Addressable serial electrode array for nerve stimulation and / or recording applications and wearable patch system with plate-carried sensing and magnetically attached disposable articles for rehabilitation and physics applications

Abstract

The present disclosure provides devices, systems, and methods for physical therapy. Electrical signals are applied to the subject via electrodes in a device worn on the body part receiving the therapy. The device can be operated remotely. The device may use artificial intelligence to evaluate and design a physical therapy procedure using the electrodes.

Description

[0001] Cross-references

[0002] This application claims the benefit of U.S. Provisional Application No. 63 / 328,349, filed on April 7, 2022, which is incorporated herein by reference in its entirety. Background Art

[0003] Neurostimulation techniques use invasive or non-invasive methods that apply electromagnetic energy to anatomical targets and induce neuromodulation of corresponding neural circuits for neurorehabilitation and other applications. However, many neurostimulation systems have a small number of electrodes, which limits the number and precision of muscle and neural targets that can be activated, and they are generally not portable or wearable.

[0004] Wiring the many electrodes in transcutaneous devices for neural or electrical stimulation and recording is challenging. Electrodes take up a very large amount of space. Routing a large number of wires to the intended site of stimulation can be difficult and expensive. For wearable transcutaneous applications, multi-layer flexible circuit boards carry the risk of reduced flexibility. Summary of the invention

[0005] In some embodiments, the present invention provides a device comprising: a first item, wherein the first item comprises 1) a first top surface, wherein the first top surface comprises a set of first connectors; and 2) a first bottom surface, wherein the first bottom surface comprises a plurality of electrodes; and a second item, wherein the second item comprises 1) a circuit board, wherein the circuit board is operably connected to the plurality of electrodes; 2) a second top surface, wherein the second top surface comprises a plurality of visualization aids, wherein each of the plurality of visualization aids independently corresponds to one of the plurality of electrodes; and 3) a second bottom surface, wherein the second bottom surface comprises a set of second connectors, wherein each of the first connectors is independently configured to couple to one of the second connectors, wherein the first connector and the second connector are configured to form a connection, and when the first connector is coupled to the second connector, the connection holds the first item and the second item together, wherein when the first item and the second item are operably connected, the first item and the second item together form a wearable object, wherein the wearable object has a wearable size and a wearable shape suitable for mounting on a part of a human body.

[0006] In some embodiments, the present invention provides a device, comprising: a) a first item, wherein the first item is disposable, wherein the first item comprises: 1) a bottom layer, wherein the bottom layer comprises: A) a hydrogel; and B) a plurality of electrodes in contact with the hydrogel, wherein the plurality of electrodes are connected in sequence, wherein the plurality of electrodes are flexible, wherein the plurality of electrodes are silver ink, wherein the plurality of electrodes are configured to stimulate the muscle tissue and the neural target when the plurality of electrodes provide electrical stimulation to the muscle tissue and the neural target; 2) an intermediate layer, wherein the intermediate layer comprises a dielectric material, wherein the intermediate layer is laminated on top of the bottom layer, in contact with the bottom layer, and is operable to connected to the bottom layer; and 3) a top layer, wherein the top layer includes a set of first connectors, wherein the first connectors are magnetic, wherein the top layer is stacked on top of the middle layer, contacts the middle layer, and is operably connected to the middle layer, wherein the bottom layer has a bottom layer shape, the middle layer has a middle layer shape, and the top layer has a top layer shape, wherein when the bottom layer and the middle layer are operably connected, and the middle layer and the top layer are operably connected, then the bottom layer shape, the middle layer shape, and the top layer shape substantially overlap; b) a second article, wherein the second article is durable, wherein the second article includes: 1) a second top surface, wherein the second top surface comprising a plurality of visualization aids, wherein each of the plurality of visualization aids independently corresponds to one of the plurality of electrodes, wherein the plurality of visualization aids are LEDs, wherein each visualization aid is configured to provide a visual signal when the electrode corresponding to the visualization aid emits an electrical signal; 2) a flexible circuit board comprising conductors, the flexible circuit board operably connected to the plurality of electrodes; and 3) a second bottom surface, wherein the second bottom surface comprises a set of second connectors, wherein the second connectors are magnetic, wherein each of the first connectors is independently configured to couple to one of the second connectors; and c) a control system operably connected to the second item, wherein the control system includes: 1) a power source; 2) a processor operably connected to the power source and configured to operate the device; 3) a stimulator operably connected to the processor, operably connected to the power source, and configured to transmit electrical stimulation to the flexible circuit board; 4) a wireless receiver operably connected to the processor and configured to receive instructions from a user for transmitting electrical stimulation to the flexible circuit board; 5) a memory system operably connected to the processor and configured to record information about the use of the device;6) a transmitter operably connected to the processor and configured to wirelessly transmit stimulation provided to a human body part in physical contact with the device and a record of movement of the human body part in response to the stimulation to a receiver external to the device; and 7) a motion detector operably connected to the processor and configured to detect movement of the human body part in physical contact with the device, wherein the power supply, the processor, the stimulator, the wireless receiver, the memory system, the transmitter, and the motion detector are in a common housing, wherein the first connector and the second connector are configured to form a connection that holds a first item and a second item together when the first connector is coupled to the second connector, wherein when the first item and the second item are operably connected, the first item and the second item together form a wearable item, wherein the wearable item has a wearable size and a wearable shape suitable for mounting on a human body part, wherein the first item has a first item shape and the second item has a second item shape, wherein when the first item and the second item are operably connected, the first item shape and the second item shape substantially overlap, and wherein the bottom layer has at least 25 cm; 2 surface area.

[0007] In some embodiments, the present invention provides a method comprising: a) contacting a body part of a human subject with a plurality of electrodes, wherein the plurality of electrodes are operably connected to a flexible circuit board, wherein the body part has a shape; b) manipulating the flexible circuit board to substantially conform to the shape of the body part; c) operably connecting a plurality of visualization aids to the flexible circuit board, wherein each of the plurality of visualization aids independently corresponds to one of the plurality of electrodes; and d) applying current to the plurality of electrodes, whereby the plurality of electrodes provide electrical stimulation to the body part.

[0008] In some embodiments, the present invention provides a method comprising: a) contacting a body part of a human subject with a plurality of electrodes, wherein the plurality of electrodes are operably connected to a flexible circuit board, wherein the body part has a shape; b) manipulating the flexible circuit board to substantially conform to the shape of the body part; c) receiving instructions from a wireless user device for transmitting electrical stimulation to the flexible circuit board; and d) selecting at least a portion of the plurality of electrodes and applying an electric current to the portion of the plurality of electrodes, whereby the portion of the plurality of electrodes provides the electrical stimulation to the body part.

[0009] In some embodiments, the present invention provides an addressable electrode system, comprising: a power source; and an article, the article comprising: (i) a plurality of sequentially connected electrodes; (ii) a plurality of indicators; and (iii) a plurality of switches, each switch independently comprising a first terminal, a second terminal, and a third terminal; wherein the first terminal of the switch is electrically coupled to the power source; wherein the second terminal of the switch is electrically coupled to one of the plurality of indicators; wherein the third terminal of the switch is electrically coupled to one of the plurality of sequentially connected electrodes; and wherein the switch is configured to simultaneously provide electrical power to the electrode and the indicator when power is provided to the first terminal of the switch by the power source.

[0010] Incorporated by Reference

[0011] Each patent, publication, and non-patent document cited in this application is hereby incorporated by reference in its entirety, as if each were individually incorporated by reference. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 A schematic diagram for implementing addressable electrodes used in the wearable system described herein is shown.

[0013] Figure 2 A set of electrode configurations described herein is shown.

[0014] Figure 3 A thin, lightweight, flexible, wearable system is shown.

[0015] Figure 4 A flexor wearable system on the inner forearm for neural stimulation is shown, which evokes finger and wrist flexion movements.

[0016] Figure 5 Shows Figure 3 Another view of the wearable system.

[0017] Figure 6 Shows Figure 3 An exploded view of the wearable system.

[0018] Figure 7 A wireless control system and method for controlling neural stimulation via the wearable patch system described herein is shown.

[0019] Figure 8 Shown are side views of a second article (electronic patch system) and a first article (disposable system) described herein.

[0020] Fig. 9 Shown are views of a disposable system described herein.

[0021] Fig.10 An electrode array of the disposable system described herein is shown.

[0022] Fig.11 A wrist-worn embodiment of the wearable patch system described herein is shown.

[0023] Fig.12 A stimulation module as described herein is shown.

[0024] Fig.13 A disposable electrode array configured to be attached to a patient's forearm and thumb is shown.

[0025] Figure 14A-14E A disposable electrode array is shown attached to a patient's forearm and thumb.

[0026] Figure 15A-Figure 15C A durable / reusable electronic patch attached to a disposable electrode array is shown.

[0027] Figure 16A-16C The fixation of an assembly comprising a durable / reusable patch and a corresponding disposable electrode array attached to the patient's forearm is shown.

[0028] Fig.17 The stimulator module is shown attached to the patient's wrist.

[0029] Fig.18 The connections between the stimulator and the flexor and extensor patches and the thumb disposable electrode array via cables are shown.

[0030] Fig.19 A graphical user interface (GUI) of an application that allows a user to control stimulation is shown.

[0031] Fig. 20 A GUI of an application that allows a user to control manual stimulation is shown.

[0032] Fig.21 The user is shown selecting multiple locations on the patch to perform electrical stimulation, with each location indicated by an LED.

[0033] Fig. 22 A GUI of an application that allows a user to control thumb stimulation is shown.

[0034] Fig.23 The GUI of the application for executing the stimulation sequence is shown. DETAILED DESCRIPTION

[0035] Neurostimulation can use electrical pulses to trigger muscle contraction or modulate nerves, spinal cord, or spinal roots. A device can generate pulses and deliver them to the skin near the stimulated muscle and nerve target through electrodes. The electrodes can be pads attached to the skin or in contact with the skin. The pulses provided can evoke action potentials in the nerves or cause muscle contraction. Neurostimulation is used, for example, in rehabilitation (e.g., physical therapy or occupational therapy), in strength training, and in evaluating nerve function. For example, neurostimulation can be used to address muscle atrophy, improve muscle weakness, or modulate spinal cord pathways to promote recovery of motor or sensory function.

[0036] Neurostimulation technology has provided positive results in neurorehabilitation and physical therapy applications, including post-stroke and injury cases. These results include improvements in movement, sensation, and independence for those living with disabilities. Neurostimulation systems with a small number of electrodes limit the number and precision of muscle and neural targets that can be activated and are generally not portable or wearable. In addition, systems / devices that do not include onboard sensing or microprocessors that can execute AI or machine learning algorithms to discern user intent may be less intuitive and practical for assistive and rehabilitation applications. User-driven neurostimulation that facilitates goal-directed rehabilitation tasks is much more effective than passive stimulation.

[0037] Another challenge in neurostimulation devices and systems is that manual placement of electrodes is difficult and time-consuming. This challenge hinders the positioning and stimulation of smaller muscles, such as those controlling the hands and fingers and spinal dorsal root targets, which are important in promoting plasticity and recovery.

[0038] The present disclosure provides systems and methods for solving the above challenges in neural stimulation. A system is disclosed herein that provides dynamic (electronically configurable) electrical stimulation to a target body region to a wearable, user-driven device. The system can be, for example, a thin, lightweight, flexible, wearable patch system. Non-limiting examples of body regions to be treated with the system include feet, calves, thighs, hips, buttocks, lower back, upper back, abdominal region, chest, shoulders, upper arms, forearms, wrists, hands, skull base, head (e.g., top of the head, forehead) and spinal cord. An exemplary device or system includes one or more items, such as a patch. For example, the item is placed behind, in front of, outside or inside the body. One or more items in the device or system can include a set of electrodes (e.g., arranged in an array, sequence or matrix) to contact the skin and provide electrical stimulation to the underlying muscle. In some embodiments, the item is communicatively coupled to a unit that provides an electrical signal. In some embodiments, the item is communicatively coupled to a microprocessor that is configured to select an electrical signal to stimulate a specific muscle, nerve or spinal cord root corresponding to a specific region of the body. In some embodiments, the systems and methods disclosed herein are used for electrical muscle stimulation (EMS), electrocorticography, or electroencephalography.

[0039] The device or system may include multiple electrodes. In some embodiments, the electrodes are daisy-chained (eg, wired together in sequence) and communicatively coupled to an indicator or control system via a switch (eg, a solid-state relay).

[0040] In some embodiments, the device or system includes a machine learning software module. The machine learning software module uses one or more machine learning algorithms to analyze the movement of the body part to which electrical stimulation is provided. The machine learning algorithm can be trained by collecting data related to the electrical signals provided to the muscle and / or neural targets (e.g., spatial information about which electrodes on the patch provide signals), the movement of the body part, or both to predict the movement of the body part. Non-limiting examples of movement include extension, flexion, angular movement (e.g., rotation), clenching (e.g., making a fist), and relaxation of one or more body parts. In some embodiments, the movement is an exercise (e.g., pressing, curling, stretching, squatting, throwing, or hip hinge).

