# US 11,998,355 B2 · Pressure sensor integration into wearable device > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,998,355 B2 - Document ID: US11998355B2 - Status: Granted - Kind: B2 - Application number: 18/311,762 - Filed: 2023-05-03 - Published: 2023-08-31 - Granted: 2024-06-04 - Earliest claimed: 2019-06-28 - Assignees: Fitbit, Inc. - Applicants: Fitbit, Inc. - Inventors: Brett Adam Coakley; Peter Colin Dess; Daniel Joel Freschl; Lindsey Michelle Sunden; Suraj Gowda; Tracy Norman Giest; Aditya Vivekanand Nadkarni - Web page: https://patentgrep.com/patent/US11998355B2 ## CPC - A61B 5/6843: {Monitoring or controlling sensor contact pressure} - A61B 5/01: Measuring temperature of body parts {; Diagnostic temperature sensing, e.g. for malignant or inflamed tissue} (clinical contact thermometers G01K13/20) - 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 5/14552: {Details of sensors specially adapted therefor} - A61B 5/332: Portable devices specially adapted therefor - A61B 5/681: {Wristwatch-type devices} - A61B 5/684: {Indicating the position of the sensor on the body} - A61B 5/6844: {Monitoring or controlling distance between sensor and tissue} - A61B 5/7221: {Determining signal validity, reliability or quality (preventing, reducing or removing noise induced by motion artefacts A61B5/7207; noise originating from a therapeutic or surgical apparatus A61B5/7217)} - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) ## Abstract The accuracy of physiological data measured through contact with skin can be validated by characterizing the forces at the surfaces where data is measured. Conventional devices do not monitor the fit of skin-based sensors, making the accuracy and confidence in physiological data dependent on the user ensuring that the device is fitted properly. Over time, the seating of a device will vary due to changes in user activity and the need to periodically remove a device. Inevitably, instances will arise where the device is not fitted correctly, which may result in skewed physiological metrics. By monitoring the forces acting on the housing of a device, the interface of skin sensors can be characterized allowing for confidence metrics in the corresponding physiological data to be determined. In some cases, a user can be notified when a device is not seated properly, and in some cases, data may even be calibrated based on the fit of a device. ## Claims ### Claim 1 A computer-implemented method, comprising: receiving heart rate data of a user from a photoplethysmographic (PPG) sensor of a wearable device being worn by the user, the PPG sensor being positioned on a skin-side surface of the wearable device such that the PPG sensor is adjacent to skin of the user when being worn by the user; receiving a set of fit data from a plurality of fit sensors of the wearable device, the plurality of fit sensors being spaced apart from each other and from the PPG sensor on the wearable device, the set of fit data being associated temporally with the heart rate data, the set of fit data being indicative of a contact force applied by the user at each of the plurality of fit sensors; generating a fit signature using at least one of curve fitting techniques, finite element analysis, a predetermined relationship, or a look-up function on the set of fit data, the fit signature including an estimated contact force applied by the user at the PPG sensor, the fit signature being indicative of a fit of the wearable device on the user; comparing the fit signature to a predetermined range; presenting, when the fit signature is outside the predetermined range, a notification to the user via a display of the wearable device or an application on another device, the notification prompting the user to adjust a position of the wearable device; designating, when the fit signature is outside the predetermined range, the heart rate data as a sub-optimal signal; and determining, when the fit signature is within the predetermined range, a heart rate of the user using the heart rate data. ### Claim 2 A computer-implemented method, comprising: receiving biometric data from a skin sensor of a wearable device; receiving a set of fit data from a plurality of fit sensors of the wearable device, the plurality of fit sensors being spaced apart from each other and from the skin sensor on the wearable device, the set of fit data being associated temporally with the biometric data, the set of fit data being indicative of a contact force applied at each of the plurality of fit sensors; generating a fit signature using at least one of curve fitting techniques, finite element analysis, a predetermined relationship, or a look-up function on the set of fit data, the fit signature including an estimated contact force applied at the skin sensor, the fit signature being indicative of a fit of the wearable device on a user; comparing the fit signature to a predetermined range; presenting, when the fit signature is outside the predetermined range, a notification to the user via a display of the wearable device, the notification prompting the user to adjust a position of the wearable device; designating, when the fit signature is outside the predetermined range, the biometric data as a sub-optimal signal; and determining, when the fit signature is within the predetermined range, a biometric of the user using the biometric data. ### Claim 3 (depends on 