Data-enabled learning and control algorithms for intelligent glucose management: The state of the art

External insulin administration is an effective way for patients with diabetes mellitus to regulate their blood glucose. Multiple daily injections (MDIs), sensor-augmented pump (SAP) and artificial pancreas (AP) are widely adopted approaches in insulin therapy. With the increasing popularity of continuous glucose monitoring (CGM) sensors, a large number of data-enabled learning and control algorithms have been developed for MDI, SAP and AP. In this paper, we perform a systemic review concerning the state-of-the-art methodologies that are developed for MDI, SAP and AP with feedback from CGM data or other available data, from a systems and control perspective. The review characterizes the traditional learning and control methods developed for the MDI, SAP and AP, including run-to-run control, proportional–integral–derivative control, fuzzy logic control and model predictive control, as well as the discussions on the roles of machine learning technologies in MDI, SAP and AP. Finally, potential future directions on the algorithm architecture design, a unified control framework for MDI, SAP and AP algorithm design and practical usage of the MDI, SAP and AP are discussed.