US 12,243,651 B2
Systems and methods for automatically displaying patterns in biological monitoring data
David L. Duke, Fishers, IN (US); Paul J. Galley, Cumberland, IN (US); Abhishek S Soni, Indianapolis, IN (US); Mark Mears, Westfield, IN (US); and Steven Bousamra, Carmel, IN (US)
Assigned to Roche Diabetes Care, Inc., Indianapolis, IN (US)
Filed by Roche Diabetes Care, Inc., Indianapolis, IN (US)
Filed on Jun. 7, 2013, as Appl. No. 13/912,318.
Prior Publication US 2014/0365136 A1, Dec. 11, 2014
Int. Cl. G16H 50/70 (2018.01); G16H 40/63 (2018.01); G16Z 99/00 (2019.01)
CPC G16H 50/70 (2018.01) [G16H 40/63 (2018.01); G16Z 99/00 (2019.02)] 21 Claims
 
1. A collection system for automatically displaying patterns in glucose data of one or more patients, the collection system comprising:
one or more processors;
an electronic display communicatively coupled to the one or more processors; and
machine readable instructions that are executed by the one or more processors, wherein the machine readable instructions cause the one or more processors to:
receive a glucose data signal indicative of ambulatory glucose levels sampled over multiple days and determined from a body fluid of the one or more patients via a glucose meter communicatively coupled to the one or more processors;
divide the glucose data signal into segments of interest;
transform, automatically, each of the segments of interest into a set of features according to a mathematical algorithm;
append discrete data to the set of features;
cluster, automatically, the segments of interest into groups of clustered segments according to a clustering algorithm, wherein each group of clustered segments is associated with an importance ranking based on a number of segments in a respective group, wherein the segments of interest are grouped in the groups of clustered segments based at least in part upon the set of features and a cluster center is associated with one of the groups of clustered segments, wherein each cluster center corresponds to a mean of one of the groups of clustered segments and includes a width indicative of the importance ranking and corresponding number of segments in the respective group, and wherein each cluster center width is proportional to the corresponding number of segments in the respective group; and
present, automatically, the cluster center and corresponding width of each one of the groups of clustered segments on the electronic display based on the importance ranking corresponding to the number of segments in the respective group of each cluster center, wherein displayed cluster centers identify information regarding patterns, sub-patterns or behaviors in the glucose data of the one or more patients that otherwise is averaged out or obscured when the ambulatory glucose levels sampled over multiple days are combined into an ambulatory glucose profile or a modal day plot.