公开(公告)号：US20240358289A1

公开(公告)日：2024-10-31

申请号：US18647671

申请日：2024-04-26

Applicant: Dexcom, Inc.

Inventor： Subhan M. KHAN ,  Jonathan M. HUGHES ,  Arunachalam PANCH SANTHANAM ,  Arturo GARCIA ,  Liang WANG ,  Yuxi ZHANG ,  Jason R. CALABRESE

IPC: A61B5/145 ,  A61B5/00

CPC classification number: A61B5/14546 ,  A61B5/14532 ,  A61B5/742

Abstract: Overlapping data streams and sensor transitions is described. In accordance with the described techniques, a first data stream of first analyte measurements is received, at a computing device and during an overlap period, from a first analyte sensor worn by a user and a second data stream of second analyte measurements is received, at the computing device and during the overlap period, from a second analyte sensor worn by the user. The first data stream and the second data stream are received concurrently during the overlap period. A combined analyte measurement is generated based on the first analyte measurements and the second analyte measurements. In one or more implementations, the combined analyte measurement is generated as a weighted average of the first analyte measurements and the second analyte measurements. The combined analyte measurement is then output on a display of the computing device.

公开(公告)号：US20240407734A1

公开(公告)日：2024-12-12

申请号：US18737588

申请日：2024-06-07

Applicant: Dexcom, Inc.

Inventor： Jee Hye PARK ,  Spencer Troy FRANK ,  David A. PRICE ,  Charles R. STROYECK ,  Arunachalam PANCH SANTHANAM ,  Joseph J. BAKER ,  Peter C. SIMPSON ,  Kazanna C. HAMES ,  Qi AN ,  Abdulrahman JBAILY ,  Justin Yi-Kai LEE ,  Stephanie Grace MOORE

IPC: A61B5/00 ,  A61B5/145 ,  G16H50/20

Abstract: A method for predicting disease is provided. The method includes generating biased analyte data by adding analyte sensor bias to historical analyte data, associating the biased analyte data with clinical disease diagnoses associated with the historical analyte data, and extracting features from the biased analyte data. The method further includes, for each model of a number of models, generating disease predictions based on different combinations of the features extracted from the biased analyte data, and evaluating the disease predictions based on the clinical disease diagnoses associated with the biased analyte data. The method further includes selecting a model and a combination of features based on a performance metric and a robustness metric.