# US 10,945,674 B2 · Methods, systems, and media for predicting sensor measurement quality

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 10,945,674 B2
- Document ID: US10945674B2
- Status: Granted
- Kind: B2
- Application number: 15/840,467
- Filed: 2017-12-13
- Published: 2019-06-13
- Granted: 2021-03-16
- Earliest claimed: 2017-12-13
- Assignees: Google Inc.
- Applicants: Google LLC
- Inventors: Yojan Patel; Melissa Frank
- Web page: https://patentgrep.com/patent/US10945674B2

## CPC

- A61B 5/721: {using a separate sensor to detect motion or using motion information derived from signals other than the physiological signal to be measured}
- G16H 40/63: for local operation
- A61B 5/0002: {Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network (endoradiosondes A61B5/07)}
- A61B 5/02405: {Determining heart rate variability}
- A61B 5/02416: {using photoplethysmograph signals, e.g. generated by infrared radiation (A61B5/14552 takes precedence)}
- A61B 5/02438: {with portable devices, e.g. worn by the patient}
- A61B 5/7267: {involving training the classification device}
- G16H 20/30: relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
- G16H 40/67: for remote operation
- G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients
- A61B 2562/0219: Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- 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

Methods, systems, and method for predicting sensor measurement quality. In some implementations, the method comprises: measuring, using a wearable computing device that includes a processor and a sensor, information indicating motion of the wearable computing device during a current time period; identifying one or more parameters associated with a determination of a likelihood that one or more measurements from the sensor configured within the wearable computing device is of sufficient quality for calculating a physiological metric using the one or more measurements from the sensor, wherein the one or more parameters include contextual parameters associated with the wearable computing device; determining the likelihood that the measurement from the sensor associated with the user device is of sufficient quality at a second time period for calculating the physiological metric using the measurement from the sensor based on the identified one or more parameters and based on the information indicating the motion of the user device during the current time period; in response to determining that the likelihood exceeds a predetermined threshold, activating the processor and the sensor and collecting a measurement from the sensor at the second time period; and updating the identified one or more parameters based on the motion of the user device during the current time period and based on the measurement from the sensor at the second time period.

## Claims

### Claim 1

A method for predicting sensor measurement quality, the method comprising:
measuring, using a wearable computing device that includes a processor and a sensor, information indicating motion of the wearable computing device during a current time period;
identifying one or more parameters associated with a determination of a likelihood that one or more measurements from the sensor configured within the wearable computing device is of sufficient quality for calculating a physiological metric using the one or more measurements from the sensor;
determining contextual information associated with the wearable computing device;
determining the likelihood that the measurement from the sensor associated with the user device is of sufficient quality at a second time period for calculating the physiological metric using the measurement from the sensor based on the identified one or more parameters, the information indicating the motion of the user device during the current time period, and the determined contextual information associated with the wearable computing device;
in response to determining that the likelihood exceeds a predetermined threshold, activating the processor and the sensor and collecting a measurement from the sensor at the second time period; and
updating the identified one or more parameters based on the motion of the user device during the current time period and based on the measurement from the sensor at the second time period.

### Claim 2 (depends on 1)

The method of claim 1, wherein the sensor is a photoplethysmography sensor and wherein the physiological metric is heart rate variability of a user of the wearable computing device.

### Claim 3 (depends on 1)

The method of claim 1, wherein the one or more parameters include a threshold associated with the information indicating the motion of the user device during the current time period, and wherein the likelihood is determined based on the threshold associated with information indicating the motion of the user device.

### Claim 4 (depends on 3)

The method of claim 3, wherein the information indicating the motion of the user device includes an acceleration of the user device, and wherein the threshold associated with the information indicating the motion of the user device is a mean acceleration measured during the current time period.

### Claim 5 (depends on 1)

The method of claim 1, further comprising, in response to determining that the likelihood does not exceed the predetermined threshold, causing the identified one or more parameters to be updated and inhibiting the processor and the sensor of the wearable computing device from being activated.

### Claim 6

A method for predicting sensor measurement quality, the method comprising:
measuring, using a wearable computing device that includes a processor and a sensor, information indicating motion of the wearable computing device during a current time period;
identifying one or more parameters associated with a determination of a likelihood that one or more measurements from the sensor configured within the wearable computing device is of sufficient quality for calculating a physiological metric using the one or more measurements from the sensor, wherein the one or more parameters are determined based on a training set comprising a plurality of training samples, and wherein a training sample from the plurality of training samples includes the information indicating the motion of the user device and a corresponding sensor measurement;
determining the likelihood that the measurement from the sensor associated with the user device is of sufficient quality at a second time period for calculating the physiological metric using the measurement from the sensor based on the identified one or more parameters and based on the information indicating the motion of the user device during the current time period;
in response to determining that the likelihood exceeds a predetermined threshold, activating the processor and the sensor and collecting a measurement from the sensor at the second time period; and
updating the identified one or more parameters based on the motion of the user device during the current time period and based on the measurement from the sensor at the second time period.

### Claim 7

A system for predicting sensor measurement quality, the system comprising:
a sensor; and
a hardware processor connected to the sensor, wherein the hardware processor is configured to:
measure information indicating motion of the wearable computing device during a current time period;
identify one or more parameters associated with a determination of a likelihood that one or more measurements from the sensor configured within the wearable computing device is of sufficient quality for calculating a physiological metric using the one or more measurements from the sensor, wherein the one or more parameters include contextual parameters associated with the wearable computing device;
determine contextual information associated with the wearable computing device;
determine the likelihood that the measurement from the sensor associated with the user device is of sufficient quality at a second time period for calculating the physiological metric using the measurement from the sensor based on the identified one or more parameters, the information indicating the motion of the user device during the current time period, and the determined contextual information associated with the wearable computing device;
in response to determining that the likelihood exceeds a predetermined threshold, activate the processor and the sensor and collecting a measurement from the sensor at the second time period; and
update the identified one or more parameters based on the motion of the user device during the current time period and based on the measurement from the sensor at the second time period.

