Patent Application
20210321883
The present technology is generally related to a modular ambulatory health status and performance tracking system.
Movement is essential to life. A small subset of the population, however, undeniably does it much better than the rest of us. Intricately understanding how athletes or other people perform at a significantly higher level than everyone else would provide insight into how to optimize and scale physical and mental well-being and toughness to the masses.
In hospitals today, a patient is valuated on a set of biometrics sometimes referred to as “standard of care” biometrics. A patient may not be able to go home, in some instances, if they have a temperature. In other instances, a patient's glucose may be elevated, and potentially requiring treatment. Biometrics associated with infections may be evaluated when determining the health of a patient and/or determining whether to discharge the patient. The “standard of care” biometrics are medical-grade biometrics.
Currently, consumers have access to activity monitors. However, these activity monitors do not produce medical grade biometrics.
The techniques of this disclosure generally relate to a modular eco-system that is adapted to provide medical-grade biometrics for one or more of diagnosing a disease by a medical facility or practitioner, tracking by a consumer their health status in real-time and human performance tracking.
In one aspect, the present disclosure provides a system comprising at least one implanted sensor device comprising one or more continuous sensors to detect a first modular set of biometrics of a subject. The system includes an assessment system with a computing device and a computer-readable storage medium comprising one or more programming instructions that, when executed, cause the computing device to receive the first modular set of biometrics over a period of time and receive a second modular set of biometrics for the subject. The computing device selectively serves a graphical user interface configured to present one or more of the first modular set and second modular set of biometrics and normalizes at least a portion of the first modular set and second modular set of biometrics over a period of time. The device generates a score indicative of a state of a biological system of the subject corresponding to a portion of biometrics of the first modular set and second modular set of biometrics and causes the score to be displayed via an electronic device.
In another aspect, the disclosure provides a method comprising sensing, by at least one implanted sensor device comprising one or more continuous sensors, a first modular set of biometrics of a subject. The method includes, by at least one processor: receiving the first modular set of biometrics from the one or more continuous sensors over a period of time; receiving a second modular set of biometrics associated with the subject; selectively serving a graphical user interface configured to present one or more of the first modular set of biometrics and the second modular set of biometrics; normalizing at least a portion of the first modular set of biometrics and the second modular set of biometrics over a period of time; generating a score indicative of a state of a biological system of the subject corresponding to the at least a portion of biometrics of the first modular set of biometrics and the second modular set of biometrics; and causing the score to be displayed via a client electronic device.
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 and drawings, and from the claims.
The present disclosure may be understood more readily by reference to the following detailed description of the embodiments taken in connection with the accompanying drawing figures, which form a part of this disclosure. It is to be understood that this application is not limited to the specific devices, methods, conditions or parameters described and/or shown herein, and that the terminology used herein is for the purpose of describing particular embodiments by way of example only and is not intended to be limiting.
In some embodiments, as used in the specification and including the appended claims, the singular forms “a,” “an,” and “the” include the plural, and reference to a particular numerical value includes at least that particular value, unless the context clearly dictates otherwise. Ranges may be expressed herein as from “about” or “approximately” one particular value and/or to “about” or “approximately” another particular value. When such a range is expressed, another embodiment includes from the one particular value and/or to the other particular value. Similarly, when values are expressed as approximations, by use of the antecedent “about,” it will be understood that the particular value forms another embodiment. It is also understood that all spatial references, such as, for example, horizontal, vertical, top, upper, lower, bottom, left and right, are for illustrative purposes only and can be varied within the scope of the disclosure. For example, the references “upper” and “lower” are relative and used only in the context to the other. Generally, similar spatial references of different aspects or components indicate similar spatial orientation and/or positioning, i.e., that each “first end” is situated on or directed towards the same end of the device. Further, the use of various spatial terminology herein should not be interpreted to limit the various location techniques or orientations for identifying objects or machines.
An “electronic device” or a “computing device” refers to a device or system that includes a processor and memory. Each device may have its own processor and/or memory, or the processor and/or memory may be shared with other devices as in a virtual machine or container arrangement. The memory can contain or receive programming instructions that, when executed by the processor, cause the electronic device to perform one or more operations according to the programming instructions. Examples of electronic devices include personal computers, servers, mainframes, virtual machines, containers, cameras, tablet computers, laptop computers, media players and the like. Electronic devices also may include appliances and other devices that can communicate in an Internet-of-things arrangement. In a client-server arrangement, the client device and the server are electronic devices, in which the server contains instructions and/or data that the client device accesses via one or more communications links in one or more communications networks. In a virtual machine arrangement, a server may be an electronic device, and each virtual machine or container also may be considered an electronic device. In the discussion above, a client device, server device, virtual machine or container may be referred to simply as a “device” for brevity. Additional elements that may be included in electronic devices are discussed in the context of
The terms “processor” and “processing device” refer to a hardware component of an electronic device that is configured to execute programming instructions. Except where specifically stated otherwise, the singular terms “processor” and “processing device” are intended to include both single-processing device embodiments and embodiments in which multiple processing devices together or collectively perform a process.
The terms “memory,” “memory device,” “data store,” “data storage facility” and the like each refer to a tangible and non-transitory device on which computer-readable data, programming instructions or both are stored. Except where specifically stated otherwise, the terms “memory,” “memory device,” “data store,” “data storage facility” and the like are intended to include single device embodiments, embodiments in which multiple memory devices together or collectively store a set of data or instructions, as well as individual sectors within such devices.
In this document, the terms “communication link” and “communication path” mean a wired or wireless path via which a first device sends communication signals to and/or receives communication signals from one or more other devices. Devices are “communicatively connected” if the devices are able to send and/or receive data via a communication link. “Electronic communication” refers to the transmission of data via one or more signals between two or more electronic devices, whether through a wired or wireless network, and whether directly or indirectly via one or more intermediary devices.
