Assessment of respiratory depression risk from wearable devices

Abstract

A computing system and method that can be used to determine a user's respiratory rate. In particular, the wearable computing device may determine the user's respiratory rate based at least in part on the heart rate data. Even more particularly, the wearable computing device may determine an overall respiratory risk metric. For example, the computing device may compare the overall respiratory risk metric to a threshold (e.g., determined by a machine learning model or user input). The wearable computing device may determine that the user is at risk for respiratory depression if the overall respiratory risk metric meets the threshold criterion. Respiratory depression refers to a condition in which the effort to breathe is reduced. In particular, the overall respiratory risk metric may represent a likelihood that the user is at risk for respiratory depression.

Description

[Technical field]

[0001] The present disclosure relates generally to determining a user's breathing rate over time. In particular, the present disclosure is directed to systems and methods for using respiratory risk metrics based on data such as heart rate data. [Background technology]

[0002] Advances in wearable technology, such as fitness trackers and smart watches, allow these devices to be used in a variety of contexts For example, fitness trackers and smart watches can be used to track a user's heart rate. Summary of the Invention

[0003] Aspects and advantages of embodiments of the disclosure will be set forth in part in the description that follows, or may be learned from the description, or may be learned by practice of the embodiments.

[0004] One exemplary aspect of the present disclosure is directed to a wearable computing device. The wearable computing device includes one or more processors and a heart rate sensor. The wearable computing device further includes a non-transitory computer-readable memory configured to store instructions that cause the one or more processors to perform operations. The operations include obtaining heart rate data via the heart rate sensor. The operations include determining a respiratory rate. The operations include determining an overall respiratory risk metric associated with a user wearing the wearable computing device, the overall respiratory risk metric representing a likelihood that the user is at risk for respiratory depression. The operations include determining whether the user is at risk for respiratory depression. The operations include providing a notification indicating that the user is at risk for respiratory depression.

[0005] Another exemplary aspect of the present disclosure is directed to a computer-implemented method for determining whether a user wearing a wearable computing device is at risk for respiratory depression. The method includes obtaining heart rate data via a heart rate sensor. The method includes determining a respiratory rate based at least in part on the heart rate data. The method includes determining an overall respiratory risk metric associated with the user wearing the wearable computing device based at least in part on the respiratory rate. The overall respiratory risk metric represents a likelihood that the user is at risk for respiratory depression. The method includes determining whether the user is at risk for respiratory depression based at least in part on the overall respiratory risk metric. The method includes providing a notification indicating that the user is at risk for respiratory depression in response to determining that the user is at risk for respiratory depression.

[0006] Other aspects of the present disclosure are directed to various systems, apparatus, non-transitory computer-readable media, user interfaces, and electronic devices.

[0007] These and other features, aspects, and advantages of various embodiments of the present disclosure will become better understood with reference to the following description and appended claims. The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the present disclosure and, together with the description, serve to explain the associated principles.

[0008] A full and effective description of the present disclosure, directed to one skilled in the art, is set forth in the present specification, which makes reference to the accompanying drawings. [Brief description of the drawings]

[0009] [Figure 1] 1 illustrates a wearable computing device according to some embodiments of the present disclosure. [Diagram 2] FIG. 1 illustrates a block diagram of components of a wearable computing device according to some embodiments of the present disclosure. [Diagram 3]1 illustrates an exemplary graphical display illustrating determined respiration rate over a sustained period of time, according to some embodiments of the present disclosure. [Figure 4] 1 illustrates exemplary respiratory effort signals for multiple users, according to some embodiments of the present disclosure. [Diagram 5] 1 shows a block diagram illustrating one or more metrics that are considered when determining a user's respiratory depression risk, according to some embodiments of the present disclosure. [Figure 6] 1 illustrates a flow diagram of a method for determining whether a user is at risk of respiratory depression and providing an instructional notification according to some embodiments of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] overview Exemplary aspects of the present disclosure are directed to a wearable computing device that may be worn, for example, on a user's wrist. The wearable computing device may include one or more processors. The wearable computing device may include a heart rate sensor (e.g., an optical sensor) disposed within a housing of the wearable computing device. The heart rate sensor may determine the user's heart rate by utilizing photoplethysmography. More specifically, a green LED light (e.g., by flashing the light) paired with a light-sensing photodiode (e.g., to determine the absorption of green light) may be used to detect the amount of blood flowing through the user's wrist. Additionally, red and infrared photoplethysmography may be used. In this manner, the user's heart rate may be consistently monitored. However, without additional processing, the benefits of such data are limited. In this manner, the wearable computing device determines the heart rate, but because additional processing of the heart rate data is limited, the computing device cannot provide further useful information.

[0011] A wearable computing device according to the present disclosure may determine a user's respiration rate. In particular, the wearable computing device may determine the user's respiration rate based at least in part on the heart rate data. The wearable computing device may additionally determine whether the user has respiratory sinus arrhythmia based at least in part on the heart rate data. Furthermore, the wearable computing device may determine the user's respiration rate based at least in part on the determined respiratory sinus arrhythmia.

