Non-invasive metabolic health monitoring and improvement assistance

Abstract

A computer-implemented method includes receiving first measurement data indicative of a body fat percentage value associated with a user. The method also includes receiving second measurement data indicative of a body shape parameter value associated with the user. Further, the method includes determining, based at least in part on the first measurement data and the second measurement data, a metabolic health score for the user. The metabolic health score is associated with a risk of metabolic syndrome given both the first measurement data and the second measurement data. The method also includes generating, based at least in part on the determined metabolic health score, a recommendation corresponding to at least one remedial action to improve the determined metabolic health score. Moreover, the method includes causing the metabolic health score and the recommendation to be visually rendered via a display of a user device.

Description

PCT / US24 / 56083 15 November 2024 (15.11.2024)NON-INVASIVE METABOLIC HEALTH MONITORING AND IMPROVEMENT ASSISTANCEFIELD

[0001] The present disclosure relates to computer-implemented methods, systems, and computer program products for non-invasive metabolic health monitoring and improvement assistance.BACKGROUND

[0002] Providing information regarding an individual’ s metabolic health can help to inform whether the individual’s metabolic health warrants the performance of remedial actions, and in some cases, which remedial actions to perform. As an example, body mass index (BMI) has been used as a metric for metabolic health, for instance, by being used to broadly classify an individual as being “underweight”, “normal weight”, “overweight”, or “obese”. However, BMI is derived based on an individual’s height and weight only with no consideration of body composition, and, as such, individuals with a “healthy” BMI might still harbor underlying metabolic risks. For instance, BMI cannot be relied upon to determine whether an individual has metabolic syndrome. Metabolic syndrome refers to a cluster of risk factors for various cardiovascular diseases, such as diabetes, heart disease, and stroke. Metabolic syndrome is present when three or more of the following conditions are true: waist circumference over 40 inches (male) or 35 inches (female); blood pressure over 130 mmHg (sys.) or 85 mmHg (dia.); fasting triglyceride level over 150 mg / dl; fasting HDL below 40 mg / dl (male) or below 50 mg / dl (female); and fasting blood sugar over 100 mg / dl.Furthermore, directly measuring some of these metabolic syndrome conditions involve invasive tests (e.g., blood tests).SUMMARY OF THE INVENTION

[0003] Aspects and advantages of embodiments of the present disclosure will be set forth in part in the following description, or can be learned from the description, or can be learned through practice of the embodiments.

[0004] Various implementations described herein relate to systems and methods to facilitate the determination of a metabolic health score of an individual by considering the individual’s body composition, without requiring invasive tests. The metabolic health score relates to a risk ofPCT / US24 / 56083 15 November 2024 (15.11.2024)metabolic syndrome for the individual and is determined based on both (i) a measured body fat percentage and (ii) a measured body shape parameter of the individual. The metabolic health score can be rendered to the individual via a user device. In this way, various implementations described herein can facilitate the provision, to an individual, of a metabolic health score which reliably characterizes their risk of metabolic syndrome, and more generally, their metabolic health, in a non-invasive and convenient manner. Additionally, information related to the metabolic health score can be rendered (e.g., low / medium / high risk of metabolic syndrome), as well as recommendations corresponding to remedial actions indicating whether to and / or how to improve the determined metabolic health score. The recommendations can be generated based on, for instance, on one or more of the measurement data (or a subset thereof), the metabolic health score, past behavior of the individual and / or one or more other individuals, capability information associated with the user device, or any other relevant information. In some implementations, the recommendations can be tailored to the measurement data for the individual. This can help to inform and guide the individual as to whether their metabolic health warrants the performance of one or more remedial actions, as well as which remedial actions to perform to improve their metabolic health. As such, various implementations described herein can enable an individual to track and improve their metabolic health (or in other words, reduce their risk of metabolic syndrome) in an accurate and non-invasive manner. In addition, in many implementations, the individual’s ongoing body measurements can be acquired without needing to visit a dedicated medical facility.

[0005] These and other features, aspects, and advantages of various embodiments of the present disclosure will become better understood with reference to the following description and appended claims. The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate example embodiments of the present disclosure and, together with the description, serve to explain the related principles.BRIEF DESCRIPTION OF THE DRAWINGS

[0006] Detailed discussion of embodiments directed to one of ordinary skill in the art is set forth in the specification, which makes reference to the appended figures, in which:

[0007] FIG. 1 depicts a block diagram of an example environment that depicts various aspects of the present disclosure.PCT / US24 / 56083 15 November 2024 (15.11.2024)

[0008] FIG. 2 depicts an overview of an example method for providing one or more metabolic health score(s) in accordance with various implementations of the present disclosure.

[0009] FIG. 3 depicts an example method for determining a metabolic health score for a given set of measurement data in accordance with various implementations of the present disclosure.

[0010] FIGS. 4A and 4B depict example interfaces that include graphical interface elements for facilitating the provision of one or more metabolic health score(s) in accordance with various implementations of the present disclosure.

[0011] FIG. 5 A depicts a flow diagram of a method for providing a metabolic health score in accordance with various implementations of the present disclosure.

[0012] FIG. 5B depicts a flow diagram of a method for providing a metabolic health score by utilizing a wearable device in accordance with various implementations of the present disclosure.

[0013] FIG. 6 depicts an example architecture of a computing device in accordance with various implementations of the present disclosure.DETAILED DESCRIPTIONOverview

[0014] Repeated use of reference characters and / or numerals in the present specification and / or figures is intended to represent the same or analogous features, elements, or operations of the present disclosure. Repeated description of reference characters and / or numerals that are repeated in the present specification is omitted for brevity.

[0015] As referred to herein, the terms “includes” and “including” are intended to be inclusive in a manner similar to the term “comprising.” As referenced herein, the terms “or” and “and / or” are generally intended to be inclusive, that is (i.e.), “A or B” or “A and / or B” are each intended to mean “A or B or both.” As referred to herein, the terms “first,” “second,” “third,” and so on, can be used interchangeably to distinguish one component or entity from another and are not intended to signify location, functionality, or importance of the individual components or entities. As referenced herein, the terms “couple,” “couples,” “coupled,” and / or “coupling” refer to chemical coupling (e.g., chemical bonding), communicative coupling, electrical and / or electromagnetic coupling (e.g., capacitive coupling, inductive coupling, direct and / or connected coupling, etc.), mechanical coupling, operative coupling, optical coupling, and / or physical coupling.PCT / US24 / 56083 15 November 2024 (15.11.2024)

[0016] As referenced herein, the term “system” can refer to hardware (e.g., application specific hardware), computer logic that executes on a general-purpose processor (e.g., a central processing unit (CPU)), and / or some combination thereof. In some embodiments, a “system” described herein can be implemented in hardware, application specific circuits, firmware, and / or software controlling a general-purpose processor. In some embodiments, a “system” described herein can be implemented as program code files stored on a storage device, loaded into a memory, and executed by a processor, and / or can be provided from computer program products, for example, computerexecutable instructions that are stored in a tangible computer-readable storage medium (e.g., random-access memory (RAM), hard disk, optical media, magnetic media).

[0017] Turning now to FIG. 1, a block diagram of an example environment 100 that depicts various aspects of the present disclosure is depicted. As illustrated in FIG. 1, the example environment 100 includes a health assessment system 110, one or more user device(s) 120, and one or more third party computing system(s) 130.

[0018] In some implementations, all or aspects of the health assessment system 110 can be implemented locally at the user device 120. In additional or alternative implementations, all or aspects of the health assessment system 110 can be implemented remotely from the user device 120 as depicted in FIG. 1 (e.g., at remote server(s)). In those implementations, the user device 120 and the health assessment system 110 can be communicatively coupled with each other via one or more networks (e.g., via a network interface 126 of the user device), such as one or more wired or wireless local area networks (“LANs,” including Wi-Fi LANs, mesh networks, Bluetooth, near-field communication, etc.) or wide area networks (“WANs”, including the Internet).

[0019] As illustrated in FIG. 1, the health assessment system 110 can include a metabolic health score engine 112, a recommendation generation engine 114, a measurement selection engine 116, and a scheduling engine 118. Some of the engines can be omitted in various implementations. In some implementations, the engines of the health assessment system 110 are distributed across one or more computing systems. Operations which can be performed by the health assessment system 110 (e.g., via one or more of these engines) are described in more detail herein, for instance, in relation to FIG. 2.

[0020] The user device 120 can be, for example, one or more of: a desktop computer, a laptop computer, a tablet, a mobile phone, a computing device of a vehicle (e.g., an in-vehicle communications system, an in-vehicle entertainment system, an in-vehicle navigation system), aPCT / US24 / 56083 15 November 2024 (15.11.2024)standalone interactive speaker (optionally having a display), a smart appliance such as a smart television, and / or a wearable apparatus of the user that includes a computing device (e.g., a watch of the user having a computing device, glasses of the user having a computing device, a virtual or augmented reality computing device). Additional and / or alternative user devices may be provided.

[0021] In various implementations, the user device 120 can include one or more input / output interface(s) 122 including one or more user input interface(s) and / or output interface(s). The user device 120 can be configured to detect user input provided by a user of the user device 120 using the one or more user input / output interface(s) 122 (e.g., via one or more input device(s)). For example, the user device 120 can be equipped with one or more touch sensitive components 122A (e.g., a keyboard and mouse, a stylus, a touch screen, a touch panel, one or more hardware buttons, etc.) that are configured to capture signal(s) corresponding to touch input directed to the user device 120. Additionally, or alternatively, the user device 120 can be equipped with one or more microphones 122B that capture audio data, such as audio data corresponding to spoken utterances of the user or other sounds in an environment of the user device 120. Some instances of input data described herein can be input data that is formulated based on user input provided by a user of the user device 120 and detected via the one or more user interface(s). For example, input data corresponding to measurement data can be typed via a physical or virtual keyboard, selected via a touch screen or a mouse, included in a spoken utterance that is detected via microphone(s) 122B of the user device 120, etc.

