Patent Application
20200268265
This disclosure relates to hearing instruments.
In many people, hearing loss is a gradual process that occurs over many years. As a result, many people grow accustomed to living with reduced hearing without recognizing the auditory experiences and opportunities they are missing. For example, a person might not realize how much less conversation he or she engages in due to his or her hearing loss. As a result of hearing loss, reduced audibility, and reduced social interaction, patients also experience follow-on effects such as dementia, depression, and generally poorer health.
This disclosure describes a computing system that receives data from one or more hearing instruments. Additionally, the computing system determines, based on the data received from the one or more hearing instruments, a heart health measure for a user of the one or more hearing instruments. The heart health measure is an indication of one or more aspects of a health of a heart of the user. The computing system may output an indication of the heart health measure. Other examples of this disclosure use data received from the one or more hearing instruments to determine levels of emotional stress. Still other examples of this disclosure use data received from the one or more hearing instruments to determine whether the user has fallen.
In one example, this disclosure describes a computer-implemented method comprising: receiving, by a computing system comprising a set of one or more electronic computing devices, heart-related data from one or more hearing instruments; determining, by the computing system, based on the heart-related data received from the one or more hearing instruments, a heart health measure for a user of the one or more hearing instruments, the heart health measure being an indication of one or more aspects of a health of a heart of the user; and outputting, by the computing system, an indication of the heart health measure to the user of the hearing instruments.
In another example, this disclosure describes a computer-implemented method comprising: receiving, by a computing system comprising one or more electronic computing devices, stress-related data from one or more hearing instruments; determining, by the computing system, based on the stress-related data, an emotional stress measure of a user of the one or more hearing instruments, the emotional stress measure being an indication of one or more aspects of a level of emotional stress of the user; and outputting, by the computing system, an indication of the emotional stress measure to the user of the hearing instruments.
In another example, this disclosure describes a computer-implemented method comprising: obtaining, by a computing system, physiological data based on signals generated by a first set of one or more sensors of a hearing instrument, wherein the physiological data includes heart-related data; modifying, by the computing system, a sensitivity level of a fall detection algorithm based on the physiological data; and performing, by the computing system, the fall detection algorithm to determine, based on signals from a second set of one or more sensors of the hearing instrument, whether a user of the hearing instrument has fallen.
In another example, this disclosure describes a computer-implemented method comprising: determining, by a computing system, whether a user of a hearing instrument has fallen; based on a determination that the user has fallen, activating, by the computing system, one or more sensors of the hearing instrument that generate heart-related data regarding the user; determining, by the computing system, based on the heart-related data, whether to prompt the user to confirm that the user has fallen; and based on a determination to prompt the user to confirm that the user has fallen, causing, by the computing system, the hearing instrument to generate a message prompting the user to confirm that the user has fallen.
This disclosure also describes examples of computing systems having one or more processors configured to perform the methods. Also described are computer-readable storage media having instructions for causing computer systems to perform the methods.
The details of one or more aspects of the disclosure are set forth in the accompanying drawings and the description below. Other features, objects, and advantages of the techniques described in this disclosure will be apparent from the description, drawings, and claims.
In this disclosure, ordinal terms such as “first,” “second,” “third,” and so on, are not necessarily indicators of positions within an order, but rather may be used to distinguish different instances of the same thing. Examples provided in this disclosure may be used together, separately, or in various combinations.
Additionally, system 100 includes a computing system 104. Computing system 104 comprises one or more electronic devices. For instance, in the example of
Hearing instruments 102 may comprise one or more of various types of devices that are configured to provide auditory stimuli to a user and that are designed for wear and/or implantation at, on, or near an ear of the user. Hearing instruments 102 may be worn, at least partially, in the ear canal or concha. One or more of hearing instruments 102 may include behind the ear (BTE) components that are worn behind the ears of the user. In some examples, hearing instruments 102 comprise devices that are at least partially implanted into or osseointegrated with the skull of the user. In some examples, one or more of hearing instruments 102 is able to provide auditory stimuli to the user via a bone conduction pathway.
In any of the examples of this disclosure, each of hearing instruments 102 may comprise a hearing assistance device. Hearing assistance devices include devices that help a user hear sounds in the user's environment. Example types of hearing assistance devices may include hearing aid devices, Personal Sound Amplification Products (PSAPs), cochlear implant systems (which may include cochlear implant magnets, cochlear implant transducers, and cochlear implant processors), and so on. In some examples, hearing instruments 102 are over-the-counter, direct-to-consumer, or prescription devices. Furthermore, in some examples, hearing instruments 102 include devices that provide auditory stimuli to the user that correspond to artificial sounds or sounds that are not naturally in the user's environment, such as recorded music, computer-generated sounds, or other types of sounds. For instance, hearing instruments 102 may include so-called “hearables,” earbuds, earphones, or other types of devices. Some types of hearing instruments provide auditory stimuli to the user corresponding to sounds from the user's environmental and also artificial sounds.
In some examples, one or more of hearing instruments 102 includes a housing or shell that is designed to be worn in the ear for both aesthetic and functional reasons and encloses the electronic components of the hearing instrument. Such hearing instruments may be referred to as in-the-ear (ITE), in-the-canal (ITC), completely-in-the-canal (CIC), or invisible-in-the-canal (IIC) devices. In some examples, one or more of hearing instruments 102 may be behind-the-ear (BTE) devices, which include a housing worn behind the ear contains all of the electronic components of the hearing instrument, including the receiver (i.e., the speaker). The receiver conducts sound to an earbud inside the ear via an audio tube. In some examples, one or more of hearing instruments 102 may be receiver-in-canal (RIC) hearing-assistance devices, which include a housing worn behind the ear that contains electronic components and a housing worn in the ear canal that contains the receiver. The techniques of this disclosure are not limited to the form of the hearing instrument, mobile device, or server device shown in
Hearing instruments 102 may be configured to communicate with each other. For instance, in any of the examples of this disclosure, hearing instruments 102 may communicate with each other using one or more wirelessly communication technologies. Example types of wireless communication technology include Near-Field Magnetic Induction (NFMI) technology, a 900 MHz technology, a BLUETOOTH™ technology, a WI-FI™ technology, audible sound signals, ultrasonic communication technology, infrared communication technology, an inductive communication technology, or another type of communication that does not rely on wires to transmit signals between devices. In some examples, hearing instruments 102 use a 2.4 GHz frequency band for wireless communication. In examples of this disclosure, hearing instruments 102 may communicate with each other via non-wireless communication links, such as via one or more cables, direct electrical contacts, and so on.
Hearing instruments 102 are configured to communicate wirelessly with computing system 104. For example, hearing instruments 102 and computing system 104 may communicate wirelessly using a BLUETOOTH™ technology, a WIFI™ technology, or another type of wireless communication technology. In the example of
Mobile device 106 may communicate with server device 108 via communication network 110. Communication network 110 may comprise one or more of various types of communication networks, such as cellular data networks, WIFI™ networks, the Internet, and so on. Mobile device 106 may communicate with server device 108 to store data to and retrieve data from server device 108. Thus, from the perspective of mobile device 106 and hearing instruments 102, server device 108 may be considered to be in the “cloud.”
Hearing instruments 102 may implement a variety of features that help a wearer of hearing instruments 102 hear better. For example, hearing instruments 102 may amplify the intensity of incoming sound, amplify the intensity of certain frequencies of the incoming sound, or translate or compress frequencies of the incoming sound. In another example, hearing instruments 102 may implement a directional processing mode in which hearing instruments 102 selectively amplifies sound originating from a particular direction (e.g., to the front of the wearer) while potentially fully or partially canceling sound originating from other directions. In other words, a directional processing mode may selectively attenuate off-axis unwanted sounds. The directional processing mode may help wearers understand conversations occurring in crowds or other noisy environments. In some examples, hearing instruments 102 may reduce noise by canceling out or attenuating certain frequencies. Furthermore, in some examples, hearing instruments 102 may help a wearer enjoy audio media, such as music or sound components of visual media, by outputting sound based on audio data wirelessly transmitted to hearing instruments 102.
As previously mentioned, a person may lose their hearing gradually over the course of many years. Because hearing loss may be a slow process, a person who is gradually losing his or her hearing may grow accustomed to living with impaired hearing and not realize the value added to the person's life by being able to fully access the auditory environment. For instance, the person may not realize how much less time he or she spends in conversation or enjoying audio media because of the person's hearing loss. This may remain true even after a person acquires a hearing instrument. That is, because a person having a hearing instrument does not always wear the hearing instrument, the person may not realize the extent to which the hearing instrument enhances his or her life while wearing the hearing instrument as opposed to when the person is not wearing the hearing instrument.
Research has shown that people who more frequently interact with others and their environments tend to have better cognitive skills and better emotional health, both of which may lead to better health outcomes. However, depression and physical inactivity may be more common among people who seldom converse with others. This problem may be especially acute for older people, who are more likely to have hearing loss.
In accordance with one or more techniques of this disclosure, a cognitive benefit measure is calculated based on data collected by hearing instruments 102. In some examples, the cognitive benefit measure is an indication of a change of a cognitive benefit of the wearer of hearing instruments 102 attributable to use of hearing instruments 102 by the wearer of hearing instruments 102. In some examples, hearing instruments 102 calculate the cognitive benefit measure. In other examples, the cognitive benefit measure is calculated by one or more computing devices of computing system 104. For instance, in the example of
As described herein, computing system 104 may calculate a cognitive benefit measure for a wearer of hearing instruments 102 based on a plurality of sub-components of the cognitive benefit measure. For example, as part of determining the cognitive benefit measure, computing system 104 may determine a plurality of sub-components of the cognitive benefit measure and may determine the cognitive benefit measure based on the plurality of sub-components of the cognitive benefit measure. In some examples, hearing instruments 102 determines one or more of the sub-components of the cognitive benefit measure. In some examples, the sub-components include one or more of an “audibility” sub-component, an “intelligibility” sub-component, a “comfort” sub-component, a “focus” sub-component, a “sociability” sub-component, and a “connectivity” sub-component. In some examples, each of the sub-components shares a common range (e.g., from 0 to 100), which may make combination of data efficient. In some examples, computing system 104 may reset each of the sub-components for each scoring period. For instance, computing system 104 may reset the values of the sub-components once per day or other recurrence period.