[0041] In some embodiments, the wearable system is configured to interoperate with a brain-computer interface (BCI). A device (e.g., a helmet) can obtain electrical signals from the brain and provide the signal to the wearable system. The wearable system may include a processor configured to execute instructions based at least in part on the signal to stimulate specific electrodes. An algorithm (e.g., a machine learning algorithm) can interpret signals from the brain to determine body movements associated with the signal. Based on this interpretation, a controller can drive electrodes to stimulate these body movements. Subjects suffering from diseases, injuries, or conditions that prevent the brain from achieving motor functions can use the wearable system disclosed herein to restore these motor functions.

[0042] Wearable system

[0043] Devices and systems disclosed herein include wearables, such as articles, patches, textiles, fabrics, and other wearable systems. In some embodiments, the wearable systems disclosed herein (e.g., wearable patch systems) can be configured to be incorporated into other textile articles, such as medical articles or clothing (e.g., casts, wraps, stents, bandages, robes, shirts, pants, underwear, watches, bracelets, headbands, helmets, or sportswear).

[0044] The wearable system can be configured to be worn by a subject. The subject can be a human subject or a non-human subject. For example, the subject can be a mammalian subject such as a dog, cat, horse, cow, pig, sheep, goat, rabbit, elephant, camelid (e.g., camel, alpaca, or llama), mouse, hamster, guinea pig, ferret, buffalo, donkey, deer, or monkey. The wearable system can be worn by a bird or reptile (e.g., chicken, duck, goose, emu, eagle, alligator, or crocodile).

[0045] In some embodiments, a system includes a first article configured to provide an electrical signal to a body part and a second article configured to provide an indication of where on the body the electrical signal is being provided.

[0046] In some embodiments, the electrical signal is configured to be used for nerve stimulation (e.g., muscle tissue or nerve target stimulation). For example, the electrical signal provided by the system disclosed herein can cause muscle contraction. The electrical signal is provided by an electrode placed on the skin surface near the stimulated muscle. In some embodiments, the system provides therapy by causing repeated muscle contraction and improving blood flow to stimulate the repair of injured muscles. Repeated contraction and relaxation cycles can also improve muscle strength. The system disclosed herein can be used for various types of muscle electrical stimulation, including transcutaneous electrical nerve stimulation (TENS), muscle electrical stimulation (EMS), electrical stimulation for tissue repair (ESTR), interferential current (IFC), neuromuscular electrical stimulation (NMES), functional electrical stimulation (FES), spinal cord stimulation (SCS) and iontophoresis.

[0047] In some embodiments, the first article has a first article shape. The second article has a second article shape. When the first article and the second article are operably connected, the first article shape and the second article shape may substantially overlap. In some embodiments, the second article shape may be larger than the first article shape. The first article shape and / or the second article shape may conform to at least a portion of a body part of a subject (e.g., a human subject). For example, the first article shape and / or the second article shape may be bent, flexed, or folded to provide sufficient electrical contact and / or physical contact or coupling with a part of the body. The first article may be disposable. The second article may be durable. The first article may include a bottom layer, an intermediate layer, and a top layer. The intermediate layer may be stacked on top of the bottom layer, may be in contact with the bottom layer, and may be operably connected to the bottom layer. The top layer may be stacked on top of the intermediate layer, may be in contact with the intermediate layer, and may be operably connected to the intermediate layer.

[0048] In some embodiments, the first article includes a plurality of electrodes and a layer of hydrogel.

[0049] Figure 3 A thin, lightweight, flexible, wearable system as described herein is shown. The wearable system can include a first item and a second item, such as a patch or textile, which can be physically and / or communicatively and / or electrically coupled. The second item can be disposed above the first item so that a portion contacts the subject's skin and a surface of the first item is visible. In some embodiments, the first item comprises a disposable system. The disposable system includes, for example, a plurality of disposable magnetic connectors for coupling the first item to the second item. The magnetic conductor can be conductive and thus configured to pass an electric current through the wearable system. Thus, the magnetic connector can provide both magnetic coupling and electrical coupling. In some embodiments, the second item comprises an electronic patch system.

[0050] The electronic patch system may include multiple patches. The patch may be made of pleats of a textile (e.g., a fiber-based material such as a fabric or cloth). The patch may include at least one indicator (or visual aid). Multiple indicators may be provided or arranged on a second item. The indicator may be placed above (e.g., disposed on the top of the patch) or below the patch so that the indicator and the patch correspond. The patch (and therefore the indicator) may be arranged in an array (e.g., a square or rectangular array, or any shape suitable for an intended body part). The indicator may include an audio indicator, a visual indicator, a tactile indicator, or an audiovisual indicator or a combination thereof. For example, in some embodiments, the indicator generates light and / or sound to warn the subject or user where and when an electrical signal is provided to the subject's body by one or more electrodes of the wearable patch system. The indicator may include, for example, a light emitting diode (LED). The indicator of the second item may correspond to one or more electrodes of the second item. When the corresponding electrode transmits a signal, the indicator may simultaneously generate a light or visual signal. For example, one or more electrodes of the first item may be placed directly below a specific indicator of the second item. When neural stimulation is provided simultaneously by multiple electrodes at different spatial regions of the patch system, indicators of the corresponding regions can simultaneously provide audiovisual signals (e.g., light up). In this way, stimulation patterns of muscle tissue and neural targets from different regions of the body under the patch can be displayed on the surface of the second article.

[0051] The electronic patch system may include a stimulator module or control system. The stimulator module may control the provision of electrical signals to a body part and monitor and record data generated by nerve stimulation caused by the provided electrical signals. The stimulator module may include multiple modular components within a housing.

[0052] The stimulator module may include a processing unit or processor (e.g., a microprocessor). In some embodiments, the processor is outside the stimulator module and is operably coupled to the stimulator module. The processor may receive instructions (e.g., provided by a health care professional or automatically provided by a computer program, e.g., by an algorithm) indicating a group of electrodes on a first article of a wearable system for providing neural stimulation to a body area covered by the wearable system. The instruction may also include a corresponding group of indicators to provide an audio signal, a video signal, a tactile signal, an audio-visual signal, or a combination thereof to a user (e.g., a wearer of a subject or patch, a supervisor, or a health professional). The processor may use, for example, a personalized resistor to determine which patch (and indicator) corresponds to which group of electrodes.

[0053] The processor may implement instructions configured to control neural stimulation. For example, the control instructions may define which electrodes will provide stimulation and at what time the stimulation will be provided. The control instructions may provide a pattern of electrical stimulation. For example, the control instructions may direct that electrical pulses be provided to a specific muscle or neural target periodically (e.g., every second, every five seconds, every 10 seconds, every 20 seconds, or every 30 seconds).

[0054] The processor may implement instructions defining the characteristics of the electrical pulses. For example, the electrical pulses may have a frequency between 1 Hz and 10 Hz, 11 Hz and 20 Hz, 21 Hz and 30 Hz, 31 Hz and 40 Hz, 41 Hz and 50 Hz, 51 Hz and 60 Hz, or 61 Hz and 70 Hz. The pulse duration may be between 50 microseconds and 100 microseconds (μs), between 100 μs and 150 μs, or between 150 μs and 200 μs. The stimulation duration may be between 0 and 5 seconds, between 5 seconds and 10 seconds, between 10 seconds and 20 seconds, or between 20 seconds and 30 seconds.

[0055] The instructions may be received from an external computing device (e.g., from a mobile computing device) connected via a wired network or a wireless network. The network may be, for example, an Ethernet network, a Wi-Fi network, or a Bluetooth network.

[0056] The stimulator module may include a motion sensing device that may include an inertial measurement unit (IMU). The IMU may include an inertial sensing integrated circuit (IC) having, for example, six or nine degrees of freedom (DOF) to sense different types of rotational motion (e.g., surge, heave, and sway) about a set of axes and translational motion (e.g., roll, pitch, and yaw) about a set of axes. The inertial measurement unit may include, for example, one or more accelerometers, gyroscopes, and / or magnetometers.

[0057] The stimulator module may include a machine learning software module that provides one or more machine learning models that may be configured to process measurements generated by the IMU, electrical signals provided by electrodes, or instructions for providing electrical signals to predict the movement of a body part wearing the patch. In some cases, the machine learning software module is external to the stimulator module. For example, the machine learning software module may be located on a server that is communicatively coupled to the stimulator module (e.g., via a wired network or a wireless network).

[0058] In some embodiments, the stimulator module (or control system) or processor is operably connected to a power source. In some embodiments, the power source and the stimulator module are in a common housing. The power source may include a battery. The power source may include an AC adapter. In some embodiments, the stimulator includes electrical components sufficient to obtain voltage and power from a main power source when plugged into a wall socket.

[0059] The stimulator module may further include a memory system operably connected to the processor and configured to record information about the use of the wearable patch system. The memory system may additionally include one or more machine learning models that can be executed by the processor on the data recorded in the memory.

[0060] The stimulator module may further include a transmitter operably connected to the processor and configured to wirelessly transmit information about the use of the device to a receiver external to the device. The transmitter may transmit the information via radio waves, such as through a Wi-Fi network or a Bluetooth network.

[0061] The disposable system may include a dielectric disposed above a plurality of electrodes. The dielectric may include any material that may serve as an electrical insulator and may be polarized by an applied electric field, such as porcelain, glass, mica, metal oxide, or plastic. Exemplary plastics may include thermoplastic polymers, such as polyvinyl chloride (PVC or vinyl) or polyethylene terephthalate (PET). The electrode may be a flexible electrode. The electrode may include a paste or ink made of one or more conductive materials or substances (e.g., metals, such as silver or gold). In some embodiments, the electrode is coated with carbon nanotubes.

[0062] Figure 3 A device worn on a forearm is shown. The exemplary device includes two sets of first and second items communicatively and physically coupled together, wherein the first set is configured to be worn on the back of a forearm and the second set is configured to be worn on the inside of a forearm. The wearable device on the back and inside of a forearm can provide electrical stimulation to muscle and neural targets configured to evoke movement of the wrist, hand, and fingers.

[0063] Figure 4 A flexor wearable system located on the inner forearm is shown for stimulating muscle and neural targets that evoke finger and wrist flexion-type movements as described herein. Figure 3 , Figure 4 Embodiments of the invention include an electronic patch system and a disposable system. The flexor patch system includes an opening that allows for pronation and supination of the wrist. In some cases, the same wearable system can be worn on the other side of the arm to stimulate additional muscle and nerve targets that perform complex movements.

[0064] Figure 5 Shows Figure 3 Another view of the wearable system. Figure 5 A first wearable system to be placed on the inside of the forearm and a second wearable system to be placed on the outside of the forearm are shown. Figure 5Additionally shown is a view of the first wearable patch system, the second wearable patch system, and the stimulator module side by side.

[0065] Figure 6 An exploded view of the wearable system described herein is shown. Figure 6 A second article (electronic patch system), a stimulator module, a first article (disposable system) and a cable are shown. The disposable can have a conductor paste or ink (e.g., silver ink) electrode on one side and a magnetic connector on the opposite side. This arrangement can produce a mechanical connection and an electrical connection with a durable / reusable electronic patch system. The stimulator (wrist-worn) can include a cloth or fabric band including an adhesive unit such as Velcro or a magnetic buckle. In some embodiments, a forearm band (not shown) can be included to surround the device when worn on the user's arm. These bands can keep all elements of the wearable patch system in good contact. These bands can be textile elastic and can have, for example, Velcro or a magnetic buckle connection.

[0066] In some embodiments, at least two stimulators can be connected to multiple patches. For example, a wearable system can include a first wearable patch system, a second wearable patch, and a first stimulator module, such as Figure 5 As shown. The first wearable patch system and the second wearable patch system can be applied to the forearm of the patient and controlled by the first stimulator module connected thereto. The wearable system can further include a third wearable patch system connected to the second stimulator module. For example, the third wearable patch can have a smaller size and can be applied to the patient's neck, and when controlled by the second stimulator, neural stimulation can be provided to the patient's spinal cord. When the patient wears the forearm patch and the patch near the spinal cord, both produce neural stimulation, and the efficacy of the stimulation can exceed the efficacy of the forearm muscle stimulation alone.

[0067] In some embodiments, wireless control system can be used to control neural stimulation via one or more stimulators. When multiple patches are connected to stimulator, user can use wireless control system to control neural stimulation. User can transmit wireless signal to stimulator, and stimulator then controls to provide electrical signal to body part from specified patch, and monitors and records the data of neural stimulation caused by provided electrical signal. For example, stimulator can control two forearm patches to produce neural stimulation with given mode, and produce neck patch with another given mode. Stimulator can control simultaneous stimulation from multiple patches. Alternatively, stimulator can control stimulation from different patches to occur with any configuration (for example, sequence or spatial arrangement) provided by user. User can save configuration and mode of neural stimulation generated from different patches for future use, without manual setting repeatedly.

[0068] In some embodiments, the wearable patch can include a transmitter that is operably connected to a processor in the patch and is configured to be wirelessly transmitted to other wearable patches. The transmitter can send information via radio waves, such as sending information through a Wi-Fi network or a Bluetooth network. Therefore, the wearable patch can communicate with other patches and control other patches. For example, a forearm patch and a neck patch can include a transmitter that is operably connected to a processor in the patch. When the forearm patch produces neural stimulation, the forearm patch can automatically control the neck patch to produce neural stimulation. Dual stimulation can significantly improve the efficacy of rehabilitation and strength training of motor or sensory functions. In addition, stimulating the spinal cord in this way can lead to greater plasticity and / or adaptability of the body, thereby providing improved rehabilitation.

