SE2350362A1 - A method for monitoring the state of an individual - Google Patents

Abstract

The present disclosure relates to a method (100) for monitoring a state of an individual, the method comprising the steps of obtaining (101) initial accelerometer data, defining (102) activity states of said individual during said first time period based on said initial accelerometer data, activity states comprising rest, move, exercise and recover. Further, the method comprises obtaining (103) heart rate variability, hrv, data, and correlating (104) the defined activity states to said hrv data defining (105) reference hrv average metrics for each activity state. Further, the method comprises obtaining (106) additional accelerometer data and hrv data in real-time, defining (107) an activity state of said individual based on said additional acceleration data in accordance with previously defined activity states based on said initial accelerometer data. Moreover, the method comprises defining (108) hrv average metrics for said additional hrv data, comparing (109) said additional hrv average metrics relative said reference hrv average metrics and determining (110) the state of the individual.

Description

TECHNICAL FIELD The present disclosure relates to a method for monitoring the state of an individual, an electronic device and a computer readable storage medium. BACKGROUND The emergence of smart watches, smart phones and other accessories capable of obtaining and processing activity values of an individual has opened up opportunities for individuals having such accessories to monitor states of their health to a larger extent. lt is common for such devices to be able to monitor pulse, breathing, steps and other metrics of individuals continuously throughout one or several days.

This opens up the possibility for said individuals to be more aware of, and improve their current state or metrics. There are varieties of electronic devices that can gather metrics of an individual analyse them and derive conclusions regarding activity states of said individual. For example, an electronic device may measure the speed of an individual, his pulse and conclude that the individual is exercising. Thus, there exist method in the present art that can conclude the activity state of an individual. The methods may derive whether an individual is e.g., exercising, moving or resting.

However, even though the present art can conclude activity states of an individual. There may be more factors to take into account within said activity state. For example, the conclusion regarding the activity state of an individual does not conclude the condition of said individual during said activity state, i.e. ifthe individual is mentally stressed or relaxed. Hence, ifthere would be methods and devices configured to not only derive the activity state of the individual but also the individuals condition within that state, that would allow the individual to gain more knowledge regarding his current conditioning within a specific activity state in real-time.

Further, the conclusion regarding the activity state of an individual are in the prior art not certain enough as activity states are mistakenly determined based on wrong interpretation of 2 the received data from an individual. E.g., increased pulse of an individual is not necessarily an indication of exercise.

Thus, even though there are methods and devices in the present art that provide information regarding an individual's activity state, there is a need for improved methods and devices that allow individuals to monitor their health more efficiently and/or more exhaustively. SUMMARY lt is therefore an object of the present disclosure to alleviate at least some of the mentioned drawbacks to provide an improved method and device that monitors activity states of an individual more efficiently and exhaustively. Specifically, the methods and devices herein is able to monitor the activity states of an individual with a greater accuracy compared to conventional solutions.

This and other objects, which will become apparent in the following, are achieved by a method and device as defined in the appended claims.

The present disclosure relates to a computer-implemented method for monitoring/determining the state of an individual, the method comprising the steps of obtaining initial accelerometer data, the accelerometer data comprising accelerometer measurement values of said individual recorded during a first time period. Further, the method comprises the steps of defining activity states of said individual during said first time period based on said initial accelerometer data, activity states comprising rest, move, exercise and recover. Further, the method comprises the step of obtaining heart rate variability, hrv, data, the hrv data comprising hrv values of said individual recorded during said first time period. Further, the method comprises the step of correlating the defined activity states to said hrv data, correlating comprises associating said hrv values to corresponding activity StateS. ln other words, in this step the method may link hrv values to different activity states. Furthermore, the method comprises the steps of defining reference hrv average metrics for each activity state.

I\/|oreover, the method comprises the steps of obtaining additional accelerometer data and hrv data in real-time and defining an activity state of said individual based on said additional 3 acceleration data in accordance with previously (in accordance with said) defined activity states based on said initial accelerometer data. Thus, the method may, in the steps of defining activity steps based on said initial accelerometer data, form a framework/model that allows for the additional accelerometer data to be inputted into the model to derive activity states of the individual in real-time. Hence, allowing for a rapid determining of activity states.

Subsequently, the method comprises the step of defining hrv average metrics for said additional hrv data (in each activity state) and comparing said additional hrv average metrics relative said reference hrv average metrics for a corresponding activity state.

