Systems and methods for generating a digital biomarker for knee and / or hip osteoarthritis

Abstract

Provided herein are systems and methods for creating and measuring digital biomarkers for knee and / or hip osteoarthritis, as well as systems and methods for using such biomarkers in the diagnosis, monitoring, and treatment of knee and / or hip osteoarthritis. In particular aspects, the systems and methods involve using at least one primary device comprising one or more capacitor-pressure sensors configured to generate raw gait data, and a remote processing device configured to generate one or more gait parameters for an individual based on the gait data, and apply one or more trained machine learning models to the gait parameters. In further aspects, systems and methods for training said machine learning models configured to generate a digital biomarker are also disclosed.

Description

SYSTEMS AND METHODS FOR GENERATING A DIGITAL BIOMARKER FOR KNEE AND / OR HIP OSTEOARTHRITISCross-Reference to Related Applications

[0001] This international application claims the benefit of U. S. Provisional Patent Application No.63 / 709,738, filed October 21, 2024, the disclosure of which is incorporated herein by reference in its entirety.Field of the Disclosure

[0002] The present disclosure relates generally to creating and measuring biomarkers for knee and / or hip osteoarthritis, and uses of such biomarkers for the diagnosis, monitoring, and treatment of knee and / or hip osteoarthritis.Background

[0003] Osteoarthritis (OA) is a prevalent medical condition which occurs when the protective cartilage that cushions the ends of bones wears down over time. When the cartilage that protects the surface of an individual’s joints get worn or damaged, additional friction is created in the joint which can result in pain, stiffness, loss of flexibility, bone spurs, and swelling among other symptoms. Osteoarthritis can affect any joint, but most commonly affects large weight-bearing joints such as the knee and hip.

[0004] Although osteoarthritis affects millions of people worldwide, the condition faces a challenge with a lack of an identified biomarker (i.e., an objective measure that captures a medical state) for osteoarthritis extent or severity. Though imaging and synovial fluid biomarkers are possible options, there has been no major progress to identify a consistently accurate and reproducible biomarker. For example, it has been documented in medical literature that traditional qualitative assessment methods, such as the Western Ontario and McMaster Universities Osteoarthritis Index’s (WOMAC), have been unable to provide distinct assessments of pain and function.Summary of the Disclosure

[0005] According to the present disclosure, provided are systems and methods capable of generating a digital biomarker that more accurately capture the disease state of knee and / or hip osteoarthritis in humans. In particular aspects, the systems and methods described are capable ofdetecting disease progression or regression. In further aspects, the systems and methods can be used as a diagnostic tool for measuring disease severity. In still further aspects, the systems and methods can be used to quantify drug efficacy for treatments, such as cartilage-modifying drug therapies.

[0006] According to one embodiment, a system for generating a digital biomarker for an individual with knee and / or hip osteoarthritis is provided. The system can include: at least one primary device comprising one or more capacitor-pressure sensors and configured to generate raw gait data; and a first remote processing device in communication with the at least one primary device and configured to analyze the raw gait data generated for the individual. The first remote processing device can include: a computer-readable storage medium having stored thereon computer-readable instructions to be executed by one or more processors; and one or more processors configured by the computer-readable instructions to perform the following operations: (i) receive the raw gait data generated by the one or more capacitor-pressure sensors of the at least one primary device; (ii) determine one or more gait parameters for the individual based at least in part on the raw gait data received; and (iii) apply one or more trained machine learning models to the one or more gait parameters to generate a digital biomarker for the individual.

[0007] In an aspect, the at least one primary device can be configured to be incorporated into an article to be worn on one or both feet of the individual.

[0008] In an aspect, the system can further include one or more secondary sensors configured to generate additional raw gait data, the one or more secondary sensors having at least one of an accelerometer, a gyroscope, and inertial measurement unit.

[0009] In an aspect, the one or more secondary sensors can be integrated into the at least one primary device.

[0010] In an aspect, one or more of the secondary sensors can be integrated into at least one secondary device in communication with at least the first remote processing device.

[0011] In an aspect, the at least one secondary device can be configured to be worn around one or both ankles and / or wrists of the individual.

[0012] In an aspect, the one or more processors of the first remote processing device can be further configured to perform the following operations: (i-b) receive the additional raw gait data generated by the one or more secondary sensors; and (ii-b) determine the one or more gait parameters for the individual based at least in part on the raw gait data and the additional raw gait data.

[0013] In an aspect, at least one of the one or more gait parameters can be based on a combination of the raw gait data generated by the one or more capacitor-pressure sensors of the at least one primary device and the additional raw gait data generated by the one or more secondary sensors.

[0014] In an aspect, the one or more machine learning models are trained by: generating at least one training dataset comprising raw gait data and / or additional raw gait data for a plurality of subjects; extracting gait parameters for each subject of the plurality of subjects based on the at least one training dataset; generating a reference dataset of gold standard measurements for the plurality of subjects; training the one or more machine learning models using at least a first portion of the at least one training dataset and at least a first portion of the reference dataset; and validating the trained one or more machine learning models using at least a second portion of the at least one training dataset and at least a second portion of the reference dataset.

[0015] In an aspect, the raw gait data can include a time-series of pressure locations and / or pressure amounts on the one or more capacitor-pressure sensors.

[0016] In an aspect, the additional raw gait data includes a time series of positional trajectories obtained from the individual.

[0017] In an aspect, the one or more gait parameters can include one or more of: a posture metric, a total walking time, a maximal time spent in a single walking sequence, a median stride velocity, a 95thpercentile stride velocity, a median stride length, a 95thpercentile stride length, a maximal 3-minute walking distance, a maximal distance walked in a single walking sequence, a percentage of stance duration over total stride duration, a stance duration, a swing duration, a step-speed asymmetry, a total number of stairs climbed per period of time, a median stair climbing or descending velocity, an 80thpercentile stair climbing or descending velocity, and a 95thpercentile stair climbing or descending velocity.

[0018] In an aspect, the digital biomarker can be indicative of a severity of knee and / or hip osteoarthritis in the individual.

[0019] In an aspect, the one or more processors can be further configured to perform the following operations: (v) evaluate a condition or a change in the condition of the individual by: (a) performing steps (i)-(iv) to generate a first digital biomarker for the individual based on data collected over a first period of time; (b) performing steps (i)-(iv) to generate a second digital biomarker for the individual based on data collected over a second period of time different from the first period of time; and (c) determining a condition of the individual and / or a change in the condition of the individual based on at least the first and second digital biomarkers.

[0020] According to another embodiment, a method for generating a digital biomarker for an individual with knee and / or hip osteoarthritis is provided. The method can include: generating, using one or more capacitor-pressure sensors of at least one primary device, raw gait data for the individual; receiving, at a first remote processing device, the raw gait data generated for the individual; determining, using one or more processors of the first remote processing device, one or more gaitparameters for the individual based at least in part on the raw gait data; and applying one or more trained machine learning models to the one or more gait parameters to generate a digital biomarker for the individual.