2) The computer-implemented method of claim 2, further comprising: controlling the skin sensor to stop collecting biometric data responsive to determining that the fit signature is outside the predetermined range; and controlling the skin sensor to resume collecting biometric data responsive to determining that the fit signature is within the predetermined range. ### Claim 4 (depends on 2) The computer-implemented method of claim 2, wherein the skin sensor is an optical sensor or an electrode-based sensor. ### Claim 5 (depends on 2) The computer-implemented method of claim 2, wherein the skin sensor is a photoplethysmographic (PPG) sensor or an electrocardiogram (ECG) sensor, a temperature sensor or a pulse oximeter (SpO2 sensor). ### Claim 6 (depends on 2) The computer-implemented method of claim 2, further comprising: receiving one or more physiological metrics of the user, and wherein the predetermined range is based at least in part on the one or more physiological metrics of the user. ### Claim 7 (depends on 6) The computer-implemented method of claim 6, wherein the one or more physiological metrics of the user comprise one of a body mass index (BMI), age, sex, weight, wrist dimension, or body fat percentage. ### Claim 8 (depends on 2) The computer-implemented method of claim 2, wherein the plurality of fit sensors measures at least one of a force, a pressure, or a deflection of a housing of the wearable device. ### Claim 9 (depends on 8) The computer-implemented method of claim 8, wherein generating the fit signature comprises determining a pressure applied to the skin sensor. ### Claim 10 (depends on 9) The computer-implemented method of claim 9, further comprising: calibrating the biometric data based at least in part on the pressure applied to the skin sensor; and recording the calibrated biometric data. ### Claim 11 (depends on 9) The computer-implemented method of claim 9, further comprising: determining confidence scores for the biometric data, the confidence score based at least in part on the pressure applied to the skin sensor. ### Claim 12 (depends on 2) The computer-implemented method of claim 2, further comprising: deleting, when the fit signature is outside the predetermined range, the biometric data. ### Claim 13 (depends on 2) The computer-implemented method of claim 2, further comprising: determining that the wearable device is not being worn based on the fit signature being outside the predetermined range and based on at least one of data provided by the skin sensor, data provided by light sensors, data provided by inertial sensors, or learned user patterns. ### Claim 14 A physiology measurement device, comprising: a housing; a skin sensor coupled to the housing, the skin sensor being configured to generate biometric data associated with a user when positioned adjacent skin of the user; a plurality of fit sensors coupled to the housing, the plurality of fit sensors being spaced apart from each other and from the skin sensor on the housing, each respective fit sensor of the plurality of fit sensors being configured to generate fit data of a contact force applied at the respective fit sensor of the plurality of fit sensors; a processor; and a memory device including instructions that, when executed by the processor, cause the memory device to: receive the biometric data from the skin sensor, the biometric data associated with a time period; receive a set of fit data from the plurality of fit sensors, the set of fit data associated with the time period; generate a fit signature using at least one of curve fitting techniques, finite element analysis, or a look-up function on the set of fit data, the fit signature being indicative of an estimated contact force applied at the skin sensor, the fit signature being indicative of a fit of the physiology measurement device on the user; compare the fit signature to a predetermined range; present, when the fit signature is outside the predetermined range, a notification to the user; and designate, when the fit signature is outside the predetermined range, the biometric data as a sub-optimal signal. ### Claim 15 (depends on 14) The physiology measurement device of claim 14, wherein the instructions when executed by the processor, further cause the memory device to: determine, when the fit signature is within the predetermined range, a biometric of the user using the biometric data. ### Claim 16 (depends on 14) The physiology measurement device of claim 14, wherein the skin sensor is a multi-wavelength optical sensor or an electrode-based sensor. ### Claim 17 (depends on 14) The physiology measurement device of claim 14, wherein the plurality of fit sensors are configured to measure a force, a pressure, or a deflection of the housing. ### Claim 18 (depends on 14) The physiology measurement device of claim 14, further comprising a display attached to the housing, wherein the notification is presented on the display. ### Claim 19 (depends on 14) The physiology measurement device of claim 14, wherein the instructions when executed by the processor, further cause the memory device to: calculate a pressure applied to the plurality of fit sensors based on data provided by the plurality of fit sensors. ### Claim 20 (depends on 14) The physiology measurement device of claim 14, wherein the notification prompts the user to adjust a position of the physiology measurement device.