[0069] Figure 7 A wireless control system and method for controlling neural stimulation via a wearable system is shown. A telecommunications system or mobile device may include an application for configuring, controlling, and / or monitoring neural stimulation from a wearable patch system (e.g., during physical therapy, occupational therapy, sports training, or medical rehabilitation), and collecting data related to electrical signals provided to the skin and movement of a body part in response to the provided electrical signals. The data may be provided to an external server (such as a cloud server) for further analysis (e.g., machine learning analysis).

[0070] A telecommunications system (e.g., a mobile device) can be configured to provide an analysis of the performance of a human subject using a wearable system in therapy, and to determine a proposed therapy regimen based on the analysis. For example, the telecommunications system can process or provide processing of motion data of a human subject to determine whether the subject is exercising correctly, or to determine a person's ability to perform complex movements or sequences of movements. This analysis can be performed using machine learning or statistical methods. In addition, the telecommunications system can analyze the movements of a human subject undergoing therapy induced by providing neural stimulation, and compare the movements with movements performed by a healthy individual. The characteristics of the analyzed movements can indicate specific situations that require a specific therapy regimen. For example, the analysis can determine that a person cannot effectively grasp an object, or cannot exercise with an appropriate range of motion. The system can recommend therapy to correct these situations. The proposed therapy regimen may include activating electrodes in a mode that is determined to provide improvements in physical therapy based on the analysis.

[0071] The application can be a desktop application or a mobile application (for example, Application or Application). The application for configuring, controlling and / or monitoring neural stimulation facilitates configuration, control or monitoring via a user interface. A non-limiting example of a user interface is a graphical user interface (GUI). In some embodiments, the GUI includes a layout. The layout can be two-dimensional. In some embodiments, the layout is three-dimensional (e.g., when multiple wearables are located at different locations on the body and electrodes can be addressed using a three-dimensional coordinate system instead of a two-dimensional coordinate system). The layout can include a grid. The grid can use Cartesian coordinates or polar coordinates. In some embodiments, the three-dimensional grid uses Cartesian coordinates, cylindrical coordinates, or spherical coordinates. A point on the grid can include two separate electrodes in an arrangement of electrodes. The arrangement of electrodes can be incorporated into or embedded in an article (e.g., a first article of a wearable system).

[0072] The electrical pulse or neural stimulation pulse can be initiated by a gesture provided to the UI. The gesture may include physical contact (e.g., with the subject's body or with an instrument or tool). The gesture may be generated by a human hand or by one or more fingers of a human hand. In some embodiments, the gesture may be generated by another body part. For example, in the case of paralysis or paraplegia of the subject, a gesture may be generated by the movement of one or both eyes (which may include blinking or blinking). The gesture may include touch. Touching the UI on a point on a user interface (e.g., a grid) may generate a control signal that may be used to provide neural stimulation or electrical stimulation to the subject via electrodes that contact the subject and correspond to the points on the user interface. Touching may include one or more taps. Tapping a point on the grid may generate an electrical pulse having the same duration as tapping. Repeated tapping of a point on the GUI may generate repeated pulses provided by the corresponding electrode (e.g., as a time series sequence). Tapping multiple points on the GUI may generate spatially distributed pulses on the grid. Touching may also include pressing on the UI (e.g., pressing of a finger or stylus). The pulse may last for a duration as long as the pressing. Touching can include sliding or dragging a finger or stylus while pressing against the surface of the device providing the UI. When a finger or stylus slides or drags over a point on the UI, the corresponding electrodes can be stimulated or activated (e.g., momentarily) to produce a pulse. Gestures can include a combination of tapping, pressing, and dragging (e.g., when multiple fingers or hands are used).

[0073] In one example, a user presses down at a certain location on the screen and slides a finger across the screen (e.g., in a shape or pattern such as a straight line, a circle, or a figure 8). As the finger slides across the screen, the corresponding electrodes activate instantaneously, reflecting the movement pattern on the finger. In this way, dynamic electrical stimulation simulating the movement of the finger is provided to the subject's body, so that the electrical pulses can be considered to "move" through the body parts covered by the electrode array.

[0074] Gestures can stimulate multiple electrodes simultaneously (e.g., in a spatial configuration). For example, multiple fingers, digits, or tools (e.g., a stylus) can tap, press, slide, and / or drag multiple points on the UI.

[0075] The gestures may be performed or provided using an input / output (I / O) device such as a keyboard, a mouse (e.g., by clicking or clicking and dragging), a trackball, a microphone (e.g., audio control or voice-controlled neural stimulation), a motion capture device (e.g., a camera that can monitor gestures that do not involve physical contact with a device including the UI), a joystick, or other I / O device. The UI may allow a user to enter a sequence of commands (e.g., a script) or upload a computer program that includes instructions for performing neural stimulation using specific electrodes of the array.

[0076] The UI can provide control of multiple electrode arrays (e.g., incorporated into multiple wearable patches). The UI can use a split screen to implement this control, wherein each split screen presents a grid including a different electrode array. In some embodiments, the UI can display multiple grids (e.g., two, three, four, five, or ten grids) simultaneously. In some embodiments, multiple UI windows can be displayed and interacted with on multiple screens or monitors.

[0077] A control signal may be provided to one or more stimulation modules. The control signal may be provided over a network (e.g., Bluetooth, Wi-Fi, or a wired network (e.g., Ethernet)). The control signal may encode information related to the type of gesture performed and / or spatial position information related to the gesture (e.g., for providing a spatial pattern of recommended neural stimulation pulses to the subject). The control signal may provide this information as an instruction that, when executed by a processor, connects the corresponding electrodes of the electrode array to a power source (e.g., via a power source or power source, such as a battery or an alternating current (A / C) adapter) using switches connected to and corresponding to the electrodes so that current is provided to the electrodes. For example, the instruction may place a first plurality of switches in an "on" position and a second (non-overlapping) plurality of switches in an "off" position, allowing neural stimulation to be generated to the electrodes connected to the "on" switches. In this manner, the current provided to the electrodes provides the subject with a spatial pattern of recommended neural stimulation pulses corresponding to the gesture provided to the UI.

[0078] Non-limiting examples of mobile devices or telecommunication systems include cell phones, smart phones, personal digital assistants (PDAs), laptop computers, desktop computers, and other types of computing devices.

[0079] Mobile devices can be used to provide dynamic (e.g., electronically movable) stimulation to subjects wearing wearable systems. Dynamic stimulation can use a touchpad or screen area on a mobile device to allow rapid motion point mapping on a body part (e.g., forearm). The technology can include, for example, an operator (e.g., a subject wearing a patch system or a health care provider) slides a finger or stylus on a touch screen control object or area to change the location where stimulation occurs on the subject's body part (i.e., which (which) electrodes on the selected patch). People can repeatedly tap a specific section of the stylus or grid to repeatedly provide electrical pulses to a specific area covered by the wearable system. An indicator (e.g., LED) indicates the current stimulation (activated electrode) position on the electronic patch system of the wearable patch system.

[0080] The user interface allows for modification of the pulses provided to the subject. For example, the user interface allows for modification of the pulse frequency, pulse duration, and / or stimulation duration. These characteristics can be changed dynamically. For example, the pulse frequency and / or pulse duration can be manually changed throughout the stimulation process. In some cases, the pattern of changing the pulse frequency and / or pulse duration can be programmed using the user interface.

[0081] Figure 8 A side view of a second article (electronic patch system) and a first article (disposable system) described herein is shown. The second article includes an indicator 802 (e.g., LED) interspersed with a solid-state relay 801. The LED is disposed above a flexible circuit or printed circuit board (PCB) 806. The underside of layer 810 may be an electrical connection system including contacts 805 of a metallized (e.g., gold) material connected to a magnet 803. The first article may include a vinyl surface 812 used as a dielectric, wherein a ferromagnetic disk 808 and a foam with a conductive adhesive 809 are disposed above the surface, and a silver ink electrode 811 is attached to the skin via a hydrogel 820. In some embodiments, alternative adhesives and conductive materials for electrodes may be used.

[0082] Removing hydrogels from metal electrodes can be difficult, time consuming, and often leaves unwanted residue. The disclosed system can solve this problem using magnetic connections by creating a multi-layer disposable with a hydrogel layer (on the bottom / skin side), a silver ink that forms a flexible electrode, a dielectric (e.g., vinyl or polyethylene terephthalate (PET)) layer, and a magnetic (and electrical) connection layer on top that is attached to a durable electronic patch system. The disposable system can then be removed and discarded after a certain number of uses without leaving residue on the electronic patch system.

[0083] The electronic patch system can be made of a flexible circuit board construction with, for example, gold-plated copper as the conductor that carries the stimulus energy. The plating, for example, nickel-copper-nickel, can be bonded to the flexible circuit conductor using, for example, a conductive epoxy or a conductive pressure sensitive adhesive (also known as a conductive transfer tape or a conductive double-sided tape (e.g., 3M 9711S)).

[0084] Fig. 9 A view of a disposable system described herein is shown. The disposable system can include a magnetic attachment and an electrode array. The magnetic attachment can automatically align the electronic patch system with electrical contacts on the disposable electrode array. The electrode array can include a plurality of electrodes configured to provide electrical signals to human skin.

[0085] Fig.10 An electrode array of a disposable system described herein is shown. The electrode array can be shaped to fit various body parts. The electrode array can also conform to a body part or portion of a body part (e.g., by bending or folding) while maintaining mechanical contact between the body and each electrode (while allowing lateral sliding when a body part, muscle flexes, or a neural target is under the electrode array), and additionally maintaining electrical contact between the body and the electrodes, allowing stimulation current to be sent to the electrodes through a conductive coating on a magnet in a magnetic attachment. Fig.10 Also shown is a thumb electrode array geometry that can cover the thumb rotator cuff plus the lateral and oblique adductor muscles.

[0086] In some embodiments, the electrodes are arranged in a square or rectangular arrangement. This arrangement can be used for neuromuscular electrical stimulation (NMES) or transcutaneous electrical nerve stimulation (TENS). The stimulator module can support multiple waveforms of both NMES mode or TENS mode.

[0087] Fig.11 A wrist-worn embodiment of a wearable system is shown. The wrist-worn embodiment may include, for example, a stimulator unit 1101 , an electrode array with hydrogel 1102 , and a wrist band 1103 .

[0088] Fig.12 An example of a stimulation module is shown. The stimulation module may include a microprocessor, an inertial motion sensor (IMU), a battery, accessible electrodes, and stimulation circuitry. Fig.12 Embodiments of the present invention are configured to be worn on the wrist, but in other embodiments, the stimulation module is worn on another part of the body. In some embodiments, the stimulation module is embedded in the patch. The wearable patch system can also be wirelessly linked to a brain-computer interface (BCI) system, for example.

[0089] The stimulation module may be used in applications including upper limb stimulation, lower limb stimulation (for both quadriceps and dorsiflexion), and neck stimulation (base of the neck).

[0090] The microprocessor may also store stimulation sequences (e.g., sequences of electrical pulses provided from electrodes to muscle or neural targets). A particular stimulation sequence may cause a particular sequence of movements. For example, a stimulation pattern may cause a user's hand to be open for a few seconds, allowing the user to position around an object. Then, a stimulation pattern may be applied that causes the user to close their hand around the object. This configuration allows a single command to trigger a useful sequence.

[0091] The microprocessor can handle stimulation multiplexing. Electrical stimulation pulses can be nested or interleaved in the time domain to allow stimulation of multiple muscle or nerve targets simultaneously, but where the individual pulses are not consistent.

[0092] Addressable electrodes

[0093] The devices and systems described herein include, for example, multiple electrodes. The characteristics of these electrodes include, for example, daisy chain or sequential wiring configurations, and communication coupling with an indicator or control system via a switch (e.g., a solid-state relay). In some embodiments, the electrodes are configured to be placed on the body (e.g., contact the skin), or in some embodiments are implantable.

[0094] Figure 1 A schematic diagram is shown for implementing electrodes used in the systems described herein.

[0095] Electrodes or electrode pairs 101 can be daisy-chained (e.g., wired together in sequence) to reduce the number of required wiring. Suitable electrode configurations include anodes and cathodes, multiphase electrodes, and return electrodes. Doubling the circuit can allow an electrode to become an anode or cathode. Switches 104 (e.g., solid-state relays, metal oxide semiconductor field effect transistors (MOSFETs) or other switch topologies) are used to connect electrodes to indicators (e.g., LEDs) or controllers 103. In some embodiments, addressable indicators and / or controllers 103 and switches 104 are integrated into a single integrated circuit (IC), further reducing the size and complexity of the architecture.

[0096] Figure 2 A non-limiting example of a set of electrode configurations described herein is shown. The electrodes can be integrated in a flexible circuit board, or in a textile to be worn on a body part. A major challenge in textiles is routing many and / or closely spaced conductive wires. Using electrodes in the form of textiles allows many electrodes to be daisy-chained with only a few conductive paths. These configurations can be used for electrocorticography (ECoG), electrical muscle stimulation (EMS), or electroencephalography.