[0022] Additionally or alternatively, the user device 120 can be configured to provide content for audible and / or visual presentation to a user of the user device 120 using the one or more input / output interface(s) 122 (e.g., via one or more output device(s)). For example, the user device 120 can be equipped with a display 122C or projector that enables content to be provided for visual presentation to the user via the user device 120. Additionally, or alternatively, the user device 120 can be equipped with one or more speakers 122D that enable content to be provided for audible presentation to the user via the user device 120.

[0023] In various implementations, the user device 120 can include one or more sensor(s) 124 configured to capture corresponding sensor data. For example, the user device 120 can be equipped with one or more vision components (such as a camera 124A) that are configured to capture vision data corresponding to images detected in a field of view of one or more of the vision components. Additionally or alternatively, the user device 120 can be equipped with a heart rate sensor 124BPCT / US24 / 56083 15 November 2024 (15.11.2024)(such as an electrocardiography sensor, a photoplethysmography sensor, etc.) that is configured to capture heart rate data of a user. Additionally or alternatively, the user device 120 can be equipped with a blood pressure sensor 124C that is configured to capture blood pressure data for a user. Additionally or alternatively, the user device 120 can be equipped with a blood composition sensor 124D that is configured to capture blood composition data (such as blood fat levels, blood glucose levels, etc.,) for a user. Additionally or alternatively, the user device 120 can be equipped with a weight sensor 124E that is configured to capture weight data for the user (e.g., a weight of the user’s body). Additionally or alternatively, the user device 120 can be equipped with a body composition sensor 124F (such as a dual-energy X-ray absorptiometry (DEXA) scan device, a bioelectrical impedance analysis device, etc.,) that is configured to capture one or more body composition data for a user’s body. Although a number of sensors have been described herein, it will be appreciated that the one or more sensor(s) 124 are not limited to these examples and can include any number of sensors which are not explicitly described herein.

[0024] Although aspects of FIG. 1 are illustrated or described with respect to a single user device having a single user, it should be understood that is for the sake of example and is not meant to be limiting. For example, one or more additional user devices of a user and / or of additional user(s) can also implement the techniques described herein. For instance, the user device 120, the one or more additional user devices, and / or any other computing devices of a user can form an ecosystem of devices that can employ techniques described herein. As an example, the user device 120 can be a smart phone device, and an additional user device can be a separate device including one or more sensors not available to the smart phone device (such as a wearable device, a smart scales device, a DEXA scan device, etc.). These additional user devices and / or computing devices (which may be referred to as auxiliary devices) may be in communication with the user device 120 and / or the health assessment system 110 (e.g., over one or more network(s), as described herein). As another example, a given user device can be utilized by multiple users in a shared setting (e.g., a group of users, a household).

[0025] The user device 120 can execute one or more applications, such as a health assessment application, via which input data can be provided and / or selected, and / or content can be rendered (e.g., audibly and / or visually). The health assessment application can be an application that is separate from an operating system of the user device 120 (e.g., one installed “on top” of the operating system) - or can alternatively be implemented directly by the operating system of the userPCT / US24 / 56083 15 November 2024 (15.11.2024)device 120. For example, the health assessment application can be a web browser installed on top of the operating system or can be an application that is integrated as part of the operating system functionality. The health assessment application can include and / or interact with all or aspects of the health assessment system 110.

[0026] Further, the user device 120 and / or the health assessment system 110 can include one or more memories for storage of data and / or software applications, one or more processors for accessing data and executing the software applications, and / or other components that facilitate communication over one or more of the networks. In some implementations, one or more of the software applications can be installed locally at the user device 120, whereas in other implementations one or more of the software applications can be hosted remotely (e.g., by one or more servers) and can be accessible by the user device 120 over one or more of the networks. In some implementations, at least some of the data processed by the user device 120 and / or the health assessment system 110 (e.g., measurement data, determined metabolic health scores, generated recommendations, any other user data, etc.,) can be encrypted before storage or use. In this way, any sensitive data can be protected at rest (e.g., in storage) and in transit (e.g., when transmitted between different entities of the example environment 100).

[0027] In some implementations, the example environment 100 includes one or more third party computing system(s) 130. The third party computing system(s) 130 can include one or more computing systems (e.g., remote server devices, desktop computers, smartphone devices, etc.,) which are owned, controlled and / or managed by one or more third parties (e.g., entities which are different from the user of the user device 120 and / or the entity that owns / manages / controls the health assessment system 110). Furthermore, the third party computing system(s) 130 can provide information that is available to the third party computing system(s) to the health assessment system 110 and / or the user device (e.g., in response to a request for the information, proactively without any explicit request, etc.). For instance, assuming the user has granted the necessary permissions, a computing system of a medical practitioner can provide sensor data obtained by the medical practitioner (e.g., DEXA scan data) for use by the health assessment system 110. In some implementations, the health assessment system 110 and / or the user device 120 can provide information to the third party computing system(s) 130. For instance, the third party computing system(s) 130 can be provided with a determined metabolic health score and / or recommendationsPCT / US24 / 56083 15 November 2024 (15.11.2024)generated by the health assessment system 110 to enable a corresponding third party (e.g., a medical practitioner) to provide services based on this information.

[0028] Turning now to FIG. 2, an overview of an example flow chart of a method 200 for providing one or more metabolic health score(s), in accordance with various implementations, is depicted. The example method 200 can involve one or more component(s) of the environment 100 described in relation to FIG. 1. At block 210, a health assessment procedure 210 is initiated. In some implementations, the health assessment procedure 210 can be initiated by a user. For instance, responsive to user input received at the user device 120 to initiate the health assessment procedure 210 (e.g., via a health assessment application executing on the user device 120), the health assessment procedure can be initiated. In some implementations, the health assessment procedure 210 can be initiated without explicit user input. For instance, the health assessment procedure 210 can be initiated by the health assessment system 110 in response to a determination that a time scheduled for a health assessment procedure 210 has occurred.

[0029] During the health assessment procedure 210, measurement data 220 for the user is retrieved (e.g., by the health assessment system 110). The measurement data 220 can be retrieved from any suitable source. For instance, in some implementations, a user can provide at least some of the measurement data to the user device 120 (e.g., via user input received at one or more interface(s) 122 of user device 120). Additionally or alternatively, the measurement data 220 can be captured by the one or more sensor(s) 124 of the user device 120, or by one or more sensor(s) of another device in communication with the health assessment system 110 and / or the user device 120. Additionally or alternatively, the measurement data 220 can be retrieved from storage accessible to the health assessment system 110. For instance, the health assessment system 110 can retrieve information previously retrieved by the health assessment system 110 (e.g., during a previous health assessment procedure 210, during creation of a user account, etc.). Additionally or alternatively, the measurement data 220 can be retrieved from a third party (e.g., via the one or more third party computing system(s) 130).

[0030] The measurement data 220 can be associated with a particular user (e.g., based on one or more measurements of the particular user’s body). The measurement data 220 can include, at least, a measured body fat percentage value and a measured body shape parameter value (e.g., for the particular user). The body shape parameter can be any suitable measurement of a user’s body shape, including one or more of visceral adipose tissue fat area (VATA), subcutaneous adiposePCT / US24 / 56083 15 November 2024 (15.11.2024)tissue fat area (SATA), visceral to subcutaneous tissue ratio (V ATA: SATA), waist circumference, waist to height ratio, or android to gynoid ratio (A:G).

[0031] In some cases, the measurement data 220 can include body shape parameter values for more than one type of body shape parameter. Additionally or alternatively, the measurement data 220 can include additional measurement data (e.g., which is not a type of body shape parameter). This additional measurement data can include any suitable additional information which can be utilized in determining a metabolic health score and / or corresponding recommendations (e.g., demographic data such as age, sex, etc., sensor data such as blood fat, blood pressure, heart rate, etc ). In this way, additional data can be taken into consideration when generating the metabolic health score (and, in some cases, the recommendations). The generated metabolic health score can thus be expected to characterize the user’s metabolic health more accurately and reliably.

[0032] In some implementations, a subset of the measurements of the measurement data 220 can be selected (e.g., using measurement selection engine 116) to be used in generating a metabolic health score and / or recommendations. For instance, when there are a plurality of body shape parameter measurements included in the measurement data 220, a subset of the plurality of body shape parameter measurements can be selected. Additionally or alternatively, when there are a plurality of additional measurements included in the measurement data 220 (corresponding to the additional measurement data described herein), a subset of the plurality of additional measurements can be selected.

[0033] The selection can be based on one or more selection criteria. For instance, the selection criteria can include determining that a particular measurement is available in the measurement data 220. As an example, the selection criteria can indicate that if a body parameter value for a particular (e.g., preferred) body parameter shape is available in the measurement data 220, this body parameter shape will be selected. Additionally or alternatively, the selection criteria can include a threshold recency of a measurement. As an example, the selection criteria can indicate that only measurements taken within a threshold period of time can be selected. This may be because it can be expected that more recent measurements are likely to be more relevant for determining a metabolic health score for the user. Additionally or alternatively, the selection criteria can include a threshold confidence associated with a given measurement. As an example, each measured value in the measurement data 220 can be associated with a confidence in that measurement. The confidence can be determined, for instance, based on the sensor used to capture the measurementPCT / US24 / 56083 15 November 2024 (15.11.2024)(e.g., a measurement captured by a relatively low-fidelity sensor can be associated with a lower confidence than a measurement captured by a relatively higher-fidelity sensor), the entity that conducted the measurement (e.g., a measurement conducted by the user can be associated with a lower confidence than a measurement conducted by a medical professional), the type of measurement (e.g., some measurements can be inherently less accurate), etc. Additionally or alternatively, the selection criteria can include a threshold correlation of a given measurement with body fat percentage. As an example, if a body shape parameter type is strongly correlated with body fat percentage, then little additional information may be added by selecting measurements of that body shape parameter type, and computational resources can therefore be wasted by processing measurements of that body shape parameter type. On the other hand, body shape parameter types which are weakly correlated (or, indeed, not correlated) with body fat percentage can provide more information to be used in determining the metabolic health score and / or corresponding recommendations, such that computational resources are not wasted on processing redundant information. In some implementations, the correlation between a body shape parameter type can be determined previously (e.g., based on statistical data across a group of individuals) and be available to the health assessment system 110 (or the measurement selection engine 116). In some implementations, the measurements in the measurement data 220 can be ranked (e.g., based on availability, recency, confidence, correlation with body fat percentage, etc.,), with only a subset of the measurements being selected based on the ranking (e.g., only the top 1, 3, 5, etc., measurements may be selected).