The medical health status system 150A may use medical-grade biometric data from the modular implanted sensor system 120 for the purposes of a medical diagnosis by a doctor, medical practitioner or healthcare facility. The consumer ambulatory health status system 150B may use medical-grade biometric data from the modular implanted sensor system 120 for the purposes of providing to the subject, health status information in real-time that may be used by the subject to make improvements in their health. Furthermore, the health status information may be an early indicator or alert of an imminent health crisis, by way of non-limiting example. The health status information may be an early indicator a health status improvement, by way of non-limiting example
The human performance tracking system 150C may use medical-grade biometric data from the modular implanted sensor system 120 for the purposes of providing to a subject, human performance information in real-time that may be used by the subject to make improvements in their performance, such as for athletic training, rehabilitation, and physical therapy.
A modular system with a combined modular ambulatory health status and performance tracking system 100B will be described in relation to
The user electronic device 101 may include a global positioning system and/or inertial navigation system for estimating a geographical location of the user electronic device 101, such estimation of geographical location being well known in the art. The inertial navigation system may include accelerometers, magnetometer and/or gyroscopes. The inertial navigation system may include an inertial measurement unit (IMU).
The system 100B may include a modular implanted sensor system 120. The modular implanted sensor system 120 may include one or more sensor devices, only sensor devices 122, 123 and 124 are shown in
The modular implanted sensor system 120 may include a continuous basic metabolic panel sensor device 124, for example. The modular implanted sensor system 120 may include a continuous infection detection sensor device 123. The modular implanted sensor system 120 may include other sensor devices, such a glucose sensor device 350 (
The term “modular” may be defined as “selectively integrated” and/or “selective functionality.” In some embodiments, a subject using the system 100B may not have need for a continuous infection detection sensor device 123. Furthermore, the continuous infection detection sensor device 123 may be needed only temporarily such as after a surgery or other condition while outside of a hospital or medical facility.
The user electronic device 101 may access a computing system 150 via a communication network 115 such as an intranet or the Internet. The network communications may use wired or wireless communication media and related protocols associated with the platform type of the electronic device 101. The electronic device 101 may communicate with the computing system 150 using known electronic communications. The computing system 150 may be a combination of systems 150A and 150B, in some embodiments. The modular implanted sensor system 120 may also communicate with the user electronic device 101. In some embodiments, the modular implanted sensor system 120 may generate a first modular set of sensor biometric data that is communicated to the user electronic device 101. In turn, the user electronic device 101 may communicate, via the communication network 115, the first modular set of sensor biometric data to the computing system 150 for further review and analysis. The computing system 150 is the assessment system having programming instructions configured to determining a score associated with a biological system of a subject using medical-grade biometrics. One or more subsets of the first modular set of sensor biometric data may be derived by the modular standard of care data sources 125. By way of non-limiting example, if the implant sensor system 120 does not include a continuous basic metabolic panel, then such subset of biometric data may be obtained using the modular standard of care data sources 125.
The user electronic device 101 may have a web browser and/or a modular ambulatory health status (MAHS) and human performance tracking (HPT) application 157 downloaded onto the electronic device 101. The MAHS and HPT application 157 may include programming functions configured to provide the user access to the computing system 150, for example. In the illustration of
The MAHS and HPT application 157 provided by the computing system 150 may include programming instructions configured to allow a first modular set of biometric data to be received and stored from the modular implant sensor system 120 into a biometric data database 159. The MAHS and HPT application 157, via the computing system 150, may include programming instructions configured to allow a second modular set of medical-grade biometric data to be received and stored by one or more of the user electronic device 105 and/or the computing system 150. The second modular set of biometric data may be stored in the biometric data database 159. The second modular set of biometric data may include data from one or more sources of the modular standard of care data sources 125. The modular standard of care data sources 125 are represented in dashed lines to represent that these sources 125 are not part of the system 100B. Instead, the application 157 may include a communications interface and/or an application programming interface (API) to access a subject's medical biometrics data to receive or retrieve different subsets of medical-grade biometric data electronically over a communication path using the Internet/Intranet 115. In other embodiments, the subsets of medical-grade biometric data may be manually entered by the user and stored in the biometric data database 159, as new subset of biometric data becomes available.
By way of a non-limiting example, the second modular set of biometric data or one or more subsets of the biometric data of the second set may be generated as a result of a recent stay in a hospital or based on a recent annual physical. The second modular set of biometric data may include one or more subsets of biometric data associated with the first set of medical-grade biometric data. Overtime, any updates in biometric data, such as the second set of biometric data may be provided by medical laboratories. In an embodiment, the computing system 150 may interface with a hospital records, medical records or other medical-grade patient monitoring systems.
The second modular set of biometric data may include one or more subsets of biometric data such as from a digital column scale 126, a point of care (PoC) lab-on-chip device 128 for providing biometric data associated with a lipid panel, a comprehensive metabolic panel 130, hematocrit 132 and certain infection data 134. Either manually or automatically, one or more of the modular standard of care data sources 125 may provide a hardcopy or an electronic version of the second modular set of biometric data.
As illustrated in
In some embodiments, the user electronic device 105 may communicate or receive data via a doctor or healthcare practitioner 136 that is stored as consult data 836 (
The memory 155 may include programming instructions for analysis 170 and calculations 172, as will be described in relation to
Common algorithms for performing classification processes by the machine learning algorithms may include a support vector machine (SVM), boosted and bagged decision trees, k-nearest neighbor, Naïve Bayes, Bayesian Belief probabilistic algorithms, and discriminant analysis. For example, Bayesian Belief probabilistic algorithms may be used with continuous metabolic panel sensor devices with specific application to glucose and potassium sensing machine learning algorithms.
