Sweating sensor data analysis

Abstract

A system and method for physiological analysis and feedback includes: multiple sensors configured to be worn on a user's skin and measure sweat data in real time, indicating levels of multiple corresponding sweat components; and one or more processors configured to receive the sweat data in real time. The processors apply the sweat data to a biomarker correlation model trained to correlate inputs including multiple sweat components, along with user-specific data including age, weight, and sex, with outputs including multiple physiological parameters. Two of the multiple physiological parameters may be oxygen consumption (VO2) and carbon dioxide elimination (VCO2). Additionally, the risk of coronary artery obstruction can be calculated by applying the calculated VO2 levels to a cardiac risk-related model trained to correlate VO2 levels with a risk level of coronary artery obstruction.

Description

Technical Field

[0001] This invention generally relates to the field of external measurement of bodily fluids or tissues and associated medical conditions. Background Technology

[0002] The adoption of wearable biosensor devices continues to expand as these devices begin to play a major role in the medical and fitness tracking industries. These fitness trackers come in a variety of shapes and forms. They can measure heart rate, steps taken, and sleep parameters. They can also connect the data to applications for goal setting, diet tracking, and other health-related tasks.

[0003] Many athletes use wearable technology to optimize their performance and collect data about their training. Additionally, dieters use such devices to track their energy expenditure (e.g., calories burned) and calorie intake. However, while wearable technology has been around for nearly a decade and has made significant strides in the last five years, today's fitness trackers offer only basic, fundamental biometric data.

[0004] Such devices are typically linked to smartphones or designed to be integrated into internal applications, such as smartwatch apps, that provide users with health and fitness-related feedback. Health and fitness tracking devices can monitor basic physiological parameters such as heart rate, steps, and sleep stages.

[0005] U.S. Patent Publication 2018 / 0263539, granted to Javey et al., describes sodium [Na+] in sweat as "potentially usable as an important biomarker for monitoring dehydration." According to Javey, wearable devices "can be configured to determine the likelihood or presence of dehydration, hyponatremia, hypokalemia, muscle cramps, ischemia, and / or pressure sores in the wearer from sensor measurements and can provide appropriate alerts and reports."

[0006] U.S. Patent 11,030,708, entitled “Method of and Device for Emplicationing Contagious Idisness Analysis and Tracking”, granted to Akutagawa and Myslinski, describes a wearable device for sensing “biomarkers (e.g., cytokines, such as interleukin-6)” to obtain indications of “stress, disease, malnutrition, injury, infection, cancer, and other conditions.”

[0007] High serum potassium levels have been implicated as a cause of numerous disease risks and physiological disturbances, and potassium levels are known to change during unstable cardiovascular conditions. Another physiological parameter with significant health implications is oxygen consumption (VO2), also known as oxygen uptake, particularly peak VO2 during physical activity such as training exercises. As described in the article, "Cardiopulmonary Exercise Testing in Heart Failure" by Malhotra et al. (JACC: Heart Failure, Vol. 4, No. 8, 2016), VO2 measured during cardiopulmonary exercise testing (CPET) indicates functional capacity. Parameters such as carbon dioxide output (VCO2) and ventilation (VE), along with VO2, can also indicate adverse adaptations during exercise. Summary of the Invention

[0008] Embodiments of the present invention provide systems and methods for generating metrics of user health. Providing users with real-time feedback on physiological parameters during exercise can improve their health and reduce health risks. Attached Figure Description

[0009] To better understand the various embodiments of the invention and to illustrate how they can be implemented, reference is made to the accompanying drawings by way of example. Structural details of the invention are shown to provide a basic understanding of the invention, and the description, taken in conjunction with the drawings, makes it clear to those skilled in the art how several forms of the invention can be embodied in practice. In the drawings:

[0010] Figure 1 This is a schematic diagram of a system for generating and reporting user health measures according to an embodiment of the present invention;

[0011] Figure 2 This is a block diagram of components of a system for implementing a process for generating and reporting user health measurements according to an embodiment of the present invention;

[0012] Figure 3 This is a flowchart of a process for generating and reporting user health measures according to an embodiment of the present invention;

[0013] Figure 4 This is a schematic diagram of a neural network model that correlates sensor data with physiological parameters according to an embodiment of the present invention;

[0014] Figure 5 This is a graph showing the correlation between sensor data of potassium electrolytes in sweat and oxygen consumption (VO2) over time, according to an embodiment of the present invention; and,

[0015] Figure 6A and Figure 6BIt is a graph showing oxygen consumption (VO2) during exercise, within the time period of multiple breaths of the user, showing the measured VO2 and the VO2 predicted by the biomarker correlation model. Detailed Implementation

[0016] Embodiments of the present invention provide systems and methods for generating and reporting measures of user health. Measurements of user health can also be used to generate health recommendations.

