NL2038024B1

NL2038024B1 - Continuous cortisol monitoring system, application, and method background

Info

Publication number: NL2038024B1
Application number: NL2038024A
Authority: NL
Inventors: Tschinkel Maren
Original assignee: Tschinkel Maren
Priority date: 2024-06-21
Filing date: 2024-06-21
Publication date: 2026-01-15

Abstract

Example implementations described herein involves a method for a user device, computer program, user device, and system for intaking continuous cortisol measurement for stress management, which can involve receiving continuous measurements of norepinephrine, epinephrine, and cortisol from a wearable device conﬁgured to measure the norepinephrine, the epinephrine, and the cortisol from a wearer of the wearable device, processing the continuous measurements of the norepinephrine, the epinephrine, and the cortisol to forecast future cortisol levels of the wearer, and for the forecasted future cortisol levels of the wearer predicted to exceed a threshold, generating a message through an application of the user device indicative of the forecasted future cortisol levels of the wearer being predicted to exceed the threshold.

Description

CONTINUOUS CORTISOL MONITORING SYSTEM, APPLICATION, AND METHOD

BACKGROUND Field

[0001] The present disclosure is directed generally to cortisol monitoring systems, and more specifically, to facilitating an application and platform system with functions directed to continuous cortisol monitoring.

Related Art

[0002] Cortisol is a stress hormone produced by the adrenal glands that is reflective of a stress response in a person. Most people have a normal or baseline cortisol level that can vary throughout the day or depending on the activity (e.g., higher in the morning or during exercise, and lower right before sleeping). The natural variation of cortisol levels help a person to wake up, to unwind for sleep, or to help the person perform normal but impactful activities, such as exercise.

[0003] Cortisol levels can also spike in response to stressful situations to help a person cope with stress. However, for people susceptible to stress attacks or anxiety attacks, a spike in cortisol levels may induce a stress attack or anxiety attack, which can be severe enough to cause a heart attack. Accordingly, such people have to manage their stress to avoid such a spike in cortisol levels, or at least be forewarned of a potential impending spike.

SUMMARY

[0004] In view of the aforementioned problems, there is a need to continuously monitor cortisol levels in order to help the user facilitate stress management. Further, there is a need for determining when a spike in cortisol levels may potentially occur in order for the user to pre-emptively manage or prevent a potential stress attack or an anxiety attack.

[0005] Example implementations described herein are directed to a system that utilizes mobile/user device functions as well as a continuous monitoring device to facilitate the above needs. In particular, the continuous monitoring device is configured to not only continuously monitor cortisol, but is also configured to continuously monitor norepinephrine and epinephrine levels. In example implementations, a function as described herein can be utilized to forecast future cortisol levels based on the current norepinephrine, epinephrine, and cortisol levels. Such information is provided to a user device, which can inform the user of the cortisol levels as well as warn the user of any predicted impending spikes in cortisol levels.

[0006] In example implementations, a user application having functions and interfaces will alarm the user that cortisol levels will rise soon based on when norepinephrine and epinephrine are released. That way, the user device can help prevent and predict possible anxiety attacks as well as heart attacks and lower the risk of any stress related diseases. The application of the user device can help track down the causes of stress in an individual and help asset in determining what really calms a particular user down based on continuously measuring the stress levels. Anxiety patients will be able to know exactly when it makes sense to take medication to calm down. In the related art, such patients take medication throughout the day without knowing when it is actually needed.

[0007] Through the example implementations, people in risk of heart attacks are able to take prevention and act before it is too late. It will help any patient struggling from stress related diseases such as heart disease, asthma, obesity, diabetes, headaches, depression and anxiety, gastrointestinal problems, Alzheimer's disease, sleeping disorders, accelerated aging, and so on.

[0008] Aspects of the present disclosure can involve a user device configured to intake continuous cortisol measurement for stress management, involving means for receiving continuous measurements of norepinephrine, epinephrine, and cortisol from a wearable device configured to measure the norepinephrine, the epinephrine, and the cortisol from a wearer of the wearable device; means for processing the continuous measurements of the norepinephrine, the epinephrine, and the cortisol to forecast future cortisol levels of the wearer, and for the forecasted future cortisol levels of the wearer predicted to exceed a threshold, means for generating a message through an application of the user device indicative of the forecasted future cortisol levels of the wearer being predicted to exceed the threshold.

[0009] Aspects of the present disclosure can involve a computer program, storing instructions for a user device configured to intake continuous cortisol measurement for stress management, involving receiving continuous measurements of norepinephrine, epinephrine, and cortisol from a wearable device configured to measure the norepinephrine, the epinephrine, and the cortisol from a wearer of the wearable device, processing the continuous measurements of the norepinephrine, the epinephrine, and the cortisol to forecast future cortisol levels of the wearer; and for the forecasted future cortisol levels of the wearer predicted to exceed a threshold, generating a message through an application of the user device indicative of the forecasted future cortisol levels of the wearer being predicted to exceed the threshold. The computer program and instructions can be stored in a non- transitory computer readable medium and executed by one or more processors.