The audibility sub-component for a wearer of hearing instruments 102 is a measure of the improvement in audibility provided to the wearer by hearing instruments 102. The audibility sub-component may be considered the amount of environmental sounds that are quieter than the wearer's unaided audiometric thresholds, but that are made audible through amplification by hearing instruments 102, scaled to a range used by the other sub-components. In other words, the audibility sub-component is related to hearing more quiet sounds in the wearer's environment. To determine the audibility sub-component, computing system 104 may compare a patient's hearing thresholds to a standardized stimulus response across frequency. For instance, in some examples, the audibility sub-component is calculated by subtracting the percentage of a standardized sound stimulus (e.g., a moderate-level (65 dB SPL) long-term averaged speech input) that is audible without a hearing instrument from the percentage of sound that is audible with a hearing instrument; both percentages are calculated by dividing the number of audible frequency channels in hearing instruments 102 by the number of total channels in the device. A channel in a hearing instrument is a subset of frequencies over which the processing of incoming sound can be different from that at other frequencies. For example, a hearing aid channel may have a highpass cutoff of 1480 Hz, and a lowpass cutoff of 1720 Hz. So, the “total channels” in a hearing aid are the number of distinct divisions of frequency. An “audible channel” is one wherein the level of the input stimulus (in dB SPL) plus the gain applied to the stimulus (in dB) results in an overall level that is above the hearing threshold of the listener in that frequency range. Each of the unaided thresholds corresponds to a different frequency. A wearer of hearing instruments 102 is unable to hear the frequency corresponding to an unaided threshold if an intensity of a sound at the corresponding frequency is below the unaided threshold. In one example, audibility sub-component is calculated as a number of frequency bands made audible by hearing instruments 102 divided by a total number of frequency bands handled by hearing instruments 102. In this example, each of the frequency bands may be a contiguous range within a frequency spectrum.
The intelligibility sub-component for the wearer of hearing instruments 102 is a numerical estimate of the improvement in speech understanding provided to the wearer by hearing instruments 102. The intelligibility sub-component may be considered a measure of understanding more words in conversation. In some examples, the intelligibility sub-component is a percentage improvement in intelligibility. For instance, in one such example, the intelligibility sub-component is equal to a first value multiplied by 100, where the first value is equal to a third value subtracted from a second value. The second value is equal to an aided intelligibility score, and the third value is equal to an unaided intelligibility score. The intelligibility scores both are calculated from the Speech Intelligibility Index (SII), which is a standardized measure of intelligibility. Of course, other measures of intelligibility scaled to the same range as the other sub-components may be used.
The comfort sub-component for the wearer of hearing instruments 102 is a numerical value indicating a measure of noise reduction provided by hearing instruments 102. The comfort sub-component may be considered a measure of noise reduction in the wearer's environment. In some examples, the comfort sub-component is equal to an average or a sum of noise reduction. For instance, in one such example, the comfort sub-component is equal to a first value. In this example, the first value is equal to a sum of the average noise reduction (in dB) across memories and environments, weighted by the time spent in each memory in a set of one or more memories and each environment in a set of one or more environments, scaled to the standardized range used in the other sub-components. In this example, hearing instruments 102 comprises different memories, which have different signal processing schemes tailored to specific listening situations. For example, there is a “Restaurant” memory, a “Music” memory, and so on. Each of the environments is an acoustic situation that hearing instruments 102 classify automatically. Example types of environments include a “Speech-in-Noise” environment, a “Quiet” environment, a “Machine Noise” environment, and so on.
The focus sub-component for the wearer of hearing instruments 102 is a numerical value indicating an amount of time hearing instruments 102 have spent in a directional processing mode. The focus sub-component may be considered a measure of the wearer being able to hear sounds most important to the wearer. The focus sub-component may be scaled to be in a range used by the other sub-components. For instance, in some examples, the focus sub-component is equal to a percentage of time spent in a directional processing mode. For instance, in one such example, the focus sub-component is equal to a first value multiplied by 100, where the first value is equal to a second value divided by a third value; the second value being equal to an amount of time spent in a directional processing mode; the third value being equal to the total amount of time hearing instruments 102 is powered on. In an omni-directional mode, hearing instruments 102 do not selectively amplify or attenuate sounds from particular directions.
The sociability sub-component for the wearer of hearing instruments 102 is a numerical value indicating an amount of time hearing instruments 102 have spent in auditory environments involving speech. The sociability sub-component may be considered a measure of time spent in conversation. The sociability sub-component may be scaled to be in a range used by the other sub-components. In some examples, the sociability sub-component is a percentage of time spent in social situations. For instance, in one such example, the sociability sub-component is equal to a first value multiplied by 100, where the first value is equal to a second value divided by a third value. In this example, the second value is equal to the amount of time spent in speech and speech in noise, and the third value is equal to the total amount of time that hearing instruments 102 is powered on.
The connectivity sub-component for the wearer of hearing instruments 102 is a numerical value indicating an amount of time hearing instruments 102 have spent streaming audio data from devices that are wirelessly connective to hearing instruments 102. The connectivity sub-component may be considered a measure of time connecting with media. In some examples, the connectivity sub-component for the wearer is a measure of the amount of time spent streaming media (or the amount of time hearing instruments 102 spent maintaining connectivity for streaming media) relative to an amount of time, such as an amount of time associated with a maximum benefit attained from streaming media. This measure may be on a same scale (e.g., 0 to 100, 0 to 50, etc.) as the other sub-components. For instance, in one such example, the connectivity sub-component may be equal to a first value. In this example, the first value is equal to an amount of time spent streaming from a separate wireless device, up to a time associated with the maximum benefit attained from streaming media, divided by the time associated with the maximum benefit attained from streaming media.
Computing system 104 may determine the cognitive benefit measure based on the sub-components in various ways. For example, computing system 104 may determine the cognitive benefit measure based on an average or weighted average of the sub-components. In other words, the cognitive benefit measure may be an average of all the sub-component data, although the sub-components may be differentially weighted before averaging occurs. For example, the “connectivity” sub-component may be weighted more than the other measures because the expectation is that the connectivity sub-component typically yields a relatively small score because patients spend only a small percentage of the time streaming audio to their hearing aids. In some examples, computing system 104 determines the weights used in calculating the weighted average by normalizing the sub-components by a maximum benefit expected or predicted for each sub-component.
In some examples, computing system 104 scales the cognitive benefit measure (and the sub-components) by use time of hearing instruments 102. For example, if a user does not wear his or her hearing instrument on a given day, the cognitive benefit measure may not be calculated, but the more the user wears hearing instruments 102, the larger the cognitive benefit measure. This type of scaling may be intuitive for the user, and time spent using hearing instruments 102 may be one contributing factor to the cognitive benefit measure over which the user has the most control.
In some examples, computing system 104 may store historical cognitive benefit measures for the wearer of hearing instruments 102. For example, computing system 104 may store a cognitive benefit measure for each day or other time period. Additionally, computing system 104 may output data based on the historical cognitive benefit measures for display. In this way, the wearer of hearing instruments 102 may be able to track the wearer's cognitive benefit measures over time. For instance, the wearer of hearing instruments 102 may be able to track his or her progress.
As noted above, the cognitive benefit measure may be calculated based on data collected by hearing instruments 102. In some examples, hearing instruments 102 writes data to a data log. For example, hearing instruments 102 may store, in memory, counter data used for calculation of sub-components. For instance, hearing instruments 102 may store data indicating an amount of time hearing instruments 102 spent streaming media, an amount of time spent in a directional processing mode, and other values. Hearing instruments 102 may flush these values out to the data log on a period basis and may reset the values.
Hearing instruments 102 may communicate data in the data log to computing system 104. Computing system 104 may receive, from hearing instruments 102, the data from the data log. Computing system 104 may use the received information to determine the cognitive benefit measure.
Hearing instruments 102 may write the data to the data log on a periodic basis, e.g., once per time period. In some examples, the duration of the time period changes during the life cycle of hearing instruments 102. For example, hearing instruments 102 may write data to the data log once every 15 minutes during the first two years of use of hearing instruments 102 and once every 60 minutes following the first two years of use of hearing instruments 102. Because hearing instruments 102 send data in the data log, as opposed to the live counter data, and hearing instruments 102 may update the data log on a periodic basis, the user may be able to access an updated cognitive benefit measures at least as often as the same periodic basis.
Furthermore, in some examples, in addition to determining a cognitive benefit measure (e.g., a brain score) for the wearer of hearing instruments 102, computing system 104 may use data collected by hearing instruments 102 to determine a body fitness measure for the wearer of hearing instruments 102. The body fitness measure for the wearer of hearing instruments 102 may be an indication of physical activity in which the wearer of hearing instruments 102 engages while wearing hearing instruments 102. Like the cognitive benefit measure, computing system 104 may determine the body fitness measure based on a plurality of sub-components. For instance, computing system 104 may determine the body fitness measure based on a “steps” sub-component, an “activity” sub-component, and a “move” sub-component. The “steps” component may indicate a number of steps (e.g., while walking or running) that the wearer of hearing instruments 102 has taken during a current scoring period. The “activity” sub-component may be a measure of vigorous activity in which the wearer of hearing instruments 102 has engaged during the current scoring period. The “move” sub-component may be based on a number time of intervals during the current scoring period in which the wearer of hearing instruments 102 moves for a given amount of time. The current scoring period may be an amount of time after which computing system 104 resets the cognitive benefit measure and/or the body fitness measure. For instance, the current scoring period may be one day, one week, or another time period. Thus, the cognitive benefit measure and the body fitness measure, and sub-components thereof, may be reset periodically or recurrently.
In some examples, computing system 104 may determine values of one or more of the sub-components of the cognitive benefit measure and the body fitness measure using goals. For instance, in one example with respect to the “steps” sub-component of the body fitness measure, the wearer of hearing instrument 103 may set a number of steps to take during a scoring period as a goal for the “steps” sub-component. In this example, computing system 104 may determine the value of the “steps” component based on the progress of the wearer of hearing instruments 102 during the scoring period toward the goal for the “steps” component. In some examples, such goals may be user-configurable. For example, computing system 104 may permit a user (e.g., the wearer of hearing instruments 102, a caregiver, a health care provider, or another person) to set the goals for particular wearers of hearing instruments or for a population of patients. For example, wearers of hearing instruments may be characterized (e.g., classified) using one or more of various techniques, such as artificial intelligence using demographic or medical information. In this example, goal(s) may be determined based upon such characterizations about wearers of hearing instruments.
In some examples, computing system 104 may determine a “wellness” measure (e.g., a wellness score) for the wearer of hearing instruments 102. The wellness measure for the wearer of hearing instruments 102 may be an indication of an overall wellness of the wearer of hearing instruments 102. Computing system 104 may determine the wellness measure based on the cognitive benefit measure and the body fitness measure of the wearer of hearing instruments 102 for a scoring period. For instance, computing system 104 may determine the wellness measure as a weighted sum of the cognitive benefit measure, the body fitness measure, and possibly one or more other factors. In some examples, computing system 104 may determine the wellness measure as a multiplication product of the cognitive benefit measure and the body fitness measure.
In some examples, hearing instruments 102 calculate the body fitness measure and/or the wellness measure. In other examples, the body fitness measure and/or the wellness measure is calculated by one or more computing devices of computing system 104. For instance, in the example of
Computing system 104 may be configured to generate alerts based on one or more of a cognitive benefit measure, body fitness measure, a wellness measure of a wearer of hearing instruments 102, or a combination thereof. An alert may alert the wearer of hearing instruments 102 or another person to the occurrence or risk of occurrence of a particular condition. In other words, computing system 104 may generate, based on the cognitive benefit measure, an alert to the wearer of hearing instruments 102 or another person. Computing system 104 may transmit an alert to a caregiver, healthcare professional, family member, or other person or persons. Computing system 104 may generate an alert when one or more of various conditions occur. For example, computing system 104 may generate an alert if computing system 104 detects a consistent downward trend in the wearer's body fitness measure, cognitive benefit measure, and/or wellness measure. In another example, computing system 104 may generate an alert if computing system 104 determines that the wearer's body fitness measure, cognitive benefit measure, and/or wellness measure are below one or more thresholds for a threshold amount of time (e.g., a particular number of days). In some examples, responsive to declaration of an alert, a therapy may be changed, or additional diagnostics may be performed, encouragement may be provided, or a communication may be initiated. In other examples, hearing instruments 102 may generate the alerts.
