Wearable device for therapy and system using same

Abstract

A system for focal vibration therapy is provided. The system comprises wearable device having one or more vibration actuators for providing focal vibration therapy, one or more sensors for sensing data associated with positional user data and physiological user data when the wearable device is worn by a user; and a controller. The controller is configured to operate the wearable device in an assessment mode to assess functional musculoskeletal movement and mobility, wherein in the assessment mode the controller is configured to access data from the one or more sensors when the user is carrying out movement(s) associated with the assessment, wherein said data forms sensor assessment data, and operate the wearable device in a focal vibration therapy mode, wherein in the focal vibration therapy mode the controller is configured to control the operation of the one or more vibration actuators based on the sensor assessment data.

Description

[0001] WEARABLE DEVICE FOR THERAPY AND SYSTEM USING SAME

[0002] FIELD OF THE DISCLOSURE

[0003] The present disclosure relates to a system for providing focal vibration therapy.

[0004] BACKGROUND

[0005] Advancements in healthcare devices are significantly enhancing the ability to treat physical conditions almost instantaneously. Modem technology has simplified the integration of electronic devices with and around the human body, paving the way for numerous innovations. Many emerging healthcare solutions take the form of wearable or implantable devices, which can monitor and alleviate various health issues more effectively. In particular, the customization of wearable technology is enabling personalised approaches to managing multiple physical ailments.

[0006] Muscle pain, often a symptom of various diseases, injuries, or disorders, remains one of the most prevalent health concerns. Its causes range from injury, overuse, and genetic predispositions to chronic stress or tension. A variety of treatments exist for muscular issues, with vibrational therapy emerging as a highly effective approach. Vibrations applied to muscles stimulate recovery and rehabilitation, with the intensity and frequency of vibrations tailored to the specific condition being addressed. This technique works by targeting the muscle with precise energy, inducing cellular activity that can, for instance, stimulate the release of osteoblasts essential for bone development.

[0007] The principles of vibration therapy rely on controlled frequency and amplitude, allowing energy to be transmitted to specific areas of the body. These vibrations not only enhance muscle recovery but also contribute to cellular regeneration and improved musculoskeletal health. Despite its benefits, current wearable vibration devices are associated with limitations. Most available devices are bulky, rigid, or stationary, restricting the user's mobility. Additionally, they often provide relief to only limited regions without delivering targeted vibrations deep into muscles and joints for specific therapeutic outcomes.

[0008] The growing demand for innovative wearable solutions in medical and fitness applications underscores the potential for improvement. There is a clear need for novel a wearable vibration device that overcomes the shortcomings of existing designs.

[0009] SUMMARY

[0010] According to a first aspect of the present disclosure, there is provided a system for providing focal vibration therapy. The system comprises a wearable device having: one or more vibration actuators for providing focal vibration therapy; one or more sensors for sensing data associated with positional user data and physiological user data when the wearable device is worn by a user; and a controller. The controller is configured to operate the wearable device in an assessment mode to assess functional musculoskeletal movement and mobility, where in the assessment mode, the controller is configured to access data from the one or more sensors when the user is carrying out movement(s) associated with the assessment, where said data forms sensor assessment data. The controller is also configured to operate the wearable device in a focal vibration therapy mode, where in the focal vibration therapy mode, the controller is configured to control the operation of the one or more vibration actuators based on the sensor assessment data.

[0011] In some examples, in the focal vibration therapy mode, the controller is further configured to: access data from the one or more sensors when the user is receiving treatment, wherein said data forms sensor therapy data, and optionally adjust the operation of the one or more vibration actuators based on the sensor therapy data.

[0012] In some examples, the controller is arranged to control the operation of the one or more vibration actuators by controlling at least one of vibration intensity or amplitude and vibration frequency of the one or more vibration actuators.

[0013] In some examples, the one or more sensors comprise at least one or more of the following: temperature sensor, inertial measurement unit (IMU), accelerometer, gyroscope, magnetometer, blood flow sensor (such as doppler or ultrasound), and electrical activity sensor.

[0014] In some examples, the controller is operatively coupled to a communications interface for enabling communication with at least one of a mobile application and a cloud platform.

[0015] In some examples, the system comprises at least one of the mobile application and the cloud platform.

[0016] In some examples, the controller is configured to operate the wearable device in the assessment mode in response to receiving a control signal from the mobile application.

[0017] In some examples, the controller is further configured to: send data including sensor assessment data and sensor therapy data from the one or more sensors to at least one of the mobile application and cloud platform for processing, and receive processed data, including adjusted vibration intensity and vibration frequency parameters, from the mobile application or cloud platform.

[0018] In some examples, the mobile application is configured to: display guided instructions during the assessment mode; display data including sensor assessment data and sensor therapy data received from the one or more sensors; receive user input data or parameters from the user; process the data including sensor assessment data, sensor therapy data, and the user input data or parameters, optionally based on machine learning, to derive adjusted vibration intensity and vibration frequency parameters, and send the adjusted vibration intensity and vibration frequency parameters to the controller to adjust the operation of the therapy mode; send and receive data including sensor assessment data and sensor therapy data to the cloud platform for processing and storage / retrieval

[0019] In some examples, the cloud platform is configured to: process data including sensor assessment data and sensor therapy data received from the controller or mobile application, optionally based on machine learning, to derive adjusted vibration intensity and vibration frequency parameters, and send the adjusted vibration intensity and vibration frequency parameters to the controller or the mobile application to adjust the operation of the therapy mode.

