Estimation of an individual's maximal oxygen uptake VO2max

Abstract

A wearable device (102) is provided for estimating maximal oxygen uptake VO2max of an individual during exercise. The wearable device (102) includes a processor (104) and a memory (106). The processor (104) is configured to receive heart rate measurement data and exercise load data of an individual (112) (e.g., a user) of the wearable device (102). The memory (106) stores instructions that cause the processor (104) to (i) obtain the heart rate and exercise load of the individual (112); (ii) normalize the obtained heart rate with respect to a maximal heart rate of the individual to provide a data pair of normalized heart rate HRn and exercise load w; (iii) apply a probabilistic model to associate normalized heart rate HRn with exercise load w and maximal oxygen uptake to provide an estimate of maximal oxygen uptake VO2max of the individual (112).

Description

TECHNICAL FIELD

[0001] The present invention relates to a method for estimating maximal oxygen uptake of an individual during exercise, a wearable device and a computing device for estimating maximal oxygen uptake VO2max of an individual. BACKGROUND

[0002] Cardiovascular fitness is of great importance in the field of exercise, fitness, diagnostics, prognosis and self-monitoring of asymptomatic individuals. Direct measurement of physical fitness requires an exercise test to the limit and is performed in a laboratory, which increases the risk of a cardiovascular event. Indirect estimation of physical fitness overcomes some of the limitations of direct measurement, but it still requires the individual to strictly undergo different types of fixed testing protocols. Maximal oxygen uptake or consumption (VO2max) of an individual refers to the maximum capacity of an individual to perform aerobic work. Typically, maximal oxygen uptake (VO2max) refers to the maximum rate of oxygen consumption measured during exercise of increasing intensity. Measurement of VO2max provides a quantitative value of endurance fitness between individuals for comparing individual training effects in endurance training. Maximal oxygen consumption reflects cardiorespiratory fitness and endurance during aerobic exercise.

[0003] In known methods, maximal oxygen uptake (VO2max) is determined without the need for any maximum exercise, these processes can be based on daily exercise performed freely by the individual. The analysis for determining maximal oxygen uptake (VO2max) is based on detecting the heart rate response during each recorded exercise (such as running, walking or cycling), which helps to determine the changes in physical fitness level. These changes are used to adjust the training plan and optimize the training load to speed up progress. Known maximal oxygen uptake (VO2max) estimation systems employ an algorithm that analyzes the relationship between heart rate and running speed at multiple points during a training (running) session. However, it requires the user to run at a variety of different speeds.

[0004] Therefore, there is a need to address the above-mentioned technical drawbacks in existing systems or techniques in estimating maximal oxygen uptake (VO2max). SUMMARY

[0005] It is an object of the present invention to provide an improved method for estimating maximal oxygen uptake (VO2max) of an individual during exercise, while avoiding one or more of the shortcomings of the prior art methods.

[0006] This object is achieved by the features of the independent claims. Further implementations are evident from the dependent claims, the specific embodiments and the figures.

[0007] The present invention provides a method, a wearable device and a computing device for estimating maximal oxygen uptake VO2max of an individual during exercise.

[0008] According to a first aspect, there is provided a method of estimating a maximum oxygen uptake VO2max of an individual during exercise, the individual having a heart rate, the method comprising:

[0009] obtaining the heart rate and exercise load of the individual;

[0010] normalizing the obtained heart rate with respect to a maximum heart rate of the individual to provide a data pair of normalized heart rate HRn and exercise load w;

[0011] applying a probabilistic model relating normalized heart rate to exercise load and maximum oxygen uptake to provide an estimate of the maximum oxygen uptake VO2max of the individual.

[0012] An advantage of the method is that it can estimate the maximum oxygen uptake VO2max of an individual from a free running exercise performed at a single running speed, or the like. Furthermore, the method can further improve the VO2max estimate by using data from multiple exercise sessions.

[0013] The estimate of the maximum oxygen uptake VO2max of the individual can be provided by determining a probability density function p(VO2max | HRn, w) using the probabilistic model. The probability density function p(VO2max | HRn, w) can be determined using Bayes’ rule:

[0014]

[0015] According to a second aspect, there is provided a wearable device for estimating a maximum oxygen uptake VO2max of an individual during exercise, the wearable device comprising: a processor for receiving heart rate measurement data and exercise load data of an individual of the device; and a memory storing instructions for causing the processor to perform the above method.