[0010] Aspects of the present disclosure can involve a system, which can involve a wearable device configured to measure norepinephrine, epinephrine, and cortisol from a wearer of the wearable device; and a user device configured to intake continuous cortisol measurement for stress management, comprising a processor, configured to execute a method involving receiving continuous measurements of norepinephrine, epinephrine, and cortisol from a wearable device configured to measure the norepinephrine, the epinephrine, and the cortisol from a wearer of the wearable device, processing the continuous measurements of the norepinephrine, the epinephrine, and the cortisol to forecast future cortisol levels of the wearer; and for the forecasted future cortisol levels of the wearer predicted to exceed a threshold, generating a message through an application of the user device indicative of the forecasted future cortisol levels of the wearer being predicted to exceed the threshold.

[0011] Aspects of the present disclosure can involve a method for a user device configured to intake continuous cortisol measurement for stress management, which can involve receiving continuous measurements of norepinephrine, epinephrine, and cortisol from a wearable device configured to measure the norepinephrine, the epinephrine, and the cortisol from a wearer of the wearable device; and for a rise in the continuous measurements of norepinephrine and epinephrine exceeding a threshold, generating a message through an application of the user device indicative of an anxiety attack occurring.

[0012] Aspects of the present disclosure can involve a method for a user device configured to intake continuous cortisol measurement for stress management, involving receiving continuous measurements of norepinephrine, epinephrine, and cortisol from a wearable device configured to measure the norepinephrine, the epinephrine, and the cortisol from a wearer of the wearable device; processing the continuous measurements of the norepinephrine, the epinephrine, and the cortisol to forecast future cortisol levels of the wearer; and for the forecasted future cortisol levels of the wearer predicted to exceed a threshold, generating a message through an application of the user device indicative of the forecasted future cortisol levels of the wearer being predicted to exceed the threshold.

BRIEF DESCRIPTION OF THE DRAWINGS

[0013] FIG. 1 illustrates an example system diagram, in accordance with an example implementation.

[0014] FIG. 2(a) illustrates an example of a sensing device, in accordance with an example implementation.

[0015] FIG. 2(b) illustrates an example of a user device, in accordance with an example implementation.

[0016] FIGS. 3(a) to 3(1} illustrate example screen interfaces and functions for the user device, in accordance with an example implementation.

[0017] FIG. 4(a) illustrates an example flow for training a function to predict future cortisol levels based on historical norepinephrine, epinephrine, and cortisol levels, in accordance with an example implementation.

[0018] FIG. 4(b) illustrates an example flow for training a function to predict probability of an anxiety attack/heart attack based on historical norepinephrine, epinephrine, and cortisol levels, in accordance with an example implementation.

[0019] FIG. 5 illustrates an example computing environment with an example computer device suitable for use in some example implementations.

DETAILED DESCRIPTION

[0020] The following detailed description provides further details of the figures and example implementations of the present application. Reference numerals and descriptions of redundant elements between figures are omitted for clarity. Terms used throughout the description are provided as examples and are not intended to be limiting. For example, the use of the term “automatic” may involve fully automatic or semi-automatic implementations involving user or administrator control over certain aspects of the implementation,

depending on the desired implementation of one of ordinary skill in the art practicing implementations of the present application. The implementations described herein are also not intended to be limiting, and can be implemented in various ways, depending on the desired implementation. Further, the example implementations described herein can be 5 conducted in singular or in any combination with each other to facilitate the desired implementation, and the present disclosure is not limited to any particular one of the example implementations described herein.

[0021] FIG. 1 illustrates an example system upon which example implementations can be applied. Each user 101 is associated with a system that involves a user device 101-1 and a wearable device 101-2. The user device 101-1 can be implemented in the form of any user device such as a mobile phone, a laptop, a tablet, a watch, or other device that is capable of executing applications and communicating with the wearable device 101-2 and/or the internet. The wearable device 101-2 can be connected to the user device 101-1 via a short- range communication interface such as BLUETOOTH, via internet or cellular connection, via local area network (LAN), directly by cable (e.g., USB cable, serial cable, etc.) or by other methods in accordance with the desired implementation. Through the connection between the wearable device 101-2 and the user device 101-1, the user device 101-1 can receive continuous measurements of stress substances norepinephrine, epinephrine, and cortisol from the wearable device 101-2 for processing.