I\/|oreover, based on said comparison, the method comprises the step of determining the state/condition/mental state (which all may be used instead of the term state) of the individual as a first (mental) state, if said hrv average metrics is lower than said reference hrv average metrics or as a second (mental) state if said hrv average metrics is greater than said reference hrv average metrics.

Scientific studies have shown correlations between low hrv and increased risk for mortality. A high HRV has been linked to a range of positive health outcomes, including better cardiovascular health, improved immune function, and lower levels of inflammation. Additionally, high HRV has been associated with better cognitive function and a lower risk of depression and anxiety.

However, during specific activity states, e.g., exercise the hrv is also reduced. Hence, as the method herein is able to measure the hrv levels of an individual in real-time compared to reference hrv average metrics (which have been collected for a longer time-period) coupled to activity states, the method can draw conclusions regarding the condition of the individual taking activity states into account. |.e., ifthe additional hrv values are lower than the hrv average metrics in said activity state, the individual may need some kind of recovery. Also, if it's the other way around, the individual is at sufficient condition.

Based on the aforementioned, the method provides the advantage of allowing the individual to monitor and reduce their mental load. 4 The activity state could be defined differently depending on the intended use, but one such definition could be rest, move, excercise, and recover. With each activity state being defined as below: Rest may be related to laying down, sitting still, or very slow motion.

I\/love may be related to easy movement such as casually moving indoors.

Excercise may be related to training activities such as outdoor walking or running.

Recover may be related to a period of rest or move after/subsequent to a period of exercise.

The accelerometer measurements may be performed in three dimensions (x, y, z) and used for determining the activity state of an individual.

The activity states in each time instant during the time period may be, as specified herein determined based on the initial accelerometer data. ln detail, it may be determined by determining the amount of variation (A) in the movement. This may be performed by calculating the variation in the accelerometer readings for each orientation. This variation could e.g., be determined by calculating the Standard Deviation of the acceleration values during a pre-determined duration, for example five seconds. The method may provide combinations of orientations such as a resultant vector.

Further, in addition to or instead of determining the amount of variation, it may be determined by calculating the overall intensity ofthe movement (B). The overall intensity may be determined by aggregating all orientations in one single value e.g., by adding them or by calculating the resultant vector. The intensity could also be determined as multiple values by keeping all or some orientations separate. ln addition to or instead of determining (A) and/or (B), an accumulated average intensity during movement (C) may be determined to define the activity states. This could be performed by dividing the accumulated intensity by the duration of the current activity state.

To derive the average intensity of a period of activity, e.g., exercise, during a time frame. ln addition to this, to or instead of determining (A) and/or (B) and/or (C), the recovery time subsequent exercise (D) may be used to determine activity states, this may be performed by multiplying the accumulated average intensity and the duration ofthe activity with a predefined factor (intensity recovery factor, IRF). The IRF can be statically pre-defined for all users or individually selected based on e.g., age, fitness level, or gender. ln addition to, or instead of (A) - (D) the activity states may be determined by determining a first activity state based on the intensity (at start of the time period) and thereafter determining a state based on: the previous activity state, the current intensity, and the accumulated average intensity (or any combination ofthese). The intensity is based on the accelerometer values. The activity states may be modelled a state machine in which a state is selected as starting state when no previous information about state exists. Transitions between two states are defined to occur at a specific predefined thresholds in relation to the intensity. The threshold can include a hysteresis to avoid state transitions back and forward between states when values are varying closely around the threshold. For the transition between RECOVER and REST a recovery time may be used as the trigger. To further increase the stability ofthe transitions between activity states, the threshold can be used in relation to the average intensity during a predefined time window (transition window, TW), e.g., one minute or five minutes. Each transition can have its own specific TW. I\/|oreover, the size of the TW can be adjusted to alter the behaviour of the method with respect to the trade-off between fast response to shifting activity states and amount of flickering between states.

The first time period is at least 3 days. ln other words, three days or more. Such a time-frame allow for sufficient data to be gathered regarding the hrv values and activity states of an individual.

The hrv average metrics may be root mean square of successive differences (RMSSD). However, the hrv average metrics may also be standard deviation of NN intervals (SDNN). However, the hrv average metrics may be any time-domain or frequency-domain method for analyzing hrv data.

The method may further comprise monitoring, in real-time, deceleration of heart beats of said individual and determining, based on said monitoring, changes in the state of said individual. The deceleration of heart beats may be compared to the hrv prior to the determining changes in the state of the individual. 6 Thus, the method may advantageously determine the recovery of the individual from having mental load. ln some aspects herein, the method may provide, if said individual has a hrv metric is lower than said reference hrv metric a notification for a graphical user interface said notification indicating for said user that the user experiences a mental load. ln some aspects herein, the method may further comprise the step of, if said state is determined as stress: - providing a recovery plan for reducing stress; - monitoring, in real-time, deceleration of heart beats of said individual.