[0020] BRIEF DESCRIPTION OF THE DRAWINGS

[0021] These and other features, aspects, and advantages of the present disclosure are described with reference to the drawings of certain embodiments, which are intended to schematically illustrate certain examples, in which:

[0022] Figure 1 shows a wearable device according to one example worn by a user.;

[0023] Figure 2 shows a plan view of the wearable device according to an example;

[0024] Figure 3 shows the wearable device of Figure 2 attached to a strap according to an example;

[0025] Figure 4 shows a diagram of a treatment cycle of a system using the wearable device according to an example;

[0026] Figure 5 shows a data flow diagram associated with a therapeutic focal vibration treatment session using the wearable device according to an example;

[0027] Figure 6 shows a data flow diagram associated with a functional mobility or musculoskeletal assessment session using the wearable device according to an example;

[0028] Figure 7 shows a user interface of a mobile device (app) for functional mobility or musculoskeletal assessment according to an example;

[0029] Figure 8 shows a flowchart illustrating an algorithm used by the system / device, according to an example.

[0030] DETAILED DESCRIPTION

[0031] Focal vibration therapy

[0032] Focal vibration therapy (also known as local vibration therapy) is a type of physical therapy that involves applying vibration to specific areas of the body to, e.g., stimulate the muscles, promote healing of damaged tissue and strain, reduce pain and improve mobility.

[0033] Focal vibration therapy can be achieved by stimulating nerve endings and increasing blood flow. This can potentially help to reduce muscle spasms and inflammation, relieve muscle tension and improve range of motion. Additionally, the vibrations are thought to help release endorphins, which are natural pain-relieving chemicals in the body. Focal vibration therapy is often used to help alleviate muscle pain and stiffness associated with conditions such as fibromyalgia, back pain, and osteoarthritis.

[0034] A general idea of the present disclosure relates to a system 100 for treating musculoskeletal (MSK) conditions and indications using focal vibration. The focal vibration may be delivered by a wearable device 110. The wearable device 110 may comprise one or more actuator(s), such as vibration actuator(s). The vibration actuator may act as a vibrator. As will be described in more detail below, the system 100 may be configured to control or adjust aspects of the treatment, such as frequency and / or amplitude of the vibration being administered to the user. The system 100 and its exemplary features are described in detail below.

[0035] In some examples, the wearable device 110 disclosed herein may be used for injury recovery, fatigue management, and enhanced athletic performance.

[0036] Wearable device

[0037] The system 100 may comprise the wearable device 110. The wearable device 110 may comprise any one or more of the following: an electronic module, optionally including a housing; at least one actuator 112, such as a focal vibration actuator, one or more batteries, one or more controllers (e.g., including microcontrollers), microprocessor(s), wireless control electronics, etc.), and one or more sensors.

[0038] In some examples, the electronic module is configured to house any one or more of: the at least one actuator 112, the one or more batteries, the one or more controllers, and the one or more sensors.

[0039] In some examples, the one or more sensors may comprise any one or more of: at least one movement / motion sensor (such as accelerometer and gyroscope), at least one temperature sensor, and at least one magnetometer sensor.

[0040] In some examples, the one or more sensors may comprise one or more Inertial Measurement Unit (IMU) sensor(s). The one or more IMU sensor(s) may be configured to measure acceleration, orientation, angular rates, and other gravitational forces as electronic signal(s). The one or more IMU sensor(s) may each comprise at least one (e.g., three) accelerometer and at least one (e.g., three) gyroscope. In some examples, the one or more IMU sensor(s) may each comprise at least one (e.g., three) Magnetometer.

[0041] The one or more sensors, such as the at one or more IMU sensor(s), at least one accelerometer and at least one gyroscope, may be arranged to provide data regarding positional and angular movement of the user’s body. Additionally, or alternatively, the one or more sensors (e.g., the at least one temperature sensor) may be configured to capture and record the surface temperature of the user’s body and / or the treatment temperature prior, during, or post treatment. The treatment temperature is the resultant temperature change during the focal vibration treatment due to any one or more of: the thermal output of the device, the thermal insulative effects of the garment, and thermal effects of the increased blood circulation occurring during the treatment.

[0042] The wearable device 110, e.g. by the controllers), may be configured to measure aspects regarding the user’s / wearer’s mobility and / or bodily movements. The mobility and movement measurement(s) may comprise data regarding motion and speed of the user’s body. The data regarding motion and speed of the user’s body may be captured by the one or more sensor(s). The data of the measured aspects may be used to provide a 3D model. For example, the controller(s) may be configured to create the 3D model based on the data. A 3D model would be used to record joint and body angles to form picture of the body and record changes in the body form. In some examples, the one or more sensors (e.g., the one or more IMU sensors and the at least one gyroscope) may be configured to measure body and joint angles of the user. “Body angles” can be a combination of body joints acting to change the angle or position of a larger part of the body, such as the movement of bending forward which requires angular change in many skeletal joints. “Joint angles” may be a measure of the changes in angular position around a single skeletal joint, such as an elbow or knee.

[0043] User assessment and adjustment of treatment

[0044] In some examples, the data (e.g., measurements) from the one or more sensors may be used, by the controller(s), to provide a numerical score of the user movement assessment. The numerical score may be related to the user’s / wearer’s mobility and / or bodily movements, such as angular change joint extension etc. An angular measurement of the joint angle may be arranged to demonstrate the amount of joint extension or flexion, which are both physio therapy measurements.

