Abstract: There is provided apparatus for controlling the delivery of insulin to a subject. The apparatus comprises a first input (18) for receiving neural information from the subject indicative of prospective or actual food and/or drink intake and a second input (15) for receiving a signal indicative of the subject's blood glucose level (BG). The apparatus further comprises a processor or processors (10) configured to determine food and/or drink characteristics based on the received neural information and to determine an amount of insulin to be delivered based on the measured blood glucose levels (BG) and the determined food and/or drink characteristics, and an output for providing an insulin pump control signal (12) indicative of the determined amount of insulin.

Abstract: A method of adaptively determining one or more compensation factors in a closed-loop insulin delivery system comprising a continuous glucose level sensor, an insulin pump, and an insulin reservoir, where the system determines an insulin meal bolus taking into account an estimated amount of carbohydrates to be ingested, CHO, a difference between a currently sensed glucose level, G, and a glucose set point, Gsp, and at least one compensation factor, ICR.

Abstract: The present disclosure relates to the prediction of physiological parameters, such as glucose levels. A training input is received, the training input comprising time-series values of a physiological parameter and time-series values of one or more further parameters. Training examples are generated form the training input, wherein each training example comprises a training dataset and a corresponding training label, wherein each training dataset is generated from the training input with time-series values restricted to a time interval, and wherein each corresponding training label represents the value of the physiological parameter a prediction period after the end of that time interval. A neural network is then trained using the training examples.

Abstract: A method of adaptively determining one or more compensation factors in a closed-loop insulin delivery system comprising a continuous glucose level sensor, an insulin pump, and an insulin reservoir, where the system determines an insulin meal bolus taking into account an estimated amount of carbohydrates to be ingested, CHO, a difference between a currently sensed glucose level, G, and a glucose set point, Gsp, and at least one compensation factor, ICR.

Abstract: The present invention relates to a controller unit and methods for controlling an insulin pump. The controller unit includes a user input that receives a gain factor. The gain factor has been calculated based on historical data in relation to a patient. The controller unit includes a measurement input for receiving data representative of a measured blood glucose level for the patient. Processing logic of the controller unit is configured to apply the measured blood glucose level to a pancreatic beta-cell insulin secretion computational model to predict an insulin output level, apply the gain factor to the predicted insulin output level to determine a patient insulin deficiency level, and calculate a control signal for controlling the insulin output level of the insulin pump based on the patient insulin deficiency level. Methods are provided for optimizing the gain factor based on the historical data in relation to the patient.

Abstract: The present invention relates to a controller unit and methods for controlling an insulin pump. The controller unit includes a user input that receives a gain factor. The gain factor has been calculated based on historical data in relation to a patient. The controller unit includes a measurement input for receiving data representative of a measured blood glucose level for the patient. Processing logic of the controller unit is configured to apply the measured blood glucose level to a pancreatic beta-cell insulin secretion computational model to predict an insulin output level, apply the gain factor to the predicted insulin output level to determine a patient insulin deficiency level, and calculate a control signal for controlling the insulin output level of the insulin pump based on the patient insulin deficiency level. Methods are provided for optimising the gain factor based on the historical data in relation to the patient.