US 12,426,811 B2
Detection of changes in patient health based on glucose data
Kamal Deep Mothilal, Maple Grove, MN (US); Michael D. Eggen, Chisago City, MN (US); Ning Yu, Columbia Heights, MN (US); John P Keane, Shoreview, MN (US); Shantanu Sarkar, Roseville, MN (US); Randal C. Schulhauser, Phoenix, AZ (US); David L. Probst, Chandler, AZ (US); Mark R. Boone, Gilbert, AZ (US); Kenneth A Timmerman, Robbinsdale, MN (US); Stanley J Taraszewski, Plymouth, MN (US); Matthew A Joyce, Maple Grove, MN (US); Amruta Paritosh Dixit, Maple Grove, MN (US); Kathryn E. Hilpisch, Cottage Grove, MN (US); Kathryn Ann Milbrandt, Ham Lake, MN (US); Laura M Zimmerman, Maple Grove, MN (US); and Matthew L Plante, Danbury, WI (US)
Assigned to Medtronic, Inc., Minneapolis, MN (US)
Filed by Medtronic, Inc., Minneapolis, MN (US)
Filed on May 16, 2022, as Appl. No. 17/663,657.
Claims priority of provisional application 63/191,201, filed on May 20, 2021.
Prior Publication US 2022/0369961 A1, Nov. 24, 2022
Int. Cl. A61B 5/145 (2006.01); A61B 5/00 (2006.01); A61B 5/0205 (2006.01); G16H 50/20 (2018.01); G16H 50/30 (2018.01)
CPC A61B 5/14532 (2013.01) [A61B 5/0205 (2013.01); A61B 5/14503 (2013.01); A61B 5/7267 (2013.01); A61B 5/7275 (2013.01); A61B 5/7282 (2013.01); G16H 50/20 (2018.01); G16H 50/30 (2018.01)] 24 Claims
OG exemplary drawing
 
1. A method comprising:
extracting at least one feature from continuous glucose sensor measurements of a patient over at least one time period, wherein the at least one feature comprises one or more of an amount of time within a pre-determined glucose level range, a number of hypoglycemia events, or a number of hyperglycemia events;
applying a machine learning model to the at least one extracted feature to produce data indicative of a risk of a cardiovascular event; and
generating an output based on the risk of the cardiovascular event.