[0021] In an aspect, the method can further include: generating, using one or more secondary sensors, additional raw gait data for the individual, wherein the one or more secondary sensors include at least one of an accelerometer, a gyroscope, and inertial measurement unit; receiving, at the first remote processing device, the additional raw gait data generated for the individual; and determining, using the one or more processors of the first remote processing device, the one or more gait parameters based at least in part on the raw gait data and the additional raw gait data.

[0022] In an aspect, the one or more of the secondary sensors can be integrated into at least one secondary device in communication with at least the first remote processing device.

[0023] In an aspect, the raw gait data and / or the additional raw gait data can be generated over a multi-stage generation phase comprising: (a) a first assessment wherein the raw gait data and / or the additional raw gait data is generated while the individual is freely walking; (b) a second assessment wherein the raw gait data and / or the additional raw gait data is generated while the individual is walking during a fixed time and / or for a fixed distance; (c) a third assessment wherein the raw gait data and / or the additional raw gait data is generated during an timed up-and-go (TUG) movement; and (d) a fourth assessment wherein the raw gait data and / or the additional raw gait data is generated during a postural test.

[0024] In an aspect, the raw gait data can include a time-series of pressure locations and / or pressure amounts on the one or more capacitor-pressure sensors, and the additional raw gait data can include a time series of positional trajectories obtained from the individual.

[0025] According to still another embodiment, a non-transitory computer-readable storage medium having stored thereon computer-readable instructions is provided. When executed by one or more processors, the computer-readable instructions cause the one or more processors to perform operations comprising: generating, using one or more capacitor-pressure sensors of at least one primary device, raw gait data for the individual; receiving, at a first remote processing device, the raw gait data generated for the individual; determining, using one or more processors of the first remote processing device, one or more gait parameters for the individual based at least in part on the raw gait data; and applying one or more trained machine learning models to the one or more gait parameters to generate a digital biomarker for the individual.

[0026] These and other aspects of the various embodiments will be apparent from and elucidated with reference to the embodiments described hereinafter.Brief Description of the Drawings

[0027] In the drawings, like reference characters generally refer to the same parts throughout the different views. Also, the drawings are not necessarily to scale, emphasis instead generally being placed upon illustrating the principles of the various embodiments.

[0028] FIG. l is a diagram illustrating a system for generating a digital biomarker for an individual with knee and / or hip osteoarthritis according to aspects of the present disclosure.

[0029] FIG. 2A is a cross-sectional view of a primary device illustrated in accordance with aspects of the present disclosure.

[0030] FIG. 2B is a side view of a secondary device illustrated in accordance with aspects of the present disclosure.

[0031] FIG. 3A is a block diagram of a primary device illustrated in accordance with aspects of the present disclosure.

[0032] FIG. 3B is a block diagram of a secondary device illustrated in accordance with aspects of the present disclosure.

[0033] FIG. 4 is a block diagram of a remote processing device illustrated in accordance with aspects of the present disclosure.

[0034] FIG. 5 is a flowchart illustrating a method of generating a digital biomarker for an individual with knee and / or hip osteoarthritis according to aspects of the present disclosure.

[0035] FIG. 6 is a flowchart illustrating a method of training one or more machine learning algorithms in accordance with aspects of the present disclosure.

[0036] FIG. 7 is a diagram illustrating the use of the present systems and methods in accordance with various aspects of the present disclosure.Detailed Description of Embodiments

[0037] As mentioned above, the present disclosure is directed to systems and methods of creating and measuring biomarkers for knee and / or hip osteoarthritis, as well as to the uses of such biomarkers for the diagnosis, monitoring, and treatment of knee and / or hip osteoarthritis. The systems and methods described herein provide a more accurate measure of the disease state of knee and / or hip osteoarthritis in humans, which improves upon the inconsistent and inaccurate metrics traditionally used in the art. In particular aspects, the systems and methods described herein provide a digital biomarker that can be used to evidence improvements in mobility, physical function, and / or pain levels in connection with knee and / or hip osteoarthritis.

[0038] Turning to FIG. 1, an exemplary system 100 for generating a digital biomarker for an individual 102 suffering from knee and / or hip osteoarthritis is illustrated in accordance with various aspects of the present disclosure. As shown, the system 100 may include at least one primary device 104 configured to generate raw gait data for the individual 102. In embodiments, the one or more primary devices 104 may comprise one or more capacitor-pressure sensors (not shown) that are used to generate raw gait data. The system 100 may also include one or more secondary devices 106 configured to generate additional raw gait data. The system 100 may also include one or more remote processing devices 108 in communication with each of the primary and secondary devices 104, 106. As described in more detail below, the one or more remote processing devices 108 may be configured to receive raw gait data and additional raw gait data from the primary and secondary devices 104, 106, and to generate a digital biomarker for the individual 102 associated with the primary and secondary devices 104, 106.

[0039] In embodiments, each of the one or more primary devices 104 may be configured to be incorporated into an article to be worn by the individual 102. In other embodiments, the primary device(s) 104 may be the wearable article itself. For example, as shown in FIG. 2 A, the primary device 104 may be a shoe 202 and / or a shoe insole 204 that incorporate the one or more capacitorpressure sensors 206. In particular embodiments, the one or more pressure sensors 206 may be provided separately from the shoe 202 and / or shoe insole 204, but are configured to be positioned within the shoe 202 and / or shoe insole 204. In certain embodiments, the shoe 202 and / or shoe insole 204 may have one or more recesses configured to receive the one or more pressure sensors 206.

[0040] In embodiments, each primary device 104 can be configured to generate raw gait data using the one or more capacitor-pressure sensors 206 disposed therein. Accordingly, in embodiments, the raw gait data can include pressure locations and / or pressure amounts obtained from the one or more capacitor-pressure sensors 206. In particular embodiments, the raw gait data can include pressure location measurements and / or pressure amount measurements obtained at a sampling frequency over a period of time (i.e., the raw gait data may include a time-series of pressure locations and / or pressure amounts). For example, each of the sensors 206 of the primary device(s) 104 may take a certain number of samples per second, including from about 1 sample per second to about 1000 samples per second.

[0041] As described herein, the terms “pressure location” and “pressure location measurement” refer to whether the particular sensor 206 detects an amount of pressure above a certain threshold at a particular location and / or orientation. For example, in some embodiments, the primary device 104 may be a shoe insole 204 having a first pressure sensor 206A located towards the front of the shoe 202 and a second pressure sensor 206B located towards the back of the shoe 202, each of whichmeasure whether the foot of the individual 102 is applying more than a baseline amount of pressure on. If, for example, the individual 102 is standing still, both of the pressure sensors 206A, 206B of the first device 104 will register pressure is present at each location. However, if the individual 102 is walking, one or both of the pressure sensors 206 A, 206B of the first device 104 may or may not register pressure present at either location, depending on the gait phase, walking speed, and / or the like.