The MAHS and HPT application 157 may include a programming instructions for displaying human performance tracking (HPT) GUIs 162, as will be described in relation to
The MAHS and HPT application 157 may include programming instructions for displaying standard of care (SoC) biometric GUIs 164 configured to display the biometric data of the standard of care biometric data including both the first set of biometric data and the second set of biometric data, as will be described in detail in relation to
An example, biometric sensor device to sense basic metabolic panel biometric data is described in US Publication Application No. 2020/0072782, incorporated herein by reference as if set forth in full below. Other biometric sensor devices, such as for continuous glucose are described in US Publication Application Nos. US 2019/0090742 and 2019/009743 both of which are incorporated herein by reference as if set forth in full below.
An example biometric sensor device is described in US Publication Application No. 2019/0336077 incorporated herein by reference as if set forth in full.
Sensors in the biometric sensor device 122 may include one or more of an inertial measurement unit; an electrocardiogram sensor; a photoplethysmogram; a thermometer; and/or a microphone.
In addition to the sensed biometric data, the biometric data database 159 may also include range values for high, normal and low. Ranges may include ranges such as acceptable, borderline high, very high, for example. The ranges of the implanted sensor devices may be provided by the manufacturer of the different implanted sensor devices. The ranges may vary per manufacturer or medical laboratory. An example of range data for certain biometric data will be described in
The medical-grade biometrics described above in relation to
The biometric sensor device 122 may include biometric sensors 802, activity senor 804 and a communication unit 806 to communicate with the user electronic device 105. The other sensor devices 123 and 124 may include its own communication unit 806 or share the communication unit 806 of sensor device 122. The modular biometric data 820 is described in
The user electronic device 105 may communicate or receive data associated with a digital column scale 126, as shown in
The user electronic device 105 may communicate or receive data associated with comprehensive metabolic panel 130, as shown in
For example, if a subject was hospitalized for hypocalcemia which is a condition associated with low calcium, calcium may be monitored individually, as well as with the parameters associated with the standard of care biometrics. The doctor may provide other instructions (i.e., consult data 836) that may be stored in the biometric data database 159 (
The user electronic device 105 may communicate or receive data associated with activity or motion data 868, based on sensed data by the activity sensor 804.
After the standard of care biometrics are stored, the data is analyzed by a health tracking module 840, as will be described in relation to
The sensor devices of the sensor system 120 are configured to provide continuous or nearly continuous sensor readings for use by one or both of health tracking module 840 and the human performance tracking module 850. In some cases, one or more biometrics of the standard of care biometrics may be updated periodically either manually or automatically in response to updated testing or physical evaluation.
The embodiments herein contemplate sharing any of the stored biometrics through an interface associated with a walk-in clinic, emergency room and medical facility, such as a hospital.
The health tracking module 840 may include programming instructions configured to calculate health scores (HS) 950, as described below in relation to the Tables. The health tracking module 840 may include programming instructions configured to normalize biometric ranges 952. The health tracking module 840 may include programming instructions configured to calculate a health score trend 954 and/or a biometric trend 960. The health tracking module 840 may include programming instructions configured to generate an alert 970 in response to an out-of-range biometric, health score level or other setting. The health tracking module 840 may include programming instructions configured to display biometrics 972 including graphs and numerical values. The health tracking module 840 may include programming instructions for graphing trends 980 such as for health scores.
The human performance tracking module 850 may include programming instructions for analysis 170 that are configured to analyze training and activity load 1002, as described in
Various biometrics determined and evaluated by the human performance tracking module 850 are shown in Tables 6-9 below.
The human performance tracking module 850 may include programming instructions to calculate 172 that are configured to calculate and track one or more of heart rate variability (HRV) 1004, resting heart rate (RHR) 306, hear rate recovery (HRR) 1008, and respiration 1010. The human performance tracking module 850 may include programming instructions for analysis 170 that are configured to analyze other SoC biometric data 1012. The other SoC biometric data 1012 may be used to identify human performance key metrics, will be described in more detail in relation to
Trends of increasing HRR indicate positive adaptation to training and increased cardiovascular conditioning. Short term decreased in HRR can indicate increased fatigue and decreased recovery status. Thus, thus high HRR (i.e., rapid recovery to normal HR) is indicative of high cardiovascular conditioning. Recognizing trends will be key for this utility. However, deviations of lower HRR from average can indicate high fatigue/low recovery from previous workout and should be factored into NFOR/OTS calculations. The cardiac parameters may include an HRV biometric. HRV biometric determines a change in the duration of each consecutive cardiac cycle. The cardiac cycle may be defined by the duration marked from the end of one heartbeat to the beginning of the next heartbeat. The cardiac cycle may include those phases corresponding to when the heart muscle relaxes and fills with blood or diastole phase; and a period of contraction and pumping of blood or systole phase. The HRV biometric may be measured by electrocardiogram (ECG) or via a pulse oximeter (photoplethsysmography or PTG), which may be part of the biometric sensor device 122. Predominant calculation used in research on HRV in athletes is log-transformed square root of the mean sum of the squared differences between R-R intervals. Resting/sleeping data should be used to avoid exertion leading to sympathetic interference. HRV measurements will be taken daily, while sleep and/or shortly after awakening. This is to avoid sympathetic interference due to activity or exertion. Single point calculations (i.e., daily value) will be displayed to user. Additionally, rolling 7-day and 30-day averages will be calculated. The system will identify trends in these averages and disregard inflections in daily value, as long-term positive or negative trends in HRV are more indicative of training adaptation and/or NFOR or OTS than daily levels.
The system may determine heart rate reserve, as will be described in TABLE 11.
The RHR biometric is the detected heart rate at rest. This measurement is tracked based on the motion data of the three-dimensional accelerometer (i.e., activity sensor 804) of the implanted biometric sensor 122, for example. The HRR biometric may be calculated based on the individual's performance and determine on a time based number (i.e., past week, past month, past 90 days, past year, etc.) by determining the actual HR max over the given time period and the HR rest over the same given time period. Example: if over the past 30 days, the heart rate (HR) max is 200 bpm and the HR rest (this can be a minimum number, or a rolling average say of the 5 minimum values) is 50 bpm, the HRR is 200−50=150. By way of non-limiting example, HR max may be determined as one of a peak number or a rolling average of the top 5 peak values over the past 30 days (or other period of time).
