# US 10,765,373 B2 · Real-time denoising and prediction for a continuous glucose monitoring system > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,765,373 B2 - Document ID: US10765373B2 - Status: Granted - Kind: B2 - Application number: 15/583,558 - Filed: 2017-05-01 - Published: 2017-11-02 - Granted: 2020-09-08 - Earliest claimed: 2016-04-29 - Assignees: Senseonics, Incorporated - Applicants: Senseonics, Incorporated - Inventors: Simone Faccioli; Xiaoxiao Chen; Andrew DeHennis - Web page: https://patentgrep.com/patent/US10765373B2 ## CPC - A61B 5/7203: {for noise prevention, reduction or removal} - A61B 5/0004: {characterised by the type of physiological signal transmitted} - A61B 5/0024: {for multiple sensor units attached to the patient, e.g. using a body or personal area network} - A61B 5/0031: {Implanted circuitry} - A61B 5/0071: {by measuring fluorescence emission} - A61B 5/14503: {invasive, e.g. introduced into the body by a catheter or needle or using implanted sensors (A61B5/1459, A61B5/1464, A61B5/1473, A61B5/1482, A61B5/14865 take precedence)} - A61B 5/14532: {for measuring glucose, e.g. by tissue impedance measurement} - A61B 5/4839: {combined with drug delivery} - A61B 5/7246: {using correlation, e.g. template matching or determination of similarity} - A61B 5/725: {using specific filters therefor, e.g. Kalman or adaptive filters (specific diagnostics methods using using bioelectric or biomagnetic signals A61B5/316)} - A61B 5/7264: {Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems} - A61B 5/7275: {Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor} - A61B 2560/0219: of externally powered implanted units - A61B 2560/0223: of calibration, e.g. protocols for calibrating sensors - G16H 20/17: delivered via infusion or injection - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA ## Abstract An analyte monitoring system may include an analyte sensor and a transmitter. The analyte sensor may include an indicator element that exhibits one or more detectable properties based on an amount or concentration of an analyte in proximity to the indicator element. The analyte sensor may be configured to generate one or more raw signals indicative of one or more analyte amounts or concentrations. The transmitter may be configured to receive from the analyte sensor one or more raw signals indicative of analyte concentration. The transmitter may be configured to denoise the raw signal using a real-time filtering technique with one or more time-varying parameters. The transmitter may be configured to predict ahead of time an analyte concentration based on one or more of the received one or more raw signals using one or more prediction models. ## Claims ### Claim 1 An analyte monitoring system comprising: an analyte sensor including an analyte indicator that exhibits one or more detectable properties based on an amount or concentration of an analyte in proximity to the analyte indicator, wherein the analyte sensor is configured to generate one or more raw signals indicative of one or more analyte amounts or concentrations; and a transmitter configured to (i) receive from the analyte sensor one or more first raw signals indicative of analyte concentration, (ii) estimate one or more time-varying parameters for a real-time filtering technique at a first time, (iii) denoise the one or more first raw signals using a real-time filtering technique with the one or more time-varying parameters estimated at the first time, (iv) receive from the analyte sensor one or more second raw signals indicative of analyte concentration, (v) estimate the one or more time-varying parameters for the real-time filtering technique at a second time, and (vi) denoise the one or more second raw signals using the real-time filtering technique with the one or more time-varying parameters estimated at the second time; wherein the one or more time-varying parameters include an error variance. ### Claim 2 (depends on 1) The analyte monitoring system of claim 1, wherein the real-time filtering technique includes Kalman filtering. ### Claim 3 (depends on 1) The analyte monitoring system of claim 1, wherein the real-time filtering technique compensates for the presence of one or more missing values in the received one or more raw signals. ### Claim 4 (depends on 1) The analyte monitoring system of claim 1, wherein the one or more time-varying parameters include a parameter λ2, where λ represents a degree to which a slope from a current time window is desired to be close to the slope from a previous time window. ### Claim 5 (depends on 1) The analyte monitoring system of claim 1, wherein the one or more time-varying parameters are estimated day-by-day. ### Claim 6 (depends on 1) The analyte monitoring system of claim 1, wherein the one or more time-varying parameters are estimated only every 144 minutes using the last 6 hours of data. ### Claim 7 (depends on 1) The analyte monitoring system of claim 1, wherein the one or more time-varying parameters are estimated using a stochastically based smoothing criterion that is based on data of a burn-in interval. ### Claim 8 (depends on 1) The analyte monitoring system of claim 1, wherein the transmitter is further configured to predict ahead of time an analyte concentration based on at least one or more of the received one or more first raw signals. ### Claim 9 (depends on 8) The analyte monitoring system of claim 8, wherein the transmitter is configured to use a forgetting factor