[0097] Electrodes can be electrically coupled to the stimulation module using, for example, wires, coiled wires, retractable wires, or in textiles or fabrics. In some embodiments, a return electrode or ground electrode is required to complete the electrode circuit via additional wires and separate electrodes. In some embodiments, a pair of electrodes includes integrated return and ground electrodes as a frame around an active (e.g., stimulation or recording) electrode. The frame can be, for example, a circular (201) frame, a rectangular frame, or a square frame. The electrodes can be arranged in an array. In some cases, the electrode array can be arranged in a serpentine flexible circuit, for example, a curved path 203 including a series of electrodes. In some embodiments, the electrode is placed in a rigid plate in a disc / patch configuration (204b). In this configuration, one or more electrodes are arranged below the disc, and the disc can be connected to another disc by a short flexible connector (e.g., a coiled wire) to allow bending, flexion, or extension for wearable applications. In some embodiments, the electrode contacts the skin via a hydrogel layer.

[0098] Daisy chains can be used for implantable electrodes to solve wiring problems for stimulation or biosignal or neural recording. For example, a set of stereo electroencephalogram (SEEG) or deep brain stimulation (DBS) electrodes 205 can also be wired in a daisy chain manner. In addition, a daisy chain array can be used for an electrocorticogram (ECoG) array 207a or strip 207b.

[0099] Machine Learning

[0100] An adaptive controller including a machine learning algorithm (e.g., a neural network) can learn to associate specific stimulation patterns with specific body movements. The controller can then drive the stimulation electrodes in a spatiotemporal pattern to encourage the subject to mimic the hand or body movements (joint angles and force levels) performed by a therapist, caregiver, or user (the healthy side).

[0101] The wearable system can use a classification model to classify body movements (e.g., exercises or portions thereof or functional movements or portions thereof). A classifier can be trained using data collected from an IMU of the wearable system to associate IMU measurements (e.g., accelerometer measurements, gyroscope measurements, and / or magnetometer measurements of translation (or displacement), rotation, velocity, acceleration, jerk, position, or other quantities) taken while the wearable device is worn with a specific movement of the body part on which the wearable device is worn. The classifier can be trained based on IMU measurements from a target subject or group of subjects (whether or not similar to the target subject, where the similarity can be based on demographic information, medical information, or similarity of injuries, diseases, or health conditions).

[0102] In some embodiments, the classifier is a neural network. The neural network may include a long short-term memory (LSTM) network. LSTM can be used to analyze the movements of a subject who is undergoing rehabilitation or strength training. As the subject's condition improves, the LSTM may forget the IMU measurements taken earlier during training and is therefore irrelevant to training or fine-tuning the machine learning model. In this way, the LSTM can accurately predict the movement of an individual.

[0103] In some embodiments, the machine learning model predicts movement by processing patterns of electrical pulses (e.g., provided during neural stimulation or electrical muscle stimulation) and associating the patterns with motion data (e.g., from an IMU). The machine learning model is trained to predict specific movements produced by specific patterns of electrical pulses. In addition, the machine learning model can be trained to predict specific patterns of electrical pulses that produce an observed movement or set of movements. The adaptive controller can observe a set of movements performed by a therapist or other professional and generate corresponding pulse sequences so that the subject imitates the therapist's movements.

[0104] Additional training of the machine learning model can be performed using observed motion data (e.g., from an IMU) and corresponding electrical pulses. For example, if the motion generated by a subject from a set of electrical pulses deviates from the motion performed by a healthy individual, the machine learning model can predict the health condition, disease, illness, or injury that afflicts the subject and prescribe a course of treatment. The machine learning model can be implemented while the subject is undergoing treatment to test the efficacy of the treatment. For example, IMU and electrical pulse data can be tested in multiple iterations during consecutive therapy appointments. The machine learning model can predict whether a therapy will be successful, how long a therapy may take, or be used to determine whether a new therapy is needed.

[0105] In addition to analyzing IMU data and / or electrical pulse data, the machine learning models described herein may also analyze medical data (e.g., from electronic health records (EHR)), demographic data, visual data (e.g., videos of exercise performance), or other data.

[0106] a. Training phase

[0107] A machine learning software module as described herein may be configured to undergo at least one training phase, wherein the machine learning software module is trained to perform one or more tasks including data extraction, data analysis, and output generation.

[0108] In some embodiments of the software application described herein, the software application includes a training module for training a machine learning software module. The training module is configured to provide training data to the machine learning software module, and the training data includes, for example, IMU measurements and corresponding body movements associated with the IMU measurements (e.g., accelerometer measurements, gyroscope measurements and / or translation (or displacement), rotation, speed, acceleration, jerkiness, magnetometer measurements of position or other quantities). In some embodiments, the training data includes simulated IMU data with corresponding simulated body movements. In some embodiments, the machine learning software module uses automatic statistical analysis of data to determine which features are extracted and / or analyzed from the IMU measurements. In some embodiments, the machine learning software module determines which features are extracted and / or analyzed from the IMU measurements based on the training received by the machine learning software module.

[0109] In some embodiments, the machine learning software module is trained using a data set and a target in a supervised learning manner. In some embodiments, the data set is divided into a training set, a test set, and a validation set in some embodiments. Specify the target of the correct classification of each input value in the data set. For example, a set of IMU data from one or more individuals is repeatedly presented to the machine learning software module, and for each sample presented during training, the output generated by the machine learning software module is compared with the desired target. The difference between the set of target and input samples is calculated, and the machine learning software module is modified to make the output closer to the desired target value. In some embodiments, a back propagation algorithm is used to make the output closer to the desired target value. After a large number of training iterations, the machine learning software module output closely matches the desired target of each sample in the input training set. Subsequently, when new input data that was not used during training is presented to the machine learning software module, the module can generate an output classification value that indicates which category the new sample is most likely to fall into. The machine learning software module can be generalized from the training to explain new, previously unseen input samples. This feature of the machine learning software module allows for the classification of virtually any input data that has a mathematically formulatable relationship to the category to which the data should be assigned.

[0110] In some embodiments, the machine learning software module utilizes an individual learning model. The individual learning model is based on a machine learning software module trained on data from a single individual, and therefore, a machine learning software module utilizing an individual learning model is configured for use on a single individual whose data the module was trained on.

[0111] In some embodiments, the machine training software module utilizes a global training model. The global training model is based on a machine training software module that has been trained on data from multiple individuals, and therefore, the machine training software module utilizing the global training model is configured for use on multiple individuals.

[0112] In some embodiments, the machine training software module utilizes a simulated training model. The simulated training model is based on a machine training software module that has been trained on data from simulated IMU measurements.

[0113] In some embodiments, the use of training models varies as the availability of IMU data changes. For example, if there is not a sufficient amount of appropriate motion data available to train the machine training software module to the desired accuracy, a simulated training model can be used. If few appropriate IMU measurements with associated anomalies are initially available, then this data scarcity may be real in the early stages of implementation. As additional data becomes available, the training model can be changed to a global or individual model. In some embodiments, a mixture of training models can be used to train the machine training software module. For example, a simulated training model and a global training model can be used to meet the training data requirements using a mixture of data from multiple subjects and simulated data.

[0114] In some embodiments, unsupervised learning is used to train a machine training software module to use input data, such as, for example, IMU data and output, such as diagnosis or body movement. In some embodiments, unsupervised learning includes feature extraction performed by a machine learning software module on the input data. The extracted features can be used for visualization, for classification, for subsequent supervised training, and more generally for representing inputs for subsequent storage or analysis. In some embodiments, each training case includes multiple IMU data.

[0115] Machine learning software modules suitable for unsupervised training include k-means clustering, mixture of multinomial distributions, affinity propagation, discrete factor analysis, hidden Markov models, Boltzmann machines, restricted Boltzmann machines, autoencoders, convolutional autoencoders, recurrent neural network autoencoders, and long short-term memory autoencoders.

[0116] The machine learning software module may include a training phase and a prediction phase. The training phase provides data to train the machine learning algorithm. Non-limiting examples of data types input into the machine learning software module for training include medical image data, clinical data (e.g., from health records), encoded data, encoded features, and metrics derived from IMU data. In some embodiments, the data input into the machine learning software module is used to construct a hypothesis function to determine the presence of body movement. In some embodiments, the machine learning software module is configured to determine whether the result of the hypothesis function is achieved, and based on the analysis, a determination is made about the data based on which the hypothesis function is constructed. In other words, the result tends to strengthen the hypothesis function of the data based on which the hypothesis function is constructed, or contradicts the hypothesis function of the data based on which the hypothesis function is constructed. In some embodiments, depending on the closeness of the result to the result determined by the hypothesis function, the machine learning algorithm may adopt, adjust, or abandon the hypothesis function of the data based on which the hypothesis function is constructed. Therefore, the machine learning algorithm described herein dynamically learns what characteristics of the input (e.g., data) through the training phase to determine whether the characteristics of the recorded IMU data of the subject are most predictive when predicting a specific body movement.

[0117] For example, a machine learning software module is provided with data to be trained so that the module can, for example, determine the most significant features of the received IMU data to operate. The machine learning software module described herein can be trained on how to analyze the IMU data, rather than using predefined instructions to analyze the IMU data. Thus, the machine learning software module described herein dynamically learns through training what characteristics of the input measurements are most predictive in determining whether the features of the IMU show body motion.

[0118] In some embodiments, the machine learning software module is trained by repeatedly presenting the machine learning software module with IMU data and, for example, body movements (e.g., flexion, relaxation, extension, or contraction of a muscle). The IMU data may include accelerometer, gyroscope, or magnetometer data generated in response to electrical stimulation of a body part.

[0119] In some embodiments, when the machine learning software module is given IMU data and is required to determine the existence of body movement, training begins. The predicted body movement is then compared with the actual body movement corresponding to the IMU data. Optimization techniques such as gradient descent and back propagation are used to update the weights in each layer of the machine learning software module to produce a closer agreement between the probability of body movement predicted by the machine learning software module and the existence of body movement. Use new IMU data and body movement to repeat the process until the accuracy of the network has reached the desired level. In this case, when the machine learning software module is given corresponding IMU data and is required to determine the type and position of body movement, training begins. Use optimization techniques to update the weights in each layer of the machine learning software module to produce a closer agreement between the body movement predicted by the machine learning software module and the actual body movement. Use new IMU data and body movement to repeat the process until the accuracy of the network has reached the desired level. Then the output data is compared with the actual body movement corresponding to the IMU data. Use optimization techniques to update the weights in each layer of the machine learning software module to produce a closer agreement between the probability of body movement predicted by the machine learning software module and the actual body movement. This process is repeated using new IMU data and body motion until the network's accuracy has reached the desired level.After training with the appropriate body motion given above, the machine learning module can analyze the IMU measurements and determine the presence, type and location of body motion, and the conditions associated with it.

[0120] In some embodiments, a machine learning software module receives the IMU data and directly determines a body movement probability of the subject, where the body movement probability comprises a probability that the IMU measurement is associated with a body movement of the subject.

[0121] In some embodiments, the user's body movements are input by a user of the system. In some embodiments, the user's body movements are input by an entity other than the user. In some embodiments, the entity may be a health care provider, a health care professional, a family member, or an acquaintance. In some embodiments, the entity may be a system, device, or additional system described herein that analyzes IMU measurements and provides data related to physiological abnormalities.

[0122] In some embodiments, strategies for collecting training data are provided to ensure that the IMU measurements represent a wide range of conditions, thereby providing a broad training data set for the machine learning software module. For example, a specified number of measurements during a set time period can be used as part of the training data set. In addition, these measurements can be specified to have a set amount of time between measurements. In some embodiments, IMU measurements acquired under conditions where the subject's physical state changes can be included in the training data set.

[0123] b. Prediction Phase

[0124] After training, the machine learning algorithm is used to determine, for example, the presence or absence of a body movement on which the system was trained using the prediction phase. Using appropriate training data, the system can recognize the type of body movement and present conditions associated with such body movement. For example, IMU measurements are taken of the subject's brain, and appropriate data derived from the IMU measurements are submitted to the system using the described trained machine learning algorithm for analysis. In some embodiments, the machine learning software algorithm detects body movement associated with a health condition.

[0125] As an example, a subject is known to have a health condition that affects mobility and has IMU measurements recorded before and after treatment with a therapy. Data from the IMU measurements and / or features and / or metrics derived from the data are submitted to a system using the described trained machine learning algorithm for analysis to determine the effectiveness of the therapy using a prediction phase.

[0126] The prediction phase uses the constructed and optimized hypothesis functions from the training phase to predict the probability of body movement. In some embodiments, in the prediction phase, a machine learning software module can be used to analyze data derived from its IMU measurements independently of any system or device described herein. In some embodiments, the new data record provides a signal window longer than the signal window required to determine the presence of the subject's body movement. In some embodiments, the longer signal can be cut into appropriate sizes, such as 10 seconds, and can then be used in the prediction phase to predict the probability of body movement of new patient data.