[0016] The wearable device optionally comprises a wireless interface for receiving the heart rate measurement data and the exercise load data from one or more sensing devices external to the wearable device.

[0017] An advantage of the wearable device is that it can estimate the maximum oxygen uptake VO2max of an individual without the need for exercise at different intensities. Furthermore, the wearable device can improve the VO2max estimate by using data from multiple exercise sessions.

[0018] According to a third aspect, there is provided a computing device for estimating a maximum oxygen uptake VO2max of an individual during exercise, the computing device comprising: a processor; a communication interface coupled to the processor for receiving heart rate measurement data and exercise load data of the individual; and a memory storing instructions for causing the processor to perform the above method.

[0019] The technical problems in the prior art are solved, wherein the technical problem is to estimate the maximum oxygen uptake VO2max of an individual from a motion performed at a single motion load, such as at a single running speed.

[0020] Thus, unlike the prior art, the method, wearable device and computing device for estimating the maximum oxygen uptake VO2max of an individual according to the present application can estimate the maximum oxygen uptake VO2max of an individual from a free running motion performed at a single speed or the like, thereby avoiding the discomfort caused to the individual by requiring running at different speeds. The method, wearable device and computing device according to the present application can improve the VO2max estimation by combining multiple motion periods and taking into account the reliability of the measured data.

[0021] These and other aspects of the present application are apparent from the following detailed description, which, taken in conjunction with the following drawings, illustrates the principles of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0022] The various implementations of the present application will now be described, by way of example only, with reference to the attached drawings in which:

[0023] Figure 1A is a block diagram of a wearable device for estimating the maximum oxygen uptake VO2max of an individual during a motion, provided by an implementation of the present application;

[0024] Figure 1B is a block diagram of a wearable device coupled with a sensing device, provided by an implementation of the present application;

[0025] Figure 1C is an exemplary view of a wearable device worn by an individual, provided by an implementation of the present application;

[0026] Figure 2 is a block diagram of a computing device for estimating the maximum oxygen uptake VO2max of an individual during a motion, provided by an implementation of the present application;

[0027] Figure 3 is a process flow architecture for estimating the maximum oxygen uptake VO2max of an individual during a motion, provided by an implementation of the present application;

[0028] Figure 4 is a flowchart of a method for estimating the maximum oxygen uptake VO2max of an individual during a motion, provided by an implementation of the present application. DETAILED DESCRIPTION

[0029] Implementations of the invention provide a method of estimating the maximal oxygen uptake VO2max of an individual without requiring the user to exercise at a plurality of different rates or intensities, e.g., estimating from a free running exercise performed at a single running speed, or a cycling exercise performed at a single exercise load. Implementations of the invention provide a wearable device for estimating the maximal oxygen uptake VO2max of an individual without requiring the user to exercise at a plurality of different exercise loads. Further, implementations of the invention provide a computing device for estimating the maximal oxygen uptake VO2max of an individual without requiring the user to exercise at a plurality of different exercise loads.

[0030] The following implementations of the invention are described in order to provide a more thorough understanding of the invention to those skilled in the art. The implementations of the invention can be used in any number of environments and with any number of systems without departing from the scope of the present invention.

[0031] To help understand the implementations of the invention, several terms introduced in the description of the implementations of the invention are first defined herein.

[0032] The terms, "first," "second," "third," and "fourth" (if any) as used herein are used to distinguish between similar objects, and are not necessarily used to describe a particular sequential or chronological order. It is to be understood that the terms so used in the description of implementations of the invention are interchangeable under appropriate circumstances such that the embodiments of the invention described herein are, for example, capable of being practiced in the sequence other than as illustrated or described herein. Furthermore, the term "comprising" and "including" and variations thereof as used herein are intended to be broad and encompass the passing reference to elements that are not essential to the practice of the invention. For example, a process, method, system, product, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements specifically named or inherent to the process, method, system, product, or apparatus. Moreover, use of the term "about" in the context of the invention is intended to encompass the passing reference to elements that are not essential to the practice of the invention.