[0017] Figure 1 This is a schematic diagram of a system 100 for generating and reporting measurements of a user's health according to an embodiment of the present invention. System 100 includes a wearable sensor device 102, which may include a skin sensor for measuring sweat components, and additional sensors that may be both sweat and non-sweat sensors. Sensor device 102 may be configured as a plurality of wearable devices, which may be worn as an armband, headband, chest strap, ring, or earphone, i.e., worn at one or more locations on the user's body where the skin is exposed to sweat.

[0018] The sensor device 102 includes at least one sensor for measuring the electrolyte components of perspiration, said electrolyte components being potassium (i.e., K+) or sodium (i.e., Na+) or both. That is, the sensor of device 102 may include electrolyte sensors for both potassium and sodium, and may also include one or more additional electrolyte sensors, such as sensors for magnesium, chloride, ammonia, and calcium.

[0019] The sensors in device 102 may also include sensors for detecting levels of metabolites such as glucose, lactate, ethanol, and uric acid. Alternatively, device 102 may include sensors for detecting additional sweat components such as zinc, caffeine, levodopa, zinc, copper, cortisol, neuropeptides, interleukin-6 (IL-6), tyrosine, cytokines, hormones, or hormone precursors. Device 102 may also include at least one non-perspiration sensor, such as a heart rate sensor, body temperature sensor, pH sensor, accelerometer, gyroscope, and blood glucose monitor.

[0020] As further described below, a processor, in conjunction with sensor device 102 or with mobile computing device 104 (which may be, for example, a smartphone or smartwatch), receives signals generated by the sensors of device 102 and processes the signals to determine the level of sweat components indicated by the signals and physiological parameters associated with the signals. In some embodiments, the processor is also configured to present indicators of physiological parameters to a user, typically on the screen of mobile computing device 104. Alternatively or additionally, the processor may send the physiological parameters to a remote server 106 for further processing, such as to record a history of user data to determine trend information that can be associated with further health parameters, including health parameters. In another embodiment, the server implements a biomarker-related model and a health-related model, as further described below, wherein the biomarker-related model is trained to correlate sensor data (“input” data) with physiological parameters, and the health-related model is trained to correlate physiological parameters with health guidelines.

[0021] Figure 2 This is a block diagram of system 100, showing the components of sensor device 102 and mobile computing device 104. Sensor device 102 includes a sweat sensor 202 for measuring the composition of a user's sweat, such as potassium and sodium. Additional sweat sensors 202 may include electrolyte sensors, such as sensors for magnesium, chloride, ammonia, and calcium. Electrolyte sensors can be configured for specific electrolytes, including any one or more of electrochemical ion-selective membrane sensors, conductivity sensors, geosynthetic response (GSR) sensors, and potentiometric ion sensors.

[0022] The sensor in device 102 may also include a sensor for detecting levels of metabolites such as glucose, lactate, ethanol, and uric acid. Alternatively, device 102 may include a sensor for detecting other sweat components, such as zinc, caffeine, levodopa, zinc, copper, cortisol, neuropeptides, interleukin-6 (IL-6), tyrosine, or cytokines.

[0023] The device 102 may also include at least one non-perspiration sensor 204, such as a body temperature sensor, pH sensor, accelerometer, gyroscope and blood glucose monitor.

[0024] The signal from the sensor, typically generated as an analog voltage, can be acquired at the sensor processor 206, which can use transmission protocols known in the art, such as Bluetooth or radio frequency identification (RFID) transmission protocols, to transmit the signal to the mobile computing device 104.

[0025] In some embodiments, the sensor processor 206 may also execute applications stored in the processor memory, such as biomarker correlation model 220a and health correlation model 230a. Alternatively, these applications may be executed by the mobile device processor 210, and in alternative embodiments, these applications are referred to as biomarker correlation model 220b and health correlation model 230b. (Hereinafter, the biomarker correlation model of the alternative embodiments is referred to as biomarker correlation model 220a / b, and the alternative to the health correlation model is referred to as health correlation model 230a / b.)

[0026] Multiple data instances can be used to train the biomarker correlation model 220a / b to correlate input data with an “output” that typically includes multiple physiological parameters. The input data includes signals from sweat sensors, indicating the levels of corresponding sweat components. The input data may also include signals from non-sweat sensors, indicating their respective biomarker levels. The input data may also include user-specific data 222a / b, such as user age, weight, sex, and height. The system can also be configured to continuously update the biomarker correlation model as new user-specific data becomes available. Training of the biomarker correlation model can be based on known machine learning (i.e., artificial intelligence) methods. The model can also be trained to provide real-time anomaly detection to identify and notify the user of abnormal physiological parameters.