[0012] In some implementations, the wearable computing device may obtain heart rate data associated with a particular time period. In particular, the wearable computing device may determine a power spectral density (e.g., based at least in part on the heart rate data associated with the particular time period). The wearable computing device may determine spectral peaks based at least in part on the power spectral density. A respiration rate may be determined based at least in part on the determined spectral peaks.

[0013] In some implementations, the wearable computing device may determine the user's respiration rate directly from respiration rate data. For example, the wearable computing device may include a respiration rate sensor configured to obtain respiration data from which the user's respiration rate may be determined. In alternative implementations, the wearable computing device may determine the user's respiration rate based on a measured heart rate.

[0014] In some implementations, the wearable computing device may determine an overall respiratory risk metric. For example, the computing device may compare the overall respiratory risk metric to a threshold (e.g., determined by a machine learning model or user input). The wearable computing device may determine that the user is at risk for respiratory depression if the overall respiratory risk metric meets the threshold criteria. Respiratory depression refers to a breathing disorder characterized by slow, ineffective breathing. During a normal breathing cycle, oxygen is inhaled into the lungs. Blood then carries the oxygen around the body, delivering it to various tissues. The blood then carries carbon dioxide back to the lungs, where it leaves the body when the person exhales. However, if a person has respiratory depression, the body may not be able to properly remove carbon dioxide, which may lead to poor use of oxygen by the lungs. This can lead to high levels of carbon dioxide and too little oxygen available to the body.

[0015] In some implementations, the overall respiratory risk metric may be based at least in part on the respiratory rate of a user wearing the wearable computing device. In some implementations, the overall respiratory risk metric may represent a likelihood that the user is at risk for respiratory depression. By way of example, the overall respiratory risk metric may include one or more metrics that may be indicative of the user's risk of respiratory depression. For example, the overall respiratory risk metric may be based at least in part on the respiratory rate and the one or more metrics. In some implementations, weight values ​​may be assigned to the respiratory rate and / or the one or more metrics. For example, the respiratory rate and / or the one or more metrics may be provided as inputs to a machine-learned model configured to determine weighted values ​​for the respiratory rate and / or the one or more metrics. In alternative implementations, the wearable computing device may assign predefined weight values ​​to the respiratory rate and / or the one or more metrics based on predefined weight values. For example, linear weighting may be applied. However, it should be understood that any suitable weighting method may be implemented.

[0016] In some implementations, the one or more metrics associated with the overall respiratory risk metric may include a percentage of a predefined period of time during which the respiratory rate is below a threshold. The threshold may be pre-determined by a machine learning model or, alternatively, by the user. For example, a person with a respiratory rate below 8 breaths / min may be deemed to have a respiratory rate that is too low and should be flagged as being at high risk for respiratory depression. Thus, the computing device may calculate a percentage of time during which the user is determined to have a respiratory rate below 8 breaths / min. The one or more metrics may include a number of segments in which there is a significant decrease in respiratory rate over a predefined period of time (e.g., a decrease of more than 3 breaths per minute within a 5 minute window). The one or more metrics may include one or more percentiles of the respiratory rate (e.g., the 5th and 10th percentiles). The one or more metrics may include a standard deviation of the respiratory rate. The one or more metrics may include an interquartile range of the respiratory rate. The one or more metrics may include a kurtosis of the distribution of the respiratory rate. The one or more metrics may include hypoxic events. The one or more metrics may include bradycardia events.

[0017] The wearable computing device may obtain a plurality of demographic factors. For example, in some implementations, the wearable computing device may obtain a plurality of demographic factors via user input. In particular, a particular value (e.g., 8 breaths / min) used in one or more metrics may be a default threshold that may be adjusted by the contextual data. Examples of contextual data may include demographic factors of the user (e.g., age, sex, body mass index, etc.). In some implementations, an overall respiratory risk metric may be determined based at least in part on the respiratory rate and the contextual data. In some implementations, the wearable computing device may obtain additional contextual data. For example, the additional contextual data may include the user's relevant medical history (e.g., by user input or by user-approved input by a medical professional). In some implementations, the relevant medical history may include, but is not limited to, whether the user has sleep apnea or any other neurological respiratory problem that may affect the user's respiratory rate.

[0018] It should be appreciated that the computing system may be configured to protect the privacy of personal information about a user. For example, in some implementations, the computing system may be configured to prompt a user to authorize sharing of contextual data and / or demographic factors provided by the user. For example, the computing system may provide a notification (e.g., a text message, email, etc.) that the user must interact with (e.g., respond to) to consent to sharing the contextual data.