In some examples, hearing instruments 102 does not have a real time clock that keeps track of the current time and date. Not including such a real time clock in hearing instruments 102 may be advantageous for various reasons. For instance, because of the extreme size constraints on hearing instruments 102, the batteries of hearing instruments 102 may need to be very small. Maintaining a real time clock in hearing instruments 102 may consume a significant amount of power from a battery or other power source that may be better used for other purposes. Hearing instruments 102 may produce a clock signal that cycles at a given frequency so that hearing instruments 102 is able to track relative time. For instance, hearing instruments 102 may be able to count clock cycles to determine that a given amount of time (e.g., five minutes) has passed following a given clock cycle, but without a real-time clock hearing instruments 102 may not be equipped to relate that relative time to an actual time and date (e.g., 11:34 A.M. on Aug. 22, 2017). Moreover, maintaining a real time clock based on this clock signal may require hearing instruments 102 to continue the clock signal even while hearing instruments 102 is not in use, which may consume a significant amount of battery power.
However, several of the sub-components of the cognitive benefit measure and the body fitness measure are time-dependent. For example, the “use score” sub-component may be based on how much time the wearer of hearing instruments 102 uses the hearing instruments 102 during a scoring period. In another example, the “engagement” sub-component may be based at least in part on how much time the wearer of hearing instruments 102 engages in conversation during a scoring period and how much time the wearer of hearing instruments 102 uses hearing instruments 102 to stream audio media during the scoring period. Moreover, in some examples, computing system 104 may need to determine times associated with log data items received from hearing instruments 102 to determine whether the log data items are associated with a current scoring period.
This disclosure describes techniques that may overcome the problems associated with determining sub-components of the cognitive benefit measure and/or the body fitness measure in the absence of a real-time clock in hearing instruments 102. For example, hearing instruments 102 may maintain a data log that stores log data items, which may include sub-component data. The sub-component data may include data from which values of sub-components may, at least partially, be determined. For example, an inertial measurement unit (IMU) of hearing instruments 102 may periodically write data to the data log indicating the number of steps taken by the wearer of hearing instruments 102. In accordance with one or more techniques of this disclosure, hearing instruments 102 may receive timestamps from a computing device in computing system 104. For example, hearing instruments 102 may receive timestamps from mobile device 106. A timestamp may be a value that indicates a time. For instance, a timestamp may indicate a number of seconds that have passed since a fixed real time (e.g., since Jan. 1, 1970). When recording data (e.g., log data items) to the data log, hearing instruments 102 may include the timestamp in the log data item. For example, hearing instruments 102 may record a log data item in the data log indicating that the wearer of hearing instruments 102 has started using hearing instruments 102. In this example, hearing instruments 102 may include the timestamp in the log data item. In this example, computing system 104 may use this data recorded in the data log to determine the “use score” sub-component.
Thus, computing system 104 may send timestamps to hearing instruments 102. Additionally, computing system 104 may receive a plurality of log data items from hearing instruments 102. Each of the log data items may include log data and one of the timestamps sent to hearing instruments 102 by computing system 104. Computing system 104 may determine, based on the timestamps and the log data in the log data items, at least one of the cognitive benefit measure or the body fitness measure. For instance, computing system 104 may use the timestamps in the log data items to determine which log data items are from a current scoring period and then only use log data in the log data items from the current scoring period when determining values of the sub-components of the cognitive benefit measure and/or body fitness measure.
Hearing instruments 102 may receive timestamps from computing system 104 in response to one or more of various events. For example, hearing instruments 102 may send a timestamp request to computing system 104 when preparing to write data to the data log. In some examples, hearing instruments 102 may periodically request timestamps from computing system 104. In some examples, computing system 104 may be configured to periodically send timestamps to hearing instruments 102 on an asynchronous basis. That is, in this example, it may not be necessary for hearing instruments 102 to send a request to computing system 104 for timestamps. For instance, computing system 104 may send a timestamp to hearing instruments 102 once every 60 seconds, 30 seconds, or other time period. In this example, hearing instruments 102 may store the timestamp (potentially overwriting a previous version of the timestamp) and then include a copy of the timestamp in a log data item when storing the log data item to the data log. Because exact precision may not be necessary when determining values of sub-components of the cognitive benefit measure and the body fitness measure, including an exactly correct time in a log data item may be unnecessary. Thus, the cycle time for hearing instruments 102 receiving timestamps may be set slow enough that an amount of energy consumed by wireless receiving and writing the timestamps to memory may be less than the amount of energy that would be consumed by hearing instruments 102 maintaining its own real time clock, while allowing for reasonable accuracy.
In some examples, computing system 104 may output a graphical user interface (GUI) for display on a display screen. For example, mobile device 106 may output the GUI for display on a display screen of mobile device 106. In another example, server device 108 may generate data defining a webpage comprising the GUI and send the data mobile device 106 or another computing device (e.g., a personal computer) for rendering for display by a web browser application. The GUI may include content similar to that shown in
In the example of
Additionally, in the example of
Storage device(s) 300 may store data. Storage device(s) 300 may comprise volatile memory and may therefore not retain stored contents if powered off. Examples of volatile memories may include random access memories (RAM), dynamic random access memories (DRAM), static random access memories (SRAM), and other forms of volatile memories known in the art. Storage device(s) 300 may further be configured for long-term storage of information as non-volatile memory space and retain information after power on/off cycles. Examples of non-volatile memory configurations may include magnetic hard discs, optical discs, floppy discs, flash memories, or forms of electrically programmable memories (EPROM) or electrically erasable and programmable (EEPROM) memories.
Radio 302 may enable hearing instrument 102 to send data to and receive data from one or more other computing devices. For example, radio 302 may enable hearing instruments 102 to send data to and receive data from mobile device 106 (
Receiver 304 comprises one or more speakers for generating audible sound. Microphone 308 detects incoming sound and generates an electrical signal (e.g., an analog or digital electrical signal) representing the incoming sound. Processor(s) 306 may process the signal generated by microphone 308 to enhance, amplify, or cancel-out particular channels within the incoming sound. Processor(s) 306 may then cause receiver 304 to generate sound based on the processed signal. In some examples, processor(s) 306 include one or more digital signal processors (DSPs).
Processor(s) 306 may cause radio 302 to transmit one or more of various types of data. For example, processor(s) 306 may cause radio 302 to transmit data to computing system 104. Furthermore, radio 302 may receive audio data from computing system 104 and processor(s) 306 may cause receiver 304 to output sound based on the audio data.
In some examples, hearing instrument 102 is a “plug-n-play” type of device. In some examples, hearing instruments 102 is programmable to help the user manage things like wind noise. Furthermore, in some examples, hearing instruments 102 comprises a custom earmold or a standard receiver module at the end of a RIC cable. The additional volume in a custom earmold may allow room for components such as sensors (accelerometers, heartrate monitors, temp sensors), a woofer-tweeter, (providing richer sound for music aficionados), and an acoustic valve that provides occlusion when desired. In some examples, a six conductor RIC cable is used for in hearing instruments with sensors, woofer-tweeters, and/or acoustic valves.
In the example of
As shown in the example of
Storage device(s) 416 may store information required for use during operation of computing device 400. In some examples, storage device(s) 416 have the primary purpose of being a short term and not a long-term computer-readable storage medium. Storage device(s) 416 may be volatile memory and may therefore not retain stored contents if powered off. Storage device(s) 416 may further be configured for long-term storage of information as non-volatile memory space and retain information after power on/off cycles. In some examples, processor(s) 402 on computing device 400 read and may execute instructions stored by storage device(s) 416.
Computing device 400 may include one or more input device(s) 408 that computing device 400 uses to receive user input. Examples of user input include tactile, audio, and video user input. Input device(s) 408 may include presence-sensitive screens, touch-sensitive screens, mice, keyboards, voice responsive systems, microphones or other types of devices for detecting input from a human or machine.
Communication unit(s) 404 may enable computing device 400 to send data to and receive data from one or more other computing devices (e.g., via a communications network, such as a local area network or the Internet). In some examples, communication unit(s) 404 may include wireless transmitters and receivers that enable computing device 400 to communicate wirelessly with the other computing devices. For instance, in the example of
Output device(s) 410 may generate output. Examples of output include tactile, audio, and video output. Output device(s) 410 may include presence-sensitive screens, sound cards, video graphics adapter cards, speakers, liquid crystal displays (LCD), or other types of devices for generating output.
Processor(s) 402 may read instructions from storage device(s) 416 and may execute instructions stored by storage device(s) 416. Execution of the instructions by processor(s) 402 may configure or cause computing device 400 to provide at least some of the functionality ascribed in this disclosure to computing device 400. As shown in the example of
Execution of instructions associated with operating system 420 may cause computing device 400 to perform various functions to manage hardware resources of computing device 400 and to provide various common services for other computer programs. Execution of instructions associated with application modules 422 may cause computing device 400 to provide one or more of various applications (e.g., “apps,” operating system applications, etc.). Application modules 422 may provide particular applications, such as text messaging (e.g., SMS) applications, instant messaging applications, email applications, social media applications, text composition applications, and so on.
Execution of instructions associated with companion application 424 may cause computing device 400 to perform one or more of various functions described in this disclosure with respect to computing system 104 (
In some examples, a GUI of companion application 424 has a plurality of different sections, that may or may not appear concurrently. For example, the GUI of companion application 424 may include a section for controlling the intensity of sound generated by (e.g., the volume of) hearing instruments 102, a section for controlling how hearing instruments 102 attenuate wind noise, a second for finding hearing instruments 102 if lost, and so on. Additionally, the GUI of companion application 424 may include a cognitive benefit section that displays data regarding a cognitive benefit measure for the wearer of hearing instruments 102. In some examples, the cognitive benefit section of companion application 424 displays a diagram similar to that shown in the example of
In some examples, companion application 424 may request data for calculating a cognitive benefit measure or body fitness measure from hearing instruments 102 each time mobile device 106 receives an indication of user input to navigate to the cognitive benefit section or body fitness measure section of companion application 424. In this way, a wearer of hearing instruments 102 may get real-time confirmation that companion application 424 is communicating with hearing instruments 102, that the data displayed are current, and may ensure that the wireless transfer of the data-log data does not interrupt or interfere with other processes in companion application 424, or on computing device 400 device. Furthermore, requesting data from hearing instruments 102 only when computing device 400 receives an indication of user input to navigate to the cognitive benefit section, the body fitness measure section, or the wellness measure section of companion application 424 may reduce demands on a power source (e.g., power source 312 of
Companion application 424 may store one or more of various types of data as historical data 426. Historical data 426 may comprise a database for storing historic data related to cognitive benefit. For example, companion application 424 may store, in historical data 426, cognitive benefit measures, body fitness measures, sub-component values, data from hearing instruments 102, and/or other data. Companion application 424 may retrieve data from historical data 426 to generate a GUI for display of past cognitive benefit measures, body fitness measures, and wellness measures of the wearer of hearing instruments 102.