[0027] Input data are typically correlated with at least two physiological parameters that are particularly relevant during exercise training using a biomarker correlation model. These two parameters are measures of oxygen consumption (VO2) and carbon dioxide elimination (VCO2). Other physiological parameters that can be correlated using a biomarker correlation model may include: calories burned, carbohydrates, fat and protein burned, potassium levels, sodium loss, lactate accumulation, glucose levels, insulin levels, bone health, stress levels, likelihood of infection (e.g., COVID-19), likelihood of kidney stones, likelihood of type 2 diabetes, likelihood of congestive heart failure, risk of heart attack, risk of hypertension, risk of stroke, likelihood of adrenal insufficiency, heart rate variability (HRV), and risk of liver disease.

[0028] The sensor processor can also be configured to calculate the respiratory exchange ratio (RER) level from the VCO2 / VO2 ratio. In a further embodiment, a subset of the biomarker correlation model is a cardiac risk correlation model trained to correlate RER and VO2 levels with the risk level of coronary artery obstruction. The processor can apply VCO2 and VO2 values ​​to calculate the RER, which, together with the VO2 value (i.e., the level), is applied to the cardiac risk correlation model to estimate the risk of coronary artery obstruction.

[0029] Health-related models 230a / b, also referred to herein as health models, are typically trained to correlate physiological parameters with health and wellness guidelines. Relevant health and wellness guidelines may include, for example, warning alerts. Alerts may indicate that certain physiological parameters predicted by the biomarker correlation model suggest the user is at risk. Alerts may also make recommendations regarding actions the user should take immediately, which may include measures such as reducing activity levels, resting, consuming carbohydrates, and / or drinking water. Health and wellness guidelines may also include exercise recommendations for the user to change the type and / or form of exercise. Health and wellness guidelines may also include nutritional recommendations, including, for example, food to be consumed during the current training exercise; food to be consumed before and / or after a specific exercise; and / or recommended calorie intake.

[0030] After relevant health and wellness guidelines are identified, they can be transmitted to the user interface as further indicators of the user's physiological parameters. Similar to biomarker models, the inputs to health models can also include cumulative data, such as trend data, which can be stored on a mobile computing device or a server (i.e., a remote computing device, such as a cloud computing device). In some embodiments, the health model is implemented on a server that receives the estimated physiological parameters as input from the mobile computing device.

[0031] As described above, users can use the sensor device during exercise, where sensor measurements are performed in real time, allowing users to receive real-time feedback. At mobile computing device 104, transmissions from the sensor device, typically wireless, can be received by mobile device processor 210. When sensor processor 206 is not configured to execute the aforementioned applications, the sensor processor can simply transmit sensor data to the mobile device processor, where the application (i.e., the model) can be executed.

[0032] Typically, mobile device processors transmit one or more indicators of values ​​for multiple physiological parameters to the user interface, such as the screen 224 of a computing device. The presentation of physiological parameters on the screen, also referred to herein as "user feedback," is performed in real time, i.e., simultaneously with receiving sensor data. In the following text, "real-time feedback" is understood to mean feedback at intervals of up to 15 minutes.

[0033] Physiological parameters presented as user feedback may also include the calculated level of RER. These physiological parameters may also be stored in a memory storage device, such as a mobile computing device or a remote server, for subsequent analysis and reporting to the user. User-specific data 222a / b is also typically stored in such a memory storage device and can be input by the user from the computing device screen 224 or accessed by the mobile computing device from a remote source such as a remote server 106. The mobile computing device 104 typically also includes a data storage module for securely storing and managing user-specific data and physiological measurements. Furthermore, data encryption and secure communication protocols are typically employed to protect user privacy and data integrity.

[0034] Figure 3 This is a flowchart of key steps in a process 300 for generating and reporting user health measurements according to an embodiment of the present invention. In a first step 312, a biomarker correlation model is trained with training data to correlate “input” data with physiological parameters. The input data includes sweat sensor data, user-specific data, and optionally non-sweat sensor data.

[0035] In operation, typically while the user is exercising, the mobile computing device acquires data from the perspiration sensor at step 314, and optionally from the non-perspiration sensor. Next, at step 316, the acquired data, along with stored user-specific data, is applied to a biomarker correlation model to determine (i.e., predict / estimate) the values ​​of physiological parameters. As mentioned above, physiological parameters may include many biomarkers, but typically include at least the levels of VCO2 and VO2.

[0036] At step 318, the processor may optionally associate physiological parameters with health guidelines, as described above.