[0042] In embodiments, each of the one or more secondary devices 106 may include one or more secondary sensors (not shown) configured to generate additional raw gait data In certain embodiments, these secondary sensors may be configured to be incorporated into an article to be worn by the individual 102. In some embodiments, one or more of the secondary sensors may be incorporated into the primary device(s) 104, or may be incorporated into a separate article to be worn by the individual 102 at a different location than the primary device(s) 104. For example, as shown in FIG. 2B, the secondary sensors (not shown) may be incorporated into a bracelet or band 210 that is worn around the individual’s 102 ankle or wrist. However, it should be appreciated that the secondary device(s) 210 may be positioned at other locations, such as on one or both wrists of the individual 102.

[0043] The secondary sensors can include, but are not limited to, one or more of an accelerometer, a gyroscope, and / or an inertial measurement unit. Accordingly, in embodiments, the additional raw gait data generated by the one or more secondary sensors may include measurements from one or more of these sensors. In particular embodiments, the additional raw gait data can include a series of positional trajectories (relative x,y,z spatial movements) obtained from the individual 102. For example, the additional raw gait data may represent spatial movements over time (i.e., a time series of spatial movements).

[0044] With reference to FIGS. 3A and 3B, block diagrams of the primary and secondary devices 104, 106 are illustrated in accordance with further aspects of the present disclosure. Turning to FIG.3 A, in addition to containing one or more primary sensors 206, each primary device 104 may include one or more processors 302 A, a receiver / transceiver 304 A, an input / output interface 306 A, an internal power source 308 A, a memory device 310A. With reference to FIG. 3B, in addition to containing one or more secondary sensors 206, each secondary device 104 may include one or more processors 302B, a receiver / transceiver 304B, an input / output interface 306B, an internal power source 308B, a memory device 310B.

[0045] In the example of FIGS. 3A and 3B, the one or more processors 302A may include a microprocessor, a multi-core processor, a multithreaded processor, an ultra-low voltage processor, an embedded processor, a digital signal processor (DSP), an application-specific system processor(ASSP), an application-specific instruction set processor (ASIP), and application-specific integrated circuit (ASIC) processor, and / or the like, including combinations thereof. The one or more processors 302A, 302B can include multiple processor cores on a single die and / or may be a part of a system on a chip (SoC) in which the processor 302 A, 302B and other components are formed into a single integrated circuit, or a single package. That is, the one or more processors 302A, 302B may be a single processor, multiple independent processors, or multiple processor cores on a single die.

[0046] In embodiments, the receiver / transceiver 304 A, 304B of each device 104, 106 can include one or more types of networking interfaces that facilitate wired and / or wireless communication between the devices 104, 106 and one or more external devices, such as the remote processing device 108. That is, the receiver / transceiver 304A, 304B may operatively connect the devices 104, 106 to one or more types of communications networks 216, which can include a direction interconnection, the Internet, a local area network (“LAN”), a metropolitan area network (“MAN”), a wide area network (“WAN”), a wired or Ethernet connection, a wireless connection, a cellular network, a short-range communication network such as Bluetooth, and / or similar types of communications networks, including combinations thereof. In particular embodiments, the receiver / transceivers 304 A, 304B comprise a specialized radio-frequency (RF) antenna configured to receive and / or transmit signals to another device wirelessly.

[0047] In embodiments, the input / output (I / O) interfaces 306A, 306B may be configured to connect and / or enable communication with one or more peripheral devices (not shown), including but not limited to additional machine-readable memory devices, diagnostic equipment, and other attachable devices. The EO interfaces 306 A, 306B may include one or more EO ports that provide a physical connection to the one or more peripheral devices. In some embodiments, the EO interface 306A, 306B may include one or more serial ports, USB ports, and / or the like.

[0048] In embodiments, the internal power sources 308A, 308B can be a wearable energy storage device, including but not limited to, aqueous or non-aqueous batteries, lithium-ion batteries, sodium-ion batteries, zinc-ion batteries, lithium-sulfur batteries, capacitors and / or supercapacitors (e.g., GCF, PVA, GCF / MnCh), and / or the like, including combinations thereof. In particular embodiments, the internal power sources 308 A, 308B may be rechargeable.

[0049] In embodiments, the primary and secondary devices 104, 106 can also include one or more types of machine-readable memory 310A, 310B. The memory 310A, 310B can include, non-transitory computer-readable memory, or may include one or more other types of memory, such as dynamic random-access memory (DRAM), static random-access memory (SRAM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), Flash memory, and / or the like, as well as combinations thereof. In embodiments, thememory 310 A, 310B can be configured to store instructions for generating gait data or additional gait data, and for transmitting such information to one or more remote processing devices 108. In further embodiments, the memory 310A, 310B can be configured to store a certain amount of gait data and / or additional gait data prior to transmitting the information to the remote processing devices 108.

[0050] As described above, the primary and secondary devices 104, 106 can each include one or more sensors 206, 312. In embodiments, the sensors 206 of the primary device(s) 104 are capacitorpressure sensors configured to generate raw gait data in the form of pressure locations and / or pressure amounts. In further embodiments, the sensors 312 of the secondary device(s) can include at least one of an accelerometer, a gyroscope, and inertial measurement unit. The secondary sensors 312 may be incorporated into a secondary device 106 as shown in FIG. 2B and FIG. 3B, but may alternatively be incorporated into the primary device 104.

[0051] Returning to FIG. 1, each of the primary and secondary device(s) 104, 106 may be in direct and / or indirect communication with one or more remote processing devices 108. As mentioned above, the primary and secondary devices 104, 106 may be physically connected to the remote processing device 108 via one or more wired connections, and / or wirelessly connected to the remote processing device 108 via one or more wireless connections. The one or more remote processing device 108 of the system 100 is configured to (i) receive raw gait data 110 from the primary device(s) 104, and (i-b) to receive additional raw gait data 112 from the secondary device(s) 106 over these communication channels.

[0052] In embodiments, the one or more remote processing devices 108 of the system 100 are further configured to: (ii) determine one or more gait parameters for the individual 102 based at least in part on the raw gait data 110 received; (ii-b) determine one or more for the individual 102 based at least in part on the raw gait data 110 and the additional raw gait data 112; (iii) apply one or more trained machine learning models to the one or more gait parameters to generate a digital biomarker for the individual 102; and (iv) store the raw gait data 110, the additional raw gait data 112, the gait parameters, and / or the digital biomarker generated for the individual 102 in a computer-readable storage medium.

[0053] With reference to FIG. 4, an exemplary remote processing device 108 is illustrated in accordance with various aspects of the present disclosure. Although a single remote processing device 108 is shown, it should be appreciated that one or more portions of the functionality may be distributed across several such devices. In the example of FIG. 4, the remote processing device 108 can include one or more processors 402 and a computer-readable memory 404 interconnected and / or in communication via a system bus 406 containing conductive circuit pathways through which instructions (e.g., machine-readable signals) may travel to effectuate communication, tasks, storage,and the like. The remote processing device 108 can be connected to a power source (not shown), which can include an internal power supply and / or an external power supply. In embodiments, the remote processing device 108 can also include one or more additional components, such as a user interface 408, a display 410, an input / output (I / O) interface 412, a networking unit 414, and the like, including combinations thereof. As shown, each of these components may be interconnected and / or in communication via the system bus 406, for example.