[0127] In some embodiments, a probability threshold can be used in conjunction with the final probability to determine whether a given record matches a trained body movement. In some embodiments, the probability threshold is used to adjust the sensitivity of the trained network. For example, the probability threshold can be 1%, 2%, 5%, 10%, 15%, 20%, 25%, 30%, 35%, 40%, 45%, 50%, 55%, 60%, 65%, 70%, 75%, 80%, 85%, 90%, 95%, 98% or 99%. In some embodiments, if the accuracy, sensitivity or specificity is lower than a predefined adjustment threshold, the probability threshold is adjusted. In some embodiments, the adjustment threshold is used to determine the parameters of the training cycle. For example, if the accuracy of the probability threshold is lower than the adjustment threshold, the system can extend the training cycle and / or require additional measurements and / or body movements. In some embodiments, additional measurements and / or body movements can be included in the training data. In some embodiments, additional measurements and / or body movements can be used to refine the training data set.

[0128] Exemplary Machine Learning Techniques

[0129] In some embodiments, the systems, methods, computer-readable media, and techniques disclosed herein use various machine learning techniques. In some embodiments, ML involves identifying and recognizing patterns in existing data to facilitate prediction of subsequent data. ML may include ML models, such as ML algorithms. Machine learning, whether analytical or statistical, can provide deductive reasoning or abductive reasoning based on real data or simulated data. The ML model may be a trained model. ML techniques may include one or more supervised ML techniques, semi-supervised ML techniques, self-supervised ML techniques, or unsupervised ML techniques. For example, an ML model may be a trained model trained by supervised learning (e.g., various parameters are determined as weights or scaling factors). ML may include one or more of regression analysis, regularization, classification, dimensionality reduction, ensemble learning, meta-learning, association rule learning, cluster analysis, anomaly detection, deep learning, or ultra-deep learning. Non-limiting examples of ML include: k-means, k-means clustering, k-nearest neighbors, learning vector quantization, linear regression, nonlinear regression, least squares regression, partial least squares regression, logistic regression, stepwise regression, multivariate adaptive regression splines, ridge regression, principal component regression, least absolute shrinkage and selection operation (LASSO), least angle regression, canonical correlation analysis, factor analysis, independent component analysis, linear discriminant analysis, multidimensional scaling, non-negative matrix factorization, principal component analysis, principal coordinates analysis, projection pursuit, Sammon mapping, t-distributed random neighbor embedding, AdaBoosting, boosting, gradient boosting, bootstrap ensemble, cumulative average , decision tree, conditional decision tree, boosted decision tree, gradient boosted decision tree, random forest, stacked generalization, Bayesian network, Bayesian belief network, Naive Bayes, Gaussian Naive Bayes, Multinomial Naive Bayes, Hidden Markov Model, Hierarchical Hidden Markov Model, Support Vector Machine, Encoder, Decoder, Autoencoder, Stacked Autoencoder, Perceptron, Multilayer Perceptron, Artificial Neural Network, Feedforward Neural Network, Convolutional Neural Network, Recurrent Neural Network, Long Short-Term Memory Network, Deep Belief Network, Deep Boltzmann Machine, Deep Convolutional Neural Network, Deep Recurrent Neural Network, Generative Adversarial Network, Visual Transformer, Long Short-Term Memory Network (LSTM), and Masked Autoencoder.

[0130] train

[0131] In some embodiments, training the ML model may include selecting one or more untrained data models to be trained using a training data set. The selected untrained data model may include any type of untrained ML model for supervised machine learning, semi-supervised machine learning, self-supervised machine learning, or unsupervised machine learning. The selected untrained data model may be specified based on an input (e.g., user input) that specifies relevant parameters of a variable used as a prediction or other variables used as potential explanatory variables. For example, the selected untrained data model may be specified to generate an output (e.g., a prediction) based on the input. Conditions for training the ML model from the selected untrained data model may also be selected, such as restrictions on the complexity of the ML model or restrictions on the refinement of the ML model beyond a certain point. The ML model may be trained using a training data set (e.g., via a computer system such as a server). In some embodiments, a first subset of the training data set may be selected to train the ML model. Then, based on the type of the selected ML model and any conditions specified for training the ML model, the selected untrained data model may be trained on the first subset of the training data set using appropriate ML techniques. In some embodiments, due to the processing power requirements of training ML models, additional computing resources (e.g., cloud computing resources) are used to train the selected untrained data model. In some embodiments, such training can continue until at least one aspect of the ML model is validated and meets the selection criteria to be used as a predictive model.

[0132] verify

[0133] In some embodiments, one or more aspects of the ML model may be validated using a second subset of the training data set (e.g., different from the first subset of the training data set) to determine the accuracy and robustness of the ML model. Such validation may include applying the ML model to the second subset of the training data set to obtain predictions derived from the second subset of the training data set. The ML model may then be evaluated to determine whether the performance is sufficient based on the derived predictions. The adequacy criteria applied to the ML model may vary depending on the size of the training data set available for training, the performance of the previous iteration of the trained model, or the performance requirements specified by the user. If the ML model does not achieve sufficient performance, additional training may be performed. Additional training may include refinement of the ML model or retraining on a different first subset of the training data set, after which the new ML model may be validated and evaluated again. When the ML model has achieved sufficient performance, in some embodiments, the ML may be stored for use now or in the future. The ML model may be stored as a set of parameter values ​​or weights for analysis of additional inputs (e.g., additional relevant parameters used as additional predicted variables, additional explanatory variables, additional user interaction data, etc.), which in some cases may also include an indication of the analysis logic or model validity. In some embodiments, multiple ML models may be stored for generating predictions under different sets of input data conditions. In some embodiments, the ML models may be stored in a database (e.g., associated with a server).

[0134] Deep Learning

[0135] The systems, methods, computer-readable media, and techniques disclosed herein can implement one or more deep learning techniques. Deep learning is an example of ML that can be based on a set of algorithms that model high-level abstractions in data using multiple processing layers that have complex structures or are otherwise composed of multiple nonlinear transformations. In some embodiments, an exit method can be used to reduce overfitting. At each training stage, a separate node exits the network (e.g., ignored) with probability 1-p or is retained with probability p, leaving a reduced network. The input and output edges of the exited nodes can also be removed. In some embodiments, the reduced network trains the data at this stage. Then, the removed nodes can be reinserted into the network with the original weights.

[0136] Decision Tree

[0137] The systems, methods, computer-readable media, and techniques disclosed herein can implement one or more decision trees or random forest techniques. A decision tree can be a supervised ML algorithm that can be applied to both regression and classification problems. A decision tree can mimic the decision-making process of the human brain. For example, a decision tree can grow from a root (basic conditions), and when the tree meets the conditions (internal nodes / features), the tree splits into multiple branches. The ends of the branches that are no longer split are the results (leaves). A decision tree can be generated using a training data set according to the following operations: (1) Starting from the root node (the entire data set), the algorithm can use a decision rule or branching criterion to split the data set into two branches; (2) Each branch in the two branches can generate a new child node; (3) For each new child node, the branching process can be repeated until the data set cannot be further split; (4) Each branching criterion can be selected to maximize information gain (e.g., quantization of the branching criterion reduces the quantization of the degree of label mixing in the child node). The label can be the data or classification predicted by the decision tree.

[0138] Random Forest

[0139] Random forest regression is an extension of the decision tree model that tends to produce more robust predictions by stretching the use of training data partitions. Decision trees can make a single pass through the data, while random forest regression can guide 50% of the data (e.g., by replacement) and build many trees. Instead of using all explanatory variables as candidates for splitting, a random subset of candidate variables can be used for splitting to produce trees with different data and different variables. The predictions from these trees (collectively referred to as forests) are then averaged to produce the final prediction. Many trees (e.g., one hundred trees) can be included in the random forest model, where multiple (e.g., 3, 6, 10, etc.) items are sampled for each split, and there is a minimum number of splits (e.g., 1, 2, 4, 10, etc.) and a minimum split size (e.g., 16, 32, 64, 128, 256, etc.) for each tree. Random forests can be trained in a similar manner to decision trees. Training a random forest may include the following operations: (1) randomly selecting k features from the total number of features; (2) creating a decision tree from these k features using the same operations used to generate a decision tree; and (3) repeating the previous two operations until a target number of trees are created.

[0140] Long Short-Term Memory (LSTM)

[0141] The systems, methods, computer-readable media, and techniques disclosed herein may implement one or more long short-term memory (LSTM) techniques. LSTM may be an artificial neural network used in the fields of artificial intelligence and deep learning. Unlike standard feedforward neural networks, LSTM may use feedback connections. LSTM architectures may provide short-term memory for recursive neural networks (RNNs). Such RNNs may not only process single data points (such as images), but may also process entire data sequences (such as speech or video). The connection weights and biases in RNNs may be changed once per training, similar to how physiological changes in synaptic strength store long-term memory. The activation pattern in the network may change once per time step, similar to how instantaneous changes in electrical discharge patterns in the brain store short-term memory. LSTM architectures may provide RNNs with short-term memory that may last for many (e.g., thousands) time steps.

[0142] In some embodiments, an LSTM unit may include a cell, an input gate, an output gate, and a forget gate. The unit may remember values ​​over arbitrary time intervals, and the input gate, output gate, and forget gate may regulate the flow of information into and out of the unit. The forget gate may decide what information to discard from a previous state by assigning a value between 0 and 1 to the previous state compared to the current input (e.g., a (rounded) value of 1 may mean retaining the information, and a value of 0 may mean discarding the information). The input gate may use the same system as the forget gate to decide which new pieces of information to store in the current state. The output gate may control which pieces of information in the current state are output (e.g., by assigning values ​​of 0 to 1 to the information, taking into account the previous state and the current state). Selectively outputting relevant information from the current state may allow the LSTM network to maintain useful, long-term dependencies for prediction in current and future time steps. LSTM networks are well suited for classification, processing, and prediction based on time series data, because lags of unknown duration may occur between important events in a time series. LSTM may solve the gradient vanishing problem that may be encountered when training traditional RNNs. In many applications, the relative insensitivity to gap length may be an advantage of LSTM over RNNs, hidden Markov models, and other sequence learning methods.

[0143] In some embodiments, LSTM can be used for one or more different types of neural networks (e.g., convolutional neural networks (CNNs), deep neural networks (DNNs), recurrent neural networks (RNNs), etc.). In some embodiments, CNNs, LSTMs, and DNNs are complementary in modeling capabilities and can be combined in a unified architecture. For example, in such a unified architecture, CNNs can be well suited for reducing frequency changes, LSTMs can be well suited for temporal modeling, and DNNs can be well suited for mapping features to more separable spaces. For example, the input features of an ML model using LSTM technology in a unified architecture can include fragment features of each of a plurality of fragments. In order to process the input features of each of a plurality of fragments, one or more CNN layers can be used to process the fragment features of the fragment to generate a first feature for the fragment. One or more LSTM layers can be used to process the first feature to generate a second feature for the fragment. One or more fully connected neural network layers can be used to process the second feature to generate a third feature for the fragment, wherein the third feature can be used for a classification operation. In some embodiments, in order to use one or more LSTM layers to process the first feature to generate the second feature, the first feature can be processed using a linear layer to generate a reduced feature having a dimension reduced from the dimension of the first feature. The reduced feature can be processed using one or more LSTM layers to generate the second feature. Short-term features with a first number of context frames can be generated based on the input features, wherein the features generated using one or more CNN layers can include long-term features with a second number of context frames, and the second number of context frames is more than the first number of context frames of the short-term features. In some embodiments, one or more CNN layers, one or more LSTM layers, and one or more fully connected neural network layers can be jointly trained to determine the trained values ​​of the parameters of one or more CNN layers, one or more LSTM layers, and one or more fully connected neural network layers. In some embodiments, the input features include log-mel features with multiple dimensions. The input features include one or more context frames indicating the temporal context of the signal (e.g., input data). The implementation of such a unified architecture can take advantage of the complementary advantages associated with each of CNN, LSTM, and DNN. For example, a convolutional layer can reduce spectral changes in the input and contribute to the modeling of the LSTM layer. Having a DNN layer after the LSTM layer can help reduce the changes in the hidden state of the LSTM layer. Training a unified architecture jointly can provide better overall performance. Training in a unified architecture can also eliminate the need to have separate CNN, LSTM, and DNN architectures. By adding multi-scale information to a unified architecture, information can be captured at different time scales.

[0144] Support Vector Machine

[0145] The systems, methods, computer-readable media, and techniques disclosed herein can implement one or more support vector machine learning techniques. In machine learning, a support vector machine (SVM) can be a supervised learning model with an associated learning algorithm that analyzes data for classification and regression analysis. SVM can be a robust prediction method based on statistical learning. SVM can be well suited for fields characterized by the presence of large amounts of data, noise patterns, or a lack of general theory.

[0146] SVM can map the input vector into a high-dimensional feature space through a pre-selected nonlinear mapping function. In this high-dimensional feature space, the best separation hyperplane can be constructed. The best hyperplane can then be used to determine things such as class separation, regression fit, or the accuracy of density estimation. More formally, SVM constructs a hyperplane or a set of hyperplanes in a high-dimensional space or infinite-dimensional space, which can be used for classification, regression, or other tasks such as outlier detection.

[0147] Support vectors can be defined as the data points that are closest to the decision plane (or hyperplane). Therefore, support vectors may be the most difficult data points to classify and may have a direct relationship to the optimal location of the decision plane. Given a set of training examples, each labeled as belonging to one of two categories, an SVM training algorithm can build a model that assigns new examples to one category or the other, making the algorithm a non-probabilistic binary linear classifier. SVMs can map training examples to points in space that maximize the width of the gap between the two categories. New examples can then be mapped into the same space and predicted to belong to a category based on which side of the gap the example falls. In addition to performing linear classification, SVMs can also efficiently perform nonlinear classification using the so-called kernel trick, implicitly mapping the input into a high-dimensional feature space.