[0033] Figure 1A is a block diagram of a wearable device 102 provided by implementations of the invention for estimating the maximal oxygen uptake VO2max of an individual during exercise. The wearable device 102 includes a processor 104 and a memory 106. The processor 104 is configured to receive heart rate measurement data and exercise load data for an individual (e.g., a user) of the wearable device 102. The memory 106 is configured to store instructions that cause the processor 104 to perform the method described above. The processor 104 is configured to normalize the acquired heart rate with respect to the individual's maximal heart rate to provide a data pair (or tuple) of normalized heart rate HRn and exercise load w. The processor 104 is configured to apply a probabilistic model to relate the normalized heart rate to the exercise load and the maximal oxygen uptake to provide an estimate of the maximal oxygen uptake VO2max of the individual.

[0034] The wearable device 102 estimates the individual's maximal oxygen uptake VO2max from free running exercise at a single running speed, thereby avoiding discomfort to the individual caused by requiring running at different speeds to estimate the maximal oxygen uptake VO2max, and the like. The wearable device 102 determines the individual's maximal oxygen uptake VO2max from a probability distribution of the ratio of maximal heart rate and work measurement (e.g., running speed measurement of free running exercise that can be performed at the same speed). The wearable device 102 can further refine the VO2max estimate by using data from multiple exercise sessions.

[0035] The exercise load data can include global positioning system (GPS) data, speed data (e.g., running speed data), pace, cadence, of the individual. The heart rate measurement data can include heart rate that can or can not be averaged over several heart rate intervals. Here, the wearable device 102 optionally includes a heart rate monitor for capturing heart rate data from a user of the wearable device 102, but the wearable device 102 can be configured to receive heart rate data wirelessly or through a wired connection from an external sensing device.

[0036] Figure 1B is a block diagram of the wearable device 102 coupled to a sensing device 110, which can be one of a plurality of sensing devices, in accordance with another implementation of the present disclosure. The wearable device 102 is communicatively connected to the sensing device 110. The wearable device 102 includes a processor 104 coupled to a memory 106. Figure 1B The wearable device 102 of includes a wireless interface 108 for receiving heart rate measurement data and exercise load data from one or more sensing devices 110 external to the wearable device 102. The sensing devices 110 optionally measure the individual's heart rate and running speed every 5 seconds. The sensing devices 110 can optionally measure other physiological parameters of the individual while exercising. For example, the sensing devices 110 can include a bicycle power meter (e.g., a pedal or crank-based power meter) to capture exercise load data for cycling sessions. The sensing devices 110 can include a GNSS receiver (e.g., a GPS receiver) to receive satellite navigation signals, thereby enabling determination of the location, altitude, and speed of the user of the device. The sensing devices 110 can also include one or more accelerometers to capture exercise (e.g., step count and pace) data from which the individual's walking / running speed and distance traveled (using knowledge of step length) can be determined.

[0037] Figure 1Cis an exemplary view of a wearable device 102 worn by an individual (i.e., user) 112 provided by implementations of the present invention. The wearable device 102 is optionally worn by the individual 112 on their arm 114. The wearable device 102 can be comfortably worn at any location on the body of the individual 112 that allows for estimation of the individual's maximal oxygen uptake VO2max during exercise. For example, the wearable device 102 can be worn on the chest of the user, possibly integrated with a heart rate sensor located above or adjacent to the user's heart.

[0038] Figure 2 is a block diagram of a computing device 202 for estimating the maximal oxygen uptake VO2max of an individual during exercise provided by implementations of the present invention. The computing device 202 includes a processor 204, a memory 206, and a communication interface 208 coupled with the processor 204. The communication interface 208 receives heart rate measurement data and exercise load data of the individual from internal sensing devices, external sensing devices, or some combination of both. The memory 206 is used to store instructions that cause the processor 204 to perform any of the methods described above. The processor 204 receives the heart rate and exercise load data and is used to normalize the acquired heart rates with respect to the individual's maximal heart rate to provide a data pair (or tuple) of normalized heart rate HRn and exercise load w. The processor 204 is used to apply a probabilistic model that relates the normalized heart rate to the exercise load and the maximal oxygen uptake to provide an estimate of the individual's maximal oxygen uptake VO2max.