The human performance tracking module 850 may include programming instructions for analysis 170 that are configure to analyze sleep 1014 of a subject, as best described in at least
The HP key biometrics 1016 may include training adaptation (TA), exertion level (EL), anaerobic threshold, metabolic lactate threshold, SpO2 an indicator for altitude acclimation, training zones, endurance level and body temperature. The calculations for these biometrics are described in
The human performance tracking module 850 may include programming instructions to calculate 172 that are configured to calculate a nonfunctional overreaching (NFOR) metrics 1018; and programming instructions for analysis 170 that are configured to analyze the NFOR metrics 1018 to determine if a subject's training routine meets the NFOR metric 1018. The human performance tracking module 850 may include programming instructions to calculate 172 that are configured to calculate a functional overreaching (FOR) metrics 1020; and programming instructions for analysis 170 that are configured to analyze the FOR metrics 1020 to determine if a subject's training routine meets the FOR metric 1020. The human performance tracking module 850 may include programming instructions to calculate 172 that are configured to calculate an overtraining syndrome metric 1022; and programming instructions for analysis 170 that are configured to analyze the OTS metric 1022 to determine if a subject's training routine meets the OTS metric 1022.
The human performance tracking module 850 may include programming instructions to calculate 172 that are configured to calculate one or more of RR metrics 1024 and HR metrics 1026. The human performance tracking module 850 may include a recovery tracking module (RTM) 1028 with may include RTM key metrics 1030, as will be described in more detail below in relation to Table 6.
The human performance tracking module 850 may include programming instructions that execute machine learning algorithms 1032 which may be part of instructions for analysis 170 (
The human performance tracking module 850 may include programing instructions configured to interface with the biometric data database 159 the motion database 168 and the HPT GUIs 162, for example. The human performance tracking module 850 may interface with other databases and programming instruction stored in memory 155
The modularity of the MAHS and HPT application 157 (
The GUI 1100 is configured to allow a user to selectively review standard of care biometrics or subset of biometrics. The subsets of biometrics are for illustrative purposes and not intended to be limiting in any way. The GUI 1100 may be configured to allow the user to download or manually enter one or more standard of care biometrics. The GUI 1100 may include a menu selection tab 1104 and a search field 1105 in tool bar 1102. The menu tab 1104 if selected may provide a drop down window of available functions. Other navigation tools may be used as well. The GUI 1100 may include a main GUI window 1120 configured to display the different subsets of standard of care biometrics. For example, the icon “cBS” if selected by the corresponding radio button 1121 or other selection tool, the programming instructions of the GUI 1100 may cause the GUI 1100 to switch to another GUI 1100 associated with the biometric data of the biometric sensor 122 (
The GUI 1100 may include additional navigation and selectin tools such as a home navigation selection button 1106, a graphs selection button 1108 and a patient file selection button 1110. The graphs selection button 1108 may navigate the user to continuously sensed data and health scores. The home navigation selection button 1106 may switch the current GUI 1100 to a home page (not shown). The graphs selection button 1108 may switch the continuous biometric data selection GUI in
By way of non-limiting example, the home navigation selection button 1106 may allow the user to select a particular tracker, such as a standard of care tracker that is shown in
As will become evident from the description herein, the modularity may allow a user to only use data from an implanted sensor system 120. For example, after surgery a user may need to continuously monitor the biological system for signs of infection. In other cases, the user may only use data from the continuous biometric sensor 122 accompanied with a human performance tracker, as will be described in more detail in relation to
Still further, the MAHS and HPT application 157 (
Still further, the MAHS and HPT application 157 (
The GUI 1100 may include programming instructions that allow a user to use the menu to import information or export information. The menu may allow the user to scan an image of the hardcopy of any of the standard of care biometric data and use feature extraction or optical character recognition (OCR) to recognize text of the hardcopy. Specifically, the numerical vales of the biometric data may be extracted and imported into the patient file, denoted by the patient file selection button 1110.
The list of menu functions is not exhaustive but only illustrative of example functionality
Assume for the sake of illustration, the radio button 1121 associated with the biometric sensor device 122 is selected. The selection of radio button 1121 is denoted by the black shading of the button 1121. After selecting radio button 1121 and selecting the graph selection button 1108, the programming instructions for GUI 1100 may cause the navigation to and display of GUI 1200 of
As can be appreciated, the icons and selection buttons are for illustrative purposes and not meant to be limiting in any way.
The selected biometric data may be from biometric sensor device 122 that senses blood pressure, heart rate, respiration rate, oxygen saturation, body temperature and/or activity, as previously described above in relation to
The GUI 1200B may include a trending graph selection button 1212, for example Assume for the sake of illustration, the trending graph selection button 1212 was selected. Accordingly, the programming instructions for the GUI 1200B may cause the navigation to and the display of GUI 1200C of
Returning again to
In the illustrated example, biometrics that were selected are displayed. However, if less biometrics are selected, then the display ranges may only include those selected or the arrangement of the display ranges may be arranged such that the selected ranges are displayed before non-selected ranges.
It should be noted that medical ranges of the standard of care biometric data are well established and vary per testing laboratory or manufacture of the sensors. The range of each biometric, as described below in relation to Tables 1-5, is used to normalize the numerical values of the biometric.
Although the examples of trending graphs are not shown, trending graphs of each biometric of the lipid panel may be determined over time as these biometrics are updated.
Returning again to
Each of the available biometrics associated with infection biometric data is individually selectable via a radio button or other selection tool.