[0037] At step 320, the processor then transmits the indicators of the physiological parameters to the user interface to provide real-time user feedback. Figure 4 This is a schematic diagram of a biomarker correlation model 400 configured as a neural network. According to embodiments of the invention, this model correlates sensor data with physiological parameters. Embodiments of the invention include multiple correlation models, which, as described above, can be configured using methods known in the art, such as neural networks or random forest algorithms. Biomarker correlation models are typically trained using large datasets containing diverse population demographics; the term "large" refers to datasets obtained from at least 10, more commonly hundreds, or more users. The "diversity" of the demographics includes data from users of at least two different categories of sex and age and / or ethnicity.

[0038] In the exemplary biomarker correlation model 400, the two incremental stages of the neural network are denoted as T.n and T n+1 As shown. Both stages have the same layers, as shown below.

[0039] The model accepts input 402, which typically includes: input from one or more sodium sensors, i.e., one or more input "channels" (typically two to reduce noise); one or more potassium channels (similarly, typically two); additional sensor inputs, as described above, in some embodiments; and user-specific inputs such as age, weight, and sex. Additional user-specific inputs may include factors such as race, height, and other personal data known to be associated with the target physiological parameter. The output generated from output layer 404 includes physiological parameters, such as VO2 and VCO2, that the biomarker correlation model has been trained to associate with the inputs. Additional outputs may include additional physiological parameters, as described above. (Health and wellness guidelines are typically output by a separately trained model.)

[0040] As indicated by model 400, the first layer of the model is designed as a "Long Short-Term Memory" (LSTM) network 406, where the "memory" input is derived from the LSTM layer of the previous time stage at each incremental time stage.

[0041] The output of the LSTM layer is fed into the feedforward layer 408, which generates the output. Additional nodes, such as a "softplus activation" layer 410, can exist between the LSTM and the feedforward layer. The softplus layer applies the activation function Y=log(l+e) x This ensures the output is always positive. (Note the function Y=log(l+e)) x () is a smooth, continuous version of the reluLayer neural network. ) The exemplary model is tested on real-time sensor data, where the predicted VO2 values ​​generated by the real-time sensor data closely align with the values ​​measured by the breathing device, indicating the practicality of the exemplary model.

[0042] Figure 5 This is a graph showing the correlation between sensor data of potassium electrolyte (referred to herein as potassium) in sweat and oxygen consumption (VO2) over time, according to an embodiment of the invention. As indicated, VO2 increases as the measured potassium decreases, indicating an inverse correlation incorporated into the correlation model.

[0043] Figure 6A and 6B This is a graph showing oxygen consumption (VO2) during the time it takes for a user to breathe multiple times during exercise, showing the results through... Figure 4The exemplary biomarker correlation model shown in the figure measures and predicts VO2, as described above. As shown, the predicted VO2 is closely aligned with the actual value, indicating the usefulness of the exemplary model.

[0044] It should be understood that the processing elements shown or described herein are preferably implemented by one or more computers in computer hardware and / or in computer software embodied in a non-transitory, computer-readable medium according to conventional techniques, such as employing computer processors, memory, I / O devices and network interfaces, coupled via computer buses or alternative connections.

[0045] Unless otherwise described, the terms "processor" and "device" are intended to include any processing device, such as a processing device that includes, for example, a CPU (Central Processing Unit) and / or other processing circuitry (e.g., a GPU), and may refer to more than one processing device. Various elements associated with a processing device may be shared by other processing devices.

[0046] As used herein, the term "memory" is intended to include memory associated with a processor or CPU, such as, for example, RAM, ROM, fixed storage devices (e.g., hard disk drives), removable storage devices (e.g., floppy disks, magnetic tapes), flash memory, etc. Such memory can be considered as computer-readable storage media.

[0047] In addition, the phrase “input / output device” or “I / O device” can include one or more input devices (e.g., keyboard, mouse, scanner, HUD, etc.) for inputting data to the processing unit, and / or one or more output devices (e.g., speaker, display, printer, HUD, AR, VR, etc.) for presenting results associated with the processing unit.

[0048] Embodiments of the present invention may include a system, a method, and / or a computer program product. The computer program product may include a computer-readable storage medium (or media) having computer-readable program instructions thereon for causing a processor to perform aspects of the present invention.

[0049] Computer-readable storage media can be tangible devices that can hold and store instructions for use by an instruction execution device. Computer-readable storage media can be, for example, but not limited to, electronic storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of computer-readable storage media includes the following: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable optical disc read-only memory (CD-ROM), digital versatile disc (DVD), Blu-ray, magnetic tape, holographic memory, memory stick, floppy disk, mechanical encoding devices, such as punch cards or raised structures in recesses on which instructions are recorded, and any suitable combination of the foregoing. As used herein, computer-readable storage media should not be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0050] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to a suitable computing / processing device, or downloaded via a network to an external computer or external storage device, such as the Internet, a local area network, a wide area network, and / or a wireless network. A network adapter card or network interface in each computing / processing device can receive computer-readable program instructions from the network and forward them to a computer-readable storage medium within the suitable computing / processing device.