[0019] In some implementations, the overall respiratory risk metric may be based at least in part on at least one of the respiratory rate or the determined tidal volume value. In particular, the breath-to-breath variability of the tidal volume may be ascertained. For example, the wearable computing device may be configured to estimate the variability of the tidal volume based at least in part on the derived respiratory effort signal. The derived respiratory effort signal may be determined by using the green photoplethysmography signal by generating a green photoplethysmography amplitude after baseline removal and creating a time series based on the peak or valley photoplethysmography envelope values. The time series values ​​may increase and decrease with the respiratory effort amplitude, whereby the variability of the tidal volume may be estimated by using a statistical metric (e.g., standard deviation of the respiratory effort amplitude over one minute). In some implementations, the overall respiratory risk metric may be based at least in part on at least one of the respiratory rate or the determined minute ventilation value. In particular, the determined minute ventilation value may be based on the tidal volume.

[0020] In some implementations, the wearable computing device may generate a graphical display showing the determined respiration rate over a duration. In particular, the wearable computing device may generate the graphical display based at least in part on the determined respiration rate. For example, the graphical display may show the user's respiration rate at discrete instants, or alternatively over a continuous period of time. In particular, the axes of the graphical display may be adjusted based at least in part on the determined respiration rate, the duration, or both. For example, the wearable computing device may utilize sliding epochs to generate the graphical display.

[0021] In some implementations, the wearable computing device may generate a graphical display that indicates the user's determined respiration rate while the user is sleeping. For example, the wearable computing device may automatically determine that the user is sleeping based at least in part on sensor data (e.g., motion data). Alternatively, the wearable computing device may determine that the user is sleeping based at least in part on user input (e.g., the user may indicate that he or she is in bed).

[0022] In some implementations, the wearable computing device may be communicatively coupled to the secondary device via one or more wireless networks. The secondary device may be an Internet of Things (IoT) device in some implementations. As a particular example, the secondary device may be associated with a smart home. The wearable computing device may interact with the secondary device to select settings associated with the wearable computing device (e.g., thresholds used to determine the overall respiratory risk metric). In some implementations, the secondary device may generate the associated data itself. In particular, the secondary device may use a non-contact based method (e.g., using a radio frequency sensor) to obtain the data. For example, in some implementations, the secondary device may be configured to obtain radar data indicative of the user's movements. The wearable computing device may receive the non-contact based data and determine whether the user is at risk for respiratory depression based at least in part on the non-contact based data. In some implementations, the determination of whether the user is at risk for respiratory depression may be based on data from the secondary device and data obtained via sensors of the wearable computing device.

[0023] The wearable computing device may be configured to provide a notification indicating that the user is at risk for respiratory depression. In particular, the wearable computing device may provide a notification to the user or a pre-approved entity that the user is at risk for respiratory depression. For example, the wearable computing device may provide a notification to the user's physician indicating that the user is at risk for respiratory depression, such that the physician may view the notification and make a decision (e.g., regarding the dosage of medication) based on the information provided. In some cases, the wearable computing device may provide an audio notification (e.g., an alarm), a physical notification (e.g., a vibration), or a visual notification indicating that the user is at risk for respiratory depression. The visual notification may further include an image (e.g., a graphical display showing the determined respiratory rate over time) or words. As another particular example, the wearable computing device may communicate with a connected secondary device such that the secondary computing device provides a notification indicating that the user is at risk for respiratory depression.

[0024] In some cases, upon determining that the user is at risk for respiratory depression, the wearable computing device may provide an immediate notification. For example, the wearable computing device may attempt to awaken the user from sleep by using a notification (e.g., auditory, vibration) in response to determining that the user is at risk for respiratory depression. In some implementations, the wearable computing device may be communicatively coupled to a secondary device, which may similarly attempt to awaken the user from sleep (e.g., by turning on the lights in the user's room, playing music from another connected device such as a speaker). In particular, the wearable computing device may provide a signal indicating that it will activate certain awakening attempts in a ranked order (e.g., ranked by how uncomfortable the awakening method is). Thus, the wearable computing device may first attempt to awaken the user by utilizing a lower ranked method before moving up the list if the user does not indicate (e.g., by user input to the wearable computing device or the secondary device) that they are awake. In particular, the wearable computing device may determine whether to move up the list of wake-up methods or skip a particular method based at least in part on the level of risk. For example, if the user needs to be woken up urgently due to a high risk level, the wearable computing device may activate a higher ranked wake-up method first, or may jump right to a higher ranked method rather than attempting a lower ranked method first.

[0025] Alternatively, the wearable computing device may compile data related to the user's respiratory depression risk and notify the user after a certain amount of time has passed (e.g., after the user awakens, after the user has finished exercising, etc.) In particular, the wearable computing device may determine whether to notify the user immediately or after a period of time based on a number of factors (e.g., the level of risk, whether the user is engaged in a particular activity such as sleeping or exercising, etc.).

[0026] A wearable computing device according to exemplary aspects of the present disclosure may provide numerous technical effects and advantages. For example, the wearable computing device provides a user with a notification that indicates that the user is at risk for respiratory depression, providing an easy at-home alternative to tedious sleep studies that the user may need to undertake to achieve similar results. Alternatively, the user may not have known that they were at risk for respiratory depression, and thus the wearable computing device described in this disclosure provides an additional safety net not previously available to the user.