[0022] The user device 101-1 is networked to a cloud server 102 via a network 100. In example implementations described herein, continuous measurements of norepinephrine, epinephrine, and cortisol are transmitted from the user device 101-1 to the cloud server 102, which is then stored as historical data in a database 103. In example implementations described herein, the continuous measurement of norepinephrine, epinephrine, and cortisol is utilized to forecast future cortisol levels. Such future cortisol levels can be provided through a machine learning function that is trained at the cloud server 102 from norepinephrine, epinephrine, and cortisol at time #, and resulting cortisol levels at a time 7 + x in the future. In this manner, a function can be constructed that can predict future cortisol levels at time £ + x given norepinephrine, epinephrine, and cortisol levels at time £. Once sucha function is trained, it can be provided to the user device accordingly. Similar functions can also be constructed by the cloud server 102 to train a function with machine learning to determine forecasts for anxiety or heart attacks as described in FIG. 4(b), which can also be provided to the user device 101-1.

[0023] Although machine learning algorithms are used to derive the predicted future cortisol levels given present norepinephrine, epinephrine, and cortisol levels, other algorithms can be utilized to construct the same function, and the present disclosure is not limited thereto.

[0024] FIG. 2(a) illustrates an example user device 101-1, in accordance with an example implementation. In the example implementation, the user device is a mobile device, but can also include laptops, wearable devices or other devices that have similar hardware configurations in accordance with the desired implementation. User device 101-1 can include camera 201, microphone 202, processor 203, memory 204, display 205, interface (I/F) 206 and sensors 207. Camera 201 can include any type of camera that is configured to record any form of video or imagery in accordance with the desired implementation. Microphone 202 can involve any form of microphone that is configured to record any form of audio in accordance with the desired implementation. Display 205 can involve a touch screen display configured to receive touch input to facilitate instructions to execute the functions as described herein, or a normal display such as a liquid crystal display (LCD) or any other display in accordance with the desired implementation. I/F 206 can include network interfaces to facilitate connections of the mobile device 101-1 to external elements such as the server, the wearable device, and any other device in accordance with the desired implementations.

[0025] Processor 203 can be in the form of hardware processors such as central processing units (CPUs) or in a combination of hardware and software units in accordance with the desired implementation. The sensors 207 can involve any set of sensors to facilitate the example implementations herein. Sensors 207 can include a gyroscope and/or accelerometer that is configured to measure any kind of orientation measurement, such as tilt angle, orientation with respect to x,y,z, access, acceleration (e.g., gravity) and so on in accordance with the desired implementation. Orientation sensor measurements can also involve gravity vector measurements to indicate the gravity vector of the device in accordance with the desired implementation. Sensors 207 can also include location sensors such as Global Positioning Satellite (GPS) sensors for determining the location of the device.

[0026] In example implementations described herein, processor(s) 203 can be configured to execute a user device application loaded from memory 204 to facilitate the functionality as shown in the screen interfaces of FIGS. 3(a) to 3(1).

[0027] FIG. 2(b) illustrates an example of a wearable device 101-2 in accordance with an example implementation. The wearable device 101-2 can include, but is not limited to, a sensing array 211, microfluidic chamber(s) 212, processor(s) 213, memory 214, power source 215, and I/F 216.

[0028] Sensing array 211 can involve an array of sensors (e.g., microneedles with sensor circuits) that are configured to conduct continuous measurements of norepinephrine, epinephrine, and cortisol, which are transmitted to the user device 101-1 through I/F 216 for providing continuous measurements of cortisol on the user device 101-1 as well as to predict future cortisol levels. To facilitate continuous measurements of norepinephrine, epinephrine, and cortisol, the sensing array 211 is configured to interact with chemicals as known in the art from microfluidic chamber(s) 212 to facilitate the measurement of norepinephrine, epinephrine, and cortisol.

[0029] In example implementations described herein, the user device 101-1 is configured to intake continuous cortisol measurement for stress management, which can involve receiving continuous measurements of norepinephrine, epinephrine, and cortisol from a wearable device 101-2 configured to measure the norepinephrine, the epinephrine, and the cortisol from a wearer of the wearable device, processing the continuous measurements of the norepinephrine, the epinephrine, and the cortisol to forecast future cortisol levels of the wearer (e.g., based on the trained function from machine learning provided by cloud server 102 as described in FIG. 4(a)); and for the forecasted future cortisol levels of the wearer predicted to exceed a threshold, generating a message through an application of the user device indicative of the forecasted future cortisol levels of the wearer being predicted to exceed the threshold as illustrated in FIG. 3(j). Such a threshold can be setin accordance with any desired implementation.

[0030] Such example implementations can also involve displaying, on the user device 101-1, the continuous measurements of cortisol in real time 301 as illustrated in FIG. 3(a).

[0031] Such example implementations can also involve, for the continuous measurements of cortisol exceeding the threshold, displaying, through the application of the user device 101-1, a recommendation to reduce the cortisol as shown in FIG. 3(g). In such example implementations, the recommendation to reduce the cortisol can include a medication recommendation 361 as shown in FIG. 3(g).