[0051] Computer-readable program instructions for performing the operations of this invention may be assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" programming language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer, partially on a remote computer, or entirely on a remote computer or server. In the latter case, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet provided by an Internet service provider). In some embodiments, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs) may execute the computer-readable program instructions to personalize the electronic circuitry in order to perform aspects of this invention by utilizing state information from the computer-readable program instructions.

[0052] In the context of describing aspects of the invention herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention, it will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0053] These computer-readable program instructions may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / steps specified in the flowcharts and / or block diagrams. These computer-readable program instructions may also be stored in a computer-readable storage medium that can instruct a computer, programmable data processing apparatus, and / or other apparatus to function in a particular manner, such that the computer-readable storage medium in which the instructions are stored includes an article of manufacture that includes implementation of the flowcharts and / or block diagrams. Figure 1 Instructions for the functions / steps specified in one or more boxes.

[0054] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus or other apparatus to cause a series of operational steps to be performed on the computer, other programmable apparatus or other apparatus to produce a computer-implemented process, such that the instructions, which execute on the computer, other programmable apparatus or other apparatus, implement the functions / steps specified in the flowchart and / or block diagram boxes.

[0055] Any flowcharts and block diagrams included herein illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of instructions, which may include one or more executable instructions for implementing one or more specified logical functions. In some alternative implementations, the functions marked in the blocks may not occur in the order shown herein. For example, two blocks shown consecutively may actually be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified function or action or executes a combination of dedicated hardware and computer instructions.

[0056] Various embodiments of the invention have been described for illustrative purposes, but are not intended to be exhaustive or limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein has been chosen to best explain the principles of the embodiments, practical application or improvement of technology relative to those found in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

[0057] Example

[0058] Examples of the present invention may include the following configurations.

[0059] Example 1 is a system for physiological analysis and feedback, comprising multiple sensors configured to be worn on a user's skin and measuring perspiration data indicating levels of multiple corresponding perspiration components. One of the perspiration components may be potassium. In addition to the multiple sensors, the system includes one or more processors having a memory containing instructions that, when executed, implement processing steps comprising: a) receiving the perspiration data; b) applying a biomarker correlation model to the perspiration data, wherein the biomarker correlation model is trained to correlate an input including the multiple perspiration components with an output including multiple physiological parameters, two of which are oxygen consumption (VO2) and carbon dioxide elimination (VCO2); c) determining values ​​of the multiple physiological parameters, including VO2 and VCO2 values, using the biomarker correlation model; d) calculating the level of the respiratory exchange ratio (RER) based on the ratio VCO2 / VO2; and e) transmitting one or more indicators of the values ​​of the multiple physiological parameters to a user interface in real time, wherein the indicators include the calculated RER level.

[0060] Example 2 is a system that includes the features of Example 1, and the one or more processors are further configured to perform the following steps: calculating the risk of coronary artery occlusion by applying the calculated VO2 level to a cardiac risk correlation model, the cardiac risk correlation model being trained to associate VO2 level with the risk level of coronary artery occlusion.

[0061] Example 3 is a system that includes the features of Example 1, or has or does not have any of the features of the additional examples listed above, and also includes determining that the risk exceeds a preset threshold and sending an alert to the user to consult a healthcare professional.

[0062] Example 4 is a system that includes the features of Example 1, with or without any of the features of the additional examples listed above, and whose perspiration data include sodium in addition to potassium.

[0063] Example 5 is a system that includes the features of Example 1, has or does not have any of the features of the additional examples listed above, and is configured to transmit metrics to the user interface in real time.

[0064] Example 6 is a system that includes the features of Example 1, or has or does not have any of the features of the additional examples listed above, and wherein a biomarker correlation model is trained to correlate multiple perspiration components with user-specific data with an output that includes multiple physiological parameters.

[0065] Example 7 is a system that includes the features of Example 6, with or without any of the features of the additional examples listed above, and user-specific data including the user's age, weight, and gender.

[0066] Example 8 is a system that includes the features of Example 1, has or does not have any of the features of Example 2, and the plurality of sensors include two sodium sensors and two potassium sensors, and the biomarker correlation model is trained based on inputs including data from the sodium sensors and data from the potassium sensors.

[0067] Example 9 is a system that includes the features of Example 1, with or without any of the features of the additional examples listed above, and the plurality of physiological parameters include the user’s blood potassium level.