[0027] Referring now to the figures, exemplary embodiments of the present disclosure will be described in more detail.

[0028] Exemplary Devices and Systems 1 illustrates a wearable computing device 100 according to an exemplary embodiment of the present disclosure. As illustrated, the wearable computing device 100 may be a wristwatch. However, it should be understood that the wearable computing device 100 may be configured to be worn elsewhere on a user's body. For example, in some implementations, the wearable computing device 100 may be a ring configured to be worn around a user's finger.

[0029] In some implementations, the wearable computing device 100 may include a display 102, a device housing 104, a band 106, and one or more sensors. In some implementations, the band 106 may be fastened to a user's arm 108 to secure the device housing 104 to the user's arm 108. In embodiments, the display 102 may be configured to present data to the user regarding the user's skin temperature, heart rate, sleep state, electroencephalogram, electrocardiogram, electromyogram, electrooculogram, and other physiological data of the user (e.g., blood oxygen level). The display 102 may also be configured to convey data from additional ambient sensors contained within the wearable computing device 100. Exemplary information conveyed to the display 102 from these additional ambient sensors may include the location, altitude, and weather of a location associated with the user. The display 102 may also convey data regarding the user's movement (e.g., whether the user is stationary, walking, and / or running).

[0030] In some implementations, the display 102 may be configured to display a notification 112. For example, the notification 112 may alert the user that the user is at risk for respiratory depression. The notification 112 may be displayed in real-time when the user is exhibiting symptoms. Alternatively, the notification 112 may be displayed when the user is able to see the notification 112 (e.g., when the user wakes up).

[0031] In some implementations, the display 102 may be configured to receive data input by a user. In embodiments, the user may request, via input on the display, that the wearable computing device 100 generate additional data for display to the user. In response, the display 102 may present instructions to the user for acquiring the data. In some examples, the wearable computing device 100 may display instructions to the user (e.g., "Place your finger on the sensor for 10 seconds").

[0032] In some implementations, the display 102 may include an interactive display screen (e.g., a touch screen or a non-touch screen). In such implementations, a user may interact with the wearable computing device 100 via the display 102 to control the operation of the wearable computing device 100. It should be appreciated that the display 102 may be used to provide content for the user to view. For example, the display 102 may be configured to display a notification indicating whether the user is at risk for respiratory depression.

[0033] In some implementations, the wearable computing device 100 may include one or more input devices 110 that may be manipulated (e.g., pressed) by a user to interact with the wearable computing device 100. For example, the one or more input devices 110 may include mechanical buttons that may be manipulated (e.g., pressed) to interact with the wearable computing device 100. In some implementations, the one or more input devices 110 (e.g., a display screen) may be manipulated to control the operation of a backlight (not shown) associated with the one or more input devices 110. It should be understood that the one or more input devices 110 may be configured to enable a user to interact with the wearable computing device 100 in any suitable manner. For example, in some implementations, the one or more input devices 110 may be manipulated by a user to navigate content (e.g., one or more menu screens) displayed on the display 102.

[0034] In some implementations, the wearable computing device 100 may include one or more sensors disposed within the device housing 104. For example, the one or more sensors may include an audio sensor, a motion sensor (e.g., an accelerometer), a pulse oximeter, an IR motion sensor, a skin temperature sensor, an internal device temperature sensor, a position sensor (e.g., a GPS), an altitude sensor, a heart rate sensor, a pressure sensor, a gyroscope, an environmental sensor (e.g., a bedside ultrasound sensor), and other physiological sensors (e.g., a blood oxygen level sensor). In an embodiment, the device housing 104 may also be configured to include one or more processors. The device housing 104 may include a port that connects an audio sensor (e.g., a microphone) to the outside of the device housing 104, allowing audio information to reach the audio sensor without having to pass through the device housing 104.

[0035] The band 106 may be configured to secure the wearable computing device 100 around a user's arm 108, for example, by connecting both ends of the band 106 with a buckle, clasp, or other similar fastening device, thereby allowing the wearable computing device 100 to be worn by the user.

[0036] 2 illustrates an exemplary computing environment including a wearable computing device 100, in accordance with an exemplary embodiment of the present disclosure. In this example, the wearable computing device 100 may include one or more processors 202, memory 204, a heart rate sensor 210, and a respiratory risk system 212.

[0037] More specifically, the one or more processors 202 may be any suitable processing device that may be incorporated into the form factor of the wearable computing device 100. For example, such processors 202 may include one or more of one or more processor cores, microprocessors, application specific integrated circuits (ASICs), FPGAs, controllers, microcontrollers, etc. The one or more processors 202 may be a single processor or multiple processors operably connected. The memory 204 may include one or more non-transitory computer-readable storage media, such as RAM, ROM, EEPROM, EPROM, flash memory devices, and combinations thereof.

[0038] In particular, in some devices, the memory 204 may store instructions for implementing the respiratory risk system 212. Thus, the wearable computing device 100 may implement the respiratory risk system 212 to perform aspects of the present disclosure.