In an embodiment, the health tracking module 840 is configured to calculate a relative sickness/wellness (or health status) score that is normalized on a scale of 0 to 100, as shown in
In general, each standard of care biometric may be a defined “normal value” with acceptable upper/lower limits. Beyond these acceptable upper/lower limits is a band of “medical concern” values and beyond that is a band of “medical crisis” values.
Referring again to
In an embodiment, the results of the blood pressure 302 (
Accordingly, the MAHS and HPT application 157 (
As another example, if blood pressure trending can be shown for T1=“8”, T2=“5”, T3=“3” indicating clearly that this patient's BP results are trending away from the “ideal” and cause for medical concern (but not a medical crisis). The time interval for determining and graphing a “trend” is user selectable by increments of 5 minutes, hourly, 4 times a day, etc., using the MAHS and HPT application 157. Hence, a trend (i.e., amount of change) can be used as a basis of generating an alert and not just a raw number at any instantiation in time.
Using heart rate 304 (
Therefore, results of a heart rate 304 may be normalized on a scale of 0 to 10 with 10 being defined as “ideal”. For a heart rate result of 122 beats per minute (bpm) at time T1, a normalized health scale result of “8” can be assigned. For a heart rate result of 185 at time T2, a normalized health scale result of “4.5” can be assigned. For a heart rate result of 228 at time T3, a normalized health scale result of “1.5” can be assigned, such as shown in Table 2.
In another example, heart rate trending can be shown for T1=“8”, T2=“4.5”, and T3=“1.5” indicating clearly that this user's heart rate is trending away from the “ideal” and cause for medical concern (but not a medical crisis). The time interval for which a “trend” is determined and graphed for any one biometric is selectable by increments of 5 minutes, hourly, 4 times a day, etc., using the MAHS and HPT application 157 (
Each biometric of the suite of standard of care biometrics will be normalized in a manner similar to what is described above. For example, the ranges for a user's lipid panel is received from a laboratory, for example, as shown in
The health score using the suite of standard of care biometrics will now be described. Table 3 represents a selected suite of the standard of care biometrics after being normalized for times T1, T2 and T3. The selected suite of the standard of care biometrics may include those biometrics described in
The algorithm and methodology applied to Tables 1 and 2 have been completed for the remaining 28 biometrics, as shown in Table 3. The normalized biometrics may be used to obtain a cumulative health score numerator value with a denominator of 300. In other words, the sum of the medical-grade 30 normalized biometric results are divided by 300 (i.e., 30 biometrics×10 for maximum normalized scale) to obtain a normalized aggregate health score on a scale of 0 to 100 with 100 being the “ideal” result. Again, the aggregated health score results can be plotted over time to show a general patient trend towards sickness (trending towards 0) or wellness (trending towards 100), as best seen in
Table 4 is an example of a selected suite of standard of care biometrics with a portion of the biometrics shown in Table 3 removed.
In
Another example of a health score uses additional biometric sensors inputs that can be added to the MAHS and HPT application 157 and system 100B by adjusting the data normalization routine. For instance, an activity tracker such as one that is incorporated into a smart watch 107 or other activity tracker, such as FITBIT ONE, may capture and evaluate daily steps and sleep quality. The smart watch 107 and activity tracker are not medical grade devices. However, biometric data from these non-medical grade sensors could be added to the medical grade suite of standard of care biometrics. In this example, the smart watch 107 or activity tracker may be configured to communicate with the user electronic device 101 (i.e., smart phone 105) to transfer data to the application 157 for subsequent transfer to the biometric database 159. An example of biometric data with added non-medical grade biometric data is shown in Table 5.
In Table 5, the biometrics 31 and 32 have been added from a non-medical grade sensor device, such as an activity tracker. For this example, with 32 biometrics, the health score is at time T1=78.0 as compared to 80.8 for 30 biometrics. The health score is at time T2=73.6 as compared to 76.2 for 30 biometrics. The health score is at time T3=69.4 as compared to 71.7 for 30 biometrics. Again, the health scores in the graph 1435 of
Adding a consumer device such as a FITBIT ONE® into the medical-grade biometrics stored in biometric data database 159 to measure steps and sleep quality does not meet the medical-grade standard of care criteria for making medical claims. The measurement of “steps” is not an accepted medical criterion, nor is sleep quality determined by movement only during sleep. The point being that adding additional biometric data into the system 150 still reinforces the overall health status trending.
Returning to Table 4, assume for the sake of illustration, another modular medical-grade biometric sensor data or test data is available. In this example, assume Hemoglobin A1C, Prothrombin (PT), etc., is available to the user and system 150 and can be modularly added to via the MAHS and HPT application 157 to the biometric data database 159 (
By comprehensively studying the performance of these model systems from the molecular level to macroscopic biomechanics, the effects of training and conditioning on their physiology, and the ability to optimize well beyond their ‘set point’, we can gain insight into how to engineer health and wellness. Insights can be gained into understanding and detecting early signs of neuromotor fatigue in order to prevent impending systematic failure. Such findings may, for example, better inform athletes or users on how to prevent injuries, combat stress and obesity as well as improve recovery and rehabilitation.
An athlete may, for example, typically implement some form of “periodization” into their training program. Physical stress and exertion can temporarily diminish an athlete's physical ability in what is called “functional overreaching”, a desired state. When executed properly, the body's adaptation to this stress may subsequently recover the athlete's physical ability to a level higher than it was prior to the stress in a process called “supercompensation”. This process may require a precise balance of training load and recovery. An imbalance of these factors can lead to undertraining and a lack of progress or nonfunctional overreaching and further to possibly overtraining syndrome.