[0068] Example 10 is a system that includes the features of any of the examples above, and the multiple perspiration components include, in addition to potassium and sodium, at least one electrolyte selected from the electrolytes magnesium, chloride, ammonia, and calcium.

[0069] Example 11 is a system that includes the features of any of the examples above, and the multiple perspiration components include at least one metabolite from the metabolites glucose, lactate, ethanol and uric acid.

[0070] Example 12 is a system that includes the features of any of the above examples, and the multiple perspiration components include at least one of zinc, caffeine, levodopa, zinc, copper, cortisol, neuropeptides, interleukin-6 (IL-6), tyrosine, or cytokines.

[0071] Example 13 is a system that includes features of any of the examples above, and further includes at least one non-sweating sensor that generates non-sweating data, wherein the one or more processors are further configured to apply the sweating and non-sweating data together with the user-specific data to the biomarker correlation model to determine the plurality of physiological parameters, wherein the biomarker correlation model is trained to correlate the sweating and the user-specific data together with the non-sweating data with the plurality of physiological parameters.

[0072] Example 14 is a system that includes the features of Example 13, and the at least one non-perspiration sensor is at least one of a body temperature sensor, a pH sensor, an accelerometer, a gyroscope, and a blood glucose monitor.

[0073] Example 15 is a system that includes features from any of the examples above. The biomarker correlation model is an artificial intelligence model, such as a neural network or a random forest classifier.

[0074] Example 16 is a system in which a biomarker correlation model is trained using a large dataset containing population demographics of varying ranges.

[0075] Example 17 is a system that includes features of any of the examples above and is configured to continuously update the biomarker correlation model as new user-specific input data is received.

[0076] Example 18 is a system that includes features of any of the examples above, receiving perspiration data at intervals of up to once every 15 minutes.

[0077] Example 19 is a system that includes features of any of the examples above, and the user interface is the user interface of either a smartwatch or a smartphone.

[0078] Example 20 is a system that includes features of any of the examples above, and also includes a wearable device that includes the one or more processors and at least one of the plurality of sensors.

[0079] Example 21 is a system that includes features of any of the examples above, and multiple sensors are integrated into a wearable device configured as an armband, headband, chest strap, ring, earphone, or temporary tattoo.

[0080] Example 22 is a system that includes features of any of the examples above and is further configured to apply values ​​of physiological parameters to a health association model, associate physiological parameters with a set of health and wellness guidelines to determine associated health and wellness guidelines, and provide personalized recommendations to the user based on the associated health and wellness guidelines to optimize user performance and well-being (where the associated health and wellness guidelines are one of multiple indicators of the values ​​of multiple physiological parameters transmitted to the user interface).

[0081] Example 23 is a system that includes the features of Example 22, and the associated health and wellness guidelines include warning alerts for the user to perform at least one of the following: reduce activity levels, rest, consume carbohydrates, and drink water.

[0082] Example 24 is a system that includes the features of Example 22, and the associated health and wellness guidelines include exercise instructions for users to change the type and / or form of exercise.

[0083] Example 25 is a system that includes the features of Example 22, and the associated health and wellness guidelines include at least one of the following nutritional indicators, which include one or more of the following: 1) food to be consumed during the current training exercise, 2) food to be consumed before and / or after a particular exercise, and 3) recommended calorie intake.

[0084] Example 26 is a system that includes the features of Example 1, and the one or more processors include a distributed processing system comprising a local processor and a remote processor, wherein the local processor receives the perspiration data and determines the one or more physiological parameters, and wherein the remote processor is configured to receive the determined values ​​of the physiological parameters from the local processor and apply the health-related model to determine the associated health and wellness guidelines.

[0085] Example 27 is a method for physiological analysis and feedback implemented by one or more processors having memory associated with instructions that, when executed, implement steps including: receiving the sweating data; applying a biomarker correlation model to the sweating data, wherein the biomarker correlation model is trained to correlate the plurality of sweating components with a plurality of physiological parameters, two of which are oxygen consumption (VO2) and carbon dioxide elimination (VCO2); determining values ​​of the plurality of physiological parameters, including the values ​​of VO2 and VCO2, by the correlation model; calculating the level of respiratory exchange ratio (RER) from the VCO2 / VO2 ratio; and transmitting one or more indicators of the determined physiological parameter values ​​to a user interface, wherein the indicators include the calculated RER level.

[0086] Further examples of the invention include features of the method of Example 28 and any additional features of Examples 2-27.