[0039] It should be understood that the term "system" may refer to specialized hardware, computer logic executing on a more general processor, or some combination thereof. Thus, a system may be implemented in hardware, application specific circuitry, firmware, and / or software controlling a general purpose processor. In one embodiment, the system may be implemented as program code files stored in a storage device, loaded into memory and executed by a processor, or may be provided from a computer program product, such as computer executable instructions, stored in a RAM, a hard disk, or a tangible computer readable storage medium, such as an optical or magnetic medium.

[0040] Memory 204 may also include data 206 and instructions 208 that may be acquired, manipulated, created, or stored by the one or more processor(s) 202. In some exemplary embodiments, such data may be accessed and used as input to respiratory risk system 212. In some examples, memory 204 may include data used to execute one or more processes and instructions that describe how those processes may be executed.

[0041] In some examples, the heart rate sensor 210 may detect a heart rate associated with a user wearing the wearable computing device 100. For example, the heart rate sensor 210 may determine the user's heart rate by utilizing photoplethysmography. More specifically, a green LED light (e.g., by flashing the light) paired with a light-sensing photodiode (e.g., to determine the absorption of green light) may be used to detect the amount of blood flowing through the user's wrist. Additionally, red and infrared photoplethysmography may be used. In this manner, the wearable computing device may determine the user's heart rate.

[0042] Exemplary User Experience 3 illustrates an exemplary user interface depicting a graph 300 of a user's respiration rate 302 as a function of time, according to some embodiments of the present disclosure. For example, the graph 300 of the user's respiration rate may show the user's respiration rate 302 over a time span 306 (e.g., on an x-axis or a y-axis). In particular, the wearable computing device may determine the user's respiration rate 302 based at least in part on heart rate data obtained from a heart rate sensor of the wearable computing device. The wearable computing device may additionally determine respiratory sinus arrhythmia. In particular, the wearable computing device may determine respiratory sinus arrhythmia based at least in part on heart rate data.

[0043] In some implementations, the wearable computing device may determine a user's respiration rate 302 based at least in part on the determined respiratory sinus arrhythmia. For example, the wearable computing device may obtain heart rate data associated with a particular time period. In particular, the wearable computing device may determine a power spectral density (e.g., based at least in part on the heart rate data associated with the particular time period). The wearable computing device may determine spectral peaks based at least in part on the power spectral density. The user's respiration rate 302 may be determined based at least in part on the determined spectral peaks.

[0044] In some implementations, an average respiration rate 304 may be presented alongside the user's respiration rate graph 300. In particular, the average respiration rate 304 may be associated with the average respiration rate over the time period depicted in the user's respiration rate graph 300. Alternatively, the average respiration rate 304 may be associated with the respiration rate outside of the time period depicted in the graph 300 (e.g., all-time average respiration rate, six-month average, sleep average, activity average, etc.).

[0045] In some implementations, the graph 300 may represent the user's respiration rate 302 for alternative timespans 306. For example, the user's respiration rate graph 300 may represent the user's respiration rate 302 for different timespans 306 based at least in part on a user interaction indicating a user's desire to view a different timespan 306 (e.g., past year, past month, past day, etc.).

[0046] In some implementations, the graph 300 may indicate when the user's respiration rate 302 is below or above a threshold. The threshold may be predetermined by a machine-learned model or, alternatively, by the user. For example, a user's respiration rate 302 below 8 breaths / min may be considered too low and should be flagged as a high risk of respiratory depression. In some implementations, the graph 300 may represent an icon indicating that the user's respiration rate 302 is at high risk. As another specific example, the graph 300 of the user's respiration rate may change the color of the line graph of the user's respiration rate 302 to indicate high risk data.

[0047] FIG. 4 illustrates an exemplary user interface depicting a graph 400 of a user's respiratory effort signal. In particular, the graph 400 of the user's respiratory effort signal may display a user's respiratory effort signal 402 over time in accordance with an exemplary embodiment of the present disclosure. In particular, the user's respiratory effort signal graph 400 may show a time span 404 (e.g., on an x-axis or a y-axis). In particular, the respiratory effort signal 402 may be determined using a green photoplethysmography signal by generating a green photoplethysmography amplitude after baseline removal and creating a time series based on peak or valley photoplethysmography envelope values. The time series values ​​may increase and decrease with the respiratory effort amplitude, whereby the variability of tidal volume may be estimated by using a statistical metric (e.g., standard deviation of the respiratory effort amplitude over one minute).

[0048] In some implementations, a time span 404 of the respiratory effort signal 402 may be presented to a user. In particular, a time span 404 of the respiratory effort signal 402 over a particular time span 406 may be determined and presented to a user.

[0049] In some implementations, the graph 400 of the user's respiratory effort signal may represent the respiratory effort signal 402 for an alternative time span 406. For example, the graph 400 of the user's respiratory effort signal may represent the respiratory effort signal 402 for an alternative time span 406 based at least in part on a user interaction indicating a user desire to view the alternative time span 406 (e.g., last sleep, last exercise, etc.).