[0054] In embodiments, the one or more processors 402 can include one or more high-speed data processors adequate to execute the program components described herein and / or perform one or more operations of the methods described herein. The one or more processors 402 may include a microprocessor, a multi-core processor, a multithreaded processor, an ultra-low voltage processor, an embedded processor, a central processing unit (CPU), a graphics processing unit (GPU), and / or the like, including combinations thereof. The one or more processors 402 can include multiple processor cores on a single die and / or may be a part of a system on a chip (SoC) in which the processor 402 and other components are formed into a single integrated circuit, or a single package. That is, the one or more processors 402 may be a single processor, multiple independent processors, or multiple processor cores on a single die.

[0055] In embodiments, the user interface 408 may be configured to receive various forms of input from a user associated with the remote processing device 108. The user interface 408 can include, but is not limited to, one or more of a keyboard, keypad, trackpad, trackball(s), capacitive keyboard, controller (e.g., a gaming controller), computer mouse, computer stylus / pen, a voice input device, and / or the like, including combinations thereof.

[0056] In embodiments, the display device 410 may be configured to display information, including text, graphs, and / or the like. In particular embodiments, the display device 410 may be configured to display gait information and digital biomarkers as described herein. The display device 410 can include, but is not limited to, a liquid crystal display (LCD), a light-emitting diode (LED) display, a touch screen or other touch-enabled display, a foldable display, a projection display, and so on, or combinations thereof.

[0057] In embodiments, the input / output (I / O) interface 412 may be configured to connect and / or enable communication with one or more external devices, including but not limited to additional machine-readable memory devices, diagnostic equipment, and other attachable devices (e.g., primary and / or secondary device 104, 106). The EO interface 412 may include one or more EO ports that provide a physical connection to the one or more peripheral devices. In some embodiments, the EO interface 412 may include one or more serial ports.

[0058] In embodiments, the networking unit 414 may include one or more types of networking interfaces that facilitate wired and / or wireless communication between the remote processing device 108 and one or more external devices (e.g., primary and / or secondary device 104, 106). That is, the networking unit 414 may operatively connect the remote processing device 108 to one or more types of communications networks 416, which can include a direction interconnection, the Internet, a local area network (“LAN”), a metropolitan area network (“MAN”), a wide area network (“WAN”), a wired or Ethernet connection, a Bluetooth connection, a wireless connection, a cellular network, and similar types of communications networks, including combinations thereof. In some embodiments, the remote processing device 108 may communicate with one or more remote / cloud-based servers and / or cloud-based services, such as remote server 418, via the communications network 416. In embodiments, these remote / cloud-based servers and / or cloud-based services may be used to store and / or process gait information and digital biomarkers as described herein.

[0059] In embodiments, the memory 404 can be variously embodied in one or more forms of machine-accessible and machine-readable memory. In some embodiments, the memory 404 includes a storage device (not shown), which can include, but is not limited to, a non-transitory storage medium, a magnetic disk storage, an optical disk storage, an array of storage devices, a solid-state memory device, and / or the like, as well as combinations thereof. The memory 404 may also include one or more other types of memory, such as dynamic random-access memory (DRAM), static random-access memory (SRAM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), Flash memory, and / or the like, as well as combinations thereof. In embodiments, the memory 404 may include one or more types of transitory and / or non-transitory memory.

[0060] The remote processing device 108 can be configured by software components stored in the memory 404 to perform one or more processes of the methods described herein. More specifically, the memory 404 can be configured to store data / information 420 and computer-readable instructions 422 that, when executed by the one or more processors 402, causes the remote processing device 108 to generate digital biomarkers for individuals with knee and / or hip osteoarthritis as described herein. Such data 420 and the computer-readable instructions 422 stored in the memory 404 may form a digital biomarker package 424 that may be incorporated into, loaded from, loaded onto, or otherwise operatively available to and from the remote processing device 108. Thus, in some embodiments, the digital biomarker package 224 and / or one or more individual software packages may be stored in a local storage device of the memory 404. However, in other embodiments, the digital biomarker package 424 and / or one or more individual software packages may be loaded onto and / or updated from a remote server or service, such as server 418, via the communications network 416.

[0061] The remote processing device 108 may also include an operating system component 426, which may be stored in the memory 404. The operating system component 426 may be an executable program facilitating the operation of the remote processing device 108. Typically, the operating system component 426 can facilitate access of the I / O interface 412, network interface 414, the user interface 408, and the display 410, and can communicate or control other components of the remote processing device 108.

[0062] Accordingly, provided herein is a computer program product 424 comprising a non-transitory computer-readable storage medium 404 having stored thereon computer-readable instructions 422 that, when executed by one or more processors (such as processors 402), cause the one or more processors to perform one or more operations of the methods described below. For example, in specific embodiments, the computer-readable storage medium 404 may include computer-readable instructions 422 that, when executed by one or more processors (such as processors 402), cause the one or more processors to perform one or more of the following operations: (i) receive raw gait data 110 from the primary device(s) 104; (i-b) to receive additional raw gait data 112 from the secondary device(s) 106 over these communication channels; (ii) determine one or more gait parameters for the individual 102 based at least in part on the raw gait data 110 received; (ii-b) determine one or more for the individual 102 based at least in part on the raw gait data 110 and the additional raw gait data 112; (iii) apply one or more trained machine learning models to the one or more gait parameters to generate a digital biomarker for the individual 102; and / or (iv) store the raw gait data 110, the additional raw gait data 112, the gait parameters, and / or the digital biomarker generated for the individual 102 in a computer-readable storage medium.

[0063] More particularly, the computer-readable storage medium 404 can include computer-readable instructions 422 that, when executed by one or more processors (such as processors 402), cause the one or more processors to perform a method for generating a digital biomarker for an individual with knee and / or hip osteoarthritis in accordance with the various aspects described herein.

[0064] For example, with reference to FIG. 5, a method 500 for generating a digital biomarker for an individual with knee and / or hip osteoarthritis is illustrated in accordance with certain aspects of the present disclosure. As shown, the method 500 can include: in a step 510, generating raw gait data 110, 112 using one or more sensors / devices; in a step 520, determining one or more gait parameters based on the raw gait data 110, 112; and in a step 530, generating a digital biomarker for the individual by applying one or more trained machine learning models to the one or more gait parameters.

[0065] As described in more detail below, the one or more trained machine learning models may be trained using training datasets including data generated using a gait imaging system, but the digital biomarker itself is generated for an individual based on gait data that does not include gait imagingdata for the individual (i.e., based only on the gait information 110, 112). As such, the digital biomarkers described herein can advantageously be generated in a variety of settings (e.g., outside of a specialized laboratory) and without the need for complex setups including expensive imaging equipment. This enables patients with mobility -limiting knee and / or hip osteoarthritis greater access to diagnostic and patient monitoring services, in addition to providing a more accurate metric for disease status. Further, as described herein, the digital biomarker can be indicative of (1) a severity, (2) mobility, (3) physical function, and / or (4) pain levels in connection with knee and / or hip osteoarthritis.