In the example of
Additionally, computing system 104 may determine, based on the data received from hearing instruments 102, a cognitive benefit measure for a wearer of hearing instruments 102 (502). The cognitive benefit measure may be an indication of a change of a cognitive benefit of the wearer of hearing instruments 102 attributable to use of hearing instruments 102 by the wearer of hearing instruments 102. In some examples, computing system 104 may scale the cognitive benefit measure based on an amount of time the wearer spends wearing hearing instruments 102.
Furthermore, in the example of
As shown in the example of
As part of determining the plurality of sub-components, computing system 104 may determine an “audibility” sub-component, an “intelligibility” sub-component, a “comfort” sub-component, a “focus” sub-component, a “sociability” sub-component, and a “connectivity” sub-component. For example, computing system 104 may determine an audibility sub-component that is a measure of the improvement in audibility provided to the wearer by hearing instruments 102. For instance, the audibility sub-component may indicate a measure of detected sounds that are amplified sounds. In this example, each of the detected sounds is a sound detected by hearing instruments 102. Furthermore, in this example, each respective amplified sound is a sound that was amplified by hearing instruments 102 because the intensity of the sound was below an audibility threshold of the wearer of hearing instruments 102. In this example, the audibility threshold of the wearer of hearing instruments 102 is an intensity level below which the wearer of hearing instruments 102 is unable to reliably hear the sound.
In some examples, computing system 104 may determine an intelligibility sub-component that indicates a measure of an improvement in speech understanding provided by hearing instruments 102. Furthermore, in some examples, computing system 104 may determine a comfort sub-component that indicates a measure of noise reduction provided by hearing instruments 102. In some examples, computing system 104 may determine a focus sub-component that indicates a measure of time hearing instruments 102 spends in directional processing modes. In this example, each of the respective directional processing modes selectively attenuates off-axis, unwanted sounds. Furthermore, in some examples, computing system 104 may determine a sociability sub-component that indicates a measure of time spent in auditory environments involving speech. In some examples, computing system 104 may determine a connectivity sub-component that indicates a measure of an amount of time hearing instruments 102 spent streaming media from devices connected wirelessly to hearing instruments 102.
In some examples, as part of determining the plurality of sub-components, computing system 104 may determine a “use score” sub-component, an “engagement score” sub-component, and an “active listening” sub-component. In such examples, computing system 104 may determine the cognitive benefit measure (e.g., a brain score) as a weighted sum of the “use score” sub-component, the “engagement score” sub-component, and the “active listening” sub-component. For instance, computing system 104 may determine the cognitive benefit measure such that a first percentage (e.g., 40%) of the cognitive benefit measure is based on the “use score” sub-component, a second percentage (e.g., 40%) of the cognitive benefit measure is based on the “engagement score” sub-component, and a third percentage (e.g., 20%) of the cognitive benefit measure is based on the “active listening” sub-component.
In such examples, the “use score” sub-component may be based on an amount of time during a scoring period that the wearer of hearing instruments 102 has used hearing instruments 102. The wearer of hearing instruments 102 may be considered to be using hearing instruments 102 when hearing instruments 102 is in the wearer's ear and turned on. In some examples, hearing instruments 102 may determine whether hearing instruments 102 are in the wearer's ears based on one or more of various signals generated by sensors 310 (
The “engagement score” sub-component may be a measure of how much the wearer of hearing instruments 102 participates in activities involving aural engagement during a scoring period. Example types of activities involving aural engagement include engaging in conversation, streaming audio data (e.g., streaming music, streaming audio data from television or a cinema), and other activities that involve the wearer of hearing instruments 102 actively listening to sounds.
In examples where the value of the “engagement score” sub-component is based on the wearer of hearing instruments 102 engaging in conversation, hearing instruments 102 may run an acoustic classifier that classifies sounds detected by hearing instruments 102. For example, the acoustic classifier may determine whether the current sound detected by hearing instruments 102 is silent, speaking and quiet, speaking with noise, music, and wind. In other examples, the acoustic classifier may classify the detected sounds into other categories.
In some examples, computing system 104 may determine the value of the “engagement score” sub-component based at least in part on an amount of time that the sound detected by hearing instruments 102 is classified into a speech category. Hearing instruments 102 may record transitions between categories as log data items in data log 324. In some examples, computing system 104 may determine the value of the “engagement score” sub-component based at least in part of a number of times that hearing instruments 102 determines during the current scoring period that the type of sound detected by hearing instruments 102 transitions to a speech category from another type of sound. For instance, computing system 104 may determine the “engagement score” sub-component based on the progress of the wearer of hearing instruments 102 toward a goal of a particular amount of time that sound detected by hearing instruments 102 is classified into a speech category
Furthermore, in some examples, computing system 104 may determine the “engagement score” sub-component based on multiple activities involving aural engagement. For example, computing system 104 may determine a first component of the “engagement score” sub-component based on engagement in conversation and a second component of the “engagement score” sub-component based on streaming audio data. In some examples, hearing instruments 102 may record log data items in data log 324 that include timestamps of when hearing instruments 102 started and stopped streaming media data. In this example, the first factor may be determined in the same manner as the “sociability” sub-component described elsewhere in this disclosure and the second factor may be determined in the same manner as the “connectivity” sub-component described elsewhere in this disclosure. In this example, a first percentage (e.g., 80%) of the “engagement score” sub-component may be based on the first factor and a second percentage (e.g., 20%) of the “engagement score” sub-component may be based on the second factor. For instance, computing system 104 may determine the “engagement score” as a weighted sum of the first and second factors.
The “active listening” sub-component may be determined based on exposure of the wearer of hearing instruments 102 to a plurality of different acoustic environments during a current scoring period. For example, hearing instruments 102 may determine whether the sound detected by hearing instruments 102 is associated with particular types of acoustic environments. Example types of acoustic environments may include speech, speech with noise, quiet, machine noise, and music. In some examples, hearing instruments 102 may record log data items in data log 324 indicating transitions between acoustic environments and timestamps associated with such transitions. Computing system 104 may increment, based on the log data, the “active listening” sub-component for each different type of acoustic environment that hearing instruments 102 detects during a scoring period. For instance, computing system 104 may increment the “active listening” sub-component by x1 points (e.g., 4 points) for exposure to a first acoustic environment, x2 for exposure to a second acoustic environment, and so on, where x1, x2, . . . x4 are the same value or two or more different values. In some examples, computing system 104 may also or alternatively determine the value of the “active listening” sub-component based on progress of the wearer of hearing instruments 102 during the current scoring period toward a goal for the “active listening” sub-component. The goal for the “active listening” sub-component may be an amount of time that hearing instruments 102 spends performing a specified function, such as processing speech, processing sound in a directional mode, etc. In another example, the goal for the “active listening” sub-component may be a number of acoustic environments that the wearer of hearing instruments 102 is to experience during the scoring period.
Furthermore, in some examples, as shown in
Additionally, computing system 104 may determine, based on the data received from hearing instruments 102, a body fitness measure for the wearer of hearing instruments 102 (602). The body fitness measure may be an indication of a level of physical activity in which the wearer of hearing instruments 102 has engaged during a scoring period while wearing hearing instruments 102. In some examples, computing system 104 may scale the body fitness measure based on an amount of time the wearer of hearing instruments 102 spends wearing hearing instruments 102.
Furthermore, in the example of
As shown in the example of
As part of determining the plurality of sub-components, computing system 104 may determine a “steps” sub-component, an “activity” sub-component, and a “move” sub-component. The “steps” sub-component may be based on a number of steps (e.g., while walking or running) that the wearer of hearing instruments 102 has taken during the current scoring period. In some examples, computing system 104 may determine a value of the “steps” sub-component based on the progress during the current scoring period of the wearer of hearing instruments 102 toward a goal for the “steps” sub-component. Furthermore, in some examples, IMU 326 determines the number of steps and hearing instruments 102 writes data indicating the number of steps to data log 324. In some examples, hearing instruments 102 stores timestamps with the number of steps.
The “activity” sub-component may be a measure of vigorous activity in which the wearer of hearing instruments 102 has engaged during the current scoring period. For example, computing system 104 may increment the “activity” sub-component in response to determining that the wearer of hearing instruments 102 has performed a vigorous activity. In some examples, computing system 104 may determine a value of the “activity” sub-component based on the progress during the current scoring period of the wearer of hearing instruments 102 toward meeting a goal for the “activity” sub-component. In such examples, the goal for the “activity” sub-component may be defined as a number of vigorous activities or amount of time engaged in vigorous activities to be performed during the current scoring period.
Computing system 104 or hearing instruments 102 may determine whether the wearer of hearing instruments 102 has performed a vigorous activity in one or more of various ways. For example, computing system 104 or hearing instruments 102 may determine that the wearer of hearing instruments 102 has performed a vigorous activity if computing system 104 has taken more than a given number of steps in a given amount of time. For instance, computing system 104 or hearing instruments 102 may assume that the wearer of hearing instruments 102 has run (or engaged in an activity more vigorous than a brisk walk) if the wearer of hearing instruments 102 has taken more than a threshold number of steps within a given time period.
Hearing instruments 102 may store one or more of various types of data to data log 324 to enable computing system 104 to determine the “activity” sub-component. For example, IMU 326 may output the number of steps taken during a given period. For instance, for every minute, IMU 326 may output the number of steps taken during that minute. Hearing instruments 102 may write a log data item including a timestamp to data log 324 if the number of steps taken during the given period is greater than a threshold associated with vigorous activity.
The “move” sub-component may be based on a number time of intervals during the current scoring period in which the wearer of hearing instruments 102 moves for a given amount of time. For example, computing system 104 may determine the “move” sub-component as a number of hours during a day in which the wearer of hearing instruments 102 was actively moving for more than 1 minute. In some examples, computing system 104 may determine the “move” sub-component based on progress of the wearer of hearing instruments 102 during the current scoring period toward a goal for the “move” sub-component. In such examples, the goal for the “move” sub-component may be defined as a given number of time intervals during the current scoring period in which the wearer of hearing instruments 102 moves for the given amount of time.
Hearing instruments 102 may store one or more of various types of data to data log 324 to enable computing system 104 to determine the “move” sub-component. For instance, in one example, hearing instruments 102 may receive timestamps from computing system 104 as described elsewhere in this disclosure. Furthermore, in this example, hearing instruments 102 may write data to data log 324 indicating that the wearer has started moving with a first timestamp and data indicating that the wearer has stopped moving with a second timestamp. Computing system 104 may analyze such data to determine whether the wearer of hearing instruments 102 was active for the given amount of time during a time interval.