[0039] The computing device 202 estimates the maximal oxygen uptake VO2max of the individual from a probabilistic distribution of the proportion of maximal heart rate and exercise load measurements from free running exercise at the same speed, etc. The computing device 202 can improve the VO2max estimate by using data from multiple exercise sessions and by taking into account the reliability of the measurement data. The computing device 202 can be, but is not limited to, selected from a cell phone, a smart watch, a personal digital assistant (PDA), a tablet, a desktop computer, a server, or a laptop.

[0040] Figure 3is a process flow architecture provided by implementations of the present invention to estimate an individual's maximal oxygen uptake, VO2max, during exercise. In step 302, a measurement of the individual's exercise load data including velocity data is obtained. The individual's exercise load data can include global positioning system (GPS) data of the individual, power meter data (e.g., from a bicycle or spin bike power meter), pace (e.g., from an accelerometer of a wearable device or an accelerometer associated with a wearable device or a portion of a wearable device, or from a treadmill), and / or cadence. In step 304, heart rate measurement data is obtained. In step 306, the individual's steady state is identified using the exercise load data (e.g., velocity data or power meter data). The individual's steady state can include the individual's running stability and constant motion while performing exercise. In step 308, the individual's velocity data is filtered to identify steady state velocity data. The filtering of the velocity data can include discarding unstable data using a sliding window technique (thereby increasing reliability). The sliding window technique determines the maximum speed variation in a velocity data measurement by calculating the difference between the maximum speed and the minimum speed within a sliding window. In step 310, the heart rate measurement data is filtered corresponding to the steady state velocity data to obtain steady state heart rate data. The steady state heart rate can be calculated from the heart rate measurements corresponding to the velocity data measurements falling within the sliding window. In step 312, the individual's steady state heart rate data and steady state velocity data is obtained. In step 314, the individual's anthropometric data is obtained. The anthropometric data can include measurements of size descriptors (e.g., height, weight, leg length, body mass index, etc.) and physical properties (e.g., gender and age) of the individual's body. In step 316, a VO2max machine learning algorithm is applied. The VO2max machine learning algorithm employs a probabilistic model to calculate a probability distribution using the steady state heart rate data and corresponding workload data to determine a probability of each possible VO2max value. In step 318, the individual's maximal oxygen uptake, VO2max, is determined. In step 320, the determined individual's maximal oxygen uptake, VO2max, is stored to improve the accuracy of the estimated VO2max in future exercise sessions.

[0041] Figure 4is a flowchart of a method for estimating a maximum oxygen uptake VO2max of an individual during exercise provided by implementations of the invention. The individual has a heart rate. In step 402, the individual's heart rate and exercise load are obtained. In step 404, the obtained heart rate is normalized with respect to the individual's maximum heart rate to provide a data pair of normalized heart rate HRn and exercise load w. In step 406, a probabilistic model is applied to relate the normalized heart rate to the exercise load and the maximum oxygen uptake to provide an estimate of the individual's maximum oxygen uptake VO2max. The method can include estimating the individual's maximum oxygen uptake VO2max from an exercise performed at a single exercise load (e.g., from a free running exercise performed at a single running speed). In addition, the method can improve the VO2max estimate by combining multiple exercise sessions and taking into account the reliability of the measured data. The method optionally includes multiple data pairs (tuples) of normalized heart rate HRn and exercise load w determined periodically throughout the exercise session.

[0042] In a first implementation, the estimate of the individual's maximum oxygen uptake VO2max is provided by determining a probability density function p(VO2max|HRn, w) using a probabilistic model. The probability density function p(VO2max|HRn, w) is optionally determined using Bayes' rule:

[0043]

[0044] In a second implementation, the method includes storing the probability density function p(VO2max|HRn, w) after determining each data pair. The method can include storing the probability density function includes discretizing the probability density function and storing the discrete values. The method can include discretizing the probability density function includes computing p(VO2max|HRn, w) for a set of discrete VO2max values and storing the resulting values.

