Dexcom, Inc. - Glucose Prediction Method Patent Application EP4664486A3

ChangeBridge: EPO Bulletin - Health Informatics (G16H)

Published March 18th, 2026

Detected March 23rd, 2026

Summary

The European Patent Office has published patent application EP4664486A3 by Dexcom, Inc. for a method of predicting future blood glucose concentrations using individualized linear black box models. The application details a technique involving estimating impulse response functions within a Reproducing Kernel Hilbert Space and applying linear prediction.

View original document View source feed page

What changed

European patent application EP4664486A3, filed by Dexcom, Inc., describes a novel method for predicting future blood glucose concentrations. The method involves creating an individualized linear black box model of glucose-insulin dynamics by estimating impulse response functions within a Reproducing Kernel Hilbert Space (RKHS). This model is then used with a linear predicting technique to forecast future glucose levels.

This publication represents a new patent application and does not impose immediate compliance obligations. However, companies in the health informatics and medical device sectors, particularly those involved in glucose monitoring and diabetes management, should be aware of this technological development. The application is designated for several European states, indicating potential future market relevance.

Source document (simplified)

← EPO Patent Bulletin

NONPARAMETRIC GLUCOSE PREDICTORS

Search Report EP4664486A3 Kind: A3 Mar 18, 2026

Applicants

Dexcom, Inc.

Inventors

DEL FAVERO, Simone, FACCHINETTI, Andrea, FACCIOLI, Simone, PILLONETTO, Gianluigi, SPARACINO, Giovanni

Abstract

A method of predicting future blood glucose concentrations of an individual patient includes: identifying an individualized linear black box model of glucose-insulin by estimating a plurality of impulse response functions each accounting for an input-output relation of a plurality of individualized patient data sets, the impulse response functions being functions in a Reproducing Kernel Hilbert Space (RKHS); and applying a linear predicting technique to the selected model using the identified impulse response functions to obtain a predicted blood glucose concentration of the individual patient at a future time.

IPC Classifications

G16H 50/20 20180101AFI20260206BHEP G16H 50/50 20180101ALI20260206BHEP

Designated States

AL, AT, BE, BG, CH, CY, CZ, DE, DK, EE, ES, FI, FR, GB, GR, HR, HU, IE, IS, IT, LI, LT, LU, LV, MC, MK, MT, NL, NO, PL, PT, RO, RS, SE, SI, SK, SM, TR

View original document →