Furthermore, in some examples, as shown in
Furthermore, in the example of
Computing system 104 may determine a wellness measure based on the cognitive benefit measure for the wearer of hearing instruments 102 and the body fitness measure for the wearer of hearing instruments 102 (704). In various examples, computing system 104 may determine the wellness measure in various ways. For example, computing system 104 may determine the wellness measure as a weighted sum of the cognitive benefit measure and the body fitness measure. For instance, in this example, computing system 104 may determine the wellness measure with equal weightings, e.g., a 50% weighting to the cognitive benefit measure and 50% weighting to the body fitness measure. In other examples, computing system 104 may use unbalanced (i.e., different) weightings of the cognitive benefit measure and the body fitness measure. The weighting for the cognitive benefit measure may be greater than the weighting for the body fitness measure. Alternatively, the weighting for the cognitive benefit measure may be less than the weighting for the body fitness measure.
As one example, computing system 104 may determine the wellness measure with a 60% weighting to the cognitive benefit measure and a 40% weighting to the body fitness measure.
In the example of
Furthermore, in some examples, as shown in
In the example of
Furthermore, in the example of
GUI 800 also includes historical icons 812A, 812B, and 812C (collectively, “historical icons 812”). In the example of
In the example of
Furthermore, in the example of
GUI 900 also includes historical icons 912A, 912B, and 912C (collectively, “historical icons 912”). Like circular diagram 910, historical icons 912 include segments with filled portions corresponding to the wearer's progress toward meeting the goals for the sub-components on previous days, e.g., Saturday, Sunday and Monday in the example of
In the example of
In some examples, a computing system (e.g., computing system 104, hearing instruments 102, and/or one or more other devices) may detect one or more user behavior conditions using hearing instruments 102. The computing system may comprise one or more processors. The user behavior conditions may be measures of behavior of the wearer of hearing instruments 102. In this example, the computing system may determine a wellness measure based on the one or more conditions.
The user behavior conditions may include the cognitive benefit measure, the body fitness measure, or other measures of the behavior of the wearer of hearing instruments 102. For instance, the cognitive benefit measure may be considered a measure of user behavior with respect to how the wearer of hearing instruments 102 uses hearing instruments 102. Similarly, the body fitness measure may be considered a measure of user behavior with respect to physical activity behavior in which the wearer of hearing instruments 102 engages. Thus, detecting one or more user behavior conditions may include detecting activity information (e.g., the body fitness measure) and detecting hearing information (e.g., the cognitive benefit measure). For instance, the computing system may determine a cognitive measure and a body measure. The computing system may further determine the wellness measure using the cognitive measure and the body measure. In some such examples, one or more of hearing instruments 102 determine the wellness measure.
In some examples, the computing system may determine the wellness measure based at least in part on the activity information and the hearing information. In some examples, the hearing information includes one or more of hearing aid usage, user engagement, and active listening. In some examples, information relating to the user behavior conditions may be transmitted (e.g., wirelessly or non-wirelessly) from the hearing instrument to a computing device (e.g., a computing device in computing system 104) and the computing device determines the wellness measure using the transmitted information.
Some examples of this disclosure include measures of use of a heart rate monitor, scoring measures of cardiovascular fitness, or other physiological parameters, to the examples provided elsewhere in this disclosure for measuring physical fitness (Body Score), cognitive wellness (Brain Score), and the combination of the two in a measure of overall wellness (Thrive Score).
This disclosure describes techniques that may integrate cardiovascular data into a measure of physical wellness or into a measure of overall wellness. For instance, an optical sensor (e.g., of one or more of hearing instruments 102) may be used to measure heart rate, collect data related to heart rate, or other data. The techniques of this disclosure may be applied to other physiological data collected by this or other sensors.
An optical sensor in a hearing instrument is capable of measuring the heart rate of a user (among other things) by interpreting changes in the reflectance from the vasculature of the ear. The following describes one technique for increasing a point total of a user for using the optical sensor or other types of sensors to monitor their cardiovascular health.
In the example of
Heart-related sensors 1124 may include one or more photoplethysmography (PPG) sensors, electrodes for collecting ECG signals, and/or other types of sensors that generate heart-related information (i.e., heart-related data). Heart-related data includes data related to a user's heart. Stress-related sensors 1126 may include one or more respiration sensors, electrodes for collecting EEG signals, and/or other types of sensors that generate information that may be used to determine an emotional stress level of the user of hearing instruments 102 (i.e., stress-related information/data).
In some of the examples provided elsewhere in this disclosure, the measure of physical wellness (the “Body Score”) has three components: (1) Steps, (2) Activity, and (3) Move. In some examples, a fourth component to the Body Score (which may be referred to as “Heart,” “Heart Health,” or some other name) may be included in the measure of physical wellness. In some examples, the Heart component tracks how many times a user of hearing instruments 102 uses the heart rate measurement feature of hearing instruments 102.
In this example, the computing system may increase a point total of the user of hearing instruments 102 for checking various measures of their cardiovascular health. In some examples, there are two measures of cardiovascular health, but the system of this disclosure for rewarding health monitoring may apply to other measures as well. The first measure is a heart rate (HR) “on demand,” in which the user explicitly checks their heart using a mobile application (e.g., companion application 424 of
In some examples, a second measure of cardiovascular health is Heart Rate Recovery (HRR). The Heart Rate Recovery feature may guide a user through a step-by-step routine that measures how quickly their heart rate returns to normal after exercise, which is an established measure of cardiovascular fitness. The faster the user's heart rate returns to normal, the stronger and healthier the user's heart. The user may explicitly initiate the Heart Rate Recovery routine and the computing system may increase a point total of the user for the completion of the Heart Rate Recovery routine. Computing system 104 (or hearing instruments 102) may add points to the “Heart Health” subcategory of the Body Score, and thus may the points to the composite Body Score and/or the composite Thrive Score.
Features similar to features 904, 906, and 908 (
In some example implementations of the Body Score, the computing system may increase a point total of the user by a maximum of a (e.g., 40) points for completing the goal set for number of steps (“Steps”), the computing system may increase the point total of the user by a maximum of b (e.g., 40) points for completing the goal set for the number of minutes of activity beyond a brisk walk (“Activity”), and the computing system may increase the point total of the user by a maximum of c (e.g., 20) points for completing the goal of moving from rest a certain number of times per hour per day (“Move”), where a, b, and c are positive numbers. These points total d (e.g., 100) possible points obtained to reach the maximum Body Score for one day. In one example of this disclosure, the maximum number of points that the computing system may add to the point total for the user in one day for “Steps” would remain at a, the maximum number of points awarded for “Activity” would decrease (e.g., to 20), the maximum number of points awarded for “Move” would remain at c, and the remaining points (e.g., 20 points) from the “Activity” subcomponent of the Body Score may be allocated to the “Heart Health” subcomponent.
In some examples of this disclosure, the computing system (e.g., computing system 104, hearing instruments 102, or another device) may reward the user of hearing instruments a given number of points (e.g., 2 points) each time the user measures their heart rate on demand, up to a given number of measures (e.g., 6 measures) per day, for a maximum point allowance of a given number of points (e.g., 12 points) per day for measuring their heart rate. The computing system may reward the user of hearing instruments 102 with a given number of points (e.g., 4 points) each time the user completed the Heart Rate Recovery routine, up to a given number of measures (e.g., 2 measures) per day, for a maximum point allowance of a given number of points (e.g., 8 points) per day for measuring their heart rate recovery. The maximum point allowance per day between these two measures of cardiovascular health would be a particular number of points (e.g., 20 points). The points earned in the Heart Health subcomponent of the Body Score (e.g., ranging from 0-20), may be added to the composite Body Score, and the composite Thrive Score. Other reward structures may be applied, as are any number of different measures of cardiovascular health.
In some examples, the Heart Health component is included in the Body Score, and the computing system increases the point total of the user of hearing instruments 102 for meeting their cardiovascular goals. Example goals may include one or more of: (1) achieving a resting heart rate within a range, (2) achieving an active heart rate (i.e., heart rate during exercise) within a range of target elevated heart rates, (3) elevating heart rate to within a range of target elevated heart rates a certain number of times per day, (4) achieving a Heart Rate Recovery score that is within a target range of scores, (5) achieving a Heart Rate Recovery score that is lower than an accumulating average of scores, thus indicating an improvement in heart health over time, or (6) achieving a Heart Rate Recovery score that is some percentage lower than measures taken previously. Of course, any number of other cardiovascular goals are possible. The values that define all of these goals, both specified and unspecified, may be set by the user of hearing instruments 102, their physician or caregiver, a loved one such as a family member, or some other third-party user.
In some examples, the computing system adds bonus points to the Body score when the user of hearing instruments 102 measures their heart rate. In such examples, a separate component for heart health is not included in the Body Score. In such examples, the existing point structure of the Body score remains unchanged. The computing system may add points on top of the Body Score (e.g., as calculated in examples provided elsewhere in this disclosure) such that the user has more ways to achieve a perfect score. The maximum Body Score (e.g., of 100) does not change. For instance, in one such example, the computing system may increase a point total of the user with 2 points per cardiovascular measure taken during a single day, whether heart rate on demand or Heart Rate Recovery, up to a maximum of 10 bonus points per day.
In some examples, the computing system adds bonus points to the aggregate Thrive score when the user of hearing instruments 102 measures their heart rate. In such examples, neither the Body Score nor Thrive Score includes a separate component for heart health. In such examples, the existing point structure of the Body score (e.g., as calculated in examples provided elsewhere in this disclosure) may remain unchanged. For instance, there may be 100 possible points for the Brain Score, 100 possible points for the Body Score, and 200 possible points for the Thrive Score. In such examples, the computing system may add points on top of the existing Thrive Score such that the user has more ways to achieve a perfect score. For instance, in one such example, the computing system may add 2 points per cardiovascular measure taken during a single day, whether heart rate on demand or Heart Rate Recovery, up to a maximum of a given number (e.g., 10) bonus points per day.
In some examples, a third component is included in the Thrive Score. In such examples, a modified Thrive Score is composed of the existing Brain and Body Scores, plus a Heart Health Score. In one such example, the user of hearing instruments 102 is rewarded for measuring their cardiovascular health. The rewards may be use-based or may be goal-based, as described elsewhere in this disclosure. In other words, the computing system may increase a point total of the user using features the heart rate measurement feature or heart rate recovery feature; or the computing system may increase the point total of the user for making progress toward a goal. In some examples where a third component for heart health is included in the Thrive Score, a Heart Health Score may be worth a maximum of 100 points per day, thus making the Thrive Score worth a maximum of 300 points per day.
While techniques of this disclosure may be implemented in an application (e.g., companion application 424 of
While this disclosure describes measures of heart rate and heart rate recovery, the techniques of this disclosure may be applied to different measures of cardiovascular fitness, such as the following:
While this disclosure describes techniques for using cardiovascular data, or the act of collecting cardiovascular data, to augment a measure of physical wellness, the same type of augmentation of the wellness measure could be accomplished using different sensors, and different physiological measures, such as the following:
Thus, some examples of this disclosure may relate to scoring of (e.g., increasing a point total for) biometric data using hearing instruments and a user interface, scoring of (increasing a point total for) cardiovascular data using hearing device and mobile user interface, and/or automatic classification of activity of the user of hearing instruments 102 when a heart rate measurement is made, thus providing context for each measurement.
In some examples, in response to receiving an indication of user input to select heart rate element 1200, a computing system (e.g., computing system 104, hearing instruments 102, and/or one or more other devices) may display a heart health interface.