[0045] The method optionally includes using the last stored probability density function p t–1 (VO2max|HRn t–1 ,w t–1 ) instead of p(VO2max):

[0046]

[0047] The method optionally includes modifying the last stored probability density function by increasing the uncertainty of p t–1 (VO2max|HRn t–1 ,w t–1 ) with respect to VO2max since the last stored probability density function p t–1 (VO2max|HRnt–1 t–1 ) as a function of time since the last stored probability density function p is represented and the following equation is obtained:

[0048]

[0049] Optionally, only when the time since the last stored probability density function p t–1 (VO2max | HRn t–1 t–1 ) exceeds 1 day, the uncertainty of the last stored probability density function p t–1 (VO2max | HRn t–1 t–1 ) with respect to VO2max is increased. Optionally, p(VO2max) relates one or more of the individual’s age, gender, body mass index, and physical activity level to VO2max.

[0050] The method can include determining a mean of the probability density function p(VO2max | HRn, w) to provide an estimate of the individual’s maximal oxygen uptake. The method can include determining a value of VO2max that maximizes the probability density function p(VO2max | HRn, w) to provide an estimate of the individual’s maximal oxygen uptake.

[0051] The probability model can be derived from a dataset comprising exercise load data, heart rate data, and VO2max of a plurality of individuals acquired from exercise cardiopulmonary function tests. The probability model is optionally based on a multivariate Gaussian distribution.

[0052] The method can include identifying and discarding standardized heart rate and exercise load data that result in p(HRn, w | VO2max) = 0,

[0053] Measuring exercise load can be performed by determining a running speed of the individual during exercise. Optionally, measuring exercise load is performed by using a bicycle power meter (e.g., a pedal power meter or a crank power meter). Optionally, measuring exercise load is performed by using a power meter of a stationary exercise machine such as a rowing machine or a spin bike.

[0054] The individual’s maximal heart rate can be estimated from the individual’s age. Optionally, when a measured maximal heart rate of the individual exceeds the maximal heart rate estimated from the individual’s age, the measured maximal heart rate is used in place of the maximal heart rate estimated from the individual’s age. The individual’s maximal heart rate can be estimated from a heart rate measurement acquired from the individual during exercise.

[0055] ​​​​In an example implementation, the motion load w comprises the individual's running speed. The measurement of running speed is used to assess the individual's running stability and even-paced motion. Optionally, a sliding window of fixed duration in the range of 60 to 120 seconds (e.g. 90 seconds) determines the maximum speed variation in the running speed measurement by calculating the difference between the maximum running speed and the minimum running speed within the sliding window. For example, if the difference between the maximum running speed and the minimum running speed is greater than 1 kilometre per hour (km / h), the entire running speed measurement within the sliding window can be considered unstable and discarded. If the entire speed measurement is unstable, a new running speed measurement can be fed into the sliding window. Optionally, an average heart rate is calculated from the heart rate measurements corresponding to the running speed measurements falling within the sliding window, and then a data pair (tuple) of average heart rate and average running speed is obtained. For example, this process can be repeated throughout the entire duration of the running motion, and if multiple stable speeds are identified, a set of data pairs (tuples) of average heart rate and average running speed can be obtained at the end of the running motion.

[0056] For each average heart rate, a normalized average heart rate is calculated by dividing the average heart rate by an estimate of the individual's maximum heart rate. For example, the estimate of the individual's maximum heart rate can be identified by using the expression 220 - age.

[0057] Then, from each normalized average heart rate and average running speed data pair, a probability density function (PDF) of VO2max is calculated by using Bayes' rule:

[0058]

[0059] Here, p(VO2max) denotes the probability density function (PDF) of VO2max obtained prior to obtaining the normalized heart rate and running speed data pair (i.e. measurement pair) (HRn,v). The individual's anthropometric data can be used to determine p(VO2max). Alternatively, if p(VO2max) is unknown, it can be set to 1. Optionally, the normalized heart rate and running speed data pairs (HRn,v) that result in p(HRn,v | VO2max) = 0 are identified and discarded (thereby improving reliability).

[0060] Alternatively, after normalizing by the individual's maximum heart rate, the sequential measurements of heart rate and running speed are used directly without assessing the individual's running stability and even-paced motion.

[0061] ​Two measurement pairs (HRn1, v1) and (HRn2, v2) can be acquired at the end of an individual's running exercise. The probability density function (PDF) of VO2max with the first measurement pair (HRn1, v1) can be computed by using Bayes' rule as follows:

[0062]

[0063] The probability density function (PDF) of VO2max with the second measurement pair (HRn2, v2) can be computed by using Bayes' rule as follows:

[0064]

[0065] The PDF p(HRn2, v2) can be determined by:

[0066] p(HRn2, v2) = ∑ p(HRn2, v2 | VO2max) p(VO2max).

