Peter Ajemba

20220189630, Jun 16, 2022

Dec 14, 2020

17/121624

- Northridge CA, US
JEFFREY NISHIDA - Chicago IL, US
PETER AJEMBA - Canyon Country CA, US
KEITH NOGUEIRA - Mission Hills CA, US
ANDREA VARSAVSKY - Santa Monica CA, US

G16H 50/20
G06N 20/00
G16H 40/63

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.

20220189631, Jun 16, 2022

Jan 29, 2021

17/163186

- Northridge CA, US
JEFFREY NISHIDA - Chicago IL, US
PETER AJEMBA - Canyon Country CA, US
KEITH NOGUEIRA - Mission Hills CA, US
ANDREA VARSAVSKY - Santa Monica CA, US

G16H 50/20
G06N 20/00
G16H 40/63

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.

20230110585, Apr 13, 2023

Dec 14, 2022

18/066212

- Northridge CA, US
Peter Ajemba - Canyon Country CA, US
Akhil Srinivasan - Woodland Hills CA, US
Jacob E. Pananen - Agoura Hills CA, US
Sarkis Aroyan - Northridge CA, US
Pablo Vazquez - Porter Ranch CA, US
Tri T. Dang - Winnetka CA, US
Ashley N. Sullivan - Canton MA, US
Raghavendhar Gautham - Northridge CA, US

A61M 5/172
A61B 5/145
A61M 5/142
A61B 5/1495

Techniques disclosed herein relate to determining a calibrated measurement value indicative of a physiological condition of a patient using sensor calibration data and a performance model. In some embodiments, the techniques involve obtaining one or more electrical signals from a sensing element of a sensing arrangement, where the one or more electrical signals are influenced by a physiological condition in a body of a patient. The techniques also involve obtaining calibration data associated with the sensing element from a data storage element of the sensing arrangement, converting the one or more electrical signals into one or more calibrated measurement parameters using the calibration data, obtaining a performance model associated with the sensing element, obtaining personal data associated with the patient, and determining, using the performance model and based on the personal data and the one or more calibrated measurement parameters, a calibrated output value indicative of the physiological condition.

20210077717, Mar 18, 2021

Sep 12, 2019

16/569401

- Northridge CA, US
Peter Ajemba - Canyon Country CA, US
Steven C. Jacks - Culver City CA, US
Robert C. Mucic - Glendale CA, US
Tyler R. Wong - Pasadena CA, US
Melissa Tsang - Sherman Oaks CA, US
Chi-En Lin - Van Nuys CA, US
Mohsen Askarinya - Chandler AZ, US
David Probst - Chandler AZ, US

A61M 5/172
A61B 5/145
A61M 5/142
A61B 5/1495

Medical devices and related systems and methods are provided. A method of calibrating an instance of a sensing element involves obtaining fabrication process measurement data from a substrate having the instance of the sensing element fabricated thereon, obtaining a calibration model associated with the sensing element, determining calibration data associated with the instance of the sensing element for converting the electrical signals into a calibrated measurement parameter based on the fabrication process measurement data using the calibration model, and storing the calibration data in a data storage element associated with the instance of the sensing element.

20210077718, Mar 18, 2021

Sep 12, 2019

16/569417

- Northridge CA, US
Peter Ajemba - Canyon Country CA, US
Akhil Srinivasan - Pacific Palisades CA, US
Jacob E. Pananen - Santa Monica CA, US
Sarkis Aroyan - Northridge CA, US
Pablo Vazquez - Porter Ranch CA, US
Tri T. Dang - Winnetka CA, US
Ashley N. Sullivan - Canton MA, US
Raghavendhar Gautham - Northridge CA, US

A61M 5/172
A61B 5/145
A61M 5/142
A61B 5/1495

Medical devices, systems and methods are provided. One method involves obtaining fabrication process measurement data for a plurality of instances of a sensing element, obtaining reference output measurement data from the plurality of instances in response to a reference stimulus, determining a predictive model for a measurement output of the sensing element as a function of fabrication process measurement variables based on the relationship between the fabrication process measurement data and the reference output measurement data, generating a simulated output measurement distribution across a range of the fabrication process measurement variables using the predictive model, identifying performance thresholds for the measurement output based on the simulated output measurement distribution, obtaining output measurement data from the instance of the sensing element in response to the reference stimulus, and verifying the output measurement data satisfies the performance threshold prior to calibrating a subsequent instance of the sensing element.

20200245910, Aug 6, 2020

Jan 27, 2020

16/773422

- Northridge CA, US
Andrea Varsavsky - Santa Monica CA, US
Peter Ajemba - Canyon Country CA, US
Jeffrey Nishida - Chicago IL, US
Keith Nogueira - Mission Hills CA, US
Elaine Gee - Windsor CA, US
Jing Liu - Woodland Hills CA, US
Sadaf S. Seleh - Encino CA, US
Taly G, Engel - Los Angeles CA, US
Benyamin Grosman - Valley Village CA, US
Steven Lai - Granada Hills CA, US
Luis A. Torres - South Gate CA, US
Chi A. Tran - Falcon Heights MN, US
David M. Sniecinski - Los Angeles CA, US

A61B 5/145
A61B 5/1468

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.

20190175079, Jun 13, 2019

Dec 13, 2017

15/840515

- Northridge CA, US
Andrea Varsavsky - Santa Monica CA, US
Taly G. Engel - Los Angeles CA, US
Keith Nogueira - Mission Hills CA, US
Andy Y. Tsai - Pasadena CA, US
Peter Ajemba - Canyon Country CA, US

A61B 5/1495
A61B 5/145
A61B 5/1473
A61B 5/00

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.

20190175080, Jun 13, 2019

Dec 13, 2017

15/840673

- Northridge CA, US
Jeffrey Nishida - Los Angeles CA, US
Taly G. Engel - Los Angeles CA, US
Keith Nogueira - Mission Hills CA, US
Andy Y. Tsai - Pasadena CA, US
Peter Ajemba - Canyon Country CA, US

A61B 5/1495
A61B 5/145
A61B 5/1473
A61B 5/00
A61M 5/142
A61M 5/172

A continuous glucose monitoring system may employ complex redundancy to take operational advantage of disparate characteristics of two or more dissimilar, or non-identical, sensors, including, e.g., characteristics relating to hydration, stabilization, and durability of such sensors. Fusion algorithms, Electrochemical Impedance Spectroscopy (EIS), and advanced Application Specific Integrated Circuits (ASICs) may be used to implement use of such redundant glucose sensors, devices, and sensor systems in such a way as to bridge the gaps between fast start-up, sensor longevity, and accuracy of calibration-free algorithms. Systems, devices, and algorithms are described for achieving a long-wear and reliable sensor which also minimizes, or eliminates, the need for BG calibration, thereby providing a calibration-free, or near calibration-free, sensor.