[0034] A metabolic health score can be determined (e.g., using the metabolic health score engine 112) based on the measurement data 220 (or in some cases, the subset of measurement data selected by the measurement selection engine 116) for the particular user. This can include determining a risk value for metabolic syndrome for the particular user, given the measurement data 220 (or in some cases, the subset of measurement data selected by the measurement selection engine 116). As an example, assuming the measurement data 220 includes a measured body fat percentage value and a measured body shape parameter value for the particular user, a risk value of metabolic syndrome for the retrieved set of measured body fat percentage and measured body shape parameter can be determined.

[0035] In some implementations, the risk value can be determined based on interpolating risk data sourced from one or more public datasets. As an example, source data from a dataset can bePCT / US24 / 56083 15 November 2024 (15.11.2024)obtained (e.g., by the health assessment system 110) which includes, for each of a number of individuals, various measurement data as well as any other relevant information. The measurement data can include, for instance, a body fat percentage value, one or more body shape parameter values, and in some cases additional measurement data. The dataset can also include, for each of the individuals, an indication of whether the individual has metabolic syndrome, an indication of how many conditions of metabolic syndrome are satisfied, an indication of which conditions of metabolic syndrome are satisfied, an indication of measurement data associated with conditions of metabolic syndrome, etc.

[0036] The source data can be divided (or in other words, partitioned) into a plurality of subsets. Each subset can be associated with a combination of (i) a subset of body fat percentage values and (ii) a subset of body shape parameter values. The subset of body fat percentage values can include a range of body fat percentage values. The range of body fat percentage values can be a subrange of the range of body fat percentage values present in the source data. For instance, the range of body fat percentage values can be determined based on a quantile of body fat percentage values present in the source data. The subset of body shape parameter values can include a range of body shape parameter values. The range of body shape parameter values can be a subrange of the range of body shape parameter values present in the source data. For instance, the range of body shape parameter values can be determined based on a quantile of body shape parameter values present in the source data.

[0037] Each subset of the source data can thus include information associated with individuals whose measurement data falls within the corresponding combination of (i) the subset of body fat percentage values and (ii) the subset of body shape parameter values. In addition, each subset of the source data can be associated with a risk value for metabolic syndrome given the corresponding combination of (i) the subset of body fat percentage values and (ii) the subset of body shape parameter values. The risk value for a given subset can be determined by aggregating the metabolic syndrome risk for each of the individuals within the given subset. For instance, the risk value for a given subset can be determined based on a proportion of individuals within the given subset which are indicated by the source data as having metabolic syndrome (e.g., if 640 out of 1000 individuals within the given subset are indicated by the source data as having metabolic syndrome, the risk value for the given subset can be determined as being 0.64). Additionally or alternatively, the risk value can be based on a relative risk of the prevalence of metabolic syndrome among individualsPCT / US24 / 56083 15 November 2024 (15.11.2024)whose measurement data falls within the combination of the subset of body fat percentage values and the subset of body shape parameter values. For instance, the relative risk for a subset can be determined using the equation RR= Prob[R|C] / Prob[R], where RR is relative risk, Prob[R|C] is the prevalence of metabolic syndrome among individuals whose measurement data falls within the combination of the subset of body fat percentage values and the subset of body shape parameter values, and ProbfR] is the prevalence of metabolic syndrome among all individuals in the source data.

[0038] Following this, any given combination of body fat percentage value and body shape parameter value can be determined based on determining an intermediate value between a plurality of the risk values of the subsets of the source data (otherwise termed subset risk values). For instance, four known risk values (e.g., subset risk values) with corresponding body fat percentage values and body shape parameter values can be determined (e.g., the nearest neighbors to a query body fat percentage value and body shape parameter value combination). An intermediate risk value for the query body fat percentage value and body shape parameter value combination can then be found based on the risk values of the four known risk values. For instance, the known risk values can be interpolated to determine the intermediate risk value. Any suitable interpolation technique can be used, including but not limited to, bilinear interpolation, bicubic interpolation, spline interpolation, nearest neighbor interpolation, etc. It will be appreciated that in some implementations, more than four known risk values (e.g., some or all of the other known risk values) can be used to determine the intermediate risk value. This may be dependent on the type of interpolation utilized. Furthermore, whilst two-dimensional interpolation is generally referred to herein (since the subsets described herein are generally associated with body fat percentage and a single body shape parameter type), it will be appreciated that in some implementations, the interpolation may be over more than two dimensions (e.g., when the subsets are associated with more than two measurement types).

[0039] As such, in some implementations, a risk value for the particular user can be determined, based on the body fat percentage value and the body shape parameter value in the measurement data 220, by determining an intermediate risk value between the known risk values. In some implementations, the determined risk value for the measurement data 220 can be provided as the metabolic health score. Additionally or alternatively, the determined risk value can be converted into a metabolic health score. For instance, in some implementations, the determined risk value canPCT / US24 / 56083 15 November 2024 (15.11.2024)be normalized such that it is provided as a score between consistent values (e.g., 0 to 100). The determined risk value can additionally or alternatively be converted such that a higher score indicates a lower risk. As an example, assuming the determined risk value is provided as a percentile risk of a user, R, the score, S, can be determined by S=l-R. In this way, the metabolic health score can be a reliable and objective indication of the risk of metabolic syndrome for the particular user.

[0040] In some implementations, a plurality of intermediate risk values (or metabolic health scores) can be determined, e.g., at a time prior to the health assessment procedure 210 being initiated. For instance, intermediate risk values can be determined at periodic intervals. The intervals can be determined based on a defined granularity. As an example, for a given body shape parameter value, an intermediate risk value can be determined for each 1% of body fat percentage, each 0.1% of body fat percentage, etc. The intermediate risk values can be used to populate a risk value map. The risk value map can provide, for each combination of body fat percentage and body shape parameter value, a risk value, at least to the defined granularity. In some implementations, the risk value map can instead be populated with metabolic health scores (e.g., by converting the intermediate risk values to corresponding metabolic health scores). In this case, the risk value map can provide, for each combination of body fat percentage and body shape parameter value, a metabolic health score, at least to the defined granularity. The risk value map can then be stored such that it is accessible to the health assessment system 110. As such, a risk value (or metabolic health score) for the particular user can be determined, using the risk value map, based on the body fat percentage value and the body shape parameter value in the measurement data 220. When a risk value is determined, a metabolic health score can be determined based on the determined risk value.

[0041] For instance, turning briefly to FIG. 3, an example method 300 for determining a metabolic health score for a given set of measurement data is depicted. As depicted in FIG. 3, a dataset has been partitioned into various subsets according to combinations of body fat percentage quartiles and body shape parameter tertiles. Namely, on graph 310, the body shape parameter tertiles correspond to low, as represented by circle points 322, 324, 326, 328; medium, as represented by triangle points 332, 334, 336, 338; and high, as represented by square points 342, 344, 346, 348. Furthermore, the body fat percentage quartiles correspond to group I, as represented by points 322, 332, and 342; group II, as represented by points 324, 334, and 344; group III, asPCT / US24 / 56083 15 November 2024 (15.11.2024)represented by points 326, 336, and 346; and group IV, as represented by points 328, 338, and 348. Each subset is also plotted against a corresponding relative risk value.

[0042] As further depicted in FIG. 3, a risk value map 350 can be populated based on determining a plurality of intermediate risk values between the known risk values (e.g., as depicted on graph 310). In the risk value map 350 of FIG. 3, the risk values are also converted into a metabolic health score, such that for each body shape parameter value and body fat percentage value, a metabolic health score is indicated. For the purposes of illustration, the risk value map 350 is depicted as a heat map, whereby the score is indicated by a particular shade. In particular, a higher score is indicated with a lighter shade, and a lower score is indicated with a darker shade, as indicated in key 360.

[0043] In some implementations, the body fat percentage value and the body shape parameter value combinations can be divided into various risk groups. As depicted in FIG. 3, these can include a low risk group 352, a medium risk group 354, and a high risk group 356. This can provide additional information regarding a particular user's risk of metabolic syndrome as to the urgency and necessity of remedial action being taken to improve their metabolic health score.Furthermore, by dividing into risk groups, remedial actions provided to users can be tailored to assist the user in moving into a lower risk group as quickly as possible. For instance, in some cases, it may be more effective to improve the body shape parameter value in order to enter a lower risk group relative to lowering body fat percentage. The remedial actions provided to the user can be tailored accordingly, as described herein.

[0044] As described herein, in some implementations, a risk value and / or metabolic health score for a retrieved set of (i) body fat percentage value and (ii) body shape parameter value can be determined by interpolating the risk values across the nearest quartile-tertile combinations, without the entire risk value map 350 being determined in advance. In some implementations, the risk value map 350 can be determined in advance and stored such that it is accessible to the health assessment system 110. A risk value and / or metabolic health score for a retrieved set of (i) body fat percentage value and (ii) body shape parameter value can then be determined based on the risk value map 350 (e.g., by finding the corresponding risk value and / or metabolic health score on the risk value map).