Claims

1. A system for physiological analysis and feedback, comprising: Multiple sensors, configured to be worn by a user on the user's skin, and to measure in real time perspiration data indicating the levels of multiple corresponding perspiration components, at least one of which is potassium; and One or more processors having memory, the memory including instructions that, when executed, perform the following steps: a) Receive the perspiration data; b) Applying a biomarker correlation model to the perspiration data, wherein the biomarker correlation model is trained to correlate input data including the plurality of perspiration components with outputs including a plurality of physiological parameters, two of which are oxygen consumption (VO2) and carbon dioxide elimination (VCO2). c) Determine the values ​​of the plurality of physiological parameters, including the values ​​of VO2 and VCO2, using the biomarker correlation model; d) Calculate the level of respiratory exchange ratio (RER) from the stated ratio VCO2 / VO2; as well as e) Transmit one or more indicators of the values ​​of the plurality of physiological parameters to the user interface, wherein the indicators include the calculated level of RER.

2. The system of claim 1, wherein the one or more processors are further configured to perform the step of: calculating the risk of coronary artery occlusion by applying the calculated VO2 level to a cardiac risk-related model, the cardiac risk-related model being trained to associate VO2 level with the risk level of coronary artery occlusion.

3. The system of claim 2 further includes determining that the risk is higher than a preset threshold and sending an alert to the user to consult a healthcare professional.

4. The system of claim 1, wherein the perspiration data includes sodium.

5. The system according to claim 1, wherein the metrics are transmitted to the user interface in real time.

6. The system of claim 1, wherein the biomarker correlation model is trained to correlate the plurality of perspiration components along with user-specific data with the output comprising a plurality of physiological parameters.

7. The system of claim 6, wherein the user-specific data includes the user's age, weight, and gender.

8. The system of claim 1, wherein the plurality of sensors comprises two sodium sensors and two potassium sensors, and wherein the biomarker correlation model is trained based on inputs including data from the two sodium sensors and data from the two potassium sensors.

9. The system of claim 1, wherein the plurality of physiological parameters includes the user's blood potassium level.

10. The system of claim 1, wherein the plurality of perspiration components include at least one electrolyte selected from magnesium, chloride, ammonia, and calcium.

11. The system of claim 1, wherein the plurality of perspiration components comprises at least one metabolite from the metabolites glucose, lactate, ethanol and uric acid.

12. The system according to claim 1, wherein the plurality of perspiration components comprises at least one of zinc, caffeine, levodopa, zinc, copper, cortisol, neuropeptides, interleukin-6 (IL-6), tyrosine, hormones, hormone precursors or cytokines.

13. The system of claim 1, further comprising at least one non-sweating sensor that generates non-sweating data, wherein the one or more processors are further configured to apply the sweating and non-sweating data together with the user-specific data to the biomarker correlation model to determine the plurality of physiological parameters, wherein the biomarker correlation model is trained to correlate the sweating and the user-specific data together with the non-sweating data with the plurality of physiological parameters.

14. The system of claim 13, wherein the at least one non-sweating sensor is at least one of a body temperature sensor, a pH sensor, an accelerometer, a gyroscope, a heart rate monitor that measures heart rate variability (HRV), and a blood glucose monitor.

15. The system according to claim 1, wherein the biomarker correlation model is an artificial intelligence model.

16. The system of claim 1, wherein the biomarker correlation model is trained using a large dataset containing population demographics of different ranges.

17. The system of claim 1, wherein the one or more processors are further configured to continuously update the biomarker correlation model upon receiving new user-specific input data.

18. The system of claim 1, wherein the perspiration data is received at intervals of up to once every 15 minutes.

19. The system of claim 1, wherein the user interface is a user interface of a smartwatch or a smartphone.

20. The system of claim 1, further comprising a wearable device, the wearable device including at least one of the one or more processors and the plurality of sensors.

21. The system of claim 1, wherein the plurality of sensors are integrated into a wearable device, the wearable device being configured as an armband, headband, chest band, ring, earphones, or temporary tattoo.

22. The system of claim 1, wherein the one or more processors are further configured to apply the value of the physiological parameter to a health-related model, associate the physiological parameter with a set of health and wellness guidelines to determine relevant health and wellness guidelines, and provide personalized recommendations to the user based on the relevant health and wellness guidelines to optimize user performance and health.

23. The system of claim 22, wherein the associated health and wellness guidelines include warning alerts for the user to perform at least one of the following: reduce activity levels, rest, consume carbohydrates, and drink water.

24. The system of claim 22, wherein the set of health and wellness guidelines includes exercise instructions for the user to change the type and / or form of exercise.

25. The system of claim 22, wherein the set of health and wellness guidelines includes at least one of the following nutritional indicators, which include one or more of the following: 1) food to be consumed during the current training exercise, 2) food to be consumed before and / or after a particular exercise, and 3) recommended calorie intake.

26. The system of claim 1, wherein the one or more processors are further configured to provide historical analysis of the user's physiological parameters over time at the user interface.