[0066] According to step 510 of the method 500, raw gait data 110, 112 is generated using one or more sensors and / or devices of a gait measurement system (e.g., system 100, etc.). In embodiments, the gait measurement system 100 can include one or more primary devices 104 and one or more secondary devices 106. Each of the primary devices 104 can include one or more capacitor-pressure sensors 206, which may be incorporated into, for example, a shoe 202 or a portion of a shoe 202 (such as a shoe insole 204). As such, the primary devices 104 can be wearable devices that are configured to be worn by the individual on their feet.

[0067] In further embodiments, the one or more secondary devices 106 can include one or more secondary sensors (not shown), including at least one of an accelerometer, a gyroscope, and / or an inertial measurement unit. The secondary devices 106 may also be wearable devices that are configured to be worn by the individual. In embodiments, the secondary devices 106 may be incorporated into the same article as the primary device 104, or may be worn separately by the individual on their ankle, wrist, or other body part.

[0068] In embodiments, each primary device 104 can be configured to generate raw gait data 110 using the one or more capacitor-pressure sensors 206 disposed therein. Accordingly, in embodiments, the raw gait data can include pressure locations and / or pressure amounts obtained from the one or more capacitor-pressure sensors 206. In particular embodiments, the raw gait data 110 can include pressure location measurements and / or pressure amount measurements obtained at a sampling frequency over a period of time (i.e., the raw gait data 110 may include a time-series of pressure locations and / or pressure amounts). For example, each of the sensors 206 of the primary device(s) 104 may take a certain number of samples per second, including from about 1 sample per second to about 1000 samples per second.

[0069] In embodiments, each secondary device 106 can be configured to generate additional raw gait data 112 using the one or more secondary sensors. In particular embodiments, the additional raw gait data 112 can include a series of positional trajectories (relative x,y,z spatial movements) obtainedfrom the individual 102. For example, the additional raw gait data 112 may represent spatial movements overtime (i.e., a time series of spatial movements).

[0070] In particular embodiments, the raw gait data 110 and / or the additional raw gait data 112 can be generated over a multi-stage assessment. That is, in embodiments, the individual 102 may be instructed to perform a multi-stage assessment while wearing the primary and / or secondary devices 104, 106. In embodiments, the multi-stage assessment can include one or more of the following assessments. In a first assessment, raw gait data 110 and / or additional raw gait data 112 is generated while the individual 102 is freely walking. In a second assessment, raw gait data 110 and / or additional raw gait data 112 is generated while the individual 102 is walking during a fixed time and / or for a fixed distance. In a third assessment, raw gait data 110 and / or additional raw gait data 112 is generated during a timed up-and-go (TUG) movement. In a fourth assessment, raw gait data 110 and / or additional raw gait data 112 is generated during a postural test.

[0071] According to step 520, the method 500 can then include synthesizing and generating one or more gait parameters based on the raw gait data 110 and / or the additional raw gait data 112. In embodiments, one or more of the gait parameters may be based on either of the raw gait data 110 or the additional raw gait data 112. In further embodiments, one or more of the gait parameters may be based on a synthesis or a combination of the gait data 110, 112 collected by different devices 104, 106.

[0072] In specific embodiments, the one or more gait parameters can include: a posture metric, a total walking time, a maximal time spent in a single walking sequence, a median stride velocity, a 95thpercentile stride velocity, a median stride length, a 95thpercentile stride length, a maximal 3-minute walking distance, a maximal distance walked in a single walking sequence, a percentage of stance duration over total stride duration, a stance duration, a swing duration, a step-speed asymmetry, a total number of stairs climbed per period of time, a median stair climbing or descending velocity, an 80thpercentile stair climbing or descending velocity, a 95thpercentile stair climbing or descending velocity, and / or the like. In certain embodiments, other measures related to assessments such as getting up time, standing up time from sitting, assessments noted in the TUG test (timed up and go) may be utilized, as well as other measures related to physical activity.

[0073] In embodiments, the one or more gait parameters can include a plurality of such gait parameters. In further embodiments, the one or more gait parameters can include multiple of the same type of gait parameter specific to two or more different mobility assessments, examples of which are described above.

[0074] According to step 530, the method 500 can then include generating a digital biomarker for the individual 102 by applying one or more trained machine learning models to the one or more gaitparameters. In embodiments, the machine learning model may comprise a recurrent neural network such as a long short term memory network (LSTM), a deep learning algorithm such as a convolutional neural network (CNN), a hybrid CNN-transformer network, and / or the like, including an ensemble of such networks. One or more of the machine learning models may be supervised, semi-supervised, or unsupervised.

[0075] In embodiments, the one or more trained machine learning models may be configured to generate a digital biomarker that is indicative of the likelihood that an individual 102 has knee and / or hip osteoarthritis. In further embodiments, the one or more trained machine learning models may be configured to generate a digital biomarker that is indicative of the severity of the knee and / or hip osteoarthritis in the individual 102. In still further embodiments, the digital biomarker may be normalized based on the posture, age, and / or BMI of the individual 102 to produce a mobility index, which can be compared to other patients.

[0076] As mentioned above, the one or more trained machine learning models may be trained to generate a digital biomarker for knee and / or hip osteoarthritis-related physical function. As such, also provided herein are systems and methods of training such machine learning models. For example, with reference to FIG. 6, a method 600 for training the one or more machine learning models is illustrated according to the present disclosure. As shown, the method 600 can include: in a step 610, generating at least one training dataset comprising gait data (e.g., raw gait data and / or additional raw gait data) for a plurality of subjects; in a step 615, extracting gait parameters for each subject based on the corresponding gait data; in a step 620, generating a reference dataset of gold standard measurements for the plurality of subjects; in a step 630, training the one or more machine learning models using some or all of the training and reference datasets; and in a step 640, the one or more trained machine learning models may undergo validation.

[0077] More specifically, in the step 610, the method 600 can include generating at least one training dataset comprising gait data, including raw gait data 110 and / or additional raw gait data 112, using one or more primary devices 104 or secondary devices 106. In embodiments, each of the subjects are monitored using a primary and / or secondary device 104, 106 configured to generate the gait data 110, 112.

[0078] It should be appreciated that various data generation schemes may be used that employ different devices and / or combinations of devices. As such, the one or more machine learning models trained in accordance with the present disclosure may be unique or customized to a particular device or combination of devices. That is, it should be appreciated that each subject may utilize the same combination of device types. For example, the training dataset may include gait data generated using shoe insoles sensors only, shoe insoles in combination with one or more wrist IMUs, two ankle IMUs,two ankle IMUs in combination with one or more wrist IMUs, shoe insole sensors in combination with one or more ankle sensors, and / or the like.