[0045] Returning now to FIG. 2, although some example methods of determining a metabolic health score (e.g., using the metabolic health score engine 112) have been described herein, it will be appreciated that any suitable method for determining a metabolic health score representing a riskPCT / US24 / 56083 15 November 2024 (15.11.2024)of metabolic syndrome given the received measurement data 220 can be utilized. For instance, in some alternative implementations, a machine learning model (not shown) can be used to provide the risk value. For instance, the machine learning model can be trained, based on the source data, to provide, based on a given set of (i) body fat percentage value and (ii) body shape parameter value, a corresponding risk value. A risk value for the particular user can be determined based on using the trained machine learning model to process (at least some of) the measurement data 220. A metabolic health score can be determined based on the determined risk value, as described herein. In some cases, the machine learning model may instead be trained to directly provide a metabolic health score. In this case, a metabolic health score for the particular user can be determined based on using the trained machine learning model to process (at least some of) the measurement data 220.

[0046] A recommendation can additionally be generated (e.g., using the recommendation generation engine 114). The recommendation can be generated based on the measurement data 220, a subset thereof (e.g., as selected by the measurement selection engine 116), the metabolic health score, and / or any other relevant information. The recommendation can correspond to at least one remedial action to improve the determined metabolic health score. As an example, responsive to determining a relatively low metabolic health score for the particular user (e.g., based on the metabolic health score corresponding to a high risk group for metabolic syndrome), the recommendation can include an indication that the user’s metabolic health score is low and should be increased. In some implementations, the remedial action can include dietary suggestions (e.g., eat more or less particular foods, consume X calories, eat a low carb diet, etc.,), exercise suggestions (e.g., perform a particular work out, achieve a certain number of steps per day, etc.,), or any other lifestyle change suggestions (e.g., sleep for Y hours per night).

[0047] In some implementations, the recommendations can be tailored to the measurement data 220. For instance, it may be determined that a reduction in the user’s body shape parameter value would make a large improvement to the user’s metabolic health score relative to a similar level of improvement in body fat percentage (or in other words, it may be determined that the user’s metabolic health score is more sensitive to changes in body shape parameter value). As an example, assume that, for the user, it is determined that a decrease in body fat percentage by 10% would not result in a change in score, whereas an improvement in the body shape parameter by 10% would improve the user’s score by 20 points. Responsive to this determination, thePCT / US24 / 56083 15 November 2024 (15.11.2024)recommendation can additionally or alternatively include an indication that the user should improve the body shape parameter value rather than the body fat percentage value (or at least prioritize improvement in the body shape parameter value over improvement in the body fat percentage value). The recommendation can additionally or alternatively include one or more remedial actions which are tailored to achieving this. For instance, a particular exercise can be known (e.g., based on academic studies and / or historical data captured by the health assessment system 110) to be particularly effective at improving the body shape parameter value. As such, the recommendation can include the particular exercise to target an improvement in the body shape parameter value. In this way, the effectiveness of the recommendations in improving the user’s metabolic health score can be improved.

[0048] Additionally or alternatively, the recommendations can be generated based on past behavior of the particular user and / or one or more other users. For instance, based on historical data associated with the particular user (and / or one or more other users), it can be determined that the particular user (and / or one or more other users) has previously been more likely to perform remedial actions of a particular type (at least relative to remedial actions of another type). As an example, assume that the particular user has previously been presented with a recommendation including a running exercise and a recommendation including a cycling exercise. Responsive to determining that the user followed the recommendation including the cycling exercise and did not follow the recommendation including a running exercise, the recommendations generated subsequently can be more likely to include cycling exercises rather than running exercises. As mentioned, this past behavioral information can also be aggregated across one or more other users. The one or more other users can be selected from a larger group of users based on one or more attributes of the particular user (e.g., age, sex, fitness profile, etc.). In this way, the effectiveness of the recommendations in modifying the behavior of users can improve over time.

[0049] Additionally or alternatively, the recommendations can be generated based on capability information associated with the user device 120 (or another device in communication with the user device 120 and / or the health assessment system 110). The capability information can, for instance, be indicative of a device type, the input / output interfaces 122 available to the device, the sensors 124 available to the device, processing capacity of the device, etc. As an example, responsive to determining that the user device 120 is capable of tracking a particular type of remedial action, a recommendation can be generated to include a remedial action of that particular type.PCT / US24 / 56083 15 November 2024 (15.11.2024)

[0050] The recommendation can be generated in any suitable manner. For instance, in some implementations, the recommendations can be selected from a database of predetermined recommendations accessible to the health assessment system 110 (e.g., locally or remotely). The selection can be conducted in any suitable manner. As an example, the input data used to generate the recommendation can be mapped to a particular recommendation in the database, and responsively the particular recommendation can be selected. For instance, the input data can be converted into a point (or in other words, an embedding) in a latent space (e.g., a recommendation space), where each predetermined recommendation in the database is also associated with a point (or embedding) in the latent space. The input data can be converted, for instance, using an embedding model. The recommendation with the point in latent space closest to the point in latent space associated with the input data can then be determined and selected as the recommendation to be proceeded with. As another example, the predetermined recommendations in the database can be ranked, based on the input data, and the highest ranking predetermined recommendation can be selected. In some implementations, the predetermined recommendations can include one or more variable parameters (e.g., achieve X number of steps per day, where X is a variable parameter). In this case, generating the recommendation can further include determining a value for the one or more variable parameters based on the input data. In some implementations, generating the recommendations can include processing, using a generative model (e.g., a large language model), the input data, to determine a generative model output, and determining the recommendation based on the generative model output.

[0051] The metabolic health score, as well as additional information (such as whether the score is poor, average, or good) can be provided as output 230. Additionally or alternatively, the generated recommendation can be provided as output 230. For instance, the metabolic health score and / or the recommendation can be rendered at the user device 120. In some implementations, the metabolic health score and / or the recommendation can be rendered audibly via a speaker 122D of the user device 120. Additionally or alternatively, the metabolic health score and / or the recommendation can be rendered visually via the display 122C of the user device 120.

[0052] For instance, turning briefly to FIG. 4 A, an example graphical user interface (GUI) 420 of the user device 120 that includes various interface elements for facilitating the provision of one or more metabolic health score(s) is depicted. Further, as shown, the user device 120 can include various system interface elements 412, 413, and 414 (e.g., hardware and / or software interfacePCT / US24 / 56083 15 November 2024 (15.11.2024)elements) that may be interacted with by a user of the user device 120 to cause the user device 120 to perform one or more actions. In some implementations, the GUI 420 can be presented as a launch screen, for instance, when the health assessment application is initially executed on the user device 120, or when a health assessment procedure is initiated (e.g., within the health assessment application).

[0053] As depicted in FIG. 4A, the GUI 420 can include a first selectable graphical interface element 422. The first selectable graphical interface element 422 can be configured such that when user input is detected that is indicative of a selection of the first selectable graphical interface element 422, the user device 120 is caused to become receptive to the provision of measurement data via one or more input interfaces of the user device 120. For instance, an additional graphical element can be visually rendered by the user device 120 which facilitates the entry of measurement data (e.g., an input field, a virtual dial, a virtual slider, etc ). Additionally or alternatively, the user device can activate the microphone 122B of the user device 120 such that the measurement data can be entered via spoken utterances captured by the microphone 122B.

[0054] As further depicted in FIG. 4A, the example GUI 420 can additionally or alternatively include a second selectable graphical interface element 424. The second selectable graphical interface element 424 can be configured such that when user input is detected that is indicative of a selection of the second selectable graphical interface element 424, the user device 120 is caused to initiate capturing sensor data using one or more sensors 124 of the user device 120. In some implementations, the second selectable graphical interface element 424 can additionally or alternatively be configured such that when user input is detected that is indicative of a selection of the second selectable graphical interface element 424, the user device 120 is caused to initiate capturing sensor data using one or more sensors of another user device in communication with the user device 120 (e.g., a wearable device, a smart sensor, etc.). Measurement data can then be determined based on the sensor data captured by the one or more sensors (e.g., by the user device 120 or an external computing device).

[0055] As further depicted in FIG. 4A, the example GUI 420 can additionally or alternatively include a third selectable graphical interface element 426. The third selectable graphical interface element 426 can be configured such that when user input is detected that is indicative of a selection of the third selectable graphical interface element 426, the user device 120 is caused to retrieve measurement data from one or more third parties (e.g., via the one or more third party computingPCT / US24 / 56083 15 November 2024 (15.11.2024)systems 130 of FIG. 1). For instance, responsive to selection of the third selectable graphical interface element 426, an additional graphical interface element can be rendered by the user device 120 to allow the user to sign in to a service provided by a third party. The user can then link the health assessment application to the third party service via interactions with the user device 120 to provide the health assessment application the necessary permissions to retrieve measurement data from the third party service.

[0056] Turning now to FIG. 4B, another example GUI 430 that includes various graphical interface elements for facilitating the provision of one or more metabolic health score(s) is depicted. In some implementations, the GUI 430 can be presented as a results screen (e.g., following the GUI 420 of FIG. 4A), where the output 230 of FIG. 2 is rendered by the user device 120. For instance, the GUI 430 can be rendered responsive to sufficient measurement data having been retrieved by the health assessment application, and / or responsive to user input indicative of a request to provide GUI 430 being received.

[0057] As depicted in FIG. 4B, the GUI 430 can include a first graphical interface element 432. The first graphical interface element 432 can include an indication of the determined metabolic health score. For instance, the first graphical interface element 432 can include a numerical indication of the metabolic health score (e.g., “Your score: 68”). Additionally or alternatively, the first graphical interface element 432 can include a graphical indication of the metabolic health score (e.g., a slider with the metabolic health score being indicated as a point at a corresponding distance along the slider). Additionally or alternatively, the first graphical interface element 432 can include a color and / or shade based on the metabolic health score (e.g., red for a low metabolic health score, green for a high metabolic health score, etc.). In some implementations, the first graphical interface element 432 can also include additional information. For instance, the first graphical interface element 432 can include an indication of whether the metabolic health score indicates that the user is at low risk, average risk, or high risk for metabolic syndrome (e.g., by providing such indications at corresponding locations along the slider).