The embodiments herein track three conditions (functional overreaching, nonfunctional overreaching and overtraining syndrome) on a spectrum. Functional overreaching is a desired state with short-term physical deficits, such as weakness, fatigue and lack of endurance. Nonfunctional overreaching results from either a higher training/recovery imbalance or that imbalance being sustained for a longer period. The same symptoms may likely present, but more intense and longer time to recover. The athlete may also likely not achieve the same desired supercompensation. When nonfunctional overreaching is sustained for long periods, it can turn into overtraining syndrome. Hence, the embodiments herein may detect early signs of overtraining syndrome. Again, similar symptoms may be present, but much more severe and much longer to recover (if at all). The primary differentiator between functional overreaching, nonfunctional overreaching and overtraining syndrome is the (1) intensity (2) consistency and (3) duration of symptoms.
The challenge for an athlete or a coach is to strike the appropriate balance of training and recovery to achieve functional overreaching and supercompensation while avoiding nonfunctional overreaching and the overtraining syndrome. This is currently a challenge for athletes because it is a highly subjective measure; different for each individualized athlete physiology; and not precisely “measurable” with existing technology and biometrics.
A goal of the recovery tracking module 1028 (
Implantable sensor system 120 may constantly collect data on the following biometrics, as shown in Table 6:
The RPE data may be determined based on a Borg RPE scale. The Borg RPE scale may be a numerical scale that ranges from 6 to 20, where 6 means “no exertion at all” and 20 means “maximal exertion.” When a measurement is taken, a number is chosen from the Borg RPE scale stored in memory. [“Perceived Exertion (Borg Rating of Perceived Exertion Scale”, www.cdc.aov/physicalactivity/basics/measuring/exertion)] The score may describe a subject's level of exertion during physical activity. A value of 6 on the same may represent a no exertion level. A value of 7 may represent a level of extremely light exertion. A value of 9 may represent a level of very light exertion. A value of 11 may represent a light exertion level. A value of 23 may represent a somewhat hard exertion level. A value of 15 may represent a hard exertion level. A value of 17 may represent a very hard exertion level. A value of 19 may represent an extremely hard exertion level. A value of 20 may represent a maximum exertion level.
The RPE score×10=HR. For example, RPE score of 15 indicates a HR=150 bpm. The RPE may be subjective and self-reported, and an objective measure of exertion will allow for more accurate analysis of performance adaptation.
Data on these biometrics in Table 6 may be transmitted via wireless communications, such as BLUETOOTH or WI-FI, to the athlete's user electronic device (provided the user electronic device is within range) every 15 minutes. This data can then be sent, via cellular or wireless signal, to the computing system 150 for processing by the human performance tracking module 850.
The biometric data from Table 6 can, for example, be used to establish unique athlete baseline averages over time for the metrics identified in Table 7. These may be calculated on a rolling average to account for training adaptations, such as shown in Table 7.
The accelerometer in the biometric sensor 122 may be used to detect when a user is active (act), at rest or sleeping. Once the machine learning algorithm 1032 (
The metric Movement Velocity Training (MVT) may have two different metrics. One MVT is determined during activity and is represented as MVTact. The MVTact may be determined using 3-D accelerometer and gyroscope data from the IMU to collect and analyze data on acceleration, frequency, duration, and intensity of movement. HR will not be used to determine MVT. Instead, HR should be used to calculate the TL (training load).
From a simplistic point of view, MVT may represent changes in posture and/or the related changing velocity.
The HVM metric may be based on amplitude of acceleration, frequency, duration and intensity data, and movement metrics that may be bucketed into a standard movement vector to denote walking by MVT and a high-velocity movement vector to denote running
The second MVT metric is determined during sleep activity and represented as MVTsleep. The MVTsleep may be determined by utilizing actigraphic methods (i.e., algorithms) by ActiGraph, LLC that analyze movement during sleep using the same data as activity tracking (acceleration, frequency, duration and intensity of 3D accelerometer and gyroscope data).
Specifically, the RTM 1028 may, for example, use machine learning algorithms 1032 to identify deviation patterns in the six (6) biometrics and/or calculated biometrics listed previously, as shown in Table 8.
Each of these deviation patterns may be normalized as a percentage of a baseline to determine a numeric score. The numeric score may be a health score. For example, the score for HRV is calculated based on equation EQ1 in the following way:
As an example, for the following values: HRVsleep=42 millesecond (ms) and HRVbaseline=75 ms, then the ScoreHRV equals −44.
Similar calculations can be done for deviation patterns for the remaining monitored biometrics to determine an overall Overreaching Score defined by equation EQ2:
The ScoreHR_sleep is determined by using the values of
The equations may need to be altered slightly to account for directionality. For example, a decrease in HRV indicates NFOR, whereas and increase in HR indicates NFOR. As a result, the equation for HR must be (HR_baseline−HR_sleep)/(HR_baseline)×100 so that a negative adaptation is shown as a negative score.
Recall that the differentiation between functional overreaching and nonfunctional overreaching is the (1) intensity (2) consistency and (3) duration of symptoms. These can be measured in the following way, as shown in Table 9:
If at least two of these qualifiers listed in Table 9 exceed their predetermined threshold for >1 week consecutively, an “NFOR Alert” can be triggered. If all three of these qualifiers in Table 9 exceed their predetermined threshold for >2 weeks, an “OTS Alert” may then be triggered. These alerts 1034 (
Over time, the machine learning algorithm 1032 (
Nonfunctional overreaching and overtraining syndrome may occur when a subject increases their physical training, for example, without the necessary rest to allow the body to recover. As is known in athletic training, nonfunctional overreaching may cause a short-term reduction in performance by the athlete. However, an athlete can often recover after a period of rest. In some scenarios, the athlete does not improve their performance by nonfunctional overreaching. However, the human performance tracking module 850 may guide the subject to functional overreaching which does lead to improved performance with a period of rest. Hence, the human performance training module 850 may provide sleep or rest recommendations 1036 (
The human performance tracking module 850 may detect an overtraining syndrome and provide a training recommendation to recover. The overtraining syndrome may cause a reduction in performance Recovery from the overtraining syndrome may require a sustained period of rest.
The method blocks below may be performed in the order shown or a different order. One or more of the blocks may be performed contemporaneously. One or more blocks may be omitted or added.