[0067] The PDF p(HRn2, v2) can be approximated as a sum over a discrete set of VO2max values (e.g., VO2max i ∈ (20 ml / kg / min,..., 90 ml / kg / min) as follows:

[0068]

[0069] In one example implementation, a probability model p(HRn, v | VO2max) that associates a normalized heart rate is determined using running speed and VO2max. The probability model can be derived from a dataset that includes exercise data and VO2max of individuals acquired from standard exercise cardiopulmonary fitness tests. In particular, the following relationship between the joint PDF, conditional PDF, and marginal PDF can be used.

[0070]

[0071] The dataset can be used to determine a probability model p(HRn, v, VO2max) that associates a normalized heart rate. For example, p(HRn, v, VO2max) can be given by a multivariate Gaussian distribution as follows:

[0072]

[0073] Here, |∑| denotes the determinant of the (3x3) covariance matrix ∑, and μ denotes the (3x1) mean vector of the distribution. Precise values of ∑ and μ can be obtained from standard exercise cardiopulmonary function tests by fitting p(HRn,v, VO2max) to such a data set while keeping it general. In particular, ∑ and μ can be given as follows (realistic example data values are provided here):

[0074] μ = [0.82, 2.77, 48.64] T

[0075]

[0076] In this case, p(VO2max) is also Gaussian with mean and variance 48.64 and 72.85, respectively. Then, the conditional PDF p(HRn,v | VO2max) is also Gaussian with (2x1) mean vector m and (2x2) covariance matrix C given by

[0077] m = [0.82, 2.77] T + [0.0019, 0.0572] T (VO2max - 48.64)

[0078]

[0079] Furthermore, the marginal PDF p(HRn,v) is Gaussian with (2x1) mean vector ξ and (2x2) covariance matrix Q given by T

[0080]

[0081] Optionally, probability models for p(HRn,v, VO2max), p(HRn,v | VO2max), or p(VO2max) other than Gaussian distributions are adapted.

[0082] The posterior PDF p(VO2max | HRn,v) can be determined numerically from the Bayes' rule given above, with its mean providing an estimate of the individual's VO2max:

[0083]

[0084] The posterior PDF is with respect to the current measurement data pair or tuple. The posterior PDF describes the probability distribution of the individual's VO2max after observing the measurement tuple of data pairs of normalized heart rate HRnand exercise load w. The posterior PDF can be the prior PDF of a subsequent measurement tuple. The prior PDF describes the information about VO2max before a new measurement tuple is determined. The prior PDF is then adjusted according to the new measurement tuple. This process is repeated for each measurement tuple (data pair). Alternatively, an estimate of the individual's VO2max can be obtained by determining the VO2max value that maximizes p(VO2max | HRn, v). Optionally, the posterior PDF p(VO2max | HRn, v) is updated and stored after each running exercise session according to Bayes' rule. At the beginning of each running exercise session, the posterior PDF p(VO2max | HRn, v) is used instead of p(VO2max).

[0085] It should be appreciated that the arrangements of the components shown in the described figures are exemplary and other arrangements can be made. It should also be appreciated that the various system components (and modules) defined by the claims below and shown in the various block diagrams represent components in some systems configured in accordance with the subject matter disclosed herein. For example, one or more of these system components (and modules) can be implemented in whole or in part by at least some of the components shown in the arrangements shown in the described figures.

[0086] Furthermore, while at least one of these components is implemented at least partially as an electronic hardware component, and thereby constitutes a machine, other components can be implemented in software, which, when included in an execution environment, constitutes a machine, hardware, or a combination of software and hardware.

[0087] While the present application and its advantages have been described in detail, it should be understood that various changes, substitutions and alterations can be made herein without departing from the spirit and scope of the application as defined by the appended claims.