[0058] As further depicted in FIG. 4B, the GUI 430 can additionally or alternatively include a second graphical interface element 434. The second graphical interface element 432 can include one or more recommendations, as described herein. In some implementations, the second graphical interface element 434 can be selectable, such that, responsive to selection of the second graphical interface element 434 the user device 120 can be caused to perform an action corresponding to thePCT / US24 / 56083 15 November 2024 (15.11.2024)recommendation(s). As an example, responsive to selection of the second graphical interface element 432, the user device 120 can be caused to open a webpage corresponding to a recommendation using a web browser application. For instance, when the recommendation relates to eating a particular diet, the user device 120 can be caused to open a webpage using a web browser application including recipes for that diet. As another example, responsive to selection of the second graphical interface element 434, the user device 120 can be caused to interact with one or more other applications available at the user device 120. For instance, when the recommendation relates to a particular exercise regime, the user device 120 can be caused to generate calendar entries for a calendar application available at the user device 120 according to the particular exercise regime. As another example, responsive to selection of the second graphical interface element 434, the user device 120 can be caused to initiate monitoring progress of a remedial action corresponding to the recommendation.

[0059] Turning back to FIG. 2, in some implementations, in the instance where the user consents to the sharing of the output 230 (e.g., the metabolic health score and / or the recommendation), the output 230 can be sent to a third party (e.g., via a corresponding third party computing system 130), such as a personal trainer, a nutritionist, a medical practitioner, etc. The user can provide consent, for instance, by providing user input to the health assessment system 110 indicative of one or more third parties with which the health assessment system 110 is allowed to share the output 230 (and / or any other personal data) with. This can enable the third party to evaluate the user’s metabolic health, to assist the user with improving their metabolic health score, and / or to provide any necessary medical intervention(s).

[0060] In some implementations, one or more subsequent health assessment procedures can be scheduled (e.g., using the scheduling engine 118). As an example, the health assessment procedure can be repeated periodically. The metabolic health score (as well as the recommendation(s) and / or any other additional information) can be updated accordingly as new measurement data is provided in each subsequent health assessment procedure. For instance, in some implementations, a time interval before the next health assessment procedure can be constant (e.g., 1 week, 1 month, 1 year, etc ). Additionally or alternatively, the time interval can be determined based on the latest metabolic health score. As an example, if the score indicates a high level of risk, the determined time interval might be shorter relative to a time interval which might be determined if the scorePCT / US24 / 56083 15 November 2024 (15.11.2024)indicated a low level of risk. A subsequent health assessment procedure can then be scheduled to occur when the determined time interval has elapsed.

[0061] Still referring to FIG. 2, at block 240, it can be determined whether the metabolic health score should be updated (and / or whether to initiate a subsequent health assessment procedure). In some implementations, the decision at block 240 can be based on determining that the time interval has elapsed. The subsequent health assessment procedure can then be initiated, for instance, by automatically initiating the health assessment procedure when the time interval has elapsed, or by rendering a prompt to complete the subsequent health assessment procedure to the user at a user device and receiving responsive user input to initiate the subsequent health assessment procedure. Additionally or alternatively, the decision at block 240 can be based on whether or not the user has provided user input indicative of a request to update the metabolic health score (and / or to initiate a subsequent health assessment procedure). Additionally or alternatively, the decision at block 240 can be based on subsequent measurement data retrieved by the health assessment system 110 (e.g., outside of any health assessment procedure). For instance, it may be determined that the subsequent measurement data is indicative of a significant change (above some threshold) in the user’s metabolic health score, thus triggering the initiation of a subsequent health assessment procedure. In this way, the user is able to track their metabolic health on an ongoing basis and can be guided in improving their metabolic health over time with a level of assistance that is appropriate for their given situation.

[0062] During the subsequent health assessment procedure, the user can provide at least one updated measurement such that the score can be updated accordingly based on the updated measurement. For instance, during the subsequent health assessment procedure, the user can provide an updated body fat percentage value, but not an updated body shape parameter value. As such, an updated metabolic health score (as well as updated recommendations) can be determined based on the updated body fat percentage value and the previously obtained body shape parameter value and provided to the user.

[0063] This process can then be performed repeatedly. In some implementations, the process can be repeated indefinitely, such that the user is enabled to monitor and improve their metabolic health score on an ongoing basis. In some implementations, the process can be repeated until the user’s score has improved to at least a threshold value (e.g., such that the metabolic health score places the user in a low risk group for metabolic syndrome).PCT / US24 / 56083 15 November 2024 (15.11.2024)

[0064] As an example, the health assessment system 110 can be provided as an application executing on, or otherwise accessible to, the user device 120 (which may be provided as, for instance, as smart phone). Furthermore, the body shape parameter value can be determined based on image data captured by the camera 124A of the user device 120. For instance, the user can capture one or more images of their body using the camera 124A of the user device 120. In some implementations, images can be captured at various angles of the user's body to provide various corresponding perspectives. The body shape parameter value can then be determined based on the image data. For instance, a machine learning model can be trained to provide an indication of a body shape parameter value based on input image data. The trained machine learning model can then be used to provide a body shape parameter value for the user based on the image data captured by the camera 124A of the user device 120. In this way, the body shape parameter value can be captured quickly and easily with relatively low cost (e.g., consumer-grade) equipment. This may also be the case for body fat percentage values. For instance, this can be captured using a smart scales device. Thus, the metabolic health score can be determined without requiring any specialist knowledge, or tools, and non-invasively. In some implementations, the body shape parameter value can be determined locally at the user device. As such, no image data needs to be sent to an external device, thereby protecting the user’s privacy.

[0065] As another example implementation, the user device 120 can be provided as, or be in communication with, a wearable device (e.g., a fitness tracker, a smart watch, a smart ring, smart glasses, etc.,). The wearable device can obtain a metabolic health score (e.g., from a user device 120, or by performing one or more of the operations described in relation to FIG. 2). Additionally or alternatively, the wearable device can obtain a recommendation (e.g., from a user device 120, or by performing one or more of the operations described in relation to FIG. 2). The wearable device can render the metabolic health score and / or the recommendation (e.g., at a display of the wearable device).

[0066] In some implementations, the recommendation can correspond to a remedial action that corresponds to an activity that is trackable by the wearable device. As such, after obtaining the recommendation, the wearable device can start tracking (or in other words, monitoring) the progress of the remedial action. For instance, the wearable device can initiate the tracking automatically, without additional user input being required. As another example, the wearable device can render a selectable graphical element configured to initiate the tracking upon user selection. In some cases,PCT / US24 / 56083 15 November 2024 (15.11.2024)the activity may be an ongoing target that can be ambiently tracked by one or more sensors of the wearable device (e.g., perform 1000 steps per day, climb 100 steps per day, etc.). As another example, the activity can be a specific workout that can be tracked by the wearable device (e.g., run for 30 minutes, rest for 2 minutes, then run for 10 more minutes). In this case, the activity can be tracked via user interface input received at the wearable device (e.g., selection of an interface element to initiate and / or end tracking of the activity) in addition to or instead of tracking using one or more sensors of the wearable device. Furthermore, one or more intermediate interface elements can be rendered during performance of the activity, for instance, to indicate progress of the activity, a next step in the activity, etc.

[0067] In some implementations, the metabolic health score can be updated based on the tracking (e.g., by the wearable device, by a user device 120, etc.). For instance, the performance and / or non-performance of the activity can be used to update the metabolic health score. As another example, sensor data captured during the performance of the activity can be used to update the metabolic health score. The updated metabolic health score can be rendered at the wearable device.

[0068] Turning now to FIG. 5A, a flow diagram of a method 500 for providing a metabolic health score, in accordance with various implementations, is depicted. The method 500 may, for instance, correspond to one or more operations described in relation to FIG. 2. For convenience, the operations of the method 500 are described with reference to a system that performs the operations. The system includes one or more processors, memory, and / or other component(s) of computing device(s). Moreover, while operations of the method 500 are shown in a particular order, this is not meant to be limiting. One or more operations may be reordered, omitted, and / or added.

[0069] At block 510, the system receives first measurement data indicative of a body fat percentage value associated with a user.

[0070] At block 512, the system receives second measurement data indicative of a body shape parameter value associated with the user. The body shape parameter value can include a measurement of at least one of: a visceral adipose tissue fat area, a subcutaneous adipose tissue fat area, a visceral to subcutaneous tissue ratio, a waist circumference, a waist circumference to height ratio, or an android to gynoid ratio. Blocks 510 and 512 may be the same or similar to operations described herein in relation to retrieving the measurement data 220 of FIG. 2.

[0071] Receiving the first measurement data and / or receiving the second measurement data can, for instance, include receiving information based on user input received by the user device.PCT / US24 / 56083 15 November 2024 (15.11.2024)Additionally or alternatively, receiving the first measurement data and / or receiving the second measurement data can include receiving information from one or more computer systems associated with a third party. Additionally or alternatively, receiving the first measurement data and / or receiving the second measurement data can include receiving information based on sensor data captured by one or more sensors of the user device and / or another device. The sensor data can, for instance, include image data captured by one or more cameras of the user device and / or another device.

[0072] At block 514, the system determines, based at least in part on the first measurement data and the second measurement data, a metabolic health score for the user. The metabolic health score may be associated with a risk of metabolic syndrome given both the first measurement data and the second measurement data. Block 514 may be the same or similar to operations described herein in relation to metabolic health score engine 112 of FIG. 2.

[0073] In some implementations, the system can determine a risk value for the first measurement data and the second measurement data based on determining an intermediate risk value between a plurality of known risk values, wherein each known risk value is associated with a corresponding body fat percentage value and body shape parameter value. The system can then determine the metabolic health score for the user based on the determined intermediate risk value.