[0032] Depending on the desired implementation, the message can include an indication of an expected time frame of a predicted spike in cortisol measurements based on the forecasted future cortisol levels as shown at 380 of FIG. 3(j).

[0033] The example implementations described herein can involve adjusting the threshold for when the user device detects that an exercise mode is engaged as described with respect to FIG. 3(d).

[0034] In the example implementations described herein, the processing the continuous measurements of the norepinephrine, the epinephrine, and the cortisol to forecast the future cortisol levels of the wearer is conducted by a function trained by a machine learning algorithm, the function configured to intake the continuous measurements of the norepinephrine, the epinephrine, and the cortisol, and output predicted cortisol levels from the continuous measurements of the norepinephrine, the epinephrine, and the cortisol as shown in FIG. 4(a).

[0035] In the example implementations described herein, the user device 101-1 can also involve transmitting the continuous measurements of the norepinephrine, the epinephrine, and the cortisol to a cloud server 102 configured to update parameters of the machine learning algorithm to output the predicted cortisol levels based on subsequent ones of the continuous measurements of the cortisol; wherein the cloud server 102 is configured to update the machine learning algorithm of the user device 101-1 for when the parameters are updated.

[0036] FIGS. 3(a) to 3(1) illustrate example screen interfaces and functions for the user device, in accordance with an example implementation. The example screen interfaces and functions for the user device 101-1 is facilitated through a user application that interfaces with the wearable device 101-2. Specifically, FIG. 3(a) illustrates an example display of live and continuous cortisol measurements measured by the wearable device 101-2. The wearable device 101-2 provides live and continuous cortisol measurements to the user device 101-1, which can be displayed in graph form or as a value as shown at interface display 301.

Example functions will be described herein can include viewing a cortisol forecast 302 and starting an exercise mode 303. Other measurements can also be displayed from the wearable device 101-2, such as, but not limited to, the levels of norepinephrine and epinephrine.

[0037] FIG. 3(b) illustrates an example screen involving a push notification for the user device, in accordance with an example implementation. In example implementations, the application can provide a push notification 310 for when the wearable device 101-2 detects a cortisol level that is beyond a threshold. In this manner, even if the user is not focused on the user application, a message can be provided for when a spike in cortisol levels, or an increase in cortisol levels beyond a threshold is detected.

[0038] FIG. 3(c) illustrates an example screen interface for when the cortisol level exceeds a threshold, in accordance with an example implementation. Such a screen interface can also be accessed for when the push notification 310 is selected to load the application.

Interface display 320 displays the cortisol levels and can provide a message to ask the user as to whether the user is exercising and had forgot to engage the exercise mode. In example implementations, such a message can be provided as a banner that automatically appears on the display for the user after a certain cortisol level threshold is reached. The interface display 320 can also review an additional function to inform the user to take action to lower the cortisol level. For example, the “What can I do?” button 321 can provide another interface that indicates functions for reducing the cortisol level as illustrated in FIG. 3(g).

[0039] FIG. 3(d) illustrates an example screen interface for when the exercise mode is engaged, in accordance with an example implementation. Exercise mode can be executed by pressing the start exercise mode button 303 in the interface screen. Depending on the desired implementation, exercise mode can also be automatically executed based on data from sensors 207 (e.g., sensor measurements indicating that the user is conducting some physical activity). In this example, the interface screen 330 removes the warning about the high cortisol level as the exercise mode has been engaged, and changes the threshold for the cortisol level. When the user wishes to end the exercise mode, then button 331 can be utilized.

[0040] FIG. 3(e) illustrates an example screen interface for when the exercise mode is ended, in accordance with an example implementation. Specifically, FIG. 3(e) illustrates an example interface display 340 that indicates the report of the workout and also allows for a function for the display of an exercise summary as shown at button 341. The user may also continue with exercise mode with the continue exercise mode button 342.

[0041] FIG. 3(f) illustrates an example screen interface for the exercise summary, for when the exercise summary button 341 is used, in accordance with an example implementation. As shown in the interface screen 350, the start of the exercise can be marked. Depending on the desired implementation, the display of the measurements can also be altered to indicate the measurements taken during exercise mode (e.g., graph line or value can change color). Other messages can be shown, such as when it was detected that the user was entering a calming down during the exercise.

[0042] FIG. 3(g) illustrates an example screen interface for providing recommendations in accordance with an example implementation. In an example, this screen interface can be provided for when the “What can I do?” button 321 is used. Example functions can include, but is not limited to, a button to call your doctor 360, to take medication 361, to recommend a breathing exercise 362, to play calming music 363, to recommend a walking/yoga exercise 364, and so on. For example, the function to call your doctor 360 may have a number pre- populated with the doctor’s number or with a number for a hospital or emergency services, in accordance with the desired implementation. The function to take medication 361 can provide recommendation as to which medications to take depending on a pre-populated medication list as provided by the doctor or the user, or otherwise in accordance with the desired implementation. The function for breathing exercise 362 can load a video demonstrating a breathing exercise video to help lower cortisol. The function to play calming music 363 can be used to help the user calm down. The function to recommend a walking/yoga exercise 364 can provide instructions or a video regarding the recommended walking or yoga exercise to perform to reduce cortisol. Through the interface shown in FIG.