[0045] In some examples, the numerical score may be determined through a calculation comprising weighted variables. The weight of the variables may be based on the improving or worsening conditions of the user through data comparison of two or more assessment and / or treatment sessions. The two or more assessment and / or treatment sessions may be sequential.

[0046] In some examples, the wearable device 110, e.g. by the controller, may be configured to provide functional assessment features. The functional assessment features may be configured to, amongst other aspects, monitor the progression of an injury and / or the recovery phase, e.g., after intense physical activity. For example, if adverse condition(s) are detected, the wearable device may be arranged to automatically adjust one or more parameters of the vibration therapy to address and / or improve the adverse conditions, using an algorithm shown in Figure 10 Examples of adverse conditions may include muscle stiffness, or higher than normal muscle tension causing discomfort, or chronic conditions such as arthritis or long-term muscular disorders. The parameters of the vibration therapy include, but are not limited to, frequency, amplitude, and duration of vibrations.

[0047] The adverse condition(s) may be assigned to different categories, with the vibration therapy being adjusted depending on the categorisation of the adverse conditions. For example, adverse conditions such as muscle stiffness and high muscle tension levels may be categorised separate to chronic conditions such as arthritis or longterm muscular disorders.

[0048] Garment and module materials

[0049] In some examples, the electronic module housing may be soft. Alternatively, or additionally, the electronic module housing may be at least partially made up of foam (e.g., PU coated EVA foam, hardness Shore 00-50). This can allow the device to conform to the body of the user, such as the contours and angles of the user’s body. This can facilitate for the vibration to be transferred much more accurately and / or easily to the user’s body.

[0050] Further, the conformity of the electronic module may enhance patient comfort, potentially allowing the device to be donned over long durations. For example, the user may wear the wearable device for several hours per da. Thus, conformity of the electronic module (e.g., its soft housing) can help with improving device comfort and potentially remove comfort limitations for receiving treatment.

[0051] In some examples, the one or more focal vibration actuators may be positioned within custom designed cases. The cases may stabilize the frequencies being provided by the actuator(s) and improve the consistency of the frequencies without lots of variation. Both the actuator(s) and their respective case may be temporarily or permanently fixed within the electronic module (e.g., inside the electronic module housing).

[0052] The wearable device 110 may comprise a garment. In some examples, the garment may be soft and / or textile.

[0053] The garment may be configured to hold the electronic module housing firmly in an interior pocket and fit comfortably on the body treatment areas.

[0054] The garment may comprise soft and / or stretchable materials, such as neoprene and Lycra. The material of the garment may be configured to conform to the body. The garment can provide support to the joint or the body location whilst they're being worn. The one or more vibration actuators 112 may be arranged within the garment and / or may be held in place via one or more pocket(s) on the back of the garment in a series of location holes in the garment, keeping the module fixed in a single location but integrated fully into the garment structure. The garment may then be attached to the body and tightened using a variety of either buckles or straps, belts, Velcro, zips, etc. Further, the garment may be able to fit all the different body parts depending on the design of the strap. The straps may form part of the wearable device.

[0055] In some examples, the material of the electronic module and / or garment may be selected (e.g., being sufficiently soft and / or flexible) such that it is capable of transmitting vibrations deep into muscles and soft tissues while targeting specific areas based on the personalized treatment program(s). In some examples, the material of the electronic module and / or garment may be at least partially made up of PU foam or EVA foam. The material may be selected based on its ability to effectively transmit vibration.

[0056] Because the electronic module is soft, e.g., due to it having a foam casing, and the straps being made of soft fabrics, the garment can be comfortable to wear. Further, the electronic module may be configured to shield the interior, optionally hard, components by soft, comfortable surfaces. This makes the module and the garment comfortable to wear, just like a sports strap or a piece of compression clothing. The wearable device may thus be suitable to be worn over long periods of time, even many hours at a time. In one example, the electronic module is lightweight and thin, so it can be worn under clothing without being seen.

[0057] In one example, the wearable device 110 is designed for optimal comfort during extended use. The materials associated with the wearable device, including the electronic module, garment, strap(s) etc, may comprise lightweight, breathable, and skin-friendly materials that minimize discomfort or irritation, even when worn for hours. Flexible and ergonomic designs that contour naturally to the body ensure the device remains secure without restricting movement. Adjustable straps or modular components could further enhance usability by accommodating different body types and therapy needs.

[0058] In one example, the wearable device has a low-profile design that may be integrated, such as attached, into everyday clothing or athletic wear.

[0059] Automatic adjustment of treatment parameters

[0060] In some examples, the wearable device, e.g. by the one or more sensors, can be arranged to measure key physiological parameters of the user, such as muscle tension, joint movement, blood flow, and electrical activity within the muscles. This data can provide a comprehensive understanding of the user’s physical state. The functional assessment and / or therapy provided may be based on such data. This data can be utilised by the wearable device, e.g., to tailor or adjust the vibration therapy disclosed herein. Tailoring or adjusting the vibration therapy may include any one or more of: providing a longer or shorter treatment duration, increasing or reducing the vibration power / amplitude, and adjust the vibration frequency. In one example, the wearable device, by the controller, may provide for functional assessment including real-time feedback, allowing users and healthcare providers to track the effectiveness of the therapy.