[0050] Illustrative Model FIG. 5 illustrates an exemplary model for predicting a respiratory depression risk for a user associated with a wearable computing device (e.g., wearable computing device 100 with respect to FIG. 1). In particular, the computing device may compare an overall respiratory risk metric 502 to a threshold (e.g., determined by a machine learning model or user input). The wearable computing device may determine that the user is at risk for respiratory depression if the overall respiratory risk metric 502 meets the threshold criteria. In particular, the overall respiratory risk metric 502 may be based at least in part on a respiratory rate. Even more particularly, the overall respiratory risk metric 502 may be associated with a user wearing the wearable computing device. In particular, the overall respiratory risk metric 502 may represent a likelihood that the user is at risk for respiratory depression. By way of example, the respiratory risk metric 502 may include one or more metrics related to respiratory depression risk. For example, the overall respiratory risk metric 502 may be predicted based at least in part on an input respiratory rate and one or more metrics.

[0051] In some implementations, the overall respiratory risk metric 502 may be predicted based on a machine-learned model, such as the respiratory risk metric model 516. In particular, the respiratory rate and one or more metrics may be input into the respiratory risk metric model 516. The respiratory risk metric model 516 may utilize the input respiratory rate and one or more metrics to output the overall respiratory risk metric 502.

[0052] In some implementations, the respiration rate and one or more metrics may be weighted by the wearable computing device. Specifically, the wearable computing device may weight the respiration rate and one or more metrics based on weight values ​​generated by the machine learning model. In some implementations, the wearable computing device may weight the respiration rate and one or more metrics based on pre-defined weight values. For example, linear weighting or any other suitable weighting method may be used.

[0053] For example, the one or more metrics may include a first input 504 (i.e., for a respiratory risk metric model), a percentage of a predetermined period of time during which the respiratory rate has elapsed below a threshold. The computing device may calculate a percentage of time during which the user is determined to have a respiratory rate below 8 breaths / min to determine the first input 504. The one or more metrics may include a second input 506. The second input 506 refers to a calculated number of segments in which there is a significant decrease in respiratory rate over a predetermined period of time (e.g., a decrease of more than 3 breaths per minute within a 5 minute window). The one or more metrics may include a third input 508. The third input refers to one or more percentiles of the respiratory rate (e.g., the 5th and 10th percentiles). The one or more metrics may include a fourth input 510. The fourth input 510 refers to a standard deviation of the respiratory rate. The one or more metrics may include a fifth input 512. The fifth input 512 refers to an interquartile range of the respiratory rate. The inputs are not limited to those shown in FIG. 5. For example, the one or more metrics may include the user's heart rate variability (HRV). In particular, a heart rate sensor (e.g., heart rate sensor 210 of FIG. 2) may be configured to calculate the beat interval between each heart beat (e.g., at a heart rate of 60 bpm, there is typically an interval of about 1 second between each beat). From this set of time intervals, an HRV metric may be obtained. For example, a set of HRV metrics may be calculated over the last 5 minutes of a recording. Exemplary HRV metrics include: (a) average beat interval; (b) root mean square of successive differences (RMSSD); (c) pNN50, which is the percentage of successive beat intervals that differ by more than 50 ms; (d) low frequency (LF) spectral power of the beat interval spectrum; and (e) high frequency (HF) spectral power of the beat interval spectrum; and kurtosis of the distribution of respiratory rate. As another example, the one or more metrics may include derivation from red and infrared photoplethysmography associated with the wearable computing device. In particular, the system may determine an estimated SpO2 using known techniques of oximetry (such as "ratio of ratios").Respiratory depression risk can then be obtained by looking for periods where the estimated SpO2 is below a threshold (e.g., 92% for an extended period of time) or where there is excessive variability in the baseline of the estimated SpO2. Further examples of metrics include hypoxic events and bradycardial events.

[0054] The wearable computing device may obtain a number of demographic factors 514. For example, in some implementations, the wearable computing device may obtain a number of demographic factors 514 via user input. In particular, a particular value (e.g., 8 breaths / min) used in one or more metrics may be a default threshold that may be adjusted by the contextual data. Examples of contextual data may include the user's demographic factors 514 (e.g., age, gender, body mass index, etc.). In some implementations, the overall respiratory risk metric 502 may be determined based at least in part on the respiratory rate and the contextual data. In some implementations, the wearable computing device may obtain additional contextual data. For example, the additional contextual data may include the user's relevant medical history (e.g., by user input or by user-approved input by a medical professional). In some implementations, the relevant medical history may include, but is not limited to, whether the user has sleep apnea or any other neurological respiratory problem that may affect the user's respiratory rate.

[0055] In some implementations, the overall respiratory risk metric 502 may be based at least in part on at least one of the respiratory rate or the determined tidal volume value. In particular, the breath-to-breath variability of the tidal volume may be ascertained. For example, the wearable computing device may be configured to estimate the variability of the tidal volume based at least in part on the derived respiratory effort signal. In some implementations, the overall respiratory risk metric may be based at least in part on at least one of the respiratory rate or the determined minute ventilation value. In particular, the determined minute ventilation value may be based on the tidal volume.