[0074] For instance, the system can obtain a dataset including, for each of a plurality of subsets of individuals in the dataset, (i) a set of body fat percentage values associated with the individuals in the subset, (ii) a set of body shape parameter values associated with the individuals in the subset, and (iii) a corresponding subset risk value for metabolic syndrome for the subset of individuals. The system can then determine an intermediate subset risk value between a plurality of subset risk values from the dataset. The metabolic health score for the user can then be determined based on the determined intermediate subset risk value.

[0075] In some implementations, the system can determine the metabolic health score for the user by utilizing a machine learning (ML) model. For instance, the system can process, using a ML model, ML input to generate corresponding ML output, wherein the ML input includes the first measurement data and the second measurement data. The system can then determine, based on the ML output, the metabolic health score for the user.

[0076] In some implementations, the system can receive additional measurement data. For instance, the body shape parameter value of the second measurement data can be a first body shapePCT / US24 / 56083 15 November 2024 (15.11.2024)parameter value of a first body shape parameter type, and the system can receive third measurement data indicative of a second body shape parameter value associated with the user, where the second body shape parameter value is of a second body shape parameter type (e.g., different to the first body shape parameter type). In some implementations, the system can select the measurement data to be used for determining the metabolic health score. For instance, in the example of FIG. 5 A, the system can select, from among the second measurement data and the third measurement data, the second measurement data to be used for determining the metabolic health score. The selection of the measurement data to be used for determining the metabolic health score can, for instance, be based on at least one of: a recency of the second measurement data, a confidence in the second measurement data, a sensitivity of the first body shape parameter type to performance of remedial actions, a sensitivity of the metabolic health score to a change in the first body shape parameter type, or a correlation between the first body shape parameter type and body fat percentage.

[0077] As another example, the system can additionally or alternatively receive fourth measurement data indicative of a measured attribute associated with the user. The measured attribute can be different to a body fat percentage and a body shape parameter type of the body shape parameter value. For instance, the measured attribute can include at least one of blood pressure information, blood sugar information, blood fat information, heart rate information, or weight information. The system can thus determine the metabolic health score for the user additionally based on the fourth measurement data.

[0078] At block 516, the system generates a recommendation. The recommendation can correspond to at least one remedial action to improve the determined metabolic health score. Block 516 may be the same or similar to operations described herein in relation to recommendation generation engine 114 of FIG. 2. For instance, the recommendation can be generated based on the measurement data, a subset thereof, the metabolic health score, and / or any other relevant information. As an example, responsive to determining a relatively low metabolic health score for the particular user (e.g., based on the metabolic health score corresponding to a high risk group for metabolic syndrome), the recommendation can include an indication that the user’s metabolic health score is low and should be increased. In some implementations, the remedial action can include dietary suggestions (e.g., eat more or less particular foods, consume X calories, eat a low carb diet, etc.,), exercise suggestions (e.g., perform a particular work out, achieve a certain number of steps per day, etc.,), or any other lifestyle change suggestions (e.g., sleep for Y hours per night). In somePCT / US24 / 56083 15 November 2024 (15.11.2024)implementations, the recommendations can be tailored to the measurement data. For instance, the recommendation can be generated so as to prioritize improvements in a particular one of the measurements based on determining that the metabolic health score is more sensitive to a change in the particular one of the measurements (e.g., relative to a change in a different one of the measurements). Additionally or alternatively, the recommendations can be generated based on past behavior of the particular user and / or one or more other users (e.g., as indicated by historical behavioral data associated with the particular user or the one or more other users). For instance, the recommendation can be generated so as to include a remedial action which is determined to be more likely to be performed by the particular user (e.g., based on their previous actions and / or the previous actions of other, similar users). In some implementations, the recommendations can be generated based on capability information associated with the user device and / or another device in communication with the user device and / or the health assessment system.

[0079] At block 518, the system causes the metabolic health score and the recommendation to be visually rendered via a display of a user device. Block 518 may be the same or similar to operations described herein in relation to rendering the output 230 of FIG. 2. In some implementations, causing the metabolic health score and the recommendation to be rendered at the user device includes transmitting data to the user device that is operable for causing the user device to render the metabolic health score and the recommendation.

[0080] For instance, the system can initially cause a first graphical user interface to be visually rendered via the display of the user device (such as GUI 420 of FIG. 4A). The first graphical user interface can include one or more interactive graphical elements to facilitate reception of the first measurement data and / or the second measurement data. To visually render the metabolic health score and the recommendation, the system can cause a second graphical user interface to be visually rendered via the display of the user device (such as GUI 430 of FIG. 4B). The second graphical user interface can include one or more graphical elements indicative of the metabolic health score and the recommendation.

[0081] In some implementations, the user device is a wearable device. In addition, the remedial action(s) can correspond to an activity that is trackable by the wearable device. For instance, the system can cause a selectable graphical element to be visually rendered via the display of the wearable device, wherein the selectable graphical element is user selectable to initiate tracking of the activity by the wearable device. Additionally or alternatively, the system can, responsive toPCT / US24 / 56083 15 November 2024 (15.11.2024)receiving an indication that the activity has been performed by the user, determine an updated metabolic health score based at least in part on the indication of the performance of the activity by the user and / or sensor data captured by one or more sensors of the wearable device during performance of the activity by the user. The system can cause the updated metabolic health score to be visually rendered via the display of the wearable device.

[0082] In some implementations, determining the metabolic health score for the user can be part of a first health assessment procedure. For instance, based at least in part on the determined metabolic health score, the system can determine a time interval, after which a second health assessment procedure (e.g., to determine an updated metabolic health score) should be performed. The system can then schedule a second health assessment procedure to be performed after the time interval.

[0083] In some implementations, at a subsequent time, the system can receive at least one of: updated first measurement data indicative of an updated body fat percentage value associated with a user and updated second measurement data indicative of an updated body shape parameter value associated with the user. The system can determine, based on at least one of the updated first measurement data and the updated second measurement data, an updated metabolic health score for the user. The system can then cause the updated metabolic health score to be visually rendered via the display of the user device.

[0084] Turning now to FIG. 5B, a flow diagram of a method 550 for providing a metabolic health score by utilizing a wearable device, in accordance with various implementations, is depicted. The method 550 may, for instance, correspond to one or more operations described in relation to FIG. 2 and / or FIG. 5A. For convenience, the operations of the method 550 are described with reference to a system that performs the operations. The system includes one or more processors, memory, and / or other component(s) of computing device(s). The system can, for instance, include a wearable device. Moreover, while operations of the method 550 are shown in a particular order, this is not meant to be limiting. One or more operations may be reordered, omitted, and / or added.

[0085] At block 560, the system obtains a metabolic health score for the user. The metabolic health score can be associated with the risk of metabolic syndrome given first measurement data indicative of a body fat percentage value associated with the user and second measurement data indicative of a body shape parameter value associated with the user. In some implementations,PCT / US24 / 56083 15 November 2024 (15.11.2024)obtaining the metabolic health score for the user can include performance of one or more operations described in relation to FIG. 2 and FIG. 5A. In some implementations, a metabolic health score that has been previously determined (e.g., by prior performance of one or more operations described in relation to FIG. 2 and FIG. 5A) can be obtained (e.g., from storage of the system). In some implementations, a metabolic health score that has been determined by another computing device (e.g., by performance, by the other computing device, of one or more operations described in relation to FIG. 2 and FIG. 5A) can be obtained (e.g., from the other computing device).

[0086] At block 562, the system obtains a recommendation. The recommendation can correspond to at least one remedial action to improve the metabolic health score for the user. The at least one remedial action can correspond to an activity that is trackable by the wearable device.

[0087] In some implementations, obtaining the recommendation can include performance of one or more operations described in relation to FIG. 2 and FIG. 5 A. For instance, the recommendation can be generated based on the measurement data, a subset thereof, the metabolic health score, and / or any other relevant information. As an example, responsive to determining a relatively low metabolic health score for the particular user (e.g., based on the metabolic health score corresponding to a high risk group for metabolic syndrome), the recommendation can include an indication that the user’s metabolic health score is low and should be increased. In some implementations, the remedial action can include dietary suggestions (e.g., eat more or less particular foods, consume X calories, eat a low carb diet, etc.,), exercise suggestions (e.g., perform a particular work out, achieve a certain number of steps per day, etc.,), or any other lifestyle change suggestions (e.g., sleep for Y hours per night). In some implementations, the recommendations can be tailored to the measurement data. For instance, the recommendation can be generated so as to prioritize improvements in a particular one of the measurements based on determining that the metabolic health score is more sensitive to a change in the particular one of the measurements (e.g., relative to a change in a different one of the measurements). Additionally or alternatively, the recommendations can be generated based on past behavior of the particular user and / or one or more other users (e.g., as indicated by historical behavioral data associated with the particular user or the one or more other users). For instance, the recommendation can be generated so as to include a remedial action which is determined to be more likely to be performed by the particular user (e.g., based on their previous actions and / or the previous actions of other, similar users). In some implementations, the recommendations can be generated based on capability information associatedPCT / US24 / 56083 15 November 2024 (15.11.2024)with the user device and / or another device in communication with the user device and / or the health assessment system.

[0088] In some implementations, a recommendation that has been previously determined (e.g., by prior performance of one or more operations described in relation to FIG. 2 and FIG. 5A) can be obtained (e.g., from storage of the system). In some implementations, a recommendation that has been determined by another computing device (e.g., by performance, by the other computing device, of one or more operations described in relation to FIG. 2 and FIG. 5A) can be obtained (e.g., from the other computing device).

[0089] At block 564, the system renders, via a display, the metabolic health score and the recommendation. For instance, the system can visually render a selectable graphical element which, upon selection by a user, causes the system to initiate tracking of the activity by the wearable device. Additionally or alternatively, the system can, responsive to receiving an indication that the activity has been performed by the user, determine an updated metabolic health score based at least in part on the indication of the performance of the activity by the user and / or sensor data captured by one or more sensors of the system during performance of the activity by the user. The system can cause the updated metabolic health score to be visually rendered via the display.

