Abstract: Systems, methods, and computer-readable media determine a representative series using multiple time series of glucose readings. Systems may comprise one or more processors (“processing”) and one or more computer-readable data storages (CRDS) storing instructions that, when executed by processing, cause processing to perform steps of the method. Some embodiments include one or more CRDS storing instructions for the methods that may be executed by one or more processors. Methods may comprise one or more processors receiving multiple time series in which each of the time series comprises glucose readings associated with respective timestamps. The time series may be generated during respective time periods. The one or more processors may adaptively determine a gamma parameter and determine a barycenter using the multiple time series and the gamma parameter. The one or more processors may apply a smoothing function to the barycenter yielding the representative series.

Abstract: There is a need for more effective and efficient predictive data analysis, such as more effective and efficient data analysis solutions for performing predictive monitoring of the glucose-insulin endocrine metabolic regulatory system. Certain embodiments utilize systems, methods, and computer program products that perform predictive data analysis by utilizing at least one of glucose surge excursion detections, steady-state glucose-insulin machine learning models, and parameter space refinement machine learning models.