Deceleration of heart beats may refer to a decrease in the rate at which the heart beats. ln some aspects, the method may continue to measure HRV. The deceleration may be indicative of that the stress /mental load of an individual is being reduced. Thus, indicating that the recovery plan has worked. ln some aspects, the method only monitors the deceleration of heart beats without providing a recovery plan.

The recovery plan may comprise instructions for ln some aspects herein, the method further comprises the step of, if said state is determined aS StFeSSZ - providing a recovery plan for reducing stress; - receiving data input, from a user, indicative ofthat said recovery plan has been performed by a user; - monitoring, in real-time, deceleration of heart beats of said individual - providing, based on said monitoring, information for said user indicative of the impact of said recovery plan relative the hrv average metrics of said user. 7 Generally, all terms used in the description are to be interpreted according to their ordinary meaning in the technical field, unless explicitly defined otherwise herein. All references to ”a/an/the [element, device, component, means, step, etc.]" are to be interpreted openly as referring to at least one instance of said element, device, component, means, step, etc., unless explicitly stated otherwise.

BRIEF DESCRIPTION OF THE DRAWINGS These and other features and advantages of the present disclosure will now be further clarified and described in more detail, with reference to the appended drawings; Figure 1 illustrates a method in in the form of a flowchart in accordance with some aspects herein; Figure 2 illustrates a method in in the form of a flowchart in accordance with some aspects herein; Figure 3 schematically illustrates an electronic device and control circuitry communicating with said electronic device; Figure 4A illustrates a graph showing two plots, one defining activity states and the other defining intensity of acceleration; Figure 4B illustrates a graph showing two plots, one defining activity states and the other defining R-R values.

DETAILED DESCRIPTION ln the following detailed description, some embodiments of the present disclosure will be described. However, it is to be understood that features of the different embodiments are exchangeable between the embodiments and may be combined in different ways, unless anything else is specifically indicated. Even though in the following description, numerous 8 specific details are set forth to provide a more thorough understanding of the present disclosure, it will be apparent to one ski||ed in the art that the present disclosure may be practiced without these specific details. ln other instances, well known constructions or functions are not described in detail, so as not to obscure the present disclosure.

Figure 1 schematically in the form of a flowchart illustrates a method 100 for monitoring a state of an individual, the method comprising the steps of obtaining 101 initial accelerometer data, the accelerometer data comprising accelerometer measurement values of said individual recorded during a first time period. The accelerometer data may be obtained from a sensor device on an electronic device worn by the individual.

Further, the method comprises the step of defining 102 activity states of said individual during said first time period based on said initial accelerometer data, activity states comprising rest, move, exercise and recover. I\/|oreover, the method comprises obtaining 103 heart rate variability, hrv, data, the hrv data comprising hrv values of said individual recorded during said first time period and correlating 104 the defined activity states to said hrv data, correlating comprises associating said hrv values to corresponding activity states. Further, the method comprises defining 105 reference hrv average metrics for each activity state and obtaining 106 additional accelerometer data and hrv data in real-time. Further, the method 100 comprises defining 107 an activity state of said individual based on said additional acceleration data in accordance with previously defined activity states based on said initial accelerometer data and defining 108 hrv average metrics for said additional hrv data. Furthermore, the method comprises the step of comparing 109 said additional hrv average metrics relative said reference hrv average metrics for a corresponding activity state and determining 110 the state of the individual as a first state, if said hrv average metrics is lower than said reference hrv average metrics or as a second state if said hrv average metrics is greater than said reference hrv average metrics. ln step 102, the method may define a plurality of activity states during said time period. Further, the step of correlating 104 may comprise linking, for each separate activity state in said time period, hrv data. Thus, the average variability may be determined for each activity state during said time period. 9 The method 100 may further in some aspects comprise the steps of monitoring 110a, in real- time, deceleration of heart beats of said individual and determining 110b, based on said monitoring, changes in the state of said individual. Thus, based on the deceleration the method may determine if the state is changed. For example, ifthe heart beats has deceleration more/less than a pre-determined threshold such a determination may be performed.

The hrv may be derived by R-R intervals obtained from sensor devices ofthe electronic device.