[0148] In support vector machines, the dimension of the feature space can be very large. For example, a quartic polynomial mapping function can map a 200-dimensional input space to a 1.6 billion-dimensional feature space. SVM helps discover knowledge from large amounts of input data.

[0149] Gradient Boosting

[0150] The systems, methods, computer readable media, and techniques disclosed herein may implement one or more gradient boosting techniques. Gradient boosting is a machine learning technique for regression and classification tasks, among others. Gradient boosting gives a predictive model in the form of an ensemble of weak predictive models, which are typically decision trees. When a decision tree is a weak learner, the resulting algorithm is called a gradient boosted tree. Like other boosting methods, the gradient boosted tree model is constructed in a staged manner, but generalizes other methods by allowing optimization of arbitrary differentiable loss functions.

[0151] k-nearest neighbors

[0152] The systems, methods, computer-readable media, and techniques disclosed herein may implement one or more K-nearest neighbor (KNN) techniques. KNN is a nonparametric classification method. In KNN classification, the output is class membership. Objects are classified by multiple votes of neighbors, where the object is assigned to the most common class among the k nearest neighbors (k is a positive integer, usually small). If k=1, the object is assigned to the class of the single nearest neighbor. In KNN regression, the output is the attribute value of the object. This value is the average of the k nearest neighbors. KNN is a type of classification in which functions are locally approximated and calculations are postponed until the function is evaluated. Since this algorithm relies on distances for classification, normalizing the training data can improve accuracy if the features represent different physical units or differ to a large extent.

[0153] The systems, methods, computer-readable media, and techniques disclosed herein may implement one or more Monte Carlo techniques. Monte Carlo is a broad class of computational algorithms that rely on repeated random sampling to obtain numerical results. The basic concept is to use randomness to solve problems that could in principle be deterministic.

[0154] One-hot encoding

[0155] The systems, methods, computer readable media, and techniques disclosed herein may implement one or more one-hot encoding techniques. One-hot encoding may be used to process categorical data. For example, an ML model may use numeric input variables. Categorical variables may be converted in a preprocessing portion. Categorical data may be nominal data or ordinal data. Ordinal data may have a sorted order of values ​​and thus may be converted to numerical data through ordinal encoding.

[0156] Example

[0157] The following embodiments describe controlling neural stimulation via a wearable system. The wearable system includes Figure 6The multiple components shown, specifically, extensor disposable electrode array, extensor patch corresponding to the extensor disposable electrode array, flexor disposable electrode array, flexor patch corresponding to the flexor disposable electrode array, stimulator, thumb disposable electrode array, flexor / extensor cable and thumb encryption dog (thumb dongle). The stimulator is paired with a user's personal device (e.g., mobile device). Allow the user to use a personal device to wirelessly control the neural stimulation of the wearable patch system.

[0158] Example 1: Attaching a disposable electrode array to a patient's skin.

[0159] Fig.13 Disposable electrode arrays configured to be attached to the forearm and thumb of a patient are shown. As shown, the disposable electrode arrays include a thumb disposable electrode array 1310, an extensor disposable electrode array 1320, and a flexor disposable electrode array 1330. The thumb disposable electrode array 1310 is configured to be worn around the patient's thumb. The extensor disposable electrode array 1320 is configured to be attached to the extensor compartment (also referred to as the posterior compartment) of the forearm, stimulating the muscles (e.g., superficial muscles and deep muscles) and neural targets in the compartment. The flexor disposable electrode array 1330 is configured to be attached to the flexor compartment (also referred to as the anterior compartment) of the forearm, stimulating the muscles and neural targets in the compartment. As shown, both the extensor disposable electrode array 1320 and the flexor disposable electrode array 1330 include a plurality of electrodes, each of which is attached to a corresponding magnetic connector. The disposable electrode arrays 1310, 1320, and 1330 are attached to a transparent sheet that can be removed from the electrodes when attached to the patient's skin.

[0160] Figure 14A-14E A disposable electrode array is shown attached to a patient's forearm and thumb. Fig.14A A flexor disposable electrode array 1410 is shown attached to the flexor compartment of a patient's forearm. Fig. 14B An extensor disposable electrode array 1420 is shown attached to the extensor compartment of a patient's forearm. Fig. 14C is a side view of a patient's arm with the extensor disposable electrode array 1420 and the flexor disposable electrode array 1410 attached to and surrounding the patient's arm. Fig. 14C As shown, when the flexor disposable electrode array and the extensor disposable electrode array are attached, most of the muscle and nerve targets on the forearm are covered.

[0161] Fig.14D and Fig.14EA disposable electrode array is shown attached to and wrapped around the patient's thumb. A magnetic connector 1440 is placed on the ligament just below the bone that connects to the thumb. A Velcro area 1430 is located on the web of the hand, and a remaining flap 1460 wraps around the thumb. The thin end of the flap 1450 has Velcro that attaches to another Velcro area 1430 on the web of the hand. Each electrode in the disposable electrode array 1470 is in direct contact with the patient's skin.

[0162] Example 2: Attaching a durable / reusable patch to a patient's skin.

[0163] After the flexor disposable electrode array and the extensor disposable electrode array are attached to the patient's forearm, the corresponding durable / reusable electronic patch is placed over the disposable electrode arrays. Figure 15A-Figure 15C A durable / reusable electronic patch attached to a disposable electrode array is shown. Fig.15A A durable / reusable flexor patch 1510 is shown corresponding to the flexor disposable electrode array 1410 attached to the patient's forearm, overlapping the disposable electrode array. Fig. 15B A durable / reusable patch 1520 is shown corresponding to the extensor disposable electrode array 1420 attached to the patient's forearm, overlapping the disposable electrode array. Fig. 15C is a side view of a patient's arm with a flexor patch 1510 and an extensor patch 1520 attached. The flexor patch 1510 has the same number of magnetic connectors as the magnetic connectors attached to the flexor disposable electrode array 1410, so that when the patch 1510 is placed over the electrode 1410, each magnetic connector in the patch can be aligned with a corresponding magnetic connector on the electrode. Similarly, the durable / reusable extensor patch 1520 has the same number of magnetic connectors as the magnetic connectors attached to the extensor disposable electrode array 1420. The thumb disposable electrode array does not require a patch to function.

[0164] like Fig. 15C As further shown in , when a durable / reusable patch is placed on a disposable electrode array, the electrodes sometimes slightly lift off the skin. To fix this lift, once the patch is placed on the disposable electrode array, the assembly can be fixed. Figure 16A-16C The attachment of an assembly comprising a durable / reusable patch and a corresponding disposable electrode array attached to the patient's forearm is shown. Multiple attachment mechanisms (e.g., straps) may be used, ensuring that the assembly contacts as much of the forearm as possible. If both a flexor patch and an extensor patch are used simultaneously, three forearm straps may be used, such as Fig.16A and Fig. 16CIf using the extensor patch alone, two forearm straps can be used. The thumb electrode does not require this piece.

[0165] Example 3. Establishing a connection between a stimulator and a durable / reusable patch.

[0166] Fig.17 The stimulator module is shown attached to the patient's wrist. The stimulator module 1710 is attached to a wrist strap and placed on the patient's wrist. The LED logo 1720 on the stimulator module 1710 is closer to the patient's finger.

[0167] The stimulator module 1710 includes three cable ports configured to connect to the flexor and extensor patches and the thumb disposable electrode array. Fig.18 The connection between the stimulator and the flexor patch and the extensor patch and the thumb disposable electrode array via a cable is shown. The flexor cable 1810 is connected between the stimulator 1850 and the flexor patch 1820. The extensor cable 1830 is connected between the stimulator module 1850 and the extensor patch 1840. The thumb dongle 1860 is connected between the stimulator module 1850 and the thumb disposable electrode array. Therefore, the stimulator has established an electrical connection with the flexor patch and the extensor patch and the thumb disposable electrode array 1870.

[0168] Example 4. Controlling neural stimulation via a wearable patch system.

[0169] When the stimulator module is connected to the flexor and extensor patches and the thumb disposable electrode array, the user is allowed to operate on a personal device (e.g., a mobile device) and control the patches and electrodes via a mobile application, web application, or desktop application. Fig.19 A graphical user interface (GUI) 1900 of an application that allows a user to control stimulation is shown. The GUI lists the name of the device 1910, refers to the stimulator that is paired with the patient's personal device, and the battery percentage of the device. The user is allowed to select the name of the patient to be stimulated. The application can store records for multiple patients. In a home care environment, the patient wearing the patch can operate a mobile device to control the stimulation. In a health care environment, a health care provider can operate on a web application or desktop application to select the name of the patient wearing the patch and control the stimulation.

[0170] The GUI also allows the user to select between manual stimulation 1940 and stimulation sequences 1950. In the manual stimulation section 1940, the user can select stimulation areas 1920, including flexors, extensors, and thumbs. Each of these stimulation categories corresponds to an electrode and patch, such as Figure 13-Figure 18As shown. When the user selects a stimulation area, the user is allowed to control which electrodes perform the stimulation. The user can save the desired input for a specific movement during manual stimulation, including the location for stimulation and its amplitude. By selecting a stimulation sequence 1950, these saved movements can be performed sequentially or simultaneously.

[0171] Fig. 20 A GUI 2000 of an application that allows a user to control manual stimulation is shown. The user can select one of flexor or extensor stimulation, with the result of the selection being shown in the stimulation selection portion 2010. A stimulation indicator 2020 (e.g., "on / off") is also displayed in the GUI and changes automatically depending on the state of the stimulation amplitude slider 2030. For example, when the slider 2030 is dragged all the way down, indicating the minimum value of the amplitude applied, the stimulation indicator 2020 automatically turns off. When the slider is dragged up from the minimum value, the button automatically turns on. Alternatively, the stimulation indicator 2020 can be turned on and off independently of the amplitude slider 2030.

[0172] As above according to Fig.18 As described, the flexor patch and the extensor patch have LEDs indicating the location of the electrodes that produce the electrical stimulation. The user can control the location of the electrodes by navigating the control area 2040. The user can move a finger on the control area 2040 to locate the desired point to perform the stimulation. The LED on the patch corresponding to the desired point can illuminate, indicating the location of the electrode that performs the stimulation. The user can also test different positions of the LED on the patch and view the patient's response to the stimulation by navigating the control area 2040.

[0173] The GUI also provides a keep LED on function 2050. When the user identifies a desired point for electrical stimulation indicated by an LED on the patch, the user can save the position of the LED by tapping keep LED on 2050. The selected LED corresponding to the position of the desired point for stimulation can turn a different color. The user can keep navigating on the control area 2040 to identify a different desired point for electrical stimulation. Another LED on the patch, representing the user's newly selected point, can illuminate.

[0174] Fig.21The user is shown selecting multiple locations on the patch to perform electrical stimulation, each location indicated by an LED. The position of the blue LED 2110 represents the first desired point that the user selected and saved by tapping the "Keep LED On" button 2050. The position of the green LED 2120 represents the new location that the user navigates on the control area 2040. As the user's finger slides on the control area 2040, the position of the green LED 2120 changes accordingly. When the user identifies a second desired point for stimulation, the user taps the Keep LED On 2050 again to save the point. As a result, the green LED 2120 turns blue, indicating that the corresponding point is selected and saved.

[0175] The GUI allows the user to save a pattern with one or more selected positions. Fig. 20 As shown, the user can tap Save Mode 2100. The desired mode can be saved in the user's profile. The user can even load the mode after adjusting the input. In some embodiments, only one mode can be saved at a time for each selected action. If another mode is saved over an already saved mode, the newly saved mode will overwrite the selected movement. When the user intends to remove a previously selected position represented by a blue LED on the patch, the user can tap Turn Off LED 2060, or tap Turn Off All 2070 to remove all selected positions. Since each mode has been saved in the user's profile, even after turning off the blue LED, the user can still tap Load Mode 2090 to restore the previously saved mode.

[0176] Fig. 22 A GUI 2200 of an application that allows a user to control thumb stimulation is shown. Instead of selecting one of extensor stimulation or flexor stimulation, the user can select thumb stimulation, which is indicated in the stimulation selection portion 2210. A stimulation indicator 2220 (e.g., on / off) is also displayed in the GUI and changes automatically depending on the state of the stimulation amplitude slider 2230. For example, when the slider 2230 is dragged all the way down to indicate the minimum value of the amplitude applied, the stimulation indicator 2220 automatically turns off. When the slider is dragged up from the minimum value, the button automatically turns on. Alternatively, the stimulation indicator 2220 can be turned on and off independently of the amplitude slider 2230.

[0177] GUI 2200 provides an electrode section 2240 that includes a visual representation of the five subsystem electrodes in the disposable thumb electrode (see Fig.14E2260). Each electrode can be selected to control a different part of the thumb movement. Depending on the movement selected by the user in the movement selection section 2260, the user can select a single electrode or multiple electrodes at a time. As shown, for example, electrode 2 and electrode 3 are selected at the same time and produce electrical stimulation. The user can also click Close All 2250 to delete the selected position.