[0061] In one example, the wearable device 110, e.g., by the controller, is configured to send and / or receive data, such as the sensor data, to / from a mobile application or cloud platform. Based on the received data, the mobile application 120 or cloud platform may be arranged to, amongst other things, generate detailed reports, potentially providing insights for medical professionals to refine treatment plans further. This capability may enhance therapeutic outcomes and expand the scope of wearable vibration technology, making it a versatile tool for both preventative and rehabilitative healthcare. By dynamically adjusting treatments and providing a treatment that has been customised for the user based on their size, weight, sex etc, the wearable devices can deliver more personalized care, ultimately improving user satisfaction and long-term health outcomes.

[0062] The ability to adjust (e.g., automatically) treatment (e.g., vibration frequency and / or amplitude), allows for optimization and / or personalization of therapy and / or addressing the specific needs of different users or adapting to changes in the body’s condition during therapy. As a result, the system can maximize therapeutic outcomes for individuals with unique recovery requirements and / or varying muscular issues.

[0063] In one example, the controller(s) is configured to process the data using machine learning (ML) and / or artificial intelligence (Al). Alternatively, or additionally, the information sent from the controller(s) to the mobile application 120 or cloud platform may be processed using machine learning and / or artificial intelligence.

[0064] In one example, use of machine learning and artificial intelligence can enable the wearable device 110 to provide intelligent, real-time adjustment capabilities. This is because, the ML and Al algorithms can analyse data collected from the one or more sensor(s) embedded in the wearable device 110, and are therefore capable of analysing data associated with muscle tension, movement patterns, or recovery indicators, to understand the user’s specific therapeutic needs. The machine learning may be used to identify trends or abnormalities in the data, and predict optimal vibration frequencies and amplitudes for different conditions, and optionally send this information back to the controllers) for controlling the vibration actuator(s) accordingly. The optimal frequencies and amplitudes may be retrieved from a reference table for a range of trend patterns.

[0065] In some examples, the controllers) is configured to analyse real-time data, e.g., according to a set of preset data rules, and then adjust vibration parameters. By learning from patterns in the user’s muscle responses and recovery progress, the controller(s), mobile application 120 , and / or cloud platform may be configured to fine-tune the vibration frequency and intensity for precise, personalized treatment. This intelligent adaptability ensures users receive therapy tailored to their unique physiological needs, enhancing recovery and overall user experience.

[0066] In one example, the wearable device 110, by the controller(s), is configured to dynamically adjust vibration frequency or amplitude, increasing their ability to deliver optimized and / or personalized therapy. This allows for individual user needs to be met and / or response to changes in the body’s condition during therapy sessions. As a result, the wearable device disclosed herein is capable of providing tailored treatments that adapt to the unique requirements of different users or evolving recovery processes.

[0067] Over time, the disclosed system, which may include data from the sensors and user inputted data from the mobile application, may learn from user feedback and therapy outcomes, continuously refining its recommendations. For example, if the wearable device detects slower muscle relaxation during a session, it might increase the vibration intensity or adjust the frequency to enhance effectiveness. This adaptability provides the wearable device with capability to deliver more precise, personalized therapy, making treatments more effective and responsive to real-time body conditions. Further, continuous assessment could allow the wearable device to implement gradual, adaptive protocols that align with the user’s evolving needs.

[0068] In one example, the one or more sensors can be used to assess the movement and mobility prior to therapy, as part of pretreatment analysis, such as when the controller operates in an assessment mode when no therapy is provided. The sensor data associated with the assessment is also referred to as sensor assessment data herein.

[0069] Additionally or alternatively, the one or more sensors can be used after treatment to assess treatment progress. The sensor data associated with the data sensed by the one or more sensors during therapy is also referred to as sensor therapy data herein.

[0070] Sensor data collected from wearable vibration devices may play a role in pretreatment analysis, setting the stage for more personalized and effective therapy. By leveraging advanced sensors capable of measuring data associated with muscle activity, joint motion, tissue tension, and even biomarkers like temperature or blood flow, the wearable device disclosed herein may provide a comprehensive snapshot of the user’s physical state before initiating treatment. This data may serve as the foundation for tailoring therapy protocols to meet individual needs.

[0071] Machine learning (ML) algorithms run on the controller, mobile application, or cloud platform, may be used to analyse this data to identify specific patterns or anomalies, such as areas of heightened muscle tension, restricted movement, or insufficient blood circulation. These insights enable the wearable device to assess the severity and type of the condition, helping to determine the ideal vibration frequency, amplitude, and treatment duration. For instance, if the sensors detect increased stiffness in a particular muscle group, the wearable device could prepare a pretreatment protocol focusing on that region with lower-frequency vibrations to gradually relax the muscle before moving to deeper therapeutic vibrations.

[0072] Additionally, pretreatment analysis, forming part of the controller assessment mode, may provide for valuable baseline data for tracking progress. The controller, mobile application or cloud platform, may be configured to compare real-time metrics (from the sensors) with initial readings and enable the wearable device to adapt its therapy over time, ensuring continuous optimization. This data-driven approach enhances precision, improves outcomes, and ensures that each session is both effective and safe.