3(g), users can understand and differentiate between a good cortisol spike versus a bad cortisol spike.

[0043] FIG. 3(h) illustrates an example chat function that can be provided through the user application, in accordance with an example implementation. Depending on the desired implementation, a chat function can be provided for 24/7 support for all possible questions regarding stress management or cortisol. Such a chat function can be implemented, for example, by an artificial intelligence (AT) bot.

[0044] FIG. 3(1) illustrates an example screen interface for forecasting cortisol, in accordance with an example implementation. The example screen interface can be provided through the function for the view cortisol forecast 302. In the example interface display 370, a prediction of future cortisol levels is displayed. If the prediction involves a spike in cortisol levels, then a message 371 can be provided that cortisol levels are expected to rise beyond the desired threshold. Functions can then be provided to either engage exercise mode 303 or call up the “What can I do?” 321 interface. Another function can be provided to return the screen interface back to the monitor 372.

[0045] FIG. 3()) illustrates an example screen interface with a push notification 380 for when forecasted cortisol levels will exceed a threshold. Through the push notification 380, the user can be warned ahead of time as to when cortisol levels are predicted to exceed a threshold so that the user can take steps in advance to counter the expected rise in cortisol.

Selecting the push notification 380 can also generate the screen interface as shown in FIG. 36).

[0046] FIG. 3(k) illustrates an example screen interface with a push notification 390 for when the predicted chance of an anxiety or a heart attack will exceed a threshold. Through the push notification 390, the user can be warned ahead of time as to when the application determines that there may be a significant chance of an impending anxiety or a heart attack based on the function as described in FIG. 4(b).

[0047] FIG. 3(1) illustrates an example screen interface with a push notification 395 for when a rapid rise in epinephrine and norepinephrine is detected, in accordance with an example implementation. In example implementations, a rapid rise in epinephrine and norepinephrine as measured from the wearable device 102-1 can be indicative of an anxiety attack or heart attack. The anxiety attack or heart attack could occur in the absence of a spike of cortisol levels or while cortisol levels are low, which may only follow on after a period of time (e.g., ten minutes). Rapid rises in epinephrine and norepinephrine can indicate that the wearer 1s undergoing stress. The threshold for the rapidity in rise to trigger the push notification 395 can be adjusted according to the desired implementation (e.g., amount over time, etc.)

[0048] Through the functions and interfaces as described from FIGS. 3(a) to 3(1), the user device can help the user proactively address anxiety attacks or heart attacks as the body can react very differently in each situation.

[0049] The functions and interfaces described from FIGS. 3(a) to 3(1) also allow the user device to accurately inform the user as to when to take stress medications or conduct other activities to reduce stress levels. In the related art, patients suffering from stress disease take medications more or less randomly through the day without being able to know when it would be actually necessary. The functions and interfaces can show the user the continuous stress levels and with that it will be able for the user to tell when it makes sense to take medications and when it is not necessary. In addition, notifications will also help the user determine what is effective in helping the user to calm down, as well determining which situations are causing stress.

[0050] FIG. 4(a) illustrates an example flow for training a function to predict future cortisol levels based on historical norepinephrine, epinephrine, and cortisol levels, in accordance with an example implementation. In this example implementation, reinforcement learning is utilized to train a function to predict future cortisol levels, however other machine learning techniques or non-machine learning techniques may also be utilized, and the present disclosure is not limited thereto.

[0051] At 401, the cloud server 102 utilizes the historical norepinephrine, epinephrine, and cortisol levels at time 7 from database 103 to provide to the reinforcement learning function to output predicted cortisol level at # + x. At 402, the output predicted cortisol level at f + x is compared to the historical cortisol level at time 7 + x from database 103. Based on the difference, a reward or penalty is issued to the reinforcement learning function at 403.

The flow of FIG. 4(a) can be continuously iterated until convergence is found, or some stopping criteria is met in accordance with the desired implementation. The delta in time x can be set to any desired implementation (e.g., five minutes, ten minutes).

[0052] Although the example implementations described herein involve machine learning to generate a function that predicts cortisol based on present continuous measurements of norepinephrine, epinephrine, and cortisol, such a function can also omit the continuous measurements of cortisol and be configured to predict cortisol based on norepinephrine and epinephrine levels. In example implementations described herein, the underlying functions presume that future cortisol levels are derivable from at least the present norepinephrine and epinephrine levels of the user. Thus, present measurements of cortisol can be omitted for training and using the function to predict cortisol levels.