Additionally, in the example of
In some instances, the scoring structure of
Such unclassified bonus points may provide credit for a resting heart rate, elevated heart rate, and using the heart rate recovery routine. In some examples, the bonus points may be classified. “Classified” points may be separated into different measures of heart health, such as resting heart rate or heart rate recovery. In order to earn full credit, a variety of different measures would have to be made (as opposed to just resting heart rate, for example). Such classified bonus points may be for checking resting heart rate. In some such examples, there may be 2 points per measure, with a maximum of 10 bonus points.
In some examples, to provide credit for resting heart rate, elevated heart rate, and using the heart rate recovery routine, boundaries may be set for what constitutes a range of desired values for those metrics. Those boundaries could be set by a manufacturer of hearing instruments 102, by the patient alone, or in conjunction with a medical professional. For example, there are normative data for what is deemed to constitute a healthy resting heart rate, or healthy heart rate recovery value. The computing system may award users for having measurement values that are deemed healthy. The measurement values that are deemed healthy may be defined as a function of the age of the user. For users who have heart health values outside of the healthy, desired range, the computing system may encourage the users to work towards betterment of their heart health, or encourage the users to consult with a medical professional.
In some examples, the resting heart rate is based on user-initiated measurements and also user-mediated classification (i.e., the user of hearing instruments 102 determines whether the user is at rest). For instance, in some examples, the user may be trusted to take measures of their heart rate while at rest. In some examples, the user may be rewarded for checking their heart rate at any time.
In some examples, the resting heart rate and/or heart rate recovery are measured automatically (e.g., on a periodic basis). In other words, the user may not need to initiate measurements of the user's heart rate and/or heart rate recovery. In some such examples, goal-based rewards may be used. However, in examples where the user initiates the measurements (e.g., of the user's heart rate) automatically, the user may be aware that such measurements may consume battery power, and therefore may disable the measurements in order to avoid the inconvenience of needing to recharge the batteries of hearing instruments 102 as frequently. Providing rewards, such as points, may help to incentivize the user to allow automatic measurements or manually perform measurements.
In the example of
In some examples, a computing system may output the expanded activity sub-component 2000 for display in response to receiving an indication of user selection of the feature 906 for the activity sub-component. The computing system may receive an indication of user input indicating which actions or activities the user is performing or was performing when measuring their heart rate.
In some examples, other types of data may contribute to one or more measures of the wellness of the user of hearing instruments 102. For example, the computing system may use signals from one or more of heart-related sensors 1124 (
In some examples, the computing system may use signals from the set of electrodes to generate an electrocardiogram (ECG) that tracks electrical activity of the user's heart. Furthermore, in some examples, the computing system may output the ECG for display (e.g., in a user interface of companion application 424). To analyze the signals from the set of electrodes, the computing system may apply an algorithm for detecting QRS complexes. Example algorithms for detecting QRS complexes include the Pan-Tompkins algorithm and algorithms based on the Hilbert transform. The computing system may analyze the QRS complexes to determine the presence or absence of P waves. The absence of P waves in combination with a rapid heart rate (e.g., greater than 100 beats per minute) may correspond to a high risk that the user has experienced an occurrence of atrial fibrillation. In some examples, the computing system may apply a machine learning system, such as a neural network, to the signals to determine risks that the user has experienced an occurrence of a cardiac arrhythmia.
In some examples, the computing system may output a message (e.g., in a user interface of companion application 424, as a text message, as an in-ear audio message, etc.) to the user in response to determining that the computing system has determined that there is an adequately high risk that the user has experienced or is experiencing a cardiac arrhythmia. For instance, in one example, the computing system may determine that there is an adequately high risk that the user has experienced or is experiencing atrial fibrillation if there is an absence of P waves and a rapid heart rate. In another example, the computing system may determine that there is an adequately high risk that the user has experienced or is experiencing periods of asystole if no heart rate can be detected. In some examples, the computing system may output such a message to a 3rd party, such as a monitoring service, a physician, a caregiver, a family member, or another type of person.
In accordance with a technique of this disclosure, the computing system may use arrhythmia-related information as part of one or more measures of the health of the user of hearing instruments 102. For instance, the arrhythmia-related information may be integrated into a heart health score for the user and/or a body score for the user. Thus, in some examples, the computing system may determine the user's heart health score and/or body score based at least on part on arrhythmia-related information. For instance, in some examples, the computing system may reduce the user's heart health sub-component if the computing system determines that a sufficiently high risk that the electrical signals represent an occurrence of a cardiac arrhythmia.
In some examples, the user may initiate an arrhythmia analysis process that measures electrical signals of the user's heart and analyzes the electrical signals to determine a risk that the electrical signals represent an occurrence of a cardiac arrhythmia. For instance, similar to feature 1306 in the example of
Similar to the example of
Furthermore, in the example of
The computing system may determine the heart health measure in any of various ways. For instance, in one example, the computing system may determine a plurality of sub-components of the heart health measure. For instance, the sub-components may include one or more of a heart rate sub-component and a heart rate recovery sub-component. The computing system may determine the heart rate sub-component as a total number of times the user initiated the process to check the user's heart rate. The computing system may determine the heart rate recovery sub-component as a total number of times the user initiated the process to check the user's heart rate recovery. In this example, the computing system may determine the heart health measure based on the plurality of sub-components of the heart health measure. For instance, the computing system may determine the heart health measure as a total of points for the sub-components.
The computing system may output an indication of the heart health measure to the user of the hearing instruments (2104). For instance, the computing system may output the indication of the heart health measure in a GUI as described elsewhere in this disclosure. In some examples, the computing system may send a message (e.g., to the user of the hearing instruments or a 3rd party) indicating the heart health measure.
In some examples, the computing system may determine, based on the data received from the one or more hearing instruments, a body measure for the user. The body measure may be an indication of physical health of the user. The computing system may output an indication of the body measure. In some examples, the computing system determines the body measure in accordance with any of the examples provided elsewhere in this disclosure, or others. Thus, in some examples, the computing system may output indications of both the heart health measure and a separate the body measure. In other examples, the heart health measure is a sub-component of the body measure. For instance, in such examples, the computing system may add together points for each of the sub-components of the body measure to determine the body measure. Furthermore, in some examples where the body measure and the heart health measure are separate, the computing system may determine a wellness measure (e.g., a Thrive Score) based on the body measure and the heart health measure. In such examples, the wellness measure may be an indication of an overall wellness of the user. For instance, the computing system may add together the body measure and the heart health measure.
In the example of
Furthermore, in the example of
However, in response to making the determination to generate the notification (“YES” branch of 2208), the computing system may send the notification to one or more recipients (2210). For instance, the computing system may send the notification to the user of the hearing instruments or a third party. The third party may be a party other than the user of the hearing instruments and other than a provider of the computing system.
In some examples, the computing system may use data from one or more sensors of hearing instruments 102 or other devices to generate stress-related data. For instance, the computing system may use data from stress-related sensors 1126 of hearing instrument 1100 (
For instance,
Additionally, in the example of
The computing system may determine the emotional stress measure in one of various ways. For instance, in some examples, a set of sensors in hearing instruments 102 may generate signals that the computing system may use to detect a respiration rate of the user. Higher respiration rates, especially when not associated with physical movement, are often a sign of emotional stress. In other words, when people are emotionally stressed, they typically breathe more but this higher respiration rate is not associated with exercise or other physical activity. IMUs, microphones, and other types of sensors may generate the signals that the computing system may use to detect the respiration rate of the user. In some examples, the computing system may detect the respiration rate of the user by based on a signal from an inward-facing microphone on the medial end of a receiver in the ear canal of the user. In such examples, an acoustic signature of respiration may be defined through supervised machine learning, and the computing system may apply algorithms that classify internal body noise as inhalation or exhalation. The computing system may use patterns of inhalation and exhalation over time to measure respiration rate. In some examples, the computing system may deduct points from an emotional stress measure for each instance where the computing system determines that the user has experienced an episode of emotional stress.
The computing system may use signals from other types of sensors in hearing instruments 102 to determine an emotional stress level of the user of hearing instruments 102. For example, the sensors in hearing instruments 102 may include electrodes configured to generate EEG signals. Certain patterns of EEG signals are associated with relaxation and stress. For instance, EEG signals that exhibit wave patterns in the alpha band are associate with relaxation. In contrast, EEG signals that exhibit wave patterns in the beta band are associated with anxious thinking and active concentration. In adults, EEG signals that exhibit wave patterns in the theta band may be associated with meditation.
In some examples, the stress-related information (i.e., stress-related data) may include self-reported information about the user's stress management practices. For example, the computing system may receive indications of user input indicating amounts of time that the user spent practicing meditation. In some examples, the computing system may receive information about the user's stress management practices from one or more software applications or devices. For example, a software application for meditation may provide information to the computing system indicating amounts of time that the user spent practicing meditation. In some examples, the software application for meditation provides audio data through hearing instruments 102.
In some examples, the computing system may use the stress-related information to determine a stress level of the user of hearing instruments. For example, the computing system may apply a neural network to the stress-related information to generate information indicative of the emotional stress level. In this example, the neural network may output a score indicative of the user's stress level.
The computing system may use stress-related information as part of one or more measures of the health of the user of hearing instruments 102. For instance, the computing system may add bonus points to a brain score of the user if the user is taking steps to manage stress. For example, the computing system may add a given number of bonus points to the brain score of the user if the stress-related information indicates that the user performs at least a particular number of minutes of meditation. In some examples, the computing system may add a particular number of bonus points to the brain score of the user if the stress-related information indicates that the user's heart rate did not rise above a particular limit while not performing a physical activity.
In the computing system may obtain the stress-related data in one or more of various ways. For instance, in one example, a particular hearing instrument in a set of hearing instruments (e.g., hearing instruments 102) may be configured to receive a request for the stress-related data and wirelessly transmit the stress-related data in response to the request. In this example, the request may be initiated by the user of the one or more hearing instruments. Furthermore, in this example, the particular hearing instrument uses electrical energy from a battery internal to the particular hearing instrument to wirelessly transmit the stress-related data to the computing system in response to the request. In some examples, the computing system may obtain the physiological data via communication channels (e.g., communication channels 1116), via a wireless communication link, or in another manner.
Additionally, the computing system may determine, based on the stress-related data, an emotional stress measure of a user of the one or more hearing instruments (2402). As before, the emotional stress measure is an indication of one or more aspects of a level of emotional stress of the user.
In the example of
In some examples, the computing system may use the point total of the user for initiating requests for stress-related data to determine a cognitive wellness score for the user. For instance, the computing system may add the points awarded for initiating requests for stress-related data to the points awarded as described elsewhere in this disclosure, to determine the cognitive wellness score.