[0178] GUI 2200 also provides a load mode 2270 and a save mode 2280, which have the same functions as the flexor mode and the extensor mode (e.g., Fig. 20 The user can save a desired pattern with a given amplitude and stimulation area by tapping Save Pattern 2280. A saved pattern can be loaded by clicking “Load Pattern” 2270.

[0179] As described above, the user can save the desired inputs for a specific movement during manual stimulation, including the location for stimulation and its amplitude. The system allows the user to select a stimulation sequence function so that the saved movements can be performed sequentially or simultaneously.

[0180] Fig.23 A GUI 2300 of an application for executing a stimulation sequence 2300 is shown. Instead of selecting manual stimulation, a user can select a stimulation sequence 2310 in which one or more saved actions can be performed. A stimulation indicator 2320 (e.g., on / off) is displayed in the GUI and changes automatically based on the state of a stimulation amplitude slider 2330. The functions of the stimulation indicator 2320 and the stimulation amplitude slider 2330 are similar to those of the embodiments of the present invention. Fig. 20 and Fig. 22 23. The motion selection section 2340 includes three saved motions to be selected by the user. As shown, for example, during manual stimulation, a hand opening motion is saved by the user. Similarly, the user can navigate the scroll-down menu to select any saved motion. The user can also select how to perform the motions in the motion motion section 2350, for example, to play in sequence or stimulate together.

[0181] Implementation

[0182] Embodiment 1. A device comprising: a first item, wherein the first item comprises 1) a first top surface, wherein the first top surface comprises a set of first connectors; and 2) a first bottom surface, wherein the first bottom surface comprises a plurality of electrodes; and a second item, wherein the second item comprises 1) a circuit board, wherein the circuit board is operably connected to the plurality of electrodes; 2) a second top surface, wherein the second top surface comprises a plurality of visualization aids, wherein each of the plurality of visualization aids independently corresponds to one of the plurality of electrodes; and 3) a second bottom surface, wherein the second bottom surface comprises a set of second connectors, wherein each of the first connectors is independently configured to be coupled to one of the second connectors, wherein the first connector and the second connector are configured to form a connection, and when the first connector is coupled to the second connector, the connection holds the first item and the second item together, wherein when the first item and the second item are operably connected, the first item and the second item together form a wearable object, wherein the wearable object has a wearable size and a wearable shape suitable for mounting on a part of a human body.

[0183] Embodiment 2. The apparatus of embodiment 1, wherein the visualization aid is a light.

[0184] Embodiment 3. A device according to embodiment 1 or 2, wherein the visualization aid is an LED.

[0185] Embodiment 4. A device according to any one of embodiments 1-3, wherein each visualization aid is configured to provide a visual signal when an electrode corresponding to the visualization aid emits an electrical signal.

[0186] Embodiment 5. A device according to any one of embodiments 1-4, wherein the plurality of electrodes are flexible.

[0187] Embodiment 6. The device of any one of Embodiments 1-5, wherein the plurality of electrodes are silver ink.

[0188] Embodiment 7. A device according to any of embodiments 1-6, wherein the plurality of electrodes are configured to stimulate the muscle tissue and the neural target when the plurality of electrodes provide electrical stimulation to the muscle tissue and the neural target.

[0189] Embodiment 8. A device according to any one of Embodiments 1-7, wherein the plurality of electrodes are connected sequentially.

[0190] Embodiment 9. A device according to any one of Embodiments 1-8, wherein the first connector and the second connector are magnetic.

[0191] Embodiment 10. An apparatus according to any one of Embodiments 1-9, wherein the first item has a first item shape and the second item has a second item shape, wherein when the first item and the second item are operably connected, the first item shape and the second item shape substantially overlap.

[0192] Embodiment 11. The apparatus of any one of Embodiments 1-10, wherein the first bottom surface has a thickness of at least 25 cm 2 surface area.

[0193] Embodiment 12. A device according to any one of Embodiments 1-11, wherein the circuit board is flexible.

[0194] Embodiment 13. A device according to any one of Embodiments 1-12, wherein the circuit board includes a conductor.

[0195] Embodiment 14. An apparatus according to Embodiment 13, wherein the conductor is gold-plated copper.

[0196] Embodiment 15. A device according to Embodiment 13 or 14, wherein the conductor is bonded to the plating.

[0197] Embodiment 16. The apparatus of any one of Embodiments 13-15, wherein the conductor is bonded to a nickel-copper-nickel plating.

[0198] Embodiment 17. The apparatus of any one of Embodiments 1-16, wherein the second item is durable.

[0199] Embodiment 18. The apparatus of any one of Embodiments 1-17, wherein the first item is disposable.

[0200] Embodiment 19. The device of any one of Embodiments 1-18, wherein the first item is configured to contact human skin.

[0201] Embodiment 20. An apparatus according to any one of Embodiments 1-19, wherein the first article includes a bottom layer, a middle layer and a top layer, wherein the middle layer is stacked on top of the bottom layer, is in contact with the bottom layer, and is operably connected to the bottom layer, and wherein the top layer is stacked on top of the middle layer, is in contact with the middle layer, and is operably connected to the middle layer.

[0202] Embodiment 21. A device according to embodiment 20, wherein the bottom layer includes the plurality of electrodes.

[0203] Embodiment 22. A device according to embodiment 20 or 21, wherein the bottom layer comprises a hydrogel and the plurality of electrodes.

[0204] Embodiment 23. A device according to any one of Embodiments 20-22, wherein the intermediate layer comprises a dielectric material.

[0205] Embodiment 24. A device according to any one of Embodiments 20-23, wherein the top layer includes the set of first connectors.

[0206] Embodiment 25. A device according to any one of Embodiments 20-24, wherein the bottom layer has a bottom layer shape, the middle layer has a middle layer shape, and the top layer has a top layer shape, wherein when the bottom layer and the middle layer are operably connected, and the middle layer and the top layer are operably connected, the bottom layer shape, the middle layer shape, and the top layer shape substantially overlap.

[0207] Embodiment 26. A device according to any one of embodiments 1-25, further comprising c) a control system, which is operably connected to the second item, wherein the control system includes 1) a power supply; 2) a processor, which is operably connected to the power supply and configured to operate the device; and 3) a stimulator, which is operably connected to the processor, operably connected to the power supply, and configured to transmit electrical stimulation to the circuit board.

[0208] Embodiment 27. A device according to embodiment 26, wherein the power supply, the processor and the stimulator are in a common housing.

[0209] Embodiment 28. An apparatus according to embodiment 26 or 27, wherein the control system further comprises a wireless receiver, which is operably connected to the processor and configured to receive instructions from a user for transmitting electrical stimulation to the circuit board.

[0210] Embodiment 29. An apparatus according to any one of Embodiments 26-28, wherein the control system further comprises a memory system operably connected to the processor and configured to record information about the use of the apparatus.

[0211] Embodiment 30. A device according to any of Embodiments 26-29, wherein the control system further includes a transmitter, which is operably connected to the processor and configured to wirelessly transmit information about the use of the device to a receiver external to the device.

[0212] Embodiment 31. A device according to embodiment 30, wherein the information about the use of the device is a stimulation provided to a part of the human body in physical contact with the device and a record of the movement of the part of the human body in response to the stimulation.

[0213] Embodiment 32. An apparatus according to any one of embodiments 26-31, wherein the control system further comprises a motion detector, which is operably connected to the processor and configured to detect movement of a part of the human body that is in physical contact with the apparatus.

[0214] Embodiment 33. A device comprising: A) a first item, wherein the first item is disposable, wherein the first item comprises: 1) a bottom layer, wherein the bottom layer comprises: A) a hydrogel; and B) a plurality of electrodes in contact with the hydrogel, wherein the plurality of electrodes are connected in sequence, wherein the plurality of electrodes are flexible, wherein the plurality of electrodes are silver ink, wherein the plurality of electrodes are configured to stimulate the muscle tissue and the neural target when the plurality of electrodes provide electrical stimulation to the muscle tissue and the neural target; 2) an intermediate layer, wherein the intermediate layer comprises a dielectric material, wherein the intermediate layer is laminated on top of the bottom layer, contacts the bottom layer, and is operably connected to the bottom layer. layer; and 3) a top layer, wherein the top layer includes a set of first connectors, wherein the first connectors are magnetic, wherein the top layer is stacked on top of the middle layer, contacts the middle layer, and is operably connected to the middle layer, wherein the bottom layer has a bottom layer shape, the middle layer has a middle layer shape, and the top layer has a top layer shape, wherein when the bottom layer and the middle layer are operably connected and the middle layer and the top layer are operably connected, the bottom layer shape, the middle layer shape, and the top layer shape substantially overlap; b) a second article, wherein the second article is durable, wherein the second article includes: 1) a second top surface, wherein the second top surface The present invention relates to a method for manufacturing a display device comprising: comprising a plurality of visual aids, wherein each of the plurality of visual aids independently corresponds to one of the plurality of electrodes, wherein the plurality of visual aids are LEDs, wherein each of the visual aids is configured to provide a visual signal when the electrode corresponding to the visual aid emits an electrical signal; 2) a flexible circuit board including conductors, the flexible circuit board being operably connected to the plurality of electrodes; and 3) a second bottom surface, wherein the second bottom surface includes a set of second connectors, wherein the second connectors are magnetic, wherein each of the first connectors is independently configured to couple to one of the second connectors ; and c) a control system operably connected to the second item, wherein the control system includes: 1) a power source; 2) a processor operably connected to the power source and configured to operate the device; 3) a stimulator operably connected to the processor, operably connected to the power source, and configured to transmit electrical stimulation to the flexible circuit board; 4) a wireless receiver operably connected to the processor and configured to receive instructions from a user for transmitting electrical stimulation to the flexible circuit board; 5) a memory system operably connected to the processor and configured to record information about the use of the device;6) a transmitter operably connected to the processor and configured to wirelessly transmit stimulation provided to a human body part in physical contact with the device and a record of movement of the human body part in response to the stimulation to a receiver external to the device; and 7) a motion detector operably connected to the processor and configured to detect movement of the human body part in physical contact with the device, wherein the power supply, the processor, the stimulator, the wireless receiver, the memory system, the transmitter and the motion detector are in a common housing, wherein the first connector and the second connector are configured to form a connection that holds the first item and the second item together when the first connector is coupled to the second connector, wherein when the first item and the second item are operably connected, the first item and the second item together form a wearable item, wherein the wearable item has a wearable size and a wearable shape suitable for mounting on the human body part, wherein the first item has a first item shape and the second item has a second item shape, wherein when the first item and the second item are operably connected, the first item shape and the second item shape substantially overlap, and wherein the bottom layer has at least 25 cm; 2 surface area.

[0215] Embodiment 34. A system comprising a device according to any one of Embodiments 1-33 and a telecommunication instrument configured to wirelessly operate the device.

[0216] Embodiment 35. A system according to embodiment 34, wherein the telecommunications device includes non-transitory computer executable code encoded on a computer readable medium, wherein the non-transitory computer executable code is configured to operate the device based on instructions provided by a user.

[0217] Embodiment 36. A system according to embodiment 35, wherein the non-transitory computer executable code is configured to use the device to monitor the performance of human subjects in physical therapy.

[0218] Embodiment 37. A system according to embodiment 35 or 36, wherein the non-transitory computer executable code is configured to provide an analysis of the performance of a human subject using the device in therapy, and to determine a proposed therapy regimen based on the analysis, wherein the proposed therapy regimen includes activating the plurality of electrodes in a pattern determined to be likely to provide an improvement in physical therapy based on the analysis.

[0219] Embodiment 38. A system according to any one of Embodiments 35-37, wherein the telecommunications instrument includes a touch screen that displays a grid, wherein the grid corresponds to the layout of the plurality of electrodes.

[0220] Embodiment 39. A system according to any one of Embodiments 35-38, wherein the telecommunications instrument includes a touch screen that displays a grid, wherein the grid corresponds to the layout of the multiple electrodes, and wherein touching the touch screen at a point on the grid activates the electrode of the multiple electrodes corresponding to the point on the grid.

[0221] Embodiment 40. A method comprising contacting a human subject with a device according to any one of embodiments 1-33.

[0222] Embodiment 41. A method comprising: a) contacting a body part of a human subject with a plurality of electrodes, wherein the plurality of electrodes are operably connected to a flexible circuit board, wherein the body part has a shape; b) manipulating the flexible circuit board to substantially conform to the shape of the body part; c) operably connecting a plurality of visualization aids to the flexible circuit board, wherein each of the plurality of visualization aids independently corresponds to one of the plurality of electrodes; and d) applying an electric current to the plurality of electrodes, whereby the plurality of electrodes provide electrical stimulation to the body part.

[0223] Embodiment 42. A method according to embodiment 41, wherein the body part includes muscle tissue and neural targets.

[0224] Embodiment 43. A method according to embodiment 41 or 42, wherein the plurality of electrodes are disposed in a hydrogel and the hydrogel is in contact with the body part.

[0225] Embodiment 44. A method according to any one of Embodiments 41-43, wherein the plurality of electrodes are silver ink.

[0226] Embodiment 45. A method according to any one of embodiments 41-44, wherein each visualization aid is configured to provide a visual signal when an electrode corresponding to the visualization aid emits an electrical signal.

[0227] Embodiment 46. A method according to Embodiment 45, wherein the plurality of visualization aids are LEDs.