[0073] In one example, the wearable device, e.g. by the controller, is configured to provide assessment of the user’s body, such as limb position, a joint mobility function, or both. For example, a body limb position and movement of the body limb may be measured by an IMU sensor, and the associated data may be accessed by the controller(s) for further processing. Joint mobility function may be assessed, e.g., by the controller, during the motion of walking or standing up or assess the walking gait of the user, or via a set of guided assessments delivered using a companion app or digital device. The wearable device 110 may perform the assessment using one or more sensors, such as a series of multi axis gyro sensors. The wearable device may perform a musculoskeletal treatment before, during, or after the assessment.

[0074] The wearable device 110 may be wirelessly controlled, e.g., from a mobile device via an app 120. For example, the one or more controller(s) may comprise or be operatively coupled to a wireless communication interface, such as wireless control electronics, enabling wearable device to send / receive data from the mobile application 120 and or cloud platform.

[0075] For example, data recorded by the controller may be sent to the mobile application or cloud platform for further processing. The mobile application may comprise a treatment program arranged to provide feed-back data back to the wearable device via the one or more controller(s). User input data or parameters, such as the self-reported Numeric Pain Rating Score (NPRS), and measured data or parameters, such as angular mobility data in degrees, time, date, duration and / or frequency of the treatment and assessment can be recorded via mobile device or stored in the cloud for further viewing remotely by the user or a third party The data or parameters are displayed on the analytics page of the app, or dashboard on the cloud platform via PC.

[0076] Results from the musculoskeletal mobility assessment may be combined with personal health or mobility data to provide a customized treatment using a machine learning algorithm. Assessment or health data results can be attributed numerical scores and then when those scores go up or down, the customized treatment can be adjusted using machine learning, such as following a set of rules, e.g., based on a numerical score (Input A), then adjust treatment protocols (output B). Personal health or mobility data can be provided during sign-on or registration with the product on the mobile app or cloud platform, or provided through preexisting medical records, for example through a healthcare system with a health record I.D. The machine learning algorithm can be trained on a set of data comprising:

[0077] Body function data, such as mobility assessment readings, and input user data such as pains scores and treatment frequency and time.

[0078] Treatment data such as time, data, duration and / or frequency.

[0079] Third party data, such as from other wearable devices, including activity data such as sleep-monitoring and pedometers.

[0080] Machine learning (ML) algorithms, e.g. running on the cloud platform and / or mobile app 120, may be configured to analyze the movement, assessment and third-party data to identify specific patterns or anomalies, such as areas of reduced muscle tension, or activity, restricted movement, or reduced activity. These insights enable the wearable device disclosed herein to assess the severity and type of the condition, helping to determine the ideal vibration frequency, amplitude, and treatment duration. For instance, if the sensors detect increased stiffness and reduced mobility in a particular muscle group, the wearable device, e.g. by the controller(s), may be configured to prepare a pretreatment protocol focusing on that region with lower-frequency vibrations to gradually relax the muscle before moving to deeper therapeutic vibrations. This process may be adjusted using machine learning algorithms.

[0081] In some examples, the one or more controllers is configured to control the operation (including frequency and intensity) of the vibration actuators. In some examples, the one or more controller(s) may be configured to process and control data for treatments, while optionally also recording the results. Processed results can be sent back to the app, before transmitting to the wearable device.

[0082] The wearable device, by the one or more controller(s), may gather user input data, such as personal data, or measure health data from the mobile app and / or cloud platform. This data is used to adjust treatment protocols, and then apply a focal vibration therapeutic treatment directly from the wearable device or advise recommended actions based on therapeutic treatment, exercises or movements that perform a therapeutic benefit to the users. The recommended treatment protocols may be based on a mixture of treatment that are determined by research to be most effective and those suggested by physiotherapy clinicians.

[0083] The user input data may include the user’s age, weight and sex. Based on the user input data, the focal vibration therapy output may vary, such as changing the frequency and amplitude of the treatment. The output frequency of the focal vibration therapy can vary between 50 to 200 Hertz (Hz). The output amplitude of the focal vibration therapy can vary between 0.1 to 1.5mm amplitude. The recommended actions based on the therapeutic treatment may include specific stretches, and movements normally directed by a physical therapist.

[0084] The treatment may exhibit effects within the targeted treatment region of the user, such as increased circulation and stimulation of blood flow, reduction in stiffness and soreness, stimulation of lymphatic drainage and increased general functional mobility.

[0085] The treatment may be provided to treat a variety of conditions, such as muscle pain, joint pain, soft tissue injury, sub-acute muscle injury, osteoporosis, and limb functionality after neurological conditions.

[0086] In one example, the electronic module form a soft therapeutic vibration module. The soft therapeutic vibration module may house the one or more vibration actuators, one or more batteries, wireless control electronics, controller, gyro sensors, movement sensors, temperature sensors, magnetometer sensors.

[0087] In one example, the garment comprises a soft textile that holds the therapeutic vibration module firmly in an interior pocket and fits comfortably on the body treatment areas.

[0088] A user interface for the assessment is shown on a mobile device 120 which is wirelessly connected to the wearable device 110, e.g. by the controller or wireless communication interface, and guides the user through several assessment steps while the module collects movement data. These are guided movement instructions where the user is shown a movement and then they have to repeat it. Measurements are recorded by the one or more sensors during the movement. Then a new movement is shown etc.

[0089] In one example, such as with reference to Figure 1, the wearable device be arranged for treatment and mobility assessment of the lower back.

[0090] In one example, such as with reference to 9a of Figure 4, wearable device may be arranged for treatment and mobility assessment of the knee.