The method 1600 may include, at block 1608, intermittently transmitting data to the athlete's electronic user device and human performance tracking (HPT) module. The method 1600 may include, at block 1610, storing the HR, RR and activity data from the one or more sensors. The method 1600 may include, at block 1612, analyzing and progressively creating baseline values for key metrics identified above in Tables 6 and 7 and ratios. As for ratios, if 5 vital signs are used as a basic case study, the normalized scale of 100 can be interpreted as a percentage. If HR, RR, BP, SpO2, TEMP at rest are all in the ideal range, a score of 100 results, for example. For a person just starting their training regimen, their initial TOTAL scores might start at 60. After 1 week, 70. After 1 month 85. This shows a trend towards an ideal range with a score of 100.
By way of non-limiting example, the human performance tracking metrics may be based on an “ideal” model. For example, if the subject plays basketball, the “ideal” model would be a function of performance metrics for an “ideal” basketball player, such as for jumping, running, etc. On the other hand, if the subject is a runner, the “ideal” model would be a function of performance metrics for an “ideal” runner or sprinter. The model may provide adjusted ranges for biometrics based on a particular human performance outcome yet to achieve.
From block 1612, the method 1600 may split between blocks 1614 and 1616. With regard to block 1614, a determination may be made whether the subject is sleeping. If the determination is “NO,” block 1614 may loop back to block 1602. If the determination is “YES,” block 1614 may proceed to
Returning again to block 1612, the method may proceed to block 1618. The method 1600, at block 1618 may include analyzing data compared to rolling baseline values for RHR, HRV, RR and activity to identify deviation patterns, as identified in Table 8. Activity may include sleep, rest or activity in the form of motion. The method 1600 may include, at block 1620, entering the baseline values into the overreaching score calculations, as describe above in relation to equation EQ1.
Returning again to block 1618, the method 1600 may include, at block 1622, looking up sleep quality data and recommendations 1036 from baseline values and human performance database. The method 1600 may include, at block 1624, displaying a recommendation 1036 based on the rolling baseline values. An example on a “rolling” baseline may include calculation over the past week (last 7 days) where today's baseline calculation replaces the value from 8 days ago, etc.
The method 1700 may include, at block 1708, calculating overreaching score from key sleep and training metrics and compared to baseline values. The method 1700 may include, at block 1710, a determination may be made whether the overreaching score meets a daily threshold. If the determination is “NO,” the method 1700 proceeds to
At block 1718, a determination can be made whether the nonfunctional overreach time threshold is met. If the determination is “NO,” the method 1700 proceeds to
The method 1700 may include, at block 1720, displaying the nonfunctional overreach indicator and recommendation 1036 specific to the nonfunctional overreaching condition. The method 1700 may include, at block 1722, determining whether an overtraining syndrome time threshold is met. If the determination is “NO,” the method 1700 proceeds to
The HP key biometrics 1016 may include a single biometric (medical grade) or calculated biometrics derived from two or more biometrics (medical-grade). From a general population perspective, vital signs may be considered Human Performance key biometrics, as an example Each of the key metrics is a score associated with a biological system of the subject. The HP key biometrics 1016 may include training adaptation (TA) 1907A, exertion level (EL) 1907B, anaerobic threshold 1907C, metabolic lactate threshold 1907D, SpO2 may be an indicator for altitude acclimation 1907E, training zones 1907F, endurance level 1907G and body temperature 1907H. Optionally, the HP key biometrics may include heart rate reserve. For example, the training adaptation (TA) 1907A may be determined based on blood pressure and heart rate. The exertion level (EL) 1907B may be calculated based on heart rate and resting rate. The metabolic lactate threshold 1907D will be described in more detail below. The metric SpO2 (i.e., altitude acclimatization) 1907E is determined. The training zones 1907F is determined by heart rate and SpO2. The endurance level 1907G may be determined by HRR. The body temperature 1907H is measured by the sensor device 122 directly for example
A potential indicator of dehydration may include a high hematocrit level. A comprehensive metabolic panel may be used for nutrition, muscle status and inflammation. Bicarbonate loading may provide an indicator representative of performance enhancing effects. Creatinine combined with BUN may represent dehydration. Glucose may be used for sports nutrition planning and intake during or after a training event. Sodium, combined with chloride, glucose, bicarbonate and hematocrit may provide a measure representative of serum osmolality or dehydration. Temperature may drive heat acclimatization efforts to improve performance Measurements of the blood pressure may be used as a metric to define a rate of recovery. Blood pressure may represent symptomatic hypotension and syncope.
A table representative of training intensity zone metrics is shown in Table 10.
A table representative is shown in Table 11.
By way of non-limiting example, the respiratory rate alone may indicate an exertion level. The respiratory rate when paired with the heart rate, an indication of increased exertion level associated with higher physiological output may be determined, for example. Alternately, an increased exertion level may be associated with lower physiological output representative of fatigue, for example.
The metabolic lactate inflection point (i.e., lactate threshold) may be represented by the exercise intensity at which the blood concentration of lactate and/or lactic acid begins to increase exponentially. It is often expressed as 85% of maximum heart rate or 75% of maximum oxygen intake, se measured in real-time by the biometric sensor device 122.
By way of non-limiting example, altitude acclimatization may be based on relative SpO2 levels that may be monitored for large inflections followed by gradual recovery to indicate a change in altitude change and acclimatization. SpO2 levels (as compared to rolling one month average) should be used to indicate acclimatization. An initial drop in SpO2 may, for example, be expected, followed by a progressing recovery over 2-4 weeks to athlete's 30-day rolling average SpO2 level indicates where in the acclimatization process an athlete may be.
The method 1900 may include, at block 1908, determining whether the body temperature is in a standard range. If the determination is “NO,” the method 1900 may trigger an alert to the user electronic device of the out-of-range temperature condition, at block 1910. If the determination is “YES,” the method 1900 may begin time stamping collected biometric data throughout training, at block 1912.