In some examples, the computing system may determine, based on the stress-related data, whether the user of the hearing instruments has achieved one or more stress management goals for the user of the hearing instruments. For example, the stress-related data may indicate an amount of time the user used hearing instruments 102 to perform guided meditation. In this example, the computing system may determine that the user has achieved a stress management goal if the user has used hearing instruments 102 to perform at least a particular number of minutes of guided meditation in a particular time period. In another example, a stress management goal may be to maintain a stable heart rate while at rest or resting respiration rate over a period of time. In this example, the IMU and associated activity-classification algorithms may be used to determine when the user is at rest. The computing system may use one or more sensors of the hearing instruments to determine values of the physiological measures of interest, such as respiration rate. Furthermore, in one example, one or more of the hearing instruments may include a sensor for detecting the galvanic skin response, which is a measure of skin conductance and may be used to measure physiological arousal, which is a proxy for stress. In this example, a stress management goal may be to keep the amount of time during which the user experiences physiological arousal to below certain thresholds. The computing system may increase the point total by one or more points to the user of the hearing instruments based on the user of the hearing instruments achieving the one or more stress management goals.
Furthermore, in the example of
In the example of
In some examples, as part of performing a notification action, the computing system may send one or more messages to an account associated with the user of hearing instruments 102, where the messages provide information about techniques to reduce stress. For example, the computing system may send email messages to an email account of the user, SMS messages to a phone number of the user, and so on. In some examples, the computing system may cause a GUI (e.g., a GUI of companion application 424 (
In some examples, as part of performing a notification action, the computing system may send a notification to a third party. The third party may be a party other than the user of hearing instruments 102 and other than a provider of the computing system. In response to receiving such a notification, the third party may advise the user of hearing instruments 102 on ways to reduce the user's stress levels.
The computing system may make the determination of whether to perform the intervention action in any of one or more ways. For example, the computing system may implement a machine learning model (e.g., a neural network) that takes the stress-related information as input and outputs an indication of whether to perform the intervention action. In some examples, the computing system may apply a rules engine that evaluates a set of rules. In such examples, a rule may indicate that an intervention action is to be performed if the stress-related information indicates that the user experiences more than a given number of stressful episodes during a particular time period (e.g., day, week, hour, etc.). In some examples, a rule may indicate not to perform an intervention action if the stress-related data indicates that the user is performing actions to reduce the user's stress level. For instance, the rule may indicate not to perform an intervention action if the stress-related data indicates that the user is exercising meditation, performing regular physical exercise, or performing other activities that are associated with stress reduction.
In response to making a determination to perform the intervention action (“YES” branch of 2408), the computing system may perform the intervention action (2410). For instance, the computing system may send an email message, output an audio message, or perform any of the other example intervention actions described elsewhere in this disclosure, or others. Otherwise, in response to making a determination not to perform the intervention action (“NO” branch of 2408), the computing system does not perform the intervention action (2412).
In some examples, in addition to or as an alternative to using heart-related information (i.e., heart-related data) to determine one or more measures of the physical or mental wellness of the user of hearing instruments 102, the computing system may use the cardiovascular-information for purposes of fall detection. Falls are a common cause of serious injury, especially among the elderly. People with certain cardiovascular conditions are at a greater risk of falling. For instance, a user is more likely to fall if there is too little oxygenated blood reaching the user's brain. The user may have too little oxygenated blood reaching the user's brain for a variety of reasons, such as when the user has low blood pressure, is experiencing a cardiac arrhythmia, has a heart rate that is abnormally fast or slow, or has an abnormally fast or slow respiration rate.
The computing system may use one or more of various techniques for detecting a fall. For instance, in some examples, the computing system may determine whether the user has fallen based on signals from IMU 326. In some examples, the computing system uses information from one or more photoplethysmography (PPG) sensors of hearing instruments 102 to detect whether the user has fallen (e.g., as described in U.S. patent application Ser. No. 16/230,110, filed Dec. 21, 2018). One challenge associated with fall detection is minimizing false alarms while reducing the chances of a real fall not being detected. False alarms can be inconvenient and waste the resources of first responders. However, the user may not receive needed help if the fall detection algorithm did not detect a real fall.
As shown in the example of
In accordance with a technique of this disclosure, the computing system may use the heart-related information to determine whether the user of hearing instruments 102 is at an increased risk of falling. In response to determining that the user is at an increased risk of falling, the computing system may change a sensitivity level of the fall detection algorithm. For instance, if the computing system determines that the user's blood pressure is low, that the user is experiencing a cardiac arrhythmia, or that the user's heart rate is abnormally high or low, the computing system may increase the sensitivity level of the fall detection algorithm. In general, a higher sensitivity level reduces the likelihood that the fall detection algorithm does not detect a fall, but also increases the likelihood of false detections.
In some examples, the fall detection algorithm may generate a value indicating a likelihood that the user has fallen. For instance, in one example, a neural network may be trained to generate the value. In this example, the neural network may take various types of data as input. For instance, the neural network may take IMU data, PPG data, or other types of data as input. Furthermore, in this example, the computing system may determine that the user has fallen if the value is greater than a threshold. Changing the sensitivity level of the fall detection algorithm based on the cardiovascular information may comprise adjusting the threshold.
In some examples, the computing system may use other information in addition to or as an alternative to the cardiovascular information to determine whether the user of hearing instruments 102 is at an increased risk of falling. For example, one or more EEG electrodes may be integrated into hearing instruments 102. In this example, the computing system may monitor EEG signals from the EEG electrodes for signs that the user might be experiencing or is at risk of experiencing an epileptic seizure. For instance, the computing system may monitor the EEG signals for spikes or sharp waves that may represent seizure activity or interictal activity. Accordingly, the computing system may increase the sensitivity level of the fall detection algorithm in response to determining that the user might be experiencing or is at risk of experiencing an epileptic seizure.
The computing system may obtain the physiological data via communication channels (e.g., communication channels 1116), via a wireless communication link, or in another manner. The physiological data includes heart-related data. For instance, the heart-related data may include one or more of data indicating a blood pressure of the user of the hearing instrument, data indicating a heart rate of the user of the hearing instrument, ECG data for the user of the hearing instrument, data regarding a potential cardiac arrythmia of the user of the hearing instrument, or other types of data related to the heart of the user. In some examples, the physiological data may include data that is not directly heart related. For instance, the physiological data may include one or more of EEG data generated by one or more electrodes included in the hearing instrument, data indicating a respiration rate of the user of the hearing instrument, data indicating a level of physical activity of the user of the hearing instrument, or other types of data regarding the user.
Furthermore, in the example of
The computing system may perform the fall detection algorithm to determine, based on signals from a second set of one or more sensors of the hearing instrument, whether a user of the hearing instrument has fallen (2504). For instance, in one example, the computing system may generate a confidence value that indicates a level of confidence that the user of the hearing instrument has fallen. In this example, the computing system may determine that the user has fallen based on the confidence value being greater than the sensitivity level. In this example, the computing system may generate the confidence level in various ways. For instance, in an example where the second set of sensors includes a PPG sensor, the computing system may determine DC component values of a PPG signal and determine differences between the DC component values. An abrupt decrease in the DC component values may correspond to the user falling. In this example, the computing system may determine the confidence value based on a mapping of differences to allowable levels of confidence. For instance, greater differences may be mapped to greater levels of confidence. In another example, a neural network may be trained to generate the level of confidence.
In some examples, the computing system modifies the sensitivity level of the fall detection algorithm in response to an indication of user input. For example, hearing instruments 102 may detect the sound of the user's voice and the computing system may detect the user saying something to the effect that they feel unsteady. In this example, the computing system may use a voice recognition toolkit to analyze the user's voice for words or phrases that indicate that the user feels unsteady. In response to detecting words or phrases that indicate that the user feels unsteady, the computing system may increase the sensitivity level of the fall detection algorithm. In some examples, the computing system may decrease the sensitivity level of the fall detecting algorithm in response to an indication of user input. For instance, if the user is planning to participate in a certain type of activity (e.g., judo), the user may provide an indication of user input to decrease the sensitivity level of the fall detection algorithm.
In some examples, the computing system may use cardiovascular information regarding the user of hearing instruments 102 to determine whether to ask the user whether assistance is needed after determining that the user has fallen. For example, the computing system may use a fall detection algorithm to determine that the user has fallen. In this example, the computing system may cause one or more of hearing instruments 102 to output an audio question that asks the user to indicate whether the user needs assistance. The user may respond in one or more of various ways, such as by providing a spoken response, performing a head gesture, or providing another type of response. In some examples, the computing system may automatically request assistance if the user does not respond within a particular amount of time.
In response to determining that the user has fallen (“YES” branch of 2600), the computing system may activate one or more sensors of hearing instrument 1100 that generate heart-related data regarding the user (2602). For instance, the one or more sensors include a PPG sensor, ECG electrodes, or other types of sensors that generate heart-related data regarding the user. Activating the one or more sensors in response to determining that the user has fallen, instead of keeping the one or more sensors constantly active, may help to conserve electrical energy from power source 1114 of hearing instrument 1100. Conserving electrical energy may be important in hearing instruments because the space in hearing instruments for larger power sources is typically very constrained.
Subsequently, the computing system may determine, based on the heart-related data, whether to prompt the user to confirm that the user has fallen (2604). The computing system may determine whether to prompt the user in one or more of various ways.
For instance, in one example where the sensors include a PPG sensor, the computing system may determine, based on heart-related data generated by the PPG sensor, a heart rate of the user. For instance, the computing system may determine the heart rate of the user based on times between peaks of maximum blood perfusion. Additionally, the computing system may determine, based on the heart rate of the user being above a first threshold or below a second threshold, whether to prompt the user the confirm that the user has fallen. That is, the user is likely to have an elevated heart rate immediately after the user experiences a fall. Accordingly, the likelihood that the user has actually fallen may be higher if the computing system determines that the user has an elevated heart rate during a period that immediately follows a time at which the user is determined to have fallen. Moreover, a low heart rate may lead to fainting, which is a common cause of falls. Accordingly, the likelihood that the user has actually fallen may be higher if the computing system determine that the user has a depressed heart rate during a period that immediately follows a time at which the user is determined to have fallen.
In some examples where the sensors include a PPG sensor, the computing system may determine, based on heart-related data generated by the PPG sensor, a level of blood perfusion of the user. For instance, the computing system may determine the level blood perfusion that is mapped to a DC signal of a signal from the PPG sensor. Additionally, the computing system may determine, based on the level of blood perfusion of the user, whether to prompt the user to confirm that the user has fallen. For instance, the user's blood perfusion may decrease to a given level if the user has fallen from a standing position. Accordingly, if the computing system determines that the user has fallen, and also determines that the user's blood perfusion has decreased, the computing system hay prompt the user to confirm that the user has fallen.
In response to determining not to prompt the user to confirm that the user has fallen (“NO” branch of 2604), the computing system may continue the process of determining whether the user has fallen. In some examples, the computing system may perform one or more additional actions, such as requesting assistance, despite making the determination not to prompt the user to confirm that the user has fallen.
On the other hand, in response to making a determination to prompt the user to confirm that the user has fallen (“YES” branch of 2604), the computing system may cause the hearing instrument to generate a message prompting the user to confirm that the user has fallen (2606). For example, the computing system may cause the hearing instrument to output an audio message asking whether the user has fallen. In some examples, the computing system may output a haptic signal that prompts the user to confirm that the user has fallen.
The following is a non-limiting list of examples that are in accordance with one or more techniques of this disclosure.