[0053] Moreover, because there are physical and health variations between users of the device, other parameters may be utilized to train the function with machine learning to account for physical and health variations affecting cortisol levels. For example, one user may experience a cortisol spike ten to twenty minutes after certain measurements of norepinephrine and epinephrine are detected, whereas another user may experience a cortisol spike in less than ten minutes with the same readings. Thus, other parameters to account for such variations (e.g., whether exercise mode is engaged, weight of the user, height of the user, gender of the user, past history of heart attacks, past history of anxiety attacks, last consumption and quantity of consumption of stress or anxiety medication, and so on in accordance with the desired implementation) may also be incorporated to training the function for machine learning, and also can be provided by the user device 101-1 to the trained function to provide the output for predicted cortisol.

[0054] FIG. 4(b) illustrates an example flow for training a function to predict the chances of an anxiety attack or a heart attack based on historical norepinephrine, epinephrine, and cortisol levels, in accordance with an example implementation. In this example implementation, reinforcement learning is utilized to train a function to predict the chances of an anxiety attack or a heart attack, however other machine learning techniques or non- machine learning techniques may also be utilized, and the present disclosure is not limited thereto.

[0055] At 411, the cloud server 102 utilizes the historical norepinephrine, epinephrine, and cortisol levels at time # from database 103 to provide to the reinforcement learning function to output predicted chances of an anxiety attack or a heart attack to occur by time # + x. At 412, the output predicted chances of an anxiety attack or a heart attack to occur at time ¢ + x is compared to whether an anxiety attack or a heart attack occurred within time 7 + x from database 103. Based on the difference, a reward or penalty is issued to the reinforcement learning function at 413. The flow of FIG. 4(b) can be continuously iterated until convergence is found, or some stopping criteria is met in accordance with the desired implementation. The delta in time x can be set to any desired implementation (e.g., five minutes, ten minutes).

[0056] Although the example implementations described herein involve machine learning to generate a function that predicts the chances of an anxiety attack or a heart attack based on present continuous measurements of norepinephrine, epinephrine, and cortisol, such a function can also omit the continuous measurements of cortisol and be configured to predict such anxiety attacks or heart attacks based on norepinephrine and epinephrine levels.

In example implementations described herein, the underlying functions presume that spikes and intensity in cortisol levels that trigger such an anxiety attack or a heart attack can be derived from at least the present norepinephrine and epinephrine levels of the user. Thus, present measurements of cortisol can be omitted for training and using the function to predict the chances of an anxiety attack or a heart attack.

[0057] Moreover, because there are physical and health variations between users of the device, other parameters may be utilized to train the function with machine learning to account for physical and health vanations affecting anxiety and heart attacks. Thus, other parameters to account for such variations (e.g., whether exercise mode is engaged, weight of the user, height of the user, gender of the user, past history of heart attacks, past history of anxiety attacks, last consumption and quantity of consumption of stress or anxiety medication, whether user is a smoker or drinker, last drink or smoke consumed, and so on in accordance with the desired implementation) may also be incorporated to training the function for machine learning, and also can be provided by the user device 101-1 to the trained function to provide the output for predicted chances of an anxiety attack or a heart attack.

[0058] The flows of FIGS. 4(a) and 4(b) can also be run periodically based on additions to the database 103 from the continuous measurements of norepinephrine, epinephrine, and cortisol levels transmitted to the cloud server 102 by the user device 101-1. If the parameters of the function are updated by the machine learning algorithm (e.g., due to the new function being more accurate than the previous function), then the updated function parameters and function can be provided from the cloud server 102 to the user device 101-1.

[0059] FIG. 5 illustrates an example computing environment with an example computer device suitable for use in some example implementations, such as a server 102 that manages a database 103 to provide updates, such as updated functions for predicting future cortisol levels, to the user device 101-1. Computer device 505 in computing environment 500 can include one or more processing units, cores, or processors 510, memory 515 (e.g, RAM,

ROM, and/or the like), internal storage 520 (e.g., magnetic, optical, solid state storage, and/or organic), and/or I/O interface 525, any of which can be coupled on a communication mechanism or bus 530 for communicating information or embedded in the computer device 505. I/O interface 525 is also configured to receive images from cameras or provide images to projectors or displays, depending on the desired implementation.

[0060] Computer device 505 can be communicatively coupled to input/user interface 535 and output device/interface 540. Either one or both of input/user interface 535 and output device/interface 540 can be a wired or wireless interface and can be detachable. Input/user interface 535 may include any device, component, sensor, or interface, physical or virtual, that can be used to provide input (e.g. buttons, touch-screen interface, keyboard, a pointing/cursor control, microphone, camera, braille, motion sensor, optical reader, and/or the like). Output device/interface 540 may include a display, television, monitor, printer, speaker, braille, or the like. In some example implementations, input/user interface 535 and output device/interface 540 can be embedded with or physically coupled to the computer device 505. In other example implementations, other computer devices may function as or provide the functions of input/user interface 535 and output device/interface 540 for a computer device 505.

