US 10,891,053 B2
Predicting glucose trends for population management
Hugh H. Ryan, Lee's Summit, MO (US); Megan Kathleen Quick, Kansas City, MO (US); and Daniel Craig Crough, Overland Park, KS (US)
Assigned to CERNER INNOVATION, INC, Kansas City, KS (US)
Filed by CERNER INNOVATION, INC., Kansas City, KS (US)
Filed on Sep. 13, 2018, as Appl. No. 16/130,793.
Application 16/130,793 is a continuation of application No. 14/581,052, filed on Dec. 23, 2014, granted, now 10,120,979.
Prior Publication US 2019/0026023 A1, Jan. 24, 2019
Int. Cl. G06F 3/06 (2006.01); G16H 50/20 (2018.01); G06F 19/00 (2018.01)
CPC G06F 3/061 (2013.01) [G06F 3/0635 (2013.01); G06F 3/0659 (2013.01); G06F 3/0685 (2013.01); G06F 19/00 (2013.01); G16H 50/20 (2018.01)] 20 Claims
OG exemplary drawing
 
1. One or more computer storage media storing computer-useable instructions, the instructions when executed by one or more computing devices, cause the one or more computing devices to perform operations comprising:
receiving, by an integrated home device associated with a patient, one or more interventions based on a determined real-time prediction, wherein the determined real-time prediction is based on analysis of a first set of glucose data corresponding to the patient by a predictive model trained by a second set of glucose data from a plurality of sources including electronic medical records associated with a plurality of patients, the determined real-time prediction indicating whether the patient is likely to have blood glucose levels corresponding to a predetermined threshold; and
automatically adjusting a frequency or dosage of medication dispensed by the integrated home device associated with the patient based on the received one or more interventions,
wherein training the predictive model includes logistic regression analysis of a plurality of data elements associated with the plurality of patients that are relevant to forecasting blood glucose levels, the plurality of data elements comprising at least one of medication data, clinical event data, surgical data, or demographic data, and wherein the first set of glucose data and the second set of glucose data includes blood glucose values and values for each of the plurality of data elements identified by the logistic regression analysis as relevant to forecasting blood glucose levels.