Figure 2 illustrates another aspect of the method in the form of a flowchart. Figure 2 illustrates that the method 100 may further comprise the steps of method further comprises the step of, if said state is determined as stress/mental load, providing 111 a recovery plan for reducing stress and monitoring 113, in real-time, deceleration of heart beats of said individual.

Further, as illustrated in Figure 2, in other aspects, the method 100 may comprise steps of, if said state is determined as stress providing 111 a recovery plan for reducing stress, receiving data input 112 indicative of that said recovery plan has been performed by a user. The data input 112 may preferably be inputted by the user, or be retrieved as sensor data gathered from sensors of a device worn by the user, the device being arranged to sense ifthe user is performing said recovery plan. For example, the sensor may monitor breathing data and sound data of the user indicative of breathing. Further, the method 100 may monitor 113, in real-time, deceleration of heart beats of said individual and provide 114, based on said monitoring, information for said user indicative of the impact of said recovery plan, preferably impact of the recovery plan relative the hrv average metrics of said user.

The method may also comprise the step of providing 115 a graphical representation of the state of the individual to a display unit of an electronic device.

Figure 3 schematically illustrates control circuitry 10 in wireless communication with an electronic device 1. Thus, the control circuitry 10 may be configured to perform the method in accordance with any aspect herein. The electronic device 1 may be any form of electronic device such as a wearable device (e.g. a smartwatch). The electronic device 1 may be configured to gather data from the individual wearing said device, thereby allowing the control circuitry 10 to obtain said data.

Thus, the control circuitry 10 may obtain 101 initial accelerometer data, the accelerometer data comprising accelerometer measurement values of said individual recorded during a first time period. Thus, the accelerometer data may be gathered by sensors (not shown) from the electronic device 1 and transmitted to the control circuitry 10 over a communication network.

Further, the electronic device 1 may obtain heart rate variability, hrv, data, the hrv data comprising hrv values of said individual recorded during said first time period. Further, the control circuitry 10 may continuously, obtain additional accelerometer data and hrv data in real-time. The control circuitry 10 may obtain such data in regular time intervals or irregularly in said continuous manner.

The steps of defining activity states, correlating, defining hrv average metrics, determining the state ofthe individual may be performed by the control circuitry 10. ln some aspects, the control circuitry 10 is integrated in the electronic device 1. However, in other aspects, the control circuitry 10 may be remote. Thus, in some aspects the control circuitry 10 may communicate with the electronic device 1 over a wired connection.

As illustrated in Figure 3, the control circuitry 10 may comprise at least one memory device 5 which may comprise any form of volatile or non-volatile computer readable memory including, without limitation, persistent storage, solid-state memory, remotely mounted memory, magnetic media, optical media, random access memory (RAM), read-only memory (ROM), mass storage media (for example, a hard disk), removable storage media (for example, a flash drive, a Compact Disk (CD) or a Digital Video Disk (DVD)), and/or any other volatile or non-volatile, non-transitory device readable and/or computer-executable memory devices that store information, data, and/or instructions that may be used by each associated control circuitry 10. Each memory device 5 may store any suitable instructions, data or information, including a computer program, software, an application including one or more of logic, rules, code, tables, etc. and/or other instructions capable of being executed by the control circuitry 10 and, utilized. I\/|emory device 5 may be used to store any calculations made by control circuitry 10 and/or any data received via output and input interfaces of the control circuitry 4. ln some embodiments, each control circuitry 10 and each memory device 5 may be considered to be integrated 11 Each memory device 10 may also store data that can be retrieved, manipulated, created, or stored by the control circuitry 10. The data may include, for instance, local updates, algorithms accelerometer data, hrv data or any other suitable data for performing the method herein. The control circuitry 10 may include, for example, one or more central processing units (CPUs), graphics processing units (GPUs) dedicated to performing calculations, and/or other processing devices. The memory device 5 can include one or more computer-readable media and can store information accessible by the control circuitry 10, including instructions/programs that can be executed by the control circuitry 10.

The control circuitry 10 may further comprise machine learning components (not shown). Then the machine learning component may comprise a trained learning algorithm configured to provide automated feedback and tracking between automated coaching suggestions (e.g.,breathing or training exercises) and so to notify the user of physical and mental outcome. The algorithm may further cluster, classification, anomaly detection and prediction based on any obtained data.