[0061] Examples of computer device 505 may include, but are not limited to, highly mobile devices (e.g., smartphones, devices in vehicles and other machines, devices carried by humans and animals, and the like), mobile devices (e.g., tablets, notebooks, laptops, personal computers, portable televisions, radios, and the like), and devices not designed for mobility (e.g., desktop computers, other computers, information kiosks, televisions with one or more processors embedded therein and/or coupled thereto, radios, and the like).

[0062] Computer device 505 can be communicatively coupled (e.g., via I/O interface 525) to external storage 545 and network 550 for communicating with any number of networked components, devices, and systems, including one or more computer devices of the same or different configuration. Computer device 505 or any connected computer device can be functioning as, providing services of, or referred to as a server, client, thin server, general machine, special-purpose machine, or another label.

[0063] I/O interface 525 can include, but is not limited to, wired and/or wireless interfaces using any communication or I/O protocols or standards (e.g., Ethernet, 802.11x,

Universal System Bus, WiMax, modem, a cellular network protocol, and the like) for communicating information to and/or from at least all the connected components, devices, and network in computing environment 500. Network 550 can be any network or combination of networks (e.g., the Internet, local area network, wide area network, a telephonic network, a cellular network, satellite network, and the like).

[0064] Computer device 505 can use and/or communicate using computer-usable or computer-readable media, including transitory media and non-transitory media. Transitory media include transmission media (e.g., metal cables, fiber optics), signals, carrier waves, and the like. Non-transitory media include magnetic media (e.g., disks and tapes), optical media (e.g., CD ROM, digital video disks, Blu-ray disks), solid state media (e.g., RAM,

ROM, flash memory, solid-state storage), and other non-volatile storage or memory.

[0065] Computer device 505 can be used to implement techniques, methods, applications, processes, or computer-executable instructions in some example computing environments. Computer-executable instructions can be retrieved from transitory media, and stored on and retrieved from non-transitory media. The executable instructions can originate from one or more of any programming, scripting, and machine languages (e.g., C, C++, C#,

Java, Visual Basic, Python, Perl, JavaScript, and others).

[0066] Processor(s) 510 can execute under any operating system (OS) (not shown), in a native or virtual environment. One or more applications can be deployed that include logic unit 560, application programming interface (API) unit 565, input unit 570, output unit 575, and inter-unit communication mechanism 595 for the different units to communicate with each other, with the OS, and with other applications (not shown). The described units and elements can be varied in design, function, configuration, or implementation and are not limited to the descriptions provided. Processor(s) 510 can be in the form of hardware processors such as central processing units (CPUs) or in a combination of hardware and software units.

[0067] In some example implementations, when information or an execution instruction is received by API unit 565, it may be communicated to one or more other units (e.g., logic unit 560, input unit 570, output unit 575). In some instances, logic unit 560 may be configured to control the information flow among the units and direct the services provided by API unit 565, input unit 570, output unit 575, in some example implementations described above. For example, the flow of one or more processes or implementations may be controlled by logic unit 560 alone or in conjunction with API unit 565. The input unit 570 may be configured to obtain input for the calculations described in the example implementations, and the output unit 575 may be configured to provide output based on the calculations described in example implementations.

[0068] In example implementations described herein, processor(s) 510 can be configured to execute a method or computer instructions to train a function through use of a machine learning algorithm by executing the flows as described in FIGS. 4(a) and 4(b).

[0069] Finally, some portions of the detailed description are presented in terms of algorithms and symbolic representations of operations within a computer. These algorithmic descriptions and symbolic representations are the means used by those skilled in the data processing arts to most effectively convey the essence of their innovations to others skilled in the art. An algorithm is a series of defined steps leading to a desired end state or result. In example implementations, the steps carried out require physical manipulations of tangible quantities for achieving a tangible result.

[0070] Unless specifically stated otherwise, as apparent from the discussion, it is appreciated that throughout the description, discussions utilizing terms such as “processing,” “computing,” “calculating,” “determining,” “displaying,” or the like, can include the actions and processes of a computer system or other information processing device that manipulates and transforms data represented as physical (electronic) quantities within the computer system’s registers and memories into other data similarly represented as physical quantities within the computer system’s memories or registers or other information storage, transmission or display devices.