μ to regulate how the one or more first raw signals are used to predict ahead of time the analyte concentration. ### Claim 10 (depends on 8) The analyte monitoring system of claim 8, wherein the transmitter is configured to predict ahead of time the analyte concentration based on at least the one or more of the received one or more first raw signals using one or more prediction models including a first-order polynomial model. ### Claim 11 (depends on 8) The analyte monitoring system of claim 8, wherein the transmitter is configured to predict ahead of time the analyte concentration based on at least the one or more of the received one or more first raw signals using one or more prediction models including a first-order autoregressive model. ### Claim 12 (depends on 8) The analyte monitoring system of claim 8, wherein the transmitter is configured to predict ahead of time the analyte concentration based on at least the one or more of the received one or more first raw signals using one or more prediction models including Kalman filtering. ### Claim 13 (depends on 8) The analyte monitoring system of claim 8, wherein the transmitter is configured to predict ahead of time the analyte concentration based on at least the one or more of the received one or more first raw signals using one or more prediction models including one or more artificial neural networks. ### Claim 14 An analyte monitoring method comprising: using an analyte sensor to generate one or more raw signals indicative of one or more analyte amounts or concentrations, wherein the analyte sensor includes an analyte indicator that exhibits one or more detectable properties based on an amount or concentration of an analyte in proximity to the analyte indicator; using a transmitter to receive from the analyte sensor one or more first raw signals indicative of analyte concentration; using the transmitter to estimate one or more time-varying parameters for a real-time filtering technique at a first time, wherein the one or more time-varying parameters include an error variance; using the transmitter to denoise the one or more first raw signals using the real-time filtering technique with the one or more time-varying parameters estimated at the first time; using the transmitter to receive from the analyte sensor one or more second raw signals indicative of analyte concentration; using the transmitter to estimate the one or more time-varying parameters for the real-time filtering technique at a second time; and using the transmitter to denoise the one or more second raw signals using the real-time filtering technique with the one or more time-varying parameters estimated at the second time. ### Claim 15 An analyte monitoring system comprising: an analyte sensor including an analyte indicator that exhibits one or more detectable properties based on an amount or concentration of an analyte in proximity to the analyte indicator, wherein the analyte sensor is configured to generate one or more raw signals indicative of one or more analyte amounts or concentrations; and a transmitter configured to (i) receive from the analyte sensor one or more first raw signals indicative of analyte concentration, (ii) estimate one or more time-varying parameters for a real-time filtering technique at a first time, (iii) denoise the one or more first raw signals using the real-time filtering technique with the one or more time-varying parameters estimated at the first time, (iv) receive from the analyte sensor one or more second raw signals indicative of analyte concentration, (v) estimate the one or more time-varying parameters for the real-time filtering technique at a second time, and (vi) denoise the one or more second raw signals using the real-time filtering technique with the one or more time-varying parameters estimated at the second time; wherein the one or more time-varying parameters include a parameter λ2, where λ represents a degree to which a slope from a current time window must be close to the slope from a previous time window. ### Claim 16 An analyte monitoring method comprising: using an analyte sensor to generate one or more raw signals indicative of one or more analyte amounts or concentrations, wherein the analyte sensor includes an analyte indicator that exhibits one or more detectable properties based on an amount or concentration of an analyte in proximity to the analyte indicator; using a transmitter to receive from the analyte sensor one or more first raw signals indicative of analyte concentration; using the transmitter to estimate one or more time-varying parameters for a real-time filtering technique at a first time, wherein the one or more time-varying parameters include a parameter λ2, where λ represents a degree to which a slope from a current time window must be close to the slope from a previous time window; and using the transmitter to denoise the one or more first raw signals using the real-time filtering technique with the one or more estimated time-varying parameters estimated at the first time; using the transmitter to receive from the analyte sensor one or more second raw signals indicative of analyte concentration; using the transmitter to estimate the one or more time-varying parameters for the real-time filtering technique at a second time; and using the transmitter to denoise the one or more second raw signals using the real-time filtering technique with the one or more time-varying parameters estimated at the second time.