[0056] FIG. 6 illustrates a flow chart diagram of an exemplary method performed in accordance with an exemplary embodiment of the present disclosure. Although FIG. 6 illustrates steps performed in a particular order for purposes of illustration and description, the method of the present disclosure is not limited to the order or arrangement specifically illustrated. Various steps of method 600 may be omitted, rearranged, combined, and / or adapted in various ways without departing from the scope of the present disclosure. In particular, the exemplary method illustrated in FIG. 6 may be performed entirely by a wearable computing device. Alternatively, in some implementations, the exemplary method illustrated in FIG. 6 may be performed by multiple devices such that the exemplary method is divided among multiple devices. In particular, the multiple devices may include a wearable computing device and a remote computing device (e.g., a server).

[0057] At 602, a computing system including one or more computing devices may acquire heart rate data. In particular, the computing system may acquire the heart rate data from a heart rate sensor. The wearable computing device may additionally determine respiratory sinus arrhythmia. In particular, the wearable computing device may determine respiratory sinus arrhythmia based at least in part on the heart rate data. Further, the wearable computing device may determine a user's respiration rate based at least in part on the determined respiratory sinus arrhythmia. As a particular example, the wearable computing device may acquire heart rate data associated with a particular time period. Specifically, the wearable computing device may determine a power spectral density (e.g., based at least in part on the heart rate data associated with the particular time period). The wearable computing device may determine a spectral peak based at least in part on the power spectral density.

[0058] At 604, the computing system may determine a respiration rate. In particular, the computing system may determine a respiration rate based at least in part on heart rate data (e.g., heart rate data obtained from a heart rate sensor). The respiration rate may be determined based at least in part on the determined spectral peaks.

[0059] At 606, the computing system may determine an overall respiratory risk metric. In particular, the overall respiratory risk metric may be associated with a user wearing the wearable computing device. Even more particularly, the overall respiratory risk metric may represent a likelihood that the user may be at risk for respiratory depression. In particular, the overall respiratory risk metric may be based at least in part on a respiratory rate (e.g., a determined respiratory rate, a measured respiratory rate, etc.). For example, the computing device may compare the overall respiratory risk metric to a threshold. In particular, the overall respiratory risk metric may be predicted by a machine-learned model based on the input respiratory rate and one or more metrics. Furthermore, the threshold may additionally be predicted by the machine-learned model. The threshold may be predicted by the machine-learned model based at least in part on demographic factors or external standards, which may be input by the manufacturer or the user.

[0060] At 608, the computing system may determine whether the user is at risk for respiratory depression. In particular, the computing system may determine whether the user is at risk for respiratory depression based at least in part on the overall respiratory risk metric. The wearable computing device may determine that the user is at risk for respiratory depression if the overall respiratory risk metric meets a threshold criterion. In particular, the overall respiratory risk metric may be based at least in part on a respiratory rate. Even more particularly, the overall respiratory risk metric may be associated with a user wearing the wearable computing device. In particular, the overall respiratory risk metric may represent a likelihood that the user is at risk for respiratory depression.

[0061] At 610, the computing system may provide a notification indicating that the user is at risk for respiratory depression. In particular, the computing system may provide a notification indicating that the user is at risk for respiratory depression in response to determining that the user is at risk for respiratory depression. In particular, the wearable computing device may provide a notification that the user is at risk for respiratory depression to the user or a pre-authorized entity. For example, the wearable computing device may provide a notification indicating that the user is at risk for respiratory depression to the user's physician, such that the physician may view the notification and make a decision (e.g., regarding the dosage of medication) based on the information provided. In some cases, the wearable computing device may provide an audio notification (e.g., an alarm), a physical notification (e.g., a vibration), or a visual notification indicating that the user is at risk for respiratory depression. The visual notification may further include an image (e.g., a graphical display showing the determined respiratory rate over time) or words. As another particular example, the wearable computing device may communicate with a connected secondary device such that the secondary computing device provides a notification indicating that the user is at risk for respiratory depression.

[0062] Although the subject matter of the present disclosure has been described in detail with respect to various specific and exemplary embodiments thereof, each example is provided for the purpose of illustration and not for the purpose of limiting the present disclosure. Those skilled in the art, upon understanding the above content, can easily make modifications, variations, and equivalents of such embodiments. Thus, the present disclosure does not exclude the inclusion of such modifications, variations, and / or additions to the subject matter as would be readily apparent to those skilled in the art. For example, features illustrated or described as part of one embodiment can be used with another embodiment to produce yet another embodiment. Thus, the present disclosure is intended to cover such modifications, variations, and equivalents.