[0090] Turning now to FIG. 6, an example architecture of a computing device 610 that may optionally be utilized to perform one or more aspects of techniques described herein is depicted. In some implementations, one or more of a user device (e.g., the user device 120 of FIG. 1), a health assessment system (e.g., the health assessment system 110 of FIG. 1) or component s) therein, and / or other component(s) may include one or more components of the example computing device 610.

[0091] The computing device 610 typically includes at least one processor 614 which communicates with a number of peripheral devices via a bus subsystem 612. These peripheral devices may include a storage subsystem 624, including, for example, a memory subsystem 625 and a file storage subsystem 626, user interface output devices 620, user interface input devices 622, and a network interface 616. The input and output devices allow user interaction with the computing device 610. The network interface 616 provides an interface to outside networks and is coupled to corresponding interface devices in other computing devices.

[0092] The user interface input devices 622 may include a keyboard, pointing devices such as a mouse, trackball, touchpad, or graphics tablet, a scanner, a touch screen incorporated into thePCT / US24 / 56083 15 November 2024 (15.11.2024)display, audio input devices such as voice recognition systems, microphones, and / or other types of input devices. In general, use of the term "input device" is intended to include all possible types of devices and ways to input information into computing device 610 or onto a communication network.

[0093] The user interface output devices 620 may include a display subsystem, a printer, a fax machine, or non-visual displays such as audio output devices. The display subsystem may include a cathode ray tube (CRT), a flat-panel device such as a liquid crystal display (LCD), a projection device, or some other mechanism for creating a visible image. The display subsystem may also provide non-visual display such as via audio output devices. In general, use of the term "output device" is intended to include all possible types of devices and ways to output information from computing device 610 to the user or to another machine or computing device.

[0094] The storage subsystem 624 stores programming and data constructs that provide the functionality of some, or all, of the modules described herein. For example, the storage subsystem 624 may include the logic to perform selected aspects of the methods disclosed herein, as well as to implement various components depicted in FIG. 1.

[0095] These software modules are generally executed by processor 614 alone or in combination with other processors. The memory 625 used in the storage subsystem 624 can include a number of memories including a main random-access memory (RAM) 630 for storage of instructions and data during program execution and a read only memory (ROM) 632 in which fixed instructions are stored. A file storage subsystem 626 can provide persistent storage for program and data files, and may include a hard disk drive, a floppy disk drive along with associated removable media, a CD-ROM drive, an optical drive, or removable media cartridges. The modules implementing the functionality of certain implementations may be stored by file storage subsystem 626 in the storage subsystem 624, or in other machines accessible by the processor(s) 614.

[0096] The bus subsystem 612 provides a mechanism for letting the various components and subsystems of computing device 610 communicate with each other as intended. Although bus subsystem 612 is shown schematically as a single bus, alternative implementations of the bus subsystem 612 may use multiple buses.

[0097] Computing device 610 can be of varying types including a workstation, server, computing cluster, blade server, server farm, or any other data processing system or computing device. Due to the ever-changing nature of computers and networks, the description of computingPCT / US24 / 56083 15 November 2024 (15.11.2024)device 610 depicted in FIG. 6 is intended only as a specific example for purposes of illustrating some implementations. Many other configurations of computing device 610 are possible having more or fewer components than the computing device depicted in FIG. 6.

[0098] In situations in which the systems described herein collect or otherwise monitor personal information about users, or may make use of personal and / or monitored information), the users may be provided with an opportunity to control whether programs or features collect user information (e.g., information about a user’s social network, social actions or activities, profession, a user’s preferences, or a user’s current geographic location), or to control whether and / or how to receive content from the content server that may be more relevant to the user. Furthermore, such user information can be encrypted before it is stored or used, so that the user information is protected against unauthorized access and / or interception. Also, certain data may be treated in one or more ways before it is stored or used, so that personal identifiable information is removed. For example, a user’s identity may be treated so that no personal identifiable information can be determined for the user, or a user’s geographic location may be generalized where geographic location information is obtained (such as to a city, ZIP code, or state level), so that a particular geographic location of a user cannot be determined. Thus, the user may have control over how information is collected about the user and / or used.

[0099] In some implementations, a method implemented by one or more processors is provided, and includes: receiving first measurement data indicative of a body fat percentage value associated with a user; receiving second measurement data indicative of a body shape parameter value associated with the user; determining, based at least in part on the first measurement data and the second measurement data, a metabolic health score for the user, wherein the metabolic health score is associated with a risk of metabolic syndrome given both the first measurement data and the second measurement data; generating, based at least in part on the determined metabolic health score, a recommendation corresponding to at least one remedial action to improve the determined metabolic health score; and causing the metabolic health score and the recommendation to be visually rendered via a display of a user device.

[0100] These and other implementations of technology disclosed herein can optionally include one or more of the following features.

[0101] In some implementations, determining the metabolic health score for the user includes: determining a risk value for the first measurement data and the second measurement data based onPCT / US24 / 56083 15 November 2024 (15.11.2024)determining an intermediate risk value between a plurality of known risk values, wherein each known risk value is associated with a corresponding body fat percentage value and body shape parameter; and determining the metabolic health score for the user based on the determined risk value. In some versions of these implementations, method further includes: obtaining a dataset, the dataset comprising, for each of a plurality of subsets of individuals in the dataset, (i) a set of body fat percentage values associated with the individuals in the subset, (ii) a set of body shape parameter values associated with the individuals in the subset, and (iii) a corresponding subset risk value for metabolic syndrome for the subset of individuals, and wherein determining the intermediate risk value between the plurality of known risk values includes: determining an intermediate subset risk value between a plurality of subset risk values from the dataset.

[0102] In some implementations, determining the metabolic health score for the user includes: processing, using a machine learning (ML) model, ML input to generate corresponding ML output, wherein the ML input includes the first measurement data and the second measurement data; and determining, based on the ML output, the metabolic health score for the user.

[0103] In some additional or alternative implementations, the user device is a wearable device, and the at least one remedial action corresponds to an activity that is trackable by the wearable device. In some versions of these implementations, the method further includes causing a selectable graphical element to be visually rendered via the display of the wearable device, wherein the selectable graphical element is user selectable to initiate tracking of the activity by the wearable device. In some additional or alternative versions of these implementations, the method further includes: responsive to receiving an indication that the activity has been performed by the user, determining an updated metabolic health score, wherein the updated metabolic health score is determined based at least in part on the indication of the performance of the activity by the user and / or sensor data captured by one or more sensors of the wearable device during performance of the activity by the user; and causing the updated metabolic health score to be visually rendered via the display of the wearable device.

[0104] In some additional or alternative implementations, generating the recommendation is further based on at least one of the first measurement data and the second measurement data, and wherein the recommendation is tailored to the at least one of the first measurement data and the second measurement data.PCT / US24 / 56083 15 November 2024 (15.11.2024)

[0105] In some additional or alternative implementations, generating the recommendation is further based on historical behavioral data associated with the user and / or one or more other users.

[0106] In some additional or alternative implementations, receiving the first measurement data and / or receiving the second measurement data includes: receiving information based on user input received by the user device, and / or receiving information from one or more computer systems associated with a third party.

[0107] In some additional or alternative implementations, receiving the first measurement data and / or receiving the second measurement data includes: receiving information based on sensor data captured by one or more sensors of the user device and / or another device. In some versions of these implementations, the sensor data includes image data captured by one or more cameras of the user device and / or another device.

[0108] In some additional or alternative implementations, the body shape parameter value includes a measurement of at least one of: a visceral adipose tissue fat area, a subcutaneous adipose tissue fat area, a visceral to subcutaneous tissue ratio, a waist circumference, a waist circumference to height ratio, or an android to gynoid ratio.

[0109] In some additional or alternative implementations, the body shape parameter value is a first body shape parameter value of a first body shape parameter type, and the method further includes: receiving third measurement data indicative of a second body shape parameter value associated with the user, the second body shape parameter value being of a second body shape parameter type different to the first body shape parameter type; and selecting from among the second measurement data and the third measurement data, the second measurement data to be used for determining the metabolic health score. In some versions of these implementations, selecting the second measurement data to be used for determining the metabolic health score is based on at least one of: a recency of the second measurement data, a confidence in the second measurement data, a sensitivity of the first body shape parameter type to performance of remedial actions, a sensitivity of the metabolic health score to a change in the first body shape parameter type, or a correlation between the first body shape parameter type and body fat percentage.

[0110] In some additional or alternative implementations, the method further includes: receiving fourth measurement data indicative of a measured attribute associated with the user, the measured attribute being different to a body fat percentage and a body shape parameter type of the body shape parameter value, wherein determining the metabolic health score for the user is further based on thePCT / US24 / 56083 15 November 2024 (15.11.2024)fourth measurement data. In some versions of these implementations, the measured attribute includes at least one of: blood pressure information, blood sugar information, blood fat information, heart rate information, or weight information.

[0111] In some additional or alternative implementations, the metabolic health score for the user is part of a first health assessment procedure, and the method further includes: determining a time interval based at least in part on the determined metabolic health score for the user; and scheduling a second health assessment procedure to be performed after the time interval.

[0112] In some additional or alternative implementations, the method further includes: subsequently receiving at least one of: updated first measurement data indicative of an updated body fat percentage value associated with a user, and updated second measurement data indicative of an updated body shape parameter value associated with the user; determining, based on the at least one of the updated first measurement data and the updated second measurement data, an updated metabolic health score for the user; and causing the updated metabolic health score to be visually rendered via the display of the user device.

[0113] In some additional or alternative implementations, the method further includes: causing a first graphical user interface to be visually rendered via the display of the user device, wherein the first graphical user interface includes one or more interactive graphical elements to facilitate reception of the first measurement data and / or the second measurement data, and wherein causing the metabolic health score and the recommendation to be visually rendered via the display of the user device includes: causing a second graphical user interface to be visually rendered via the display of the user device, wherein the second graphical user interface includes one or more graphical elements indicative of the metabolic health score and the recommendation.