[0071] Example implementations may also relate to an apparatus for performing the operations herein. This apparatus may be specially constructed for the required purposes, or it may include one or more general-purpose computers selectively activated or reconfigured by one or more computer programs. Such computer programs may be stored in a computer readable medium, such as a computer-readable storage medium or a computer-readable signal medium. A computer-readable storage medium may involve tangible mediums such as, but not limited to optical disks, magnetic disks, read-only memories, random access memories, solid state devices and drives, or any other types of tangible or non-transitory media suitable for storing electronic information. A computer readable signal medium may include mediums such as carrier waves. The algorithms and displays presented herein are not inherently related to any particular computer or other apparatus. Computer programs can involve pure software implementations that involve instructions that perform the operations of the desired implementation.

[0072] Various general-purpose systems may be used with programs and modules in accordance with the examples herein, or it may prove convenient to construct a more specialized apparatus to perform desired method steps. In addition, the example implementations are not described with reference to any particular programming language.

It will be appreciated that a variety of programming languages may be used to implement the teachings of the example implementations as described herein. The instructions of the programming language(s) may be executed by one or more processing devices, e.g., central processing units (CPUs), processors, or controllers.

[0073] As is known in the art, the operations described above can be performed by hardware, software, or some combination of software and hardware. Various aspects of the example implementations may be implemented using circuits and logic devices (hardware), while other aspects may be implemented using instructions stored on a machine-readable medium (software), which if executed by a processor, would cause the processor to perform a method to carry out implementations of the present application. Further, some example implementations of the present application may be performed solely in hardware, whereas other example implementations may be performed solely in software. Moreover, the various functions described can be performed in a single unit, or can be spread across a number of components in any number of ways. When performed by software, the methods may be executed by a processor, such as a general purpose computer, based on instructions stored on a computer-readable medium. If desired, the instructions can be stored on the medium in a compressed and/or encrypted format.

[0074] Moreover, other implementations of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the teachings of the present application. Various aspects and/or components of the described example implementations may be used singly or in any combination. It is intended that the specification and example implementations be considered as examples only, with the true scope and spirit of the present application being indicated by the following claims.

Claims

CONCLUSIONS

1. A method for a user device configured to receive a continuous stressor measurement for managing stress, comprising: receiving continuous measurements of norepinephrine, epinephrine, and cortisol from a wearable device configured to measure norepinephrine, epinephrine, and cortisol from a wearer of the wearable device; and for predicted future stressor levels of the wearer, based on the continuous measurements of norepinephrine, epinephrine, and cortisol, predicted to exceed a threshold, generating a message through an application of the user device indicative of the predicted future stressor levels of the wearer that are predicted to exceed a threshold.

2. A method for a user device configured to receive a continuous stressor measurement for managing stress, comprising: receiving continuous measurements of norepinephrine, epinephrine, and cortisol from a wearable device configured to measure norepinephrine, epinephrine, and cortisol from a wearer of the wearable device; and for an increase in the continuous measurements of norepinephrine and epinephrine that exceeds a threshold, generating a message through an application of a user device indicative of the occurrence of an anxiety attack.

The method of claim 1 or 2, further comprising processing the continuous stressor measurements, subsequent to receiving the continuous measurements, to predict future stressor levels of the wearer.

The method of claim 3, wherein processing the continuous measurements of norepinephrine, epinephrine, and cortisol to predict future stressor levels of the wearer is performed by a machine learning algorithm, the function configured to record the continuous measurements of norepinephrine, epinephrine, and cortisol and outputting predicted stressor levels from the continuous measurements of norepinephrine, epinephrine, and cortisol.

The method of claim 4, further comprising transmitting the continuous measurements of the norepinephrine, epinephrine, and cortisol to a cloud server configured to update parameters of the machine learning algorithm that outputs the predicted stressor levels based on the subsequent continuous measurements of the norepinephrine, epinephrine, and cortisol; wherein the cloud server is configured to update the machine learning algorithm of a user device when the parameters are updated.

6. The method of any preceding claim, further comprising displaying, on the user device, the continuous stress substance measurements in real time.

7. The method of claim 6, comprising, for the continuous stressor measurements that exceed the threshold, displaying, through the application of the user device, a recommendation to reduce the stressor.

The method of claim 7, wherein the recommendation to reduce the stressor comprises a medication recommendation.

9. The method of any preceding claim, wherein the message includes an indication of an expected time span of a predicted peak in the stressor measurements based on the forecasted future stressor levels.

10. The method of any preceding claim, further comprising adjusting the threshold when a user device detects that a training mode is enabled.

11. A computer program storing instructions that, when executed by one or more processors, perform the method of any one of claims 1 to 10.

12. A user device comprising a processor configured to perform the method of any one of claims 1 to 10.

13. The user device of claim 12, wherein the user device is a mobile device.

14. A system comprising:

a wearable device configured to record norepinephrine, epinephrine, and cortisol from a wearer of the wearable device; and a user device configured to record continuous stress hormone measurements for managing stress, comprising a processor configured to perform the method of any of claims 1 to 10.