A computer-implemented method comprising: receiving, by a computing system comprising a set of one or more electronic computing devices, heart-related data from one or more hearing instruments; determining, by the computing system, based on the heart-related data received from the one or more hearing instruments, a heart health measure for a user of the one or more hearing instruments, the heart health measure being an indication of one or more aspects of a health of a heart of the user; and outputting, by the computing system, an indication of the heart health measure to the user of the hearing instruments.
The computer-implemented method of example 1A, wherein: a particular hearing instrument in the set of hearing instruments is configured to receive a request for the heart-related data and wirelessly transmit the heart-related data in response to the request, wherein the request is initiated by the user of the one or more hearing instruments, the particular hearing instrument uses electrical energy from a battery internal to the particular hearing instrument to wirelessly transmit the heart-related data to the computing system in response to the request, determining the heart health measure comprises increasing, by the computing system, a point total of the user by one or more points based on a number of times that the user initiated a request for the heart-related data during a scoring time period; and the method further comprises: determining, by the computing system, based on the heart-related data, whether to generate a notification; and based on a determination to generate the notification, sending, by the computing device, the notification to one or more recipients.
The computer-implemented method of example 2A, wherein the one or more recipients include at least one of: the user of the hearing instruments, or a third party, wherein the third party is a party other than the user of the hearing instruments and other than a provider of the computing system.
The computer-implemented method of any of examples 1A-3A, wherein determining the heart health measure comprises: determining, by the computing system, a plurality of sub-components of the heart health measure; and determining, by the computing system, the heart health measure based on the plurality of sub-components of the heart health measure.
The computer-implemented method of example 4A, wherein determining the plurality of sub-components comprises one or more of: determining, by the computing system, a heart rate sub-component, or determining, by the computing system, a heart rate recovery sub-component.
The computer-implemented method of any of examples 1A-5A, further comprising: determining, by the computing system, based on the data received from the one or more hearing instruments, a body measure for the user, the body measure being an indication of physical health of the user; and outputting, by the computing system, an indication of the body measure.
The computer-implemented method of example 6A, wherein the heart health measure is a sub-component of the body measure.
The computer-implemented method of example 6A, further comprising determining a wellness measure based on the body measure and the heart health measure, the wellness measure being an indication of an overall wellness of the user.
The computer-implemented method of any of examples 1A-8A, wherein: the heart-related data from the one or more hearing instruments is based on one or more of: a signal from a photoplethysmography (PPG) sensor of the one or more hearing instruments, a signal from an inertial measurement unit (IMU) of the one or more hearing instruments, or one or more signals from electrocardiogram (ECG) electrodes of the one or more hearing instruments.
A computer-implemented method comprising: receiving, by a computing system comprising one or more electronic computing devices, stress-related data from one or more hearing instruments; determining, by the computing system, based on the stress-related data, an emotional stress measure of a user of the one or more hearing instruments, the emotional stress measure being an indication of one or more aspects of a level of emotional stress of the user; and outputting, by the computing system, an indication of the emotional stress measure to the user of the hearing instruments.
The computer-implemented method of example 1B, further comprising: a particular hearing instrument in the set of hearing instruments is configured to receive a request for the stress-related data and wirelessly transmit the stress-related data in response to the request, wherein the request is initiated by the user of the one or more hearing instruments, the particular hearing instrument uses electrical energy from a battery internal to the particular hearing instrument to wirelessly transmit the stress-related data to the computing system in response to the request, determining the emotional stress measure comprises increasing, by the computing system, a point total of the user by one or more points based on a number of times that the user initiated a request for the stress-related data during a scoring time period; the method further comprises: determining, by the computing system, based on the stress-related data, whether to perform an intervention action; and based on a determination to perform the intervention action, performing, by the computing device, the intervention action.
The computer-implemented method of example 2B, wherein performing the intervention action comprises sending a notification to a third party, wherein the third party is a party other than the user of the hearing instruments and other than a provider of the computing system.
The computer-implemented method of any of examples 2B-3B, wherein performing the intervention action comprises one or more of: instructing the one or more hearing instruments to output a metronomic rhythm and an audio message encouraging the user of the hearing instruments to synchronize their breathing to the metronomic rhythm, sending a message to the user of the hearing instruments suggesting stress management techniques.
The computer-implemented method of any of examples 2B-4B, wherein determining the emotional stress measure comprises: determining, by the computing system, based on the stress-related data, whether the user of the hearing instruments has achieved one or more stress management goals for the user of the hearing instruments; and increasing, by the computing system, the point total of the user by one or more points based on the user of the hearing instruments achieving the one or more stress management goals.
The computer-implemented method of any of examples 1B-5B, wherein the stress-related data comprises one or more of: data regarding meditation practices of the user of the hearing instruments, data regarding physical activity levels of the user of the hearing instruments, or data regarding a respiration rate of the user of the hearing instruments.
A computer-implemented method comprising: obtaining, by a computing system, physiological data based on signals generated by a first set of one or more sensors of a hearing instrument, wherein the physiological data includes heart-related data; modifying, by the computing system, a sensitivity level of a fall detection algorithm based on the physiological data; and performing, by the computing system, the fall detection algorithm to determine, based on signals from a second set of one or more sensors of the hearing instrument, whether a user of the hearing instrument has fallen.
The computer-implemented method of example 1C, wherein the computing system is included in the hearing instrument.
The computer-implemented method of any of examples 1C-2C, wherein the heart-related data comprises one or more of: data indicating a blood pressure of the user of the hearing instrument, data indicating a heart rate of the user of the hearing instrument, electrocardiogram (ECG) data for the user of the hearing instrument, or data regarding a potential cardiac arrythmia of the user of the hearing instrument.
The computer-implemented method of any of examples 1C-3C, wherein the physiological data comprises one or more: electroencephalogram (EEG) data generated by one or more electrodes included in the hearing instrument, data indicating a respiration rate of the user of the hearing instrument, or data indicating a level of physical activity of the user of the hearing instrument.
The computer-implemented method of any of examples 1C-4C, wherein performing the fall detecting algorithm comprises: generating, by the computing system, a confidence value that indicates a level of confidence that the user of the hearing instrument has fallen; and determining, by the computing system, that the user has fallen based on the confidence value being greater than the sensitivity level.
The computer-implemented method of any of examples 1C-5C, further comprising modifying the sensitivity level in response to receiving an indication of user input.
A computer-implemented method comprising: determining, by a computing system, whether a user of a hearing instrument has fallen; based on a determination that the user has fallen, activating, by the computing system, one or more sensors of the hearing instrument that generate heart-related data regarding the user; determining, by the computing system, based on the heart-related data, whether to prompt the user to confirm that the user has fallen; and based on a determination to prompt the user to confirm that the user has fallen, causing, by the computing system, the hearing instrument to generate a message prompting the user to confirm that the user has fallen.
The method of example 1D, wherein: the one or more sensors include a photoplethysmography (PPG) sensor, and determining whether to prompt the user comprises: determining, by the computing system, based on heart-related data generated by the PPG sensor, a heart rate of the user; and determining, by the computing system, based on the heart rate of the user being above a first threshold or below a second threshold, whether to prompt the user the confirm that the user has fallen.
The method of any of examples 1D-2D, wherein: the one or more sensors include a photoplethysmography (PPG) sensor, and determining whether to prompt the user comprises: determining, by the computing system, based on heart-related data generated by the PPG sensor, a level of blood perfusion of the user; and determining, by the computing system, based on the level of blood perfusion of the user, whether to prompt the user the confirm that the user has fallen.
A computing system comprising: a communication unit configured to receive data from one or more hearing instruments; and one or more processors configured to perform the methods of any of examples 1A-3D.
A computing system comprising means for performing the methods of any of examples 1A-3D.
A computer-readable storage medium having instructions stored thereon that, when executed, cause a computing system to perform the methods of any of examples 1A-3D.
It is to be recognized that depending on the example, certain acts or events of any of the techniques described herein can be performed in a different sequence, may be added, merged, or left out altogether (e.g., not all described acts or events are necessary for the practice of the techniques). Moreover, in certain examples, acts or events may be performed concurrently, e.g., through multi-threaded processing, interrupt processing, or multiple processors, rather than sequentially.
In one or more examples, the functions described may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functions may be stored on or transmitted over, as one or more instructions or code, a computer-readable medium and executed by a hardware-based processing unit. Computer-readable media may include computer-readable storage media, which corresponds to a tangible medium such as data storage media, or communication media including any medium that facilitates transfer of a computer program from one place to another, e.g., according to a communication protocol. In this manner, computer-readable media generally may correspond to (1) tangible computer-readable storage media which is non-transitory or (2) a communication medium such as a signal or carrier wave. Data storage media may be any available media that can be accessed by one or more computers or one or more processing circuits to retrieve instructions, code and/or data structures for implementation of the techniques described in this disclosure. A computer program product may include a computer-readable medium.
By way of example, and not limitation, such computer-readable storage media can comprise RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage, or other magnetic storage devices, flash memory, cache memory, or any other medium that can be used to store desired program code in the form of instructions or data structures and that can be accessed by a computer. Also, any connection is properly termed a computer-readable medium. For example, if instructions are transmitted from a website, server, or other remote source using a coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of medium. It should be understood, however, that computer-readable storage media and data storage media do not include connections, carrier waves, signals, or other transient media, but are instead directed to non-transient, tangible storage media. Disk and disc, as used herein, includes compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk and Blu-ray disc, where disks usually reproduce data magnetically, while discs reproduce data optically with lasers. Combinations of the above should also be included within the scope of computer-readable media.
Functionality described in this disclosure may be performed by fixed function and/or programmable processing circuitry. For instance, instructions may be executed by fixed function and/or programmable processing circuitry. Such processing circuitry may include one or more processors, such as one or more digital signal processors (DSPs), general purpose microprocessors, application specific integrated circuits (ASICs), field programmable logic arrays (FPGAs), or other equivalent integrated or discrete logic circuitry. Accordingly, the term “processor,” as used herein may refer to any of the foregoing structure or any other structure suitable for implementation of the techniques described herein. In addition, in some aspects, the functionality described herein may be provided within dedicated hardware and/or software modules configured for encoding and decoding, or incorporated in a combined codec. Also, the techniques could be fully implemented in one or more circuits or logic elements. Processing circuits may be coupled to other components in various ways. For example, a processing circuit may be coupled to other components via an internal device interconnect, a wired or wireless network connection, or another communication medium.
The techniques of this disclosure may be implemented in a wide variety of devices or apparatuses, including a wireless handset, an integrated circuit (IC) or a set of ICs (e.g., a chip set). Various components, modules, or units are described in this disclosure to emphasize functional aspects of devices configured to perform the disclosed techniques, but do not necessarily require realization by different hardware units. Rather, as described above, various units may be combined in a hardware unit or provided by a collection of interoperative hardware units, including one or more processors as described above, in conjunction with suitable software and/or firmware.
Various examples have been described. These and other examples are within the scope of the following claims.
This patent application claims the benefit of U.S. Provisional Patent Application No. 62/810,298, filed Feb. 25, 2019, and U.S. Provisional Patent Application No. 62/854,710, filed May 30, 2019, the entire content of each of which is incorporated by reference.
| Number | Date | Country | |
|---|---|---|---|
| 62810298 | Feb 2019 | US | |
| 62854710 | May 2019 | US |