[0079] In particular embodiments, the raw gait data 110 generated by each primary device 104 can include pressure location measurements and / or pressure amount measurements obtained at a sampling frequency over a period of time (i.e., the raw gait data may include a time-series of pressure locations and / or pressure amounts). The additional raw gait data 112 generated by each secondary device 106 can include a series of positional trajectories (relative x,y,z spatial movements) obtained from the subject.

[0080] In certain embodiments, the gait data 110, 112 may be generated over a multi -phase data collection stage, wherein each subject is monitored using the primary and / or secondary devices 104, 106 while performing specific movement-related tasks. For example, the multi-phase data collection stage can include three assessment parts: (1) a free-walking measurements; (2) task assessments; and (3) postural assessment. In embodiments, the task assessments can include walking during a fixed time or a fixed distance (20m or 6MWT), a timed up-and-go (TUG) assessment, and / or the like.

[0081] In embodiments, the method 600 may then include, in a step 615, extracting a plurality of gait parameters for each subject based on their corresponding gait data 110, 112. The gait parameters may be based on one or both types of gait data 110, 112 of the training dataset. In specific embodiments, the one or more gait parameters can include: a posture metric, a total walking time, a maximal time spent in a single walking sequence, a median stride velocity, a 95thpercentile stride velocity, a median stride length, a 95thpercentile stride length, a maximal 3-minute walking distance, a maximal distance walked in a single walking sequence, a percentage of stance duration over total stride duration, a stance duration, a swing duration, a step-speed asymmetry, a total number of stairs climbed per period of time, a median stair climbing or descending velocity, an 80thpercentile stair climbing or descending velocity, a 95thpercentile stair climbing or descending velocity, and / or the like. In embodiments, the one or more gait parameters can include a plurality of such gait parameters. In further embodiments, the one or more gait parameters can include multiple of the same type of gait parameter specific to two or more different mobility assessments, examples of which are described above.

[0082] The method 600 may also include, in a step 620, a reference dataset of gold standard mobility measurements for each of the plurality of subjects. For example, the gold standard mobility measurements may be generated using a video- or camera-based system (e.g., a Vicon™ system), as well as a pressure-sensitive walkway system (e.g., a GAITRite® system). In embodiments, the gold standard mobility measurements may also be generated using one of the “gold standard” systems over a multi-phase data collection stage, examples of which are described above. It should be appreciatedthat the gold standard mobility measurements may be generated before, after, or concurrently with the gait data (e.g., gait data 110, 112). In other words, the data of the training and reference datasets may be generated before, after, or concurrently with one another for each subject.

[0083] After the training and reference datasets are generated, the method 600 may then include, in a step 630, training the one or more machine learning models using some or all of the training and reference datasets. In particular embodiments, a first subset of the training and reference datasets are used to train the one or more machine learning models. The first subsets may include corresponding subject entries for a certain percentage of the overall dataset. For example, the first subsets may include from about 50% to about 90% of the entries in the training dataset and the corresponding entries from the reference dataset. In particular embodiments, feature-selection machine learning methods are used to identified relevant gait parameters, which are then classified and a composite measure is generated according to the most sensitive metrics identified in subjects with osteoarthritis.

[0084] In a step 640, the one or more trained machine learning models may then undergo validation. For example, in embodiments, a second subset of the training and reference datasets may be used to verify and validate the composite measurements generated by the one or more machine learning models. The second subsets may include corresponding subject entries for a certain percentage of the overall dataset. For example, the second subsets may include from about 10% to about 50% of the entries in the training dataset and the corresponding entries from the reference dataset. In embodiments, the first and second subsets of the training and reference datasets may be mutually exclusive (i.e., there is no overlap between the data of the first subset and the data of the second subset). In further embodiments, the entries of the first and second subsets may be randomly selected from the overall datasets. In still further embodiments, more than one validation subset may be created.

[0085] In particular embodiments, the validation step 640 may include applying the trained machine learning models to only the second subset of the training dataset in order to generate a composite measure, which may then be compared with a reference mobility metric generated based on the data of the second subset of the reference dataset.

[0086] In accordance with various aspects of the present disclosure, the systems and methods described herein can be utilized to detect disease progression / regression, monitor the severity of disease, and quantify drug efficacy for various treatments in individuals with knee and / or hip osteoarthritis. Put another way, the systems and methods of the present disclosure provide more accurate and reproducible biomarkers for knee and / or hip osteoarthritis, improves disease monitoring, expands access to affordable monitoring, and improves osteoarthritis treatment planning.

[0087] For example, with reference to FIG. 7, the method 500 described herein may be repeated at various points in time with respect to an individual 102 having knee and / or hip osteoarthritis. As shown, a first digital biomarker may be generated for an individual 102 at a first point in time in a step 710, which includes performing the steps of method 500. After a period of time, a second digital biomarker may be generated for the individual 102 in a step 720, which includes performing the steps of method 500 again. As described herein the gait data 110, 112 generated at these various steps 710, 720, 730 may be stored along with the generated gait parameters and / or digital biomarkers, for example, in the memory 404 of a remote processing device 108 or another data repository.

[0088] Based on the first and second digital biomarkers generated in steps 710, 720, the systems and methods described herein may determine a condition of the individual 102 and / or a change in the condition of the individual 102. In particular embodiments, a pharmaceutical therapy may be started and / or changed based on the first and second digital biomarkers generated in steps 710, 720. In specific embodiments, the pharmaceutical therapy can include administering an effective dosage of a structure-modifying compound or otherwise changing / modifying the dosage of such compounds, as well as changing the length of treatment or frequency of dosage administration.

[0089] It should be appreciated that the raw gait data 110 and the additional raw gait data 112 generated in the step 710 are generated at a time proximate to the first point in time (e.g., over a first measurement period 712), while the raw gait data 110 and the additional raw gait data 112 generated in the step 720 are generated at a time proximate to the second point in time (e.g., over a second measurement period 722), and therefore these datasets are different / non-overlapping.

[0090] It should also be appreciated that this process may be repeated any number of times to generate, for example, at least a third digital biomarker (in a step 730) based on measurements over a third measurement period 732. Because the systems and methods do not require elaborate equipment arrangements such as multiple cameras or pressure-monitoring flooring, the systems and methods of the present disclosure can be implemented in a variety of settings and may be utilized more frequently as needed.

[0091] As described above, various combinations of specialized devices and sensors for generating and detecting motion-related information (e.g., gait data) are disclosed. Although particular emphasis is placed on certain devices and combinations of devices, it should be appreciated that other devices and combinations of devices may be utilized to generate one or more trained machine learning models that are specific to said devices and / or combinations of devices. For example, according to various embodiments, motion-related information can be generated using shoe insoles sensors only, shoe insoles in combination with one or more wrist IMUs, two ankle IMUs, two ankle IMUs in combination with one or more wrist IMUs, shoe insole sensors in combination withone or more ankle sensors, and / or the like. As such, for each combination of devices, one or more specialized machine learning models may be developed that are specific to said combination of devices.