The determination made at block 1908 may be repeated for each specific key biometric 1016. In other words, if any particular metric is out-of-range by a certain threshold from the baseline values, an alert may be generated and displayed by the user electronic device. In some embodiments, an alert may include an audible alert indicator.
The method 1900 may include, at block 1914, transmit biometric data, collected by the implanted sensor system 120, at end of training session to the computing system 150. The method 1900 may include, at block 1916, store biometric sensor data, and analyze the data to develop baseline values for HP key metrics. The method 1900 may include, at block 1918, selectively display statistics from the workout on the user electronic device via application 157. Examples of displayed statistics is shown in
The method 1900 may include, at block 1920, comparing the baseline values and trend analysis based on stored biometric data (i.e., key metrics 1016) captured during training. The method 1900 may include, at block 1922, look up training recommendations based on workout statistics and trend identification (ID). The method 1900 may include, at block 1924, displaying trending recommendations on the user electronic device via the application 157, as will be described in relation to
The human performance tracking GUI 2000A may include navigational tools for selecting and displaying activity biometrics using the activity button 2010. The biometric data is collected for each training session and/or during sleep. The user may be able to display any of the biometrics capture during sleep separately from those metrics captured during training, as will be described in relation to
The human performance tracking GUI 2000B may include a similar navigation tools as described above in relation to
The human performance tracking GUI 2000B may include tracked performance metrics. For example, the human performance tracking GUI 2000 may display a chart 2020 or graphs of HRV over a period of time. In the illustration, the period of time is a one-week interval. However, other increments of time may be displayed based on a user selection. The GUI 2000B may include a current HRV reading 2022 and/or a percentage of change 2024.
For example, the human performance tracking GUI 2000B may display a chart 2030 of RHR over a period of time. In the illustration, the period of time is a one-week interval. However, other increments of time may be displayed based on a user selection. The human performance tracking GUI 2000B may include a current RHR reading 2032 and/or a percentage of change 2034.
The human performance tracking GUI 2000B may include an e-coaching field 2040 configured to display information associated with a recommendation to improve the physical condition of the subject or to improve training and recovery.
The performance tracking is not limited to athlete training. The performance tracking may be used to access the biological system of a subject or patient undergoing a rehabilitation routine, such as during activity associated with physical therapy, occupational therapy and the like, intended to improve a subject's ability to perform activity.
The performing tracking may include tracking basic metabolic panel biometrics. For example, deficiencies in sodium or potassium may be depleted based on certain training routines and the level of exertion. According, as these biometrics become depleted, the application 157 may provide alerts to recommend the need to take certain supplements or vitamins to raise levels of depleted biometrics. The example of sodium and potassium are meant to be illustrative and not intended to be limiting. Any of the continuously sensed biometrics which are out-of-range may cause the application 157 to generate an alert and/or recommendation.
It should be understood that any of the scores for health or performance are biological system scores that may use continuously sensed biometrics are part of the inputs for calculating a score.
It should be understood that various aspects disclosed herein may be combined in different combinations than the combinations specifically presented in the description and accompanying drawings. It should also be understood that, depending on the example, certain acts or events of any of the processes or methods described herein may be performed in a different sequence, may be added, merged, or left out altogether (e.g., all described acts or events may not be necessary to carry out the techniques). In addition, while certain aspects of this disclosure are described as being performed by a single module or unit for purposes of clarity, it should be understood that the techniques of this disclosure may be performed by a combination of units or modules associated with, for example, a medical device.
In one or more examples, the described techniques or one or more blocks of the methods may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functions may be stored as one or more instructions or code on a computer-readable medium and executed by a hardware-based processing unit. Computer-readable media may include non-transitory computer-readable media that corresponds to a tangible medium such as data storage media (e.g., RAM, ROM, EEPROM, flash 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).
Instructions may be executed by 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 physical structure suitable for implementation of the described techniques and blocks of methods herein. Also, the techniques could be fully implemented in one or more circuits or logic elements.
A bus 2100 serves as the main information highway interconnecting the other illustrated components of the hardware. CPU 2105 is the central processing unit of the system, performing calculations and logic operations as may be required to execute a program. CPU 2105, alone or in conjunction with one or more of the other elements disclosed in
Program instructions, software or interactive modules for providing the interface and performing any querying or analysis associated with one or more data sets may be stored in the computer-readable storage media 2120. Optionally, the program instructions may be stored on a tangible, non-transitory computer-readable medium such as a compact disk, a digital disk, flash memory, a memory card, a universal serial bus (USB) drive, an optical disc storage medium and/or other recording medium.
An optional display interface 2130 may permit information from the bus 2100 to be displayed on the display 2135 in audio, visual, graphic or alphanumeric format. Communication with external devices may occur using various communication ports 2140. A communication port 2140 may be attached to a communications network, such as the Internet or an intranet 115 (
The hardware may also include an interface 2145, such as graphical user interface (GUI), that allows for receipt of data from input devices such as a keyboard or other input device 2150 such as a mouse, a joystick, a touch screen, a remote control, a pointing device, a video input device and/or an audio input device. The GUIs, described herein, may be displayed using a browser application being executed by an electronic device and served by a server of the system 100B. For example, hypertext markup language (HTML) may be used for designing the GUI with HTML tags to the images of the assets and other information stored in or served from memory 155.
In this document, “electronic communication” refers to the transmission of data via one or more signals between two or more electronic devices, whether through a wired or wireless network, and whether directly or indirectly via one or more intermediary devices. Devices are “communicatively connected” if the devices are able to send and/or receive data via electronic communication.
The features and functions described above, as well as alternatives, may be combined into many other different systems or applications. Various alternatives, modifications, variations or improvements may be made by those skilled in the art, each of which is also intended to be encompassed by the disclosed embodiments.
