Processing irregular glucose data using dynamic time warping

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.