### Claim 8 (depends on 7)

The system of claim 7, wherein the sensor is a photoplethysmography sensor and wherein the physiological metric is heart rate variability of a user of the wearable computing device.

### Claim 9 (depends on 7)

The system of claim 7, wherein the one or more parameters include a threshold associated with the information indicating the motion of the user device during the current time period, and wherein the likelihood is determined based on the threshold associated with information indicating the motion of the user device.

### Claim 10 (depends on 9)

The system of claim 9, wherein the information indicating the motion of the user device includes an acceleration of the user device, and wherein the threshold associated with the information indicating the motion of the user device is a mean acceleration measured during the current time period.

### Claim 11 (depends on 7)

The system of claim 7, wherein the hardware processor is further configured to, in response to determining that the likelihood does not exceed the predetermined threshold, cause the identified one or more parameters to be updated and inhibit the processor and the sensor of the wearable computing device from being activated.

### Claim 12

A system for predicting sensor measurement quality, the system comprising:
a sensor; and
a hardware processor connected to the sensor, wherein the hardware processor is configured to:
measure information indicating motion of the wearable computing device during a current time period;
identify one or more parameters associated with a determination of a likelihood that one or more measurements from the sensor configured within the wearable computing device is of sufficient quality for calculating a physiological metric using the one or more measurements from the sensor, wherein the one or more parameters include contextual parameters associated with the wearable computing device, wherein the one or more parameters are determined based on a training set comprising a plurality of training samples, and wherein a training sample from the plurality of training samples includes the information indicating the motion of the user device and a corresponding sensor measurement;
determine the likelihood that the measurement from the sensor associated with the user device is of sufficient quality at a second time period for calculating the physiological metric using the measurement from the sensor based on the identified one or more parameters and based on the information indicating the motion of the user device during the current time period;
in response to determining that the likelihood exceeds a predetermined threshold, activate the processor and the sensor and collecting a measurement from the sensor at the second time period; and
update the identified one or more parameters based on the motion of the user device during the current time period and based on the measurement from the sensor at the second time period.

### Claim 13

A non-transitory computer-readable medium containing computer executable instructions that, when executed by a processor, cause the processor to perform a method for predicting sensor measurement quality, the method comprising:
measuring, using a wearable computing device that includes a processor and a sensor, information indicating motion of the wearable computing device during a current time period;
identifying one or more parameters associated with a determination of a likelihood that one or more measurements from the sensor configured within the wearable computing device is of sufficient quality for calculating a physiological metric using the one or more measurements from the sensor, wherein the one or more parameters include contextual parameters associated with the wearable computing device;
determining contextual information associated with the wearable computing device;
determining the likelihood that the measurement from the sensor associated with the user device is of sufficient quality at a second time period for calculating the physiological metric using the measurement from the sensor based on the identified one or more parameters, the information indicating the motion of the user device during the current time period, and the determined contextual information associated with the wearable computing device;
in response to determining that the likelihood exceeds a predetermined threshold, activating the processor and the sensor and collecting a measurement from the sensor at the second time period; and
updating the identified one or more parameters based on the motion of the user device during the current time period and based on the measurement from the sensor at the second time period.

### Claim 14 (depends on 13)

The non-transitory computer-readable medium of claim 13, wherein the sensor is a photoplethysmography sensor and wherein the physiological metric is heart rate variability of a user of the wearable computing device.

### Claim 15 (depends on 13)

The non-transitory computer-readable medium of claim 13, wherein the one or more parameters include a threshold associated with the information indicating the motion of the user device during the current time period, and wherein the likelihood is determined based on the threshold associated with information indicating the motion of the user device.

### Claim 16 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the information indicating the motion of the user device includes an acceleration of the user device, and wherein the threshold associated with the information indicating the motion of the user device is a mean acceleration measured during the current time period.

### Claim 17 (depends on 13)

The non-transitory computer-readable medium of claim 13, wherein the method further comprises, in response to determining that the likelihood does not exceed the predetermined threshold, causing the identified one or more parameters to be updated and inhibiting the processor and the sensor of the wearable computing device from being activated.

### Claim 18

A non-transitory computer-readable medium containing computer executable instructions that, when executed by a processor, cause the processor to perform a method for predicting sensor measurement quality, the method comprising:
measuring, using a wearable computing device that includes a processor and a sensor, information indicating motion of the wearable computing device during a current time period;
identifying one or more parameters associated with a determination of a likelihood that one or more measurements from the sensor configured within the wearable computing device is of sufficient quality for calculating a physiological metric using the one or more measurements from the sensor, wherein the one or more parameters include contextual parameters associated with the wearable computing device, wherein the one or more parameters are determined based on a training set comprising a plurality of training samples, and wherein a training sample from the plurality of training samples includes the information indicating the motion of the user device and a corresponding sensor measurement;
determining the likelihood that the measurement from the sensor associated with the user device is of sufficient quality at a second time period for calculating the physiological metric using the measurement from the sensor based on the identified one or more parameters the information indicating the motion of the user device during the current time period;
in response to determining that the likelihood exceeds a predetermined threshold, activating the processor and the sensor and collecting a measurement from the sensor at the second time period; and
updating the identified one or more parameters based on the motion of the user device during the current time period and based on the measurement from the sensor at the second time period.