Claims

1. An estimate of an individual's maximum oxygen uptake during exercise VO2max The method, wherein the individual (112) has a heart rate, is characterized in that The method comprises: obtaining the heart rate and exercise load of the individual (112); normalizing the obtained heart rate relative to a maximum heart rate of the individual to provide a normalized heart rate HRn and data pairs of exercise load w ​ Applying a probabilistic model to correlate the normalized heart rate with exercise load and maximal oxygen uptake to provide an estimate of the individual's maximal oxygen uptake from exercise performed at a single exercise load VO2max .

2. The method of claim 1, wherein, Also included are multiple pairs of data of standardized heart rate determined periodically throughout the exercise period HRn and exercise load w .

3. The method according to claim 1 or 2, characterized in that, an estimate of the maximum oxygen uptake of the individual is provided by determining a probability density function using the probability model VO2max ​​ 4. The method of claim 3, wherein, the probability density function is determined using Bayes' rule:

5. The method of claim 3, wherein, Also included is storing the probability density function after determining each data pair .

6. The method of claim 5, wherein, VO2max 7. The method of claim 6, wherein, Discretizing the probability density function includes calculating Storing the probability density function comprises discretizing the probability density function and storing the discrete values. values for a set of discrete values, and storing the resulting values.

8. The method of claim 5, wherein, Also included is the use of a last stored probability density function Instead of :

9. The method of claim 8, wherein, also including modifying the last stored probability density function by adding a probability density function uncertainty in VO2max since the last stored probability density function was stored as a function of time since the last stored probability density function was stored is represented and the following is obtained:

10. The method of claim 9, wherein, only if a time since storing the last stored probability density function the last stored probability density function is more than 1 day the uncertainty of the last stored probability density function VO2max increases.

11. The method of claim 3, wherein, one or more of the individual's age, gender, body mass index, and physical activity level are associated with VO2max the individual's risk of developing a cardiovascular disease.

12. The method of claim 3, wherein, Also included is determining a mean of the probability density function to provide an estimate of the individual's maximal oxygen uptake.

13. The method of claim 3, wherein, Also includes determining the probability density function Maximized VO2max values ​​to provide an estimate of the individual's maximum oxygen uptake.

14. The method of claim 1 or 2, wherein, The probabilistic model is derived from a data set comprising exercise load data, heart rate data, and VO2max .

15. The method of claim 1 or 2, wherein, VO2max 16. The method of claim 1 or 2, wherein, Also included is identifying and discarding standardized heart rate and exercise load data that results in ​ 17. The method of claim 1 or 2, wherein, The probability model is based on a multivariate Gaussian distribution.

18. The method of claim 1 or 2, wherein, Measuring the exercise load is performed by determining the running speed of the individual (112) during exercise.

19. The method of claim 1 or 2, wherein, Measuring the exercise load is performed by using a bicycle power meter.

20. The method of claim 1 or 2, wherein, Measuring the exercise load is performed by using a rowing machine or a power meter of a stationary exercise machine.

21. The method of claim 20, wherein, The maximum heart rate of the individual is estimated from the age of the individual.

22. The method of claim 1 or 2, wherein, When it is determined that the maximum measured heart rate of the individual exceeds the maximum heart rate estimated from the age of the individual, the maximum measured heart rate is used instead of the maximum heart rate estimated from the age of the individual.

23. A wearable device (102) for estimating maximal oxygen uptake of an individual during exercise The maximum heart rate of the individual is estimated from heart rate measurements obtained from the individual (112) during exercise. characterized in that VO2max The wearable device (102) comprises: a processor (104) for receiving heart rate measurement data and exercise load data of a user of the wearable device (102); 24. The wearable device (102) of claim 23, characterized by a memory (106) storing instructions for causing the processor (104) to perform the method according to any of claims 1-22.

25. The wearable device (102) of claim 23, wherein, The wearable device (102) further comprises a wireless interface (108) for receiving the heart rate measurement data and the exercise load data from one or more sensing devices (110) external to the wearable device (102).

26. A computing device (202) for estimating maximal oxygen uptake of an individual during exercise comprises a heart rate monitor for capturing heart rate data from a user of the wearable device (102). characterized in that VO2max The computing device (202) comprises: a processor (204); a communication interface (208) coupled to the processor (204) for receiving heart rate measurement data and exercise load data of the individual (112); a memory (206) storing instructions for causing the processor (204) to perform the method according to any of claims 1-22.

Images