27. The system of claim 1, wherein the user interface is integrated with a social network or online platform to enable data sharing and participation with other users.

28. The system of claim 1, wherein the user interface includes audio or visual feedback to guide the user to achieve optimal physiological parameters.

29. The system of claim 1, wherein the plurality of sensors are detachable and can be repositioned on different areas of the user's body.

30. The system according to claim 1 further includes a data storage module for securely storing and managing user-specific data and physiological measurements.

31. The system of claim 1, wherein the one or more processors employ data encryption and secure communication protocols to protect user privacy and data integrity.

32. The system of claim 1, wherein the one or more processors perform real-time anomaly detection to identify and notify the user of abnormal physiological patterns.

33. The system of claim 1, wherein the one or more processors include a distributed processor, the distributed processor including a local processor and a remote processor, wherein the local processor receives the sweating data and determines the one or more physiological parameters, and wherein the remote processor is configured to receive the determined values ​​of the physiological parameters from the local processor and apply the health-related model to determine the relevant health and health guidelines.

34. A method for physiological analysis and feedback implemented by one or more processors, said one or more processors having memory associated with instructions that, when executed, implement steps including the following: a) Receive perspiration data; b) Applying a biomarker correlation model to the sweating data, wherein the biomarker correlation model is trained to correlate multiple sweat components acquired from the sweating data, the multiple sweat components including at least a measure of potassium and multiple physiological parameters, wherein two of the multiple physiological parameters are oxygen consumption (VO2) and carbon dioxide elimination (VCO2). c) Determine the values ​​of the plurality of physiological parameters using the relevant model, wherein the values ​​of the plurality of physiological parameters include the values ​​of VO2 and VCO2; d) Calculate the respiratory exchange ratio (RER) level based on the stated VCO2 / VO2 ratio; and e) Transmit one or more indicators of the determined physiological parameters to the user interface in real time, wherein the indicators include the calculated level of RER.

35. The method of claim 34, further comprising receiving non-sweating data from at least one non-sweating sensor, wherein the correlation model correlates the sweating and non-sweating data with the plurality of physiological parameters.

36. The method of claim 35, wherein receiving the non-sweating data from at least one non-sweating sensor includes receiving the non-sweating data from at least one of a body temperature sensor, a pH sensor, an accelerometer, a gyroscope, and a blood glucose monitor.

37. The method of claim 34, wherein the plurality of physiological parameters includes the user's blood potassium level.

38. The method of claim 34, wherein the plurality of physiological parameters includes the risk of coronary artery occlusion.

39. The method of claim 39 further includes determining that the risk is higher than a preset threshold and sending an alert to the user to consult a healthcare professional.

40. The method of claim 34, wherein the metrics are transmitted to the user interface in real time.

41. The method of claim 34, wherein the biomarker correlation model is trained to correlate the plurality of perspiration components, along with user-specific data, with the output comprising a plurality of physiological parameters.

42. The method of claim 34, wherein the user-specific data includes the user's age, weight, and gender.

43. The method of claim 34, wherein the plurality of perspiration components comprises at least one electrolyte from an electrolyte list, and wherein the electrolyte list comprises at least sodium, magnesium, chloride, ammonia, and calcium.

44. The method of claim 34, wherein the plurality of perspiration components includes at least one metabolite selected from the metabolites glucose, lactate, ethanol and uric acid.

45. The method of claim 34, wherein the plurality of perspiration components comprises at least one of zinc, caffeine, levodopa, zinc, copper, cortisol, neuropeptides, interleukin-6 (IL-6), tyrosine, or cytokines.

46. ​​The method of claim 34, wherein the step further comprises applying a health-related model to the determined value of the physiological parameter, associating the physiological parameter with a set of health and wellness guidelines to determine relevant health and wellness guidelines, and wherein the relevant health and wellness guidelines are one of the indicators of the value of the one or more determined physiological parameters transmitted to the user interface.

47. The method of claim 46, wherein the associated health and wellness guidelines include warning alerts for the user to perform at least one of the following: reduce activity levels, rest, consume carbohydrates, and drink water.

48. The method of claim 46, wherein the set of health and wellness guidelines includes exercise instructions for the user to change the type and / or form of exercise.

49. The method of claim 46, wherein the set of health and wellness guidelines includes at least one of the following nutritional indicators, which include one or more of the following: 1) food to be consumed during the current exercise, 2) food to be consumed before and / or after a particular exercise, and 3) recommended calorie intake.

50. The method of claim 34, wherein the processor is a distributed processor comprising a local processor and a remote processor, wherein the local processor receives the sweating data and determines the one or more physiological parameters, and wherein the remote processor receives the determined values ​​of the physiological parameters from the local processor and applies the health-related model to determine the associated health and health guidelines.

Images