[0091] In one example, such as with reference to 9b of Figure 4, wearable device may be arranged for treatment and mobility assessment of the elbow, lower arm or upper arm region.

[0092] In one example, such as with reference to 9c of Figure 4, the wearable device may be arranged for t treatment and mobility assessment of the shoulder.

[0093] In use, the user may select a treatment type from the mobile application 120. Also, the personal data from the user may be used to indicate the treatment area and type.

[0094] Further aspects of the invention are described in the attached drawings as follows.

[0095] Figure 1 shows an example of a wearable focal vibration therapy device 110 worn on the lower back for treatment of lower back pain. The device comprises a soft textile adjustable strap (1) engineered to hold an integrated soft focal vibration device (2). The soft textile can comprise a foam casing. Each element is soft to ensure that the wearable device conforms to the user’s body shape, conforming to contours and angles. This allows the therapy to be delivered as near as possible to the targeted area. Also, the strap can be adapted to various body regions due to the malleability of the wearable device. The soft device ensures the device can be worn over long periods of time without significant irritation. The device delivers focal vibration therapy to the lower back area to ease back pain and increase mobility of the muscles, whilst also recording data related to the treatment (e.g., treatment program, frequency, amplitude, duration, time of day, date) and, data relating to the wearer’s movement, position and body state. The lower back strap may be designed to hold the treatment module in the L1-L5 lumbar area for effective treatment of the lower back and paraspinal muscles. Data relating to movement of the user’s body and joints are recorded during and after treatment. This data is then processed for analysis. Movement of the wearer’s body and joints can be recorded during or after treatment. The data can then be processed for analysis The wearable device is soft and comfortable to wear whilst walking or during lifestyle activities. Depending on the activity the user is engaged in whilst wearing the device, the treatment may vary. The treatment may vary in vibration amplitude, intensity, vibration frequency or duration. The activities may comprise sitting, standing, walking, cardio, weight training, and a variety of sports.

[0096] The treatment could be varied depending on the location and activity of the wearer, i.e. if they are walking or seated, or at work. The device can be worn during a wide range of activities due to its low profile and comfortable design.

[0097] Figure 2 shows an example of the wearable device 110 acting as a focal vibration treatment and musculoskeletal assessment device. The device may comprise a soft foam body 111 with plural integrated focal vibration motors 112 and an embedded electronics control module 113 including amongst other components a rechargeable battery, controller, sensors, LED display, switch interface, charging port, wireless transmitter forming part of the wireless communication interface. The control module 113 processes instructions, which are received from the onboard controller as a result of personalized treatment configurations directed by the machine learning algorithm combined with the available sensor data. Based on the processing the control module 113, e.g. by the controller, is configured to control the focal vibration motors 112 and can transmit and / or receive data via the wireless transmitter. An LED display may alert the user to indicate the state of the wearable device. Examples of the various states maybe; treatment device connected to a mobile device, treatment in progress, battery state information, treatment program information.

[0098] In some examples, the soft foam body 111 can be a PU coated EVA foam, hardness Shore00-50.

[0099] Figure 3 shows an example of the wearable device 110 acting as a focal vibration treatment and musculoskeletal assessment device inserted into a textile based wearable device strap 114 where the device strap is designed hold the device against the user’s body. In some examples, the strap may be provided with Velcro, to fasten the device to the user’s body. In the present example, the wearable device strap would suit the lower back area of the body.

[0100] Figure 4 shows an example of a typical full treatment cycle using the system 100 of the present disclosure according to an example. Step one the user selects and starts a treatment session via a mobile device (app) user interface 120. The treatment protocol and command are sent wirelessly via Bluetooth to the wearable device 110 and the wearer receives a focal vibration therapeutic treatment. Following the treatment the user performs a mobility assessment 10 guided by instructions on the mobile device (app) user interface 120 which received movement measurements from sensors on the wearable device 110. In other examples, the mobility assessment 10 may take place before or during the treatment. The measurement data, which may be used for the mobility assessment and new treatment protocols, may be displayed on the mobile device (app) user interface 120 and also sent to a cloud server via WIFI. The measurement data may be processed using Machine Learning (ML) with input / output rules set for a variety of measurement data, and a new treatment session protocol may be created. Cycle is repeated. Here is an example of the machine learning process. Machine learning (ML) algorithms can be used to analyze movement, assessment and third-party data to identify specific patterns or anomalies, such as areas of reduced muscle tension, or activity, restricted movement, increased pain or reduced activity. These insights can enable the device to assess the severity and type of the condition, helping to determine the ideal vibration frequency, amplitude, and treatment duration. For instance, if the sensors detect increased stiffness and reduced mobility in a particular muscle group, the device could prepare a pretreatment protocol focusing on that region with lower-frequency vibrations to gradually relax the muscle before moving to deeper therapeutic vibrations. This process would be adjusted using machine learning algorithms.

[0101] In some examples, the mobility assessment 10 may vary depending on the progress of the recovery of the user. Different assessment protocols may be offered according to the progress. The mobility assessment 10 may measure moving parts of the body and determine their degree of function.

[0102] In some examples, the wearable device strap shown as 9 is designed for treatment of the lower back, but the wearable device strap can also be adapted to be provided on other body areas of musculoskeletal treatment such as the knee 9a, arm 9b or shoulder 9c. In other examples, the wearable device strap may be adapted to provide for more than one body area with a single strap. The musculoskeletal assessment features of the innovation apply to objective mobility assessment of these body parts in the same manner as described.