Claims

1. 1. A wearable computing device, comprising: one or more processors; A heart rate sensor; a non-transitory computer-readable memory configured to store instructions that, when executed by the one or more processors, cause the one or more processors to perform operations, the operations including: acquiring heart rate data via the heart rate sensor; determining a respiration rate based at least in part on the heart rate data; determining an overall respiratory risk metric associated with a user wearing the wearable computing device based at least in part on the respiratory rate, the overall respiratory risk metric representing a likelihood that the user is at risk of respiratory depression; determining whether the user is at risk of respiratory depression based at least in part on the overall respiratory risk metric; in response to determining that the user is at risk of respiratory depression, providing a notification to the user indicating that the user is at risk of respiratory depression; 2. A wearable computing device comprising:

2. determining whether the user is at risk of respiratory depression; comparing the overall respiratory risk metric to a threshold; determining that the user is at risk of respiratory depression if the overall respiratory risk metric meets a threshold criterion; The wearable computing device of claim 1 , comprising:

3. The wearable computing device of claim 1 , wherein the heart rate sensor includes one or more optical sensors.

4. determining said respiratory rate, determining respiratory sinus arrhythmia based at least in part on the heart rate data; determining the respiratory rate based at least in part on the respiratory sinus arrhythmia; The wearable computing device of claim 1 , comprising:

5. determining said respiratory rate, acquiring, via the heart rate sensor, heart rate data associated with a particular time period; determining a power spectral density based at least in part on the heart rate data associated with the particular time period; determining a spectral peak based at least in part on the power spectral density; determining the respiration rate based at least in part on the spectral peaks; and The wearable computing device of claim 4 , further comprising:

6. The operation, 10. The wearable computing device of claim 1, further comprising: generating a graphical display illustrating the determined respiration rate over a sustained period of time based at least in part on the determined respiration rate.

7. determining the overall respiratory risk metric, determining at least one metric related to the respiratory depression risk based at least in part on the respiratory rate, the at least one metric comprising: determining a percentage of a predetermined period of time during which the respiration rate is below a threshold; determining the overall respiratory risk metric based at least in part on the respiratory rate and the one or more metrics; The wearable computing device of claim 1 , comprising:

8. determining the overall respiratory risk metric, obtaining, via user input, a plurality of demographic factors; determining the overall respiratory risk metric based at least in part on at least one of the respiratory rate or one or more of the plurality of demographic factors; The wearable computing device of claim 1 , comprising:

9. 10. The wearable computing device of claim 1, wherein determining the overall respiratory risk metric is based at least in part on at least one of the respiratory rate or a determined minute ventilation value.

10. The wearable computing device of claim 1 , wherein determining the overall respiratory risk metric is based at least in part on at least one of the respiratory rate or a determined tidal volume value.

11. 11. The wearable computing device of claim 10, wherein the overall respiratory risk metric is based at least in part on at least one of the respiratory rate, or a tidal volume variation value based at least in part on the determined tidal volume value.

12. 1. A computer-implemented method for determining whether a user wearing a wearable computing device is at risk for respiratory depression, comprising: acquiring heart rate data via a heart rate sensor; determining a respiration rate based at least in part on the heart rate data; determining an overall respiratory risk metric associated with a user wearing the wearable computing device based at least in part on the respiratory rate, the overall respiratory risk metric representing a likelihood that the user is at risk of respiratory depression; determining whether the user is at risk of respiratory depression based at least in part on the overall respiratory risk metric; in response to determining that the user is at risk of respiratory depression, providing a notification to the user indicating that the user is at risk of respiratory depression; A computer-implemented method comprising:

13. determining whether the user is at risk of respiratory depression; comparing the overall respiratory risk metric to a threshold; determining that the user is at risk of respiratory depression if the overall respiratory risk metric meets a threshold criterion; 13. The computer-implemented method of claim 12, comprising:

14. The computer-implemented method of claim 12 , wherein the heart rate sensor includes one or more optical sensors.

15. 13. The computer-implemented method of claim 12, further comprising generating a graphical representation of the determined respiration rate over a duration based at least in part on the determined respiration rate.

16. determining the overall respiratory risk metric, determining at least one metric related to the respiratory depression risk based at least in part on the respiratory rate, the at least one metric including a percentage of a predetermined period of time during which the respiratory rate is below a threshold; determining the overall respiratory risk metric based at least in part on the respiratory rate and the at least one metric; 13. The computer-implemented method of claim 12, comprising:

17. determining the overall respiratory risk metric, obtaining, via user input, a plurality of demographic factors; determining the overall respiratory risk metric based at least in part on a combination of the respiratory rate and the plurality of demographic factors; 13. The computer-implemented method of claim 12, comprising:

18. 13. The computer-implemented method of claim 12, wherein determining the overall respiratory risk metric is based at least in part on a combination of the respiratory rate and determined minute ventilation values.

19. 13. The computer-implemented method of claim 12, wherein determining the overall respiratory risk metric is based at least in part on a combination of the respiratory rate and determined tidal volume values.

20. 20. The computer-implemented method of claim 19, wherein the overall respiratory risk metric is based at least in part on a combination of the respiratory rate and a tidal volume variation value that is based at least in part on the determined tidal volume value.

Images