[0114] In some implementations, a method implemented by one or more processors is provided, and includes obtaining, by a wearable device, a metabolic health score for the user, wherein the metabolic health score is associated with the risk of metabolic syndrome given first measurement data indicative of a body fat percentage value associated with the user, and second measurement data indicative of a body shape parameter value associated with the user; obtaining, by the wearable device, a recommendation based on the determined metabolic health score, the recommendation corresponding to at least one remedial action to improve the metabolic health score for the user, wherein the at least one remedial action corresponds to an activity that is trackable by the wearablePCT / US24 / 56083 15 November 2024 (15.11.2024)device; and rendering, via a display of the wearable device, the metabolic health score and the recommendation.

[0115] In addition, some implementations include one or more processors (e.g., central processing unit(s) (CPU(s)), graphics processing unit(s) (GPU(s), and / or tensor processing unit(s) (TPU(s)) of one or more computing devices, where the one or more processors are operable to execute instructions stored in associated memory, and where the instructions are configured to cause performance of any of the aforementioned methods. Some implementations also include one or more computer readable storage media (e.g., transitory and / or non-transitory) storing computer instructions executable by one or more processors to perform any of the aforementioned methods. Some implementations also include a computer program product including instructions executable by one or more processors to perform any of the aforementioned methods.PCT / US24 / 56083 15 November 2024 (15.11.2024)Additional Disclosure

[0116] The technology discussed herein makes reference to servers, databases, software applications, and other computer-based systems, as well as actions performed by, and information sent to and from such systems. The inherent flexibility of computer-based systems allows for a great variety of possible configurations, combinations, and divisions of tasks and functionality between and among components. For instance, processes discussed herein can be implemented using a single device or component or multiple devices or components working in combination. Databases and applications can be implemented on a single system or distributed across multiple systems. Distributed components can operate sequentially or in parallel.

[0117] While the present subj ect matter has been described in detail with respect to various specific example embodiments thereof, each example is provided by way of explanation, not limitation of the disclosure. Those skilled in the art, upon attaining an understanding of the foregoing, can readily produce alterations to, variations of, and equivalents to such embodiments. Accordingly, the subject disclosure does not preclude inclusion of such modifications, variations and / or additions to the present subject matter as would be readily apparent to one of ordinary skill in the art. For instance, features illustrated or described as part of an embodiment can be used with another embodiment to yield a still further embodiment. Thus, it is intended that the present disclosure covers such alterations, variations, and equivalents.

Claims

PCT / US24 / 56083 15 November 2024 (15.11.2024)CLAIMSWhat is claimed is:

1. A computer-implemented method, comprising:receiving first measurement data indicative of a body fat percentage value associated with a user;receiving second measurement data indicative of a body shape parameter value associated with the user;determining, based at least in part on the first measurement data and the second measurement data, a metabolic health score for the user, wherein the metabolic health score is associated with a risk of metabolic syndrome given both the first measurement data and the second measurement data;generating, based at least in part on the determined metabolic health score, a recommendation corresponding to at least one remedial action to improve the determined metabolic health score; andcausing the metabolic health score and the recommendation to be visually rendered via a display of a user device.

2. The computer-implemented method of claim 1, wherein determining the metabolic health score for the user comprises:determining a risk value for the first measurement data and the second measurement data based on determining an intermediate risk value between a plurality of known risk values, wherein each known risk value is associated with a corresponding body fat percentage value and body shape parameter; anddetermining the metabolic health score for the user based on the determined risk value.

3. The computer-implemented method of claim 2, further comprising:obtaining a dataset, the dataset comprising, for each of a plurality of subsets of individuals in the dataset, (i) a set of body fat percentage values associated with the individuals in the subset, (ii) a set of body shape parameter values associated with thePCT / US24 / 56083 15 November 2024 (15.11.2024)individuals in the subset, and (iii) a corresponding subset risk value for metabolic syndrome for the subset of individuals, and wherein determining the intermediate risk value between the plurality of known risk values comprises:determining an intermediate subset risk value between a plurality of subset risk values from the dataset.

4. The computer-implemented method of claim 1, wherein determining the metabolic health score for the user comprises:processing, using a machine learning (ML) model, ML input to generate corresponding ML output, wherein the ML input comprises the first measurement data and the second measurement data; anddetermining, based on the ML output, the metabolic health score for the user.

5. The computer-implemented method of any one of the preceding claims, wherein the user device is a wearable device, and wherein the at least one remedial action corresponds to an activity that is trackable by the wearable device.

6. The computer-implemented method of claim 5, further comprising:causing a selectable graphical element to be visually rendered via the display of the wearable device, wherein the selectable graphical element is user selectable to initiate tracking of the activity by the wearable device.

7. The computer-implemented method of claim 5 or claim 6, further comprising:responsive to receiving an indication that the activity has been performed by the user, determining an updated metabolic health score, wherein the updated metabolic health score is determined based at least in part on the indication of the performance of the activity by the user and / or sensor data captured by one or more sensors of the wearable device during performance of the activity by the user; andcausing the updated metabolic health score to be visually rendered via the display of the wearable device.PCT / US24 / 56083 15 November 2024 (15.11.2024)8. The computer-implemented method of any one of the preceding claims, wherein generating the recommendation is further based on at least one of the first measurement data and the second measurement data, and wherein the recommendation is tailored to the at least one of the first measurement data and the second measurement data.

9. The computer-implemented method of any one of the preceding claims, wherein generating the recommendation is further based on historical behavioral data associated with the user and / or one or more other users.

10. The computer-implemented method of any one of the preceding claims, wherein receiving the first measurement data and / or receiving the second measurement data comprises:receiving information based on user input received by the user device, and / or receiving information from one or more computer systems associated with a third party.

11. The computer-implemented method of any one of the preceding claims, wherein receiving the first measurement data and / or receiving the second measurement data comprises:receiving information based on sensor data captured by one or more sensors of the user device and / or another device.

12. The computer-implemented method of claim 9, wherein the sensor data comprises image data captured by one or more cameras of the user device and / or another device.

13. The computer-implemented method of any one of the preceding claims, wherein the body shape parameter value comprises a measurement of at least one of:a visceral adipose tissue fat area,a subcutaneous adipose tissue fat area,a visceral to subcutaneous tissue ratio,a waist circumference,a waist circumference to height ratio, orPCT / US24 / 56083 15 November 2024 (15.11.2024)an android to gynoid ratio.

14. The computer-implemented method of any one of the preceding claims, wherein the body shape parameter value is a first body shape parameter value of a first body shape parameter type, the method further comprising:receiving third measurement data indicative of a second body shape parameter value associated with the user, the second body shape parameter value being of a second body shape parameter type different to the first body shape parameter type; andselecting from among the second measurement data and the third measurement data, the second measurement data to be used for determining the metabolic health score.

15. The computer-implemented method of claim 14, wherein selecting the second measurement data to be used for determining the metabolic health score is based on at least one of:a recency of the second measurement data,a confidence in the second measurement data,a sensitivity of the first body shape parameter type to performance of remedial actions,a sensitivity of the metabolic health score to a change in the first body shape parameter type, ora correlation between the first body shape parameter type and body fat percentage.

16. The computer-implemented method of any one of the preceding claims, further comprising:receiving fourth measurement data indicative of a measured attribute associated with the user, the measured attribute being different to a body fat percentage and a body shape parameter type of the body shape parameter value, wherein determining the metabolic health score for the user is further based on the fourth measurement data.

17. The computer-implemented method of claim 16, wherein the measured attribute comprises at least one of:PCT / US24 / 56083 15 November 2024 (15.11.2024)blood pressure information,blood sugar information,blood fat information,heart rate information, orweight information.

18. The computer-implemented method of any one of the preceding claims, wherein the metabolic health score for the user is part of a first health assessment procedure, the method further comprising:determining a time interval based at least in part on the determined metabolic health score for the user; andscheduling a second health assessment procedure to be performed after the time interval.

19. The computer-implemented method of any one of the preceding claims, further comprising:subsequently receiving at least one of: updated first measurement data indicative of an updated body fat percentage value associated with a user, and updated second measurement data indicative of an updated body shape parameter value associated with the user;determining, based on the at least one of the updated first measurement data and the updated second measurement data, an updated metabolic health score for the user; and causing the updated metabolic health score to be visually rendered via the display of the user device.

20. The computer-implemented method of any one of the preceding claims, further comprising:causing a first graphical user interface to be visually rendered via the display of the user device, wherein the first graphical user interface comprises one or more interactive graphical elements to facilitate reception of the first measurement data and / or the secondPCT / US24 / 56083 15 November 2024 (15.11.2024)measurement data, and wherein causing the metabolic health score and the recommendation to be visually rendered via the display of the user device comprises:causing a second graphical user interface to be visually rendered via the display of the user device, wherein the second graphical user interface comprises one or more graphical elements indicative of the metabolic health score and the recommendation.

21. A computer-implemented method compri sing :obtaining, by a wearable device, a metabolic health score for the user, wherein the metabolic health score is associated with the risk of metabolic syndrome given first measurement data indicative of a body fat percentage value associated with the user, and second measurement data indicative of a body shape parameter value associated with the user;obtaining, by the wearable device, a recommendation based on the determined metabolic health score, the recommendation corresponding to at least one remedial action to improve the metabolic health score for the user, wherein the at least one remedial action corresponds to an activity that is trackable by the wearable device; andrendering, via a display of the wearable device, the metabolic health score and the recommendation.

22. A system comprising one or more processors and a memory, the memory storing computer-readable instructions that, when executed by the one or more processors, cause the system to perform the computer-implemented method according to any one of claims 1 to 21.

23. A computer program product comprising computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the method of any one of claims 1 to 21.

Images