[0103] The mobility assessment would be related to the condition being treated, i.e., lower back mobility assessment for low back pain gathering data on movement of the lower back. A leg mobility assessment might be measuring knee movement mobility after knee surgery or arthritis. The machine learning algorithm may be adjusted for each body part to account for variation in muscle, joint mobility, pain levels, activity and position relating to that body part and how best to treat injury of that area.

[0104] Figure 5 shows an example of the data flow for a therapeutic focal vibration treatment session where the treatment session is selected and initiated by the user on the mobile device (app) user interface 120 in step 12, which may result in the mobile application sending a control signal to the controller to trigger an assessment mode. The treatment session information is sent wirelessly to the wearable device 110 in step 13 and a treatment is started. Data, by the one or more sensors, from the treatment session is then sent wirelessly back to the mobile device (app) user interface 120 in step 14 for processing and display. Data is then sent from the mobile device (app) 120 to a cloud-based server in step 15 for further processing (e.g., data being added to health records and can be dashboard for third party such as clinicians or health providers), storage and display by either the user or a third-party user. In some examples, a third party can ‘push’ a customized treatment protocol to a user after reviewing their data for example.

[0105] Figure 6 shows an example of the data flow for a functional mobility or musculoskeletal assessment session where the assessment session is selected and initiated by the user on the mobile device (app) 120 user interface in step 12. The assessment session information is sent wirelessly to the wearable device 110 in step 13. Data, e.g. by the one or more sensors, from the assessment session is then sent wirelessly back to the mobile device (app) user interface 120 in step 14 for processing and display to the user. Data is then sent from the mobile device (app) 120 to a cloud-based server in step 15 for further processing, storage and display by either the user or a third-party user. An algorithm for a mobility score may be created using a combination of data from the movement and position sensors. For example, positive changes on the data from these sensors would be averaged and displayed as a mobility score.

[0106] Figures 5 and 6 show the system in treatment or assessment ‘modes’, respectively. These can occur separately or concurrently if needed.

[0107] Figure 7 shows an example of the mobile device (app) user interface 120 for the functional mobility or musculoskeletal assessment (i.e., the assessment session). The user starts by wearing the wearable device 110 and initiating the assessment on the app 120 in step 16. Then the user performs a set of movements as guided by the mobile device (app) user interface 120 in step 17. While each movement is conducted by the user the wearable device measures and records movement data via a set of embedded sensors, then the wearable device sends the measurements wirelessly to the mobile device, which then displays the movement results on the mobile device (app) user interface. After each movement is completed, a new movement can be started. A prescribed series of movements is performed and records with the results displayed on the mobile device (app) user interface 120 in step 18. The completed series of movement tests form a mobility or musculoskeletal function assessment with a resultant score for objective monitoring, diagnosis or progress tracking. The score may be calculated by measuring movement and applying a weighting factor. The weighting factors may consider variables related to the personal data of the user (age, weight, condition, injury etc.) and / or may be guided by clinically guided rules, e.g. used in physiotherapy for treating musculoskeletal conditions.

[0108] The assessment can be used for tracking progress, for ML to adjust treatment protocols and also to judge which movement cause MSK pain (as pain can be recorded before, during and after assessment steps).

[0109] Figure 8 shows an example of a typical algorithm used in this invention. Key features are: a) User personal and health information, musculoskeletal survey information entered via an App. Data processed with added Machine Learning (ML1). For ML1, a weighting score is applied to users based on their personalization data and MSK health data. This will put users into categories of disability due to their condition and also apply an ’red flags’ that may affect the treatment and assessment protocols, i.e., longer duration + higher amplitude treatments for users with low disability. Weighting score factors may consider variables related to the personal data of the user (age, weight, condition, injury etc.) and put users into groups of different treatment patterns. b) Mobility assessment data (e.g., angular movement, movement speed, 3D movement signature) gathered by the wearable device prior to a focal vibration therapeutic treatment using the wearable device. c) Mobility assessment data and user input Pain Score data (e.g., user imputed using a scale of 1-10, which is a standard method to record pain (called NPRS)) are processed by the App and reported to server for display on App / Dashboard / Desktop via cloud service. A weighting may be applied to each of the mobility improvements / worsening and then create the score. In one example, the formula of ((lx + 2y + 3z) / n) may be used, where “lx”, “2y” and “3z” are each a combination of a mobility measurement and a weighting factor, and n is the number of data points or mobility measurements used. This is an example of how the algorithm may be applied. For example, x, y, z may be the mobility measurements, which may differ for each mobility assessment. Further, the coefficient (e.g., 1, 2, and 3) may be the weighting factors applied to their respective mobility measurement, e.g., based on their importance to the assessment.

[0110] Scores may be fed back to the wearable device using Machine Learning loops ML2 / ML3 to adjust the treatment output of the focal vibration therapeutic treatment using the wearable device.

[0111] The personal and health information is used in the ML algorithms to adjust treatment protocols and can include any one or more of:

[0112] Demographics: Age, gender, ethnicity, and race

[0113] • Medical history: Past medical history, diagnoses, and allergies

[0114] • Medications: Prescribed medications and medication history

[0115] • Vital signs: Vital signs and laboratory results

[0116] • Immunizations: Immunization dates

[0117] • Progress notes: Progress notes and problem lists

[0118] • Administrative and billing data: Administrative and billing insurance data

[0119] • Radiology: Radiology reports

[0120] The user may input such data on registration, however this information may also be obtained via a link to health information databases, such as Oswestry data.

