Medtronic Minimed, Inc.

Keith Nogueira

Peter Ajemba

Jeffrey Nishida

Andrea Varsavsky

Andy Y Tsai

Bradley Chi Liang

Xiaolong Li

Rajiv Shah

Taly G Engel

Brian T Kannard

Mike C Liu

Jaeho Kim

Yunfeng Lu

Michael E Miller

Rebecca K Gottlieb

Ning Yang

Steven C Jacks

Elaine Gee

Yuxiang Zhong

Raghavendhar Gautham

Pratik J Agrawal

Bahman Engheta

Benyamin Grosman

Kenneth W Cooper

Fei Yu

Luis A Torres

Steven Lai

Sadaf S Seleh

Chi A Tran

Leonardo Nava-Guerra

Georgios Mallas

Jing Liu

David M Sniecinski

Methods, systems, and devices for modeling a relationship between glucose sensitivity and a sensor electrical property are described herein. More particularly, the methods, systems, and devices describe partitioning an input signal feature space relating glucose sensitivity and a sensor electrical property into subspaces and training a model for each subspace. For example, the subspace models may form a mosaic of models, for which the output is more accurate than a single model.

Model mosaic framework for modeling glucose sensitivity

A continuous glucose monitoring system may utilize externally sourced information regarding the physiological state and ambient environment of its user for externally calibrating sensor glucose measurements. Externally sourced factory calibration information may be utilized, where the information is generated by comparing metrics obtained from the data used to generate the sensor's glucose sensing algorithm to similar data obtained from each batch of sensors to be used with the algorithm in the future. The output sensor glucose value of a glucose sensor may also be estimated by analytically optimizing input sensor signals to accurately correct for changes in sensitivity, run-in time, glucose current dips, and other variable sensor wear effects. Correction actors, fusion algorithms, EIS, and advanced ASICs may be used to implement the foregoing, thereby achieving the goal of improved accuracy and reliability without the need for blood-glucose calibration, and providing a calibration-free, or near calibration-free, sensor.

Methods, systems, and devices for calibration and optimization of glucose sensors and sensor output

A method for optional external calibration of a calibration-free glucose sensor uses values of measured working electrode current (Isig) and EIS data to calculate a final sensor glucose (SG) value. Counter electrode voltage (Vcntr) may also be used as an input. Raw Isig and Vcntr values may be preprocessed, and low-pass filtering, averaging, and/or feature generation may be applied. SG values may be generated using one or more models for predicting SG calculations. When an external blood glucose (BG) value is available, the BG value may also be used in calculating the SG values. A SG variance estimate may be calculated for each predicted SG value and modulated, with the modulated SG values then fused to generate a fused SG. A Kalman filter, as well as error detection logic, may be applied to the fused SG value to obtain a final SG, which is then displayed to the user.

Optional sensor calibration in continuous glucose monitoring

Methods, systems, and devices for improving continuous glucose monitoring ('CGM') are described herein. More particularly, the methods, systems, and devices describe applying micro machine learning models to generate predicted sensor glucose values. The system may use the predicted sensor glucose values to display a sensor glucose value to a user. The layered models may generate more reliable sensor glucose predictions across many scenarios, leading to a reduction of sensor glucose signal blanking. The methods, systems, and devices described herein further comprise applying a plurality of micro model to estimate sensor glucose values under outlier conditions. The system may prioritize the models that are trained for certain outlier conditions when the system detects those outlier condition based on the sensor data.

Micro models and layered prediction models for estimating sensor glucose values and reducing sensor glucose signal blanking

Methods, systems, and devices for improving continuous glucose monitoring ('CGM') are described herein. More particularly, the methods, systems, and devices describe applying layered machine learning models to generate predicted sensor glucose values. The system may use the predicted sensor glucose values to display a sensor glucose value to a user. The layered models may generate more reliable sensor glucose predictions across many scenarios, leading to a reduction of sensor glucose signal blanking. The methods, systems, and devices described herein further comprise applying a plurality of micro model to estimate sensor glucose values under outlier conditions. The system may prioritize the models that are trained for certain outlier conditions when the system detects those outlier condition based on the sensor data.

Medical devices and related systems and methods are provided. A method of estimating a physiological condition using a first sensing arrangement involves obtaining a sensor translation model associated with a relationship between the first sensing arrangement and a second sensing arrangement, wherein the second sensing arrangement is different from the first sensing arrangement, obtaining one or more measurements from a sensing element coupled to the processing system of the first sensing arrangement, determining simulated measurement data for the second sensing arrangement by applying the sensor translation model to the one or more measurements from the sensing element of the first sensing arrangement, and determining an estimated value for the physiological condition by applying an estimation model associated with the second sensing arrangement to the simulated measurement data.

Methods and systems for real-time sensor measurement simulation

A continuous glucose monitoring system may utilize electrode current (Isig) signals, Electrochemical Impedance Spectroscopy (EIS), and Vcntr values to optimize sensor glucose (SG) calculation in such a way as to enable reduction of the need for blood glucose (BG) calibration requests from users.

Methods, systems, and devices for continuous glucose monitoring

Electrochemical impedance spectroscopy (EIS) may be used in conjunction with continuous glucose monitoring (CGM) to enable identification of valid and reliable sensor data, as well implementation of Smart Calibration algorithms.

Sensor systems, devices, and methods for continuous glucose monitoring

A processor-implemented method comprises obtaining current operational context information associated with a sensing device; obtaining an expected calibration factor parameter model associated with a patient; calculating an expected calibration factor value based on the expected calibration factor parameter model and the current operational context information; obtaining one or more electrical signals from the sensing device, the one or more electrical signals having a signal characteristic indicative of a physiological condition; converting the one or more electrical signals into a calibrated measurement value for the physiological condition using the expected calibration factor value; and outputting the calibrated measurement value for the physiological condition.

Personalized parameter modeling methods and related devices and systems

Medical devices and related systems and methods are provided. A method of estimating a physiological condition involves determining a translation model based at least in part on relationships between first measurement data corresponding to instances of a first sensing arrangement and second measurement data corresponding to instances of a second sensing arrangement, obtaining third measurement data associated with the second sensing arrangement, determining simulated measurement data for the first sensing arrangement by applying the translation model to the third measurement data, and determining an estimation model for a physiological condition using the simulated measurement data, wherein the estimation model is applied to subsequent measurement output provided by an instance of the first sensing arrangement to obtain an estimated value for the physiological condition.

Translation modeling methods and systems for simulating sensor measurements

Growing community of inventors

Mission Hills, CA, United States of America

Keith Nogueira