公开(公告)号：US20190041345A1

公开(公告)日：2019-02-07

申请号：US16158043

申请日：2018-10-11

Applicant: MEDTRONIC MINIMED, INC.

Inventor： KEITH NOGUEIRA ,  TALY G. ENGEL ,  XIAOLONG LI ,  BRADLEY C. LIANG ,  RAJIV SHAH ,  JAEHO KIM ,  MIKE C. LIU ,  ANDY Y. TSAI ,  ANDREA VARSAVSKY ,  FEI YU

IPC: G01N27/02 ,  G01N27/416 ,  G01N33/49 ,  G01N33/487

Abstract: 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.

公开(公告)号：US20220233108A1

公开(公告)日：2022-07-28

申请号：US17156490

申请日：2021-01-22

Applicant: MEDTRONIC MINIMED, INC.

Inventor： PETER AJEMBA ,  KEITH NOGUEIRA

IPC: A61B5/145 ,  G06N20/00 ,  G16H50/20 ,  G16H40/63 ,  G16H50/30 ,  A61B5/00

Abstract: 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.

公开(公告)号：US20220233109A1

公开(公告)日：2022-07-28

申请号：US17163149

申请日：2021-01-29

Applicant: MEDTRONIC MINIMED, INC.

Inventor： PETER AJEMBA ,  KEITH NOGUEIRA

IPC: A61B5/145 ,  A61B5/00 ,  G06N20/20

Abstract: 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.

公开(公告)号：US20220189630A1

公开(公告)日：2022-06-16

申请号：US17121624

申请日：2020-12-14

Applicant: MEDTRONIC MINIMED, INC.

Inventor： ELAINE GEE ,  JEFFREY NISHIDA ,  PETER AJEMBA ,  KEITH NOGUEIRA ,  ANDREA VARSAVSKY

IPC: G16H50/20 ,  G06N20/00 ,  G16H40/63

Abstract: Methods, systems, and devices for improving continuous glucose monitoring (“CGM”) are described herein. More particularly, the methods, systems, and devices describe retrieving a machine learning model that is trained to classify CGM sensor data and blanking the CGM sensor data based on an outlier classification from the machine learning model. The system may terminate sensors for which there is an aggregation of blanked CGM sensor data. The methods, systems, and devices described herein may additionally comprise a machine learning model that is trained to detect and correct for erroneous sensor use conditions based on error patterns in sensor data. The system may determine resolutions for correcting the detected erroneous sensor use conditions.

公开(公告)号：US20220245306A1

公开(公告)日：2022-08-04

申请号：US17163233

申请日：2021-01-29

Applicant: MEDTRONIC MINIMED, INC.

Inventor： PETER AJEMBA ,  KEITH NOGUEIRA

IPC: G06F30/27 ,  G16H50/50 ,  G16H10/40 ,  G16H50/20

Abstract: 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.

公开(公告)号：US20220240818A1

公开(公告)日：2022-08-04

申请号：US17163273

申请日：2021-01-29

Applicant: MEDTRONIC MINIMED, INC.

Inventor： PETER AJEMBA ,  KEITH NOGUEIRA

IPC: A61B5/145 ,  G06K9/62 ,  G06F1/16 ,  G16H10/60

Abstract: 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.

公开(公告)号：US20220189631A1

公开(公告)日：2022-06-16

申请号：US17163186

申请日：2021-01-29

Applicant: MEDTRONIC MINIMED, INC.

Inventor： ELAINE GEE ,  JEFFREY NISHIDA ,  PETER AJEMBA ,  KEITH NOGUEIRA ,  ANDREA VARSAVSKY

IPC: G16H50/20 ,  G06N20/00 ,  G16H40/63

Abstract: Methods, systems, and devices for improving continuous glucose monitoring (“CGM”) are described herein. More particularly, the methods, systems, and devices describe retrieving a machine learning model that is trained to classify CGM sensor data and blanking the CGM sensor data based on an outlier classification from the machine learning model. The system may terminate sensors for which there is an aggregation of blanked CGM sensor data. The methods, systems, and devices described herein may additionally comprise a machine learning model that is trained to detect and correct for erroneous sensor use conditions based on error patterns in sensor data. The system may determine resolutions for correcting the detected erroneous sensor use conditions.