[0092] It should be appreciated that all combinations of the foregoing concepts and additional concepts discussed in greater detail below (provided such concepts are not mutually inconsistent) are contemplated as being part of the inventive subject matter disclosed herein. In particular, all combinations of claimed subject matter appearing at the end of this disclosure are contemplated as being part of the inventive subject matter disclosed herein. It should also be appreciated that terminology explicitly employed herein that also may appear in any disclosure incorporated by reference should be accorded a meaning most consistent with the particular concepts disclosed herein.

[0093] All definitions, as defined and used herein, should be understood to control over dictionary definitions, definitions in documents incorporated by reference, and / or ordinary meanings of the defined terms.

[0094] The terms “individual”, “patient”, and “subject” are used herein synonymously and interchangeably unless otherwise specified explicitly or implicitly by the context of its use. In various examples, these terms may refer to a human person, but can also refer to a non-human animal.

[0095] The indefinite articles “a” and “an,” as used herein in the specification and in the claims, unless clearly indicated to the contrary, should be understood to mean “at least one.”

[0096] The phrase “and / or,” as used herein in the specification and in the claims, should be understood to mean “either or both” of the elements so conjoined, i.e., elements that are conjunctively present in some cases and disjunctively present in other cases. Multiple elements listed with “and / or” should be construed in the same fashion, i.e., “one or more” of the elements so conjoined. Other elements may optionally be present other than the elements specifically identified by the “and / or” clause, whether related or unrelated to those elements specifically identified.

[0097] As used herein in the specification and in the claims, “or” should be understood to have the same meaning as “and / or” as defined above. For example, when separating items in a list, “or” or “and / or” shall be interpreted as being inclusive, i.e., the inclusion of at least one, but also including more than one, of a number or list of elements, and, optionally, additional unlisted items. Only terms clearly indicated to the contrary, such as “only one of’ or “exactly one of,” or, when used in the claims, “consisting of,” will refer to the inclusion of exactly one element of a number or list of elements. In general, the term “or” as used herein shall only be interpreted as indicating exclusive alternatives (i.e., “one or the other but not both”) when preceded by terms of exclusivity, such as “either,” “one of,” “only one of,” or “exactly one of.”

[0098] As used herein in the specification and in the claims, the phrase “at least one,” in reference to a list of one or more elements, should be understood to mean at least one element selected from any one or more of the elements in the list of elements, but not necessarily including at least one of each and every element specifically listed within the list of elements and not excluding any combinations of elements in the list of elements. This definition also allows that elements may optionally be present other than the elements specifically identified within the list of elements to which the phrase “at least one” refers, whether related or unrelated to those elements specifically identified.

[0099] As used herein, although the terms first, second, third, etc. may be used herein to describe various elements or components, these elements or components should not be limited by these terms. These terms are only used to distinguish one element or component from another element or component. Thus, a first element or component discussed below could be termed a second element or component without departing from the teachings of the inventive concept.

[0100] Unless otherwise noted, when an element or component is said to be “connected to,” “coupled to,” or “adjacent to” another element or component, it will be understood that the element or component can be directly connected or coupled to the other element or component, or intervening elements or components may be present. That is, these and similar terms encompass cases where one or more intermediate elements or components may be employed to connect two elements or components. However, when an element or component is said to be “directly connected” to another element or component, this encompasses only cases where the two elements or components are connected to each other without any intermediate or intervening elements or components.

[0100] In the claims, as well as in the specification above, all transitional phrases such as “comprising,” “including,” “carrying,” “having,” “containing,” “involving,” “holding,” “composed of,” and the like are to be understood to be open-ended, i.e., to mean including but not limited to. Only the transitional phrases “consisting of’ and “consisting essentially of’ shall be closed or semiclosed transitional phrases, respectively.

[0101] It should also be understood that, unless clearly indicated to the contrary, in any methods claimed herein that include more than one step or act, the order of the steps or acts of the method is not necessarily limited to the order in which the steps or acts of the method are recited.

[0102] The above-described examples of the described subject matter can be implemented in any of numerous ways. For example, some aspects can be implemented using hardware, software or a combination thereof. When any aspect is implemented at least in part in software, the software code can be executed on any suitable processor or collection of processors, whether provided in a single device or computer or distributed among multiple devices / computers.

[0103] The present disclosure can be implemented as a system, a method, and / or a computer program product at any possible technical detail level of integration. The computer program product can include a computer readable storage medium (or media) having computer readable program instructions thereon for causing a processor to carry out aspects of the present disclosure.

[0104] The computer readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device. The computer readable storage medium can be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of the computer readable storage medium comprises the following: a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable readonly memory (EPROM or Flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanically encoded device such as punch-cards or raised structures in a groove having instructions recorded thereon, and any suitable combination of the foregoing. A computer readable storage medium, as used herein, is not to be construed as being transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission media (e.g., light pulses passing through a fiber-optic cable), or electrical signals transmitted through a wire.

[0105] Computer readable program instructions described herein can be downloaded to respective computing / processing devices from a computer readable storage medium or to an external computer or external storage device via a network, for example, the Internet, a local area network, a wide area network and / or a wireless network. The network can comprise copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers and / or edge servers. A network adapter card or network interface in each computing / processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium within the respective computing / processing device.

[0106] Computer readable program instructions for carrying out operations of the present disclosure can be assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data, configuration data for integrated circuitry, or either source code or object code written in any combination of one or more programming languages, comprising an object oriented programming language such as Smalltalk, C++, or the like, and procedural programming languages, such as the“C” programming language or similar programming languages. The computer readable program instructions can execute entirely on the user’s computer, partly on the user’s computer, as a standalone software package, partly on the user’s computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, comprising a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider). In some examples, electronic circuitry comprising, for example, programmable logic circuitry, field-programmable gate arrays (FPGA), or programmable logic arrays (PLA) can execute the computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present disclosure.

[0107] Aspects of the present disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to examples of the disclosure. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer readable program instructions.

[0108] The computer readable program instructions can be provided to a processor of a, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. These computer readable program instructions can also be stored in a computer readable storage medium that can direct a computer, a programmable data processing apparatus, and / or other devices to function in a particular manner, such that the computer readable storage medium having instructions stored therein comprises an article of manufacture comprising instructions which implement aspects of the function / act specified in the flowchart and / or block diagram or blocks.

[0109] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process, such that the instructions which execute on the computer, other programmable apparatus, or other device implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0110] The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program productsaccording to various examples of the present disclosure. In this regard, each block in the flowchart or block diagrams can represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the blocks can occur out of the order noted in the Figures. For example, two blocks shown in succession can, in fact, be executed substantially concurrently, or the blocks can sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flowchart illustration, and combinations of blocks in the block diagrams and / or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts or carry out combinations of special purpose hardware and computer instructions.[oni] Other implementations are within the scope of the following claims and other claims to which the applicant can be entitled.

