbot, exploits sensors and actuators to dispense the necessary amount of liquid carbohydrates. It relies on a cloud solution (Nightscout) to acquire the patient's blood glucose values, which are constantly updated thanks to a commercial wearable continuous glucose monitor (CGM).
Keywords: Carbohydrates; Cyber-Physical Systems; Diabetes; Hypoglycemia; Internet of Things.