[0121] Body worn device capable of functional musculoskeletal joint movement assessment combined with a focal vibration therapeutic treatment.

[0122] Machine learning guided focal vibration treatment driven by an onboard objective assessment function that mimics a clinician directed musculoskeletal assessment.

[0123] Ergonomic lightweight body-worn garment according to the enclosed drawings designed specifically for the above functions.

[0124] The device is suitable for remote treatment of musculoskeletal and joint conditions such as injuries or arthritis, neurological conditions (stroke, multiple sclerosis)

[0125] Figure 9 shows a function diagram, of the focal vibration device with wireless electronics controls and processing. The block diagram shows the modes of control from manual and app control options, along with switching options and LED outputs.

[0126] Figure 10 shows an example of how machine learning algorithms could be used to adjust the focal vibration treatment shown in Figure 8. For the example of ML2 an NPRS pain score is input by the user to an app. If the NPRS score is <= or >5 then the amplitude of the treatment is adjusted according to a rule set as shown. For the example ML3, a mobility score is calculated from on assessment score gathered during device assessment tests with a weighting factor applied for personalization factors. Then if the mobility score is <= or >5 then the frequency of the vibration treatment is adjusted according to list of optimum frequencies.

[0127] In one example, provided is a single self-applied system for the treatment and assessment of musculoskeletal conditions. The system comprises a wearable device. The wearable device may also be referred to as a focal vibration (known also as a local vibration, or focal muscle vibration) stimulation device. The wearable device is arranged to deliver a therapeutic treatment to the wearer for relief of ailments caused by a range of musculoskeletal conditions that require rehabilitation. Additionally, the treatment device is able to perform an objective physical therapy relevant assessment of functional and Musculoskeletal mobility on the targeted body area by recording measurements from a plurality of embedded sensors within the device. Results and data from the functional assessment can then be used to adjust the treatment function using a machine learning loop, hence providing an intelligent treatment / assessment cycle, similar to that provided by a physical therapist or clinician for rehabilitation or treatment of musculoskeletal conditions or injury. The described device in the specification relates to use for treatment and recovery of lower back pain but the invention may be used for other body areas such as knee or shoulder.

Claims

CLAIMS1. A system for providing focal vibration therapy, comprising a wearable device having: one or more vibration actuators for providing focal vibration therapy; one or more sensors for sensing data associated with positional user data and physiological user data when the wearable device is worn by a user; and a controller, configured to: operate the wearable device in an assessment mode to assess functional musculoskeletal movement and mobility, wherein in the assessment mode the controller is configured to access data from the one or more sensors when the user is carrying out movement(s) associated with the assessment, wherein said data forms sensor assessment data, operate the wearable device in a focal vibration therapy mode, wherein in the focal vibration therapy mode the controller is configured to control the operation of the one or more vibration actuators based on the sensor assessment data.

2. The system of claim 1, wherein in the focal vibration therapy mode, the controller is further configured to: access data from the one or more sensors when the user is receiving treatment, wherein said data forms sensor therapy data, and optionally adjust the operation of the one or more vibration actuators based on the sensor therapy data.

3. The system of claim 1 or 2, wherein the controller is arranged to control the operation of the one or more vibration actuators by controlling at least one of vibration intensity or amplitude and vibration frequency of the one or more vibration actuators.

4. The system of any one of claims 1 to 3, wherein the one or more sensors comprise at least one or more of the following: temperature sensor; inertial measurement unit (IMU), accelerometer, gyroscope, magnetometer. blood flow sensor, such as doppler or ultrasound / ultrasonic; and electrical activity sensor.

5. The system of any of the claims 1 to 4, wherein the controller is operatively coupled to a communications interface for enabling communication with at least one of a mobile application and a cloud platform.

6. The system of claim 5, comprising at least one of the mobile application andthe cloud platform.

7. The system of claim 5 or 6, wherein the controller is configured to operate the wearable device in the assessment mode in response to receiving a control signal from the mobile application.

8. The system of any one of claims 5 to 7, wherein the controller is further configured to: send data including sensor assessment data and sensor therapy data from the one or more sensors to at least one of the mobile application and cloud platform for processing, and receive processed data, including adjusted vibration intensity and vibration frequency parameters, from the mobile application or cloud platform.

9. The system of claim 8, wherein the mobile application is configured to: display guided instructions during the assessment mode; display data including sensor assessment data and sensor therapy data received from the one or more sensors; receive user input data or parameters from the user; process the data including sensor assessment data, sensor therapy data, and the user input data or parameters, optionally based on machine learning, to derive adjusted vibration intensity and vibration frequency parameters, and send the adjusted vibration intensity and vibration frequency parameters to the controller to adjust the operation of the therapy mode; send and receive data including sensor assessment data and sensor therapy data to the cloud platform for processing and storage / retrieval.

10. The system of claim 8, wherein the cloud platform is configured to: process data including sensor assessment data and sensor therapy data received from the controller or mobile application, optionally based on machine learning, to derive adjusted vibration intensity and vibration frequency parameters, and send the adjusted vibration intensity and vibration frequency parameters to the controller or the mobile application to adjust the operation of the therapy mode.

Images