[0112] While several inventive embodiments have been described and illustrated herein, those of ordinary skill in the art will readily envision a variety of other means and / or structures for performing the function and / or obtaining the results and / or one or more of the advantages described herein, and each of such variations and / or modifications is deemed to be within the scope of the inventive embodiments described herein. More generally, those skilled in the art will readily appreciate that all parameters, dimensions, materials, and configurations described herein are meant to be exemplary and that the actual parameters, dimensions, materials, and / or configurations will depend upon the specific application or applications for which the inventive teachings is / are used. Those skilled in the art will recognize, or be able to ascertain using no more than routine experimentation, many equivalents to the specific inventive embodiments described herein. It is, therefore, to be understood that the foregoing embodiments are presented by way of example only and that, within the scope of the appended claims and equivalents thereto, inventive embodiments may be practiced otherwise than as specifically described and claimed. Inventive embodiments of the present disclosure are directed to each individual feature, system, article, material, kit, and / or method described herein. In addition, any combination of two or more such features, systems, articles, materials, kits, and / or methods, if such features, systems, articles, materials, kits, and / or methods are not mutually inconsistent, is included within the inventive scope of the present disclosure.

Claims

ClaimsWhat is claimed is:

1. A system for generating a digital biomarker for an individual with knee and / or hip osteoarthritis, the system comprising:at least one primary device comprising one or more capacitor-pressure sensors and configured to generate raw gait data;a first remote processing device in communication with the at least one primary device and configured to analyze the raw gait data generated for the individual, the first remote processing device comprising:a computer-readable storage medium having stored thereon computer-readable instructions to be executed by one or more processors; andone or more processors configured by the computer-readable instructions to perform the following operations:(i) receive the raw gait data generated by the one or more capacitor-pressure sensors of the at least one primary device;(ii) determine one or more gait parameters for the individual based at least in part on the raw gait data received; and(iii) apply one or more trained machine learning models to the one or more gait parameters to generate a digital biomarker for the individual.

2. The system of claim 1 , wherein the at least one primary device is configured to be incorporated into an article to be worn on one or both feet of the individual.

3. The system of claim 1, further comprising one or more secondary sensors configured to generate additional raw gait data, the one or more secondary sensors including at least one of an accelerometer, a gyroscope, and inertial measurement unit.

4. The system of claim 3, wherein the one or more secondary sensors are integrated into the at least one primary device.

5. The system of claim 3, wherein one or more of the secondary sensors are integrated into at least one secondary device in communication with at least the first remote processing device.

6. The system of claim 5, wherein the at least one secondary device is configured to be worn around one or both ankles and / or wrists of the individual.

7. The system of claim 3, wherein the one or more processors of the first remote processing device are further configured to perform the following operations:(i-b) receive the additional raw gait data generated by the one or more secondary sensors;and(ii-b) determine the one or more gait parameters for the individual based at least in part on the raw gait data and the additional raw gait data.

8. The system of claim 7, wherein at least one of the one or more gait parameters are based on a combination of the raw gait data generated by the one or more capacitor-pressure sensors of the at least one primary device and the additional raw gait data generated by the one or more secondary sensors.

9. The system of claim 1, wherein the one or more machine learning models are trained by: generating at least one training dataset comprising raw gait data and / or additional raw gait data for a plurality of subjects;extracting gait parameters for each subject of the plurality of subjects based on the at least one training dataset;generating a reference dataset of gold standard measurements for the plurality of subjects; training the one or more machine learning models using at least a first portion of the at least one training dataset and at least a first portion of the reference dataset; andvalidating the trained one or more machine learning models using at least a second portion of the at least one training dataset and at least a second portion of the reference dataset.

10. The system of claim 1, wherein the raw gait data includes a time-series of pressure locations and / or pressure amounts on the one or more capacitor-pressure sensors.

11. The system of claim 3, wherein the additional raw gait data includes a time series of positional trajectories obtained from the individual.

12. The system of claim 3, wherein the one or more gait parameters include one or more of: a posture metric, a total walking time, a maximal time spent in a single walking sequence, a medianstride velocity, a 95thpercentile stride velocity, a median stride length, a 95thpercentile stride length, a maximal 3 -minute walking distance, a maximal distance walked in a single walking sequence, a percentage of stance duration over total stride duration, a stance duration, a swing duration, a stepspeed asymmetry, a total number of stairs climbed per period of time, a median stair climbing or descending velocity, an 80thpercentile stair climbing or descending velocity, and a 95thpercentile stair climbing or descending velocity.

13. The system of claim 1, wherein the digital biomarker is indicative of a severity of knee and / or hip osteoarthritis in the individual.

14. The system of claim 1, wherein the one or more processors are further configured to perform the following operations:(iv) evaluate a condition or a change in the condition of the individual by:(a) performing steps (i)-(i v) to generate a first digital biomarker for the individual based on data collected over a first period of time;(b) performing steps (i)-(iv) to generate a second digital biomarker for the individual based on data collected over a second period of time different from the first period of time; and (c) determining a condition of the individual and / or a change in the condition of the individual based on at least the first and second digital biomarkers.

15. A method for generating a digital biomarker for an individual with knee and / or hip osteoarthritis, the method comprising:generating, using one or more capacitor-pressure sensors of at least one primary device, raw gait data for the individual;receiving, at a first remote processing device, the raw gait data generated for the individual; determining, using one or more processors of the first remote processing device, one or more gait parameters for the individual based at least in part on the raw gait data; andapplying one or more trained machine learning models to the one or more gait parameters to generate a digital biomarker for the individual.

16. The method of claim 15, further comprising:generating, using one or more secondary sensors, additional raw gait data for the individual, wherein the one or more secondary sensors include at least one of an accelerometer, a gyroscope, and inertial measurement unit;receiving, at the first remote processing device, the additional raw gait data generated for the individual; anddetermining, using the one or more processors of the first remote processing device, the one or more gait parameters based at least in part on the raw gait data and the additional raw gait data.

17. The method of claim 16, wherein the one or more of the secondary sensors are integrated into at least one secondary device in communication with at least the first remote processing device.

18. The method of claim 16, wherein the raw gait data and / or the additional raw gait data is generated over a multi-stage generation phase comprising: (a) a first assessment wherein the raw gait data and / or the additional raw gait data is generated while the individual is freely walking; (b) a second assessment wherein the raw gait data and / or the additional raw gait data is generated while the individual is walking during a fixed time and / or for a fixed distance; (c) a third assessment wherein the raw gait data and / or the additional raw gait data is generated during an timed up-and-go (TUG) movement; and (d) a fourth assessment wherein the raw gait data and / or the additional raw gait data is generated during a postural test.

19. The method of claim 16, wherein the raw gait data includes a time-series of pressure locations and / or pressure amounts on the one or more capacitor-pressure sensors, and wherein the additional raw gait data includes a time series of positional trajectories obtained from the individual.

20. A non-transitory computer-readable storage medium having stored thereon computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:generating, using one or more capacitor-pressure sensors of at least one primary device, raw gait data for an individual;receiving, at a first remote processing device, the raw gait data generated for the individual; determining, using one or more processors of the first remote processing device, one or more gait parameters for the individual based at least in part on the raw gait data; andapplying one or more trained machine learning models to the one or more gait parameters to generate a digital biomarker for the individual.

Images