Figures 4A and 4B illustrates plots which may be provided by the control circuitry when performing some steps of the method. Figure 4A illustrates acceleration values, where the Y- axis is intensity of acceleration and X-axis is time. As illustrated in Figure 4A, there are two plots in the graph. The plot A illustrates the acceleration intensity and the plot B illustrates the activity states assigned during the time period. The higher the B plot is along the X-axis may indicate a more active state, e.g. exercise. On the contrary, the plot B being at 0 may indicate rest. Thus, the method herein may in accordance with Figure 4A obtain initial accelerometer data, the accelerometer data comprising accelerometer measurement values of said individual recorded during a first time period and define activity states of said individual during said first time period based on said initial accelerometer data, activity states comprising rest, move, eXeFClSe afid FeCOVeF.

Figure 4B illustrates heart data relative activity states. The plot A being heart data (in this case R-R intervals) and the plot B being activity states. Thus, Figure 4B may correlate the defined activity states to said hrv data by associating hrv values to corresponding activity states. As an exemplary note, Figure 4B has fractioned the time period into 8 activity states. Thus, for each of said activity states average hrv metrics may be determined. 12 lt should be noted that Figures 4A and 4B are shown for exemplary purpose and are in no way limiting for the present disclosure. Further, as appreciated by the skilled person in the art, Figures 4A and B are not recorded during the same time period (as the activity states differ). ln some aspects ofthe method, the steps of 101-105 may be omitted, instead the method may store predefined activity states based on initial accelerometer data forming an activity model. Then the method may comprise the steps of obtaining additional accelerometer data and hrv data in real-time, defining an activity state of said individual based on said additional acceleration data based on said activity model. Further, the method may comprise defining hrv average metrics for said additional hrv data and comparing said additional hrv average metrics relative said reference hrv average metrics for a corresponding activity state. Moreover, the method may comprise determining the state ofthe individual as a first state, if said hrv average metrics is lower than said reference hrv average metrics or as a second state if said hrv average metrics is greater than said reference hrv average metrics.

Claims (10)

Claims

1. A method (100) for monitoring a state of an individual, the method comprising the steps of: obtaining (101) initial accelerometer data, the accelerometer data comprising accelerometer measurement values of said individual recorded during a first time period; defining (102) activity states of said individual during said first time period based on said initial accelerometer data, activity states comprising rest, move, exercise and recover; obtaining (103) heart rate variability, hrv, data, the hrv data comprising hrv values of said individual recorded during said first time period; correlating (104) the defined activity states to said hrv data, correlating comprises associating said hrv values to corresponding activity states; defining (105) reference hrv average metrics for each activity state; obtaining (106) additional accelerometer data and hrv data in real-time; defining (107) an activity state of said individual based on said additional acceleration data in accordance with previously defined activity states based on said initial accelerometer data; defining (108) hrv average metrics for said additional hrv data; comparing (109) said additional hrv average metrics relative said reference hrv average metrics for a corresponding activity state; determining (110) the state ofthe individual as a first state, if said hrv average metrics is lower than said reference hrv average metrics or as a second state if said hrv average metrics is greater than said reference hrv average metrics.

2. The method (100) according to any one ofthe preceding claims, wherein the first time period is at least 3 days.

3. The method (100) according to any one ofthe preceding claims, wherein hrv average metrics comprises at least one of root mean square of successive differences, RI\/ISSD, and standard deviation of NN intervals, SDNN or any other suitable hrv averagemetrics.

The method (100) according to any one ofthe preceding claims, wherein the method further comprises the step of: - monitoring (110a), in real-time, deceleration of heart beats of said individual - determining (110b), based on said monitoring, changes in the state of said individual.

The method (100) according to any one ofthe preceding claims, wherein said first state is stress and said second state is recovery.

The method (100) according to c|aim 4, wherein the method further comprises the step of, if said state is determined as stress: - providing (111) a recovery plan for reducing stress; - monitoring (113), in real-time, deceleration of heart beats of said individual.

The method (100) according to c|aim 4, wherein the method further comprises the step of, if said state is determined as stress: - providing (111) a recovery plan for reducing stress; - receiving data input (112) indicative ofthat said recovery plan has been performed by a user; - monitoring (113), in real-time, deceleration of heart beats of said individual - providing (114), based on said monitoring, information for said user indicative of the impact of said recovery plan relative the hrv average metrics of said user.

The method (100) according to any one of the preceding c|aim, further comprising the step of providing (115) a graphical representation of the state ofthe individual to a display unit of an electronic device.

An electronic device (1) comprising control circuitry (10) configured to perform the method (100) according to any one of the preceding claims.

10. A computer-readable storage medium storing one or more programs configured to be executed by one or more control circuitry (10), the one or more programs including instructions for performing the method (100) of any of claims 1-8.