[0228] Embodiment 47. A method according to any one of Embodiments 41-46, further comprising operably connecting a current source to the flexible circuit board.

[0229] Embodiment 48. A method according to any one of Embodiments 41-47, wherein the flexible circuit board is operably connected to a current source.

[0230] Embodiment 49. A method according to any one of embodiments 41-48, further comprising tracking the movement of the body part in response to the electrical stimulation.

[0231] Embodiment 50. A method according to any one of embodiments 41-49, further comprising tracking the movement of the body part in response to the electrical stimulation, and designing a physical therapy regimen based at least in part on the movement of the body part in response to the electrical stimulation, wherein the physical therapy regimen includes a pattern of electrical signals applied via the multiple electrodes.

[0232] Embodiment 51. A method comprising: a) contacting a body part of a human subject with a plurality of electrodes, wherein the plurality of electrodes are operably connected to a flexible circuit board, wherein the body part has a shape; b) manipulating the flexible circuit board to substantially conform to the shape of the body part; c) receiving instructions from a wireless user device for transmitting electrical stimulation to the flexible circuit board; and d) selecting at least a portion of the plurality of electrodes and applying an electric current to the portion of the plurality of electrodes, thereby the portion of the plurality of electrodes provides the electrical stimulation to the body part.

[0233] Embodiment 52. A method according to embodiment 51, wherein the body part includes muscle tissue and neural targets.

[0234] Embodiment 53. A method according to embodiment 51 or 52, wherein the plurality of electrodes are disposed in a hydrogel and the hydrogel is in contact with the body part.

[0235] Embodiment 54. A method according to any one of Embodiments 51-53, wherein the plurality of electrodes are silver ink.

[0236] Embodiment 55. A method according to any one of embodiments 51-54, further comprising operably connecting a plurality of visualization aids to the flexible circuit board, wherein each of the plurality of visualization aids independently corresponds to one of the plurality of electrodes, and wherein each visualization aid is configured to provide a visual signal when the electrode corresponding to the visualization aid emits an electrical signal.

[0237] Embodiment 56. A method according to any one of embodiments 51-55, wherein the flexible circuit board is operably connected to a plurality of visualization aids, wherein each of the plurality of visualization aids independently corresponds to one of the plurality of electrodes, and wherein each visualization aid is configured to provide a visual signal when the electrode corresponding to the visualization aid emits an electrical signal.

[0238] Embodiment 57. A method according to Embodiment 56, wherein the plurality of visualization aids are LEDs.

[0239] Embodiment 58. A method according to any one of Embodiments 51-57, further comprising operably connecting a current source to the flexible circuit board.

[0240] Embodiment 59. A method according to any one of Embodiments 51-58, wherein the flexible circuit board is operably connected to a current source.

[0241] Embodiment 60. A method according to any one of embodiments 51-59, further comprising tracking the movement of the body part in response to the electrical stimulation.

[0242] Embodiment 61. A method according to any of embodiments 51-60, further comprising tracking the movement of the body part in response to the electrical stimulation, and designing a physical therapy regimen based at least in part on the movement of the body part in response to the electrical stimulation, wherein the physical therapy regimen comprises a pattern of electrical signals applied via the multiple electrodes.

[0243] Embodiment 62. An addressable electrode system comprising: a power source; and an article, the article comprising: (i) a plurality of sequentially connected electrodes; (ii) a plurality of indicators; and (iii) a plurality of switches, each switch independently comprising a first terminal, a second terminal and a third terminal; wherein the first terminal of the switch is electrically coupled to the power source; wherein the second terminal of the switch is electrically coupled to one of the plurality of indicators; wherein the third terminal of the switch is electrically coupled to one of the plurality of sequentially connected electrodes; and wherein the switch is configured to simultaneously provide electrical power to the electrode and the indicator when power is provided to the first terminal of the switch by the power source.

[0244] Embodiment 63. A system according to embodiment 62, wherein the article is a textile.

[0245] Embodiment 64. A system according to embodiment 62 or 63, wherein the item is subdivided into multiple patches.

[0246] Embodiment 65. A system according to embodiment 64, wherein each of the multiple indicators independently corresponds to a patch among the multiple patches.

[0247] Embodiment 66. A system according to embodiment 65, wherein the indicator is disposed above the patch.

[0248] Embodiment 67. A system according to any one of Embodiments 62-66, wherein the plurality of sequentially connected electrodes are connected in a daisy chain configuration.

[0249] Embodiment 68. A system according to any one of Embodiments 62-67, wherein the switch comprises a solid-state relay.

[0250] Embodiment 69. A system according to any of Embodiments 62-67, wherein the switch comprises a metal oxide semiconductor field effect transistor (MOSFET).

[0251] Embodiment 70. A system according to any of Embodiments 62-69, wherein one of the plurality of indicators and one of the plurality of switches are incorporated into a single integrated circuit (IC).

[0252] Embodiment 71. A system according to any of Embodiments 62-70, wherein the second terminal of each switch is electrically coupled to at most one indicator.

[0253] Embodiment 72. A system according to any of Embodiments 62-71, wherein the second terminal of each switch is electrically coupled to at most one electrode.

[0254] Embodiment 73. A system according to any of Embodiments 62-72, wherein each electrode of the plurality of sequentially connected electrodes is electrically coupled to a return electrode.

[0255] Embodiment 74. A system according to embodiment 73, wherein each return electrode is integrated with one of the plurality of sequentially connected electrodes.

[0256] Embodiment 75. A system according to any one of embodiments 62-74, wherein the plurality of sequentially connected electrodes include at least a first electrode and a second electrode, wherein the first electrode is connected to the second electrode via a coiled wire, wherein the coiled wire is flexible.

[0257] Embodiment 76. A system according to any of embodiments 62-75, wherein each indicator produces visible light.

[0258] Embodiment 77. A system according to embodiment 76, wherein each indicator is a light emitting diode (LED).

[0259] Embodiment 78. A method for providing neural stimulation, comprising: a) receiving a gesture of a user at a user interface (UI), wherein the gesture is physical contact with the user interface; b) generating a control signal based at least in part on the gesture; c) generating a recommended spatial pattern of neural stimulation pulses for a subject from the control signal; and d) providing current to at least one of a plurality of electrodes in contact with the subject to provide the spatial pattern of the neural stimulation pulses to the subject.

[0260] Embodiment 79. A method according to embodiment 78, wherein the user interface includes a graphical user interface (GUI).

[0261] Embodiment 80. A method according to embodiment 79, wherein the GUI includes a layout, wherein the layout corresponds to the spatial configuration of the multiple electrodes.

[0262] Embodiment 81. A method according to embodiment 80, wherein the layout includes at least two dimensions.

[0263] Embodiment 82. A method according to embodiment 81, wherein the layout is a grid.

[0264] Embodiment 83. A method according to any one of Embodiments 78-81, further comprising displaying the user interface on a telecommunications device.

[0265] Embodiment 84. A method according to Embodiment 83, wherein the telecommunications device is a mobile device.

[0266] Embodiment 85. A method according to any one of embodiments 78-84, wherein the user interface is provided by a software application.

[0267] Embodiment 86. A method according to Embodiment 85, wherein the software application is a mobile application.

[0268] Embodiment 87. A method according to any one of embodiments 78-86, wherein the physical contact with the user interface occurs at a portion of the user interface, wherein the portion of the user interface corresponds to the position of at least one of the plurality of electrodes on the subject.

[0269] Embodiment 88. A method according to Embodiment 87, wherein the physical contact originates from a hand or a stylus.

[0270] Embodiment 89. A method according to embodiment 88, wherein the physical contact includes one or more taps.

[0271] Embodiment 90. A method according to embodiment 89, wherein the one or more tappings are simultaneous.

[0272] Embodiment 91. A method according to embodiment 89, wherein the one or more taps are continuous in time.

[0273] Embodiment 92. A method according to embodiment 87, wherein the physical contact includes pressing for an extended period of time.

[0274] Embodiment 93. A method according to Embodiment 92, wherein the physical contact further includes dragging.

[0275] Embodiment 94. A method according to any one of Embodiments 78-93, wherein the control signal is provided via a network.

[0276] Embodiment 95. A method according to Embodiment 94, wherein the network is a wired network or a wireless network.

[0277] Embodiment 96. A method according to Embodiment 95, wherein the network is Ethernet, Bluetooth or Wi-Fi.

[0278] Embodiment 97. A method according to any one of Embodiments 78-96, wherein the plurality of electrodes comprises an array of electrodes.

[0279] Embodiment 98. A method according to Embodiment 97, wherein the array of electrodes is embedded in an article.

[0280] Embodiment 99. A method according to Embodiment 98, wherein the article is a textile.

[0281] Embodiment 100. A method according to Embodiment 99, wherein the textile is incorporated into a wearable device.

[0282] Embodiment 101. A method according to any of embodiments 78-100, wherein the generating the recommended spatial pattern of neural stimulation pulses is performed by a processor.

[0283] Embodiment 102. A method according to embodiment 101, wherein the control signal provides a set of instructions that, when executed by the processor, generate the recommended spatial pattern of neural stimulation pulses.

[0284] Embodiment 103. A system for providing neural stimulation, comprising: a telecommunications device; a stimulation module; an electrode array; a power source; the telecommunications device comprising: a software application, the software application being configured to provide a user interface, the user interface being configured to accept a gesture, wherein the gesture is physical contact with the user interface and to generate a control signal based at least in part on the gesture; a transmitter, the transmitter being configured to send the control signal to the stimulation module; the electrode array comprising: a plurality of electrodes, wherein each electrode is electrically coupled to the power source via a switch, wherein each switch is configured to connect or disconnect the corresponding electrode to or from the power source; the stimulation module comprising: a receiver, the receiver being configured to receive the control signal; a processor, which is operably coupled to the receiver, the processor being configured to generate a recommended pattern of neural stimulation pulses from the control signal; and a switch unit, the switch unit being configured to configure each switch to connect or disconnect the corresponding electrode in response to the recommended pattern of neural stimulation pulses.

[0285] Embodiment 104. A system comprising: a first device as in Embodiment 1; and a second device as in Embodiment 1.

[0286] Embodiment 105. A system according to embodiment 105, wherein the second device is operably coupled to the neck of the subject, wherein the second device is configured to provide a second neural stimulation to the spinal cord.

[0287] Embodiment 106. A system according to embodiment 106, wherein the second device is configured to provide the second neural stimulation in response to the first neural stimulation provided by the first device.

[0288] Embodiment 107. A system according to Embodiment 107, wherein the second device is configured to provide the second neural stimulation simultaneously with the first neural stimulation provided by the first device.

[0289] Embodiment 108. A system according to embodiment 107, wherein the second device is configured to provide the second neural stimulation after the first neural stimulation provided by the first device.

[0290] Embodiment 109. A system according to any of Embodiments 107-109, wherein the second device is configured to provide the second neural stimulation for a duration that is longer than a duration of the first neural stimulation provided by the first device.

[0291] Embodiment 110. A system according to any of Embodiments 107-110, wherein the second device is configured to provide the second neural stimulation for a duration that is the same as a duration of the first neural stimulation provided by the first device.

[0292] Embodiment 111. A device comprising: a first item, wherein the first item comprises 1) a plurality of electrodes; and 2) a hydrogel layer; and a second item, wherein the second item comprises 1) a circuit board operably connected to the plurality of electrodes; 2) a second top surface, wherein the second top surface comprises a plurality of visualization aids, wherein each of the plurality of visualization aids independently corresponds to one of the plurality of electrodes; wherein when the first item and the second item are operably connected, the first item and the second item together form a wearable object, wherein the wearable object has a wearable size and a wearable shape suitable for mounting on a part of a human body.

Claims

1. A device comprising: a) a first article, wherein the first article comprises: 1) a first top surface, wherein the first top surface includes a set of first connectors; and 2) a first bottom surface, wherein the first bottom surface comprises a plurality of electrodes; and b) a second article, wherein the second article comprises: 1) a circuit board operably connected to the plurality of electrodes; 2) a second top surface, wherein the second top surface includes a plurality of visualization aids, wherein each visualization aid of the plurality of visualization aids independently corresponds to one electrode of the plurality of electrodes; and 3) a second bottom surface, wherein the second bottom surface includes a set of second connectors, wherein each of the first connectors is independently configured to couple to one of the second connectors, wherein the first connector and the second connector are configured to form a connection that holds the first item and the second item together when the first connector is coupled to the second connector, When the first article and the second article are operably connected, the first article and the second article together form a wearable object, wherein the wearable object has a wearable size and a wearable shape suitable for being mounted on a part of a human body.

2. The apparatus of claim 1, wherein the visualization aid is a light.

3. The device of claim 1, wherein the visual aid is an LED. 4 . The apparatus of claim 1 , wherein each visualization aid is configured to provide a visual signal when an electrode corresponding to the visualization aid emits an electrical signal.

5. The device of claim 1, wherein the plurality of electrodes are flexible.

6. The apparatus of claim 1, wherein the plurality of electrodes are silver ink.

7. The apparatus of claim 1, wherein the plurality of electrodes are configured to stimulate the muscle tissue and the neural target when the plurality of electrodes provide electrical stimulation to the muscle tissue and the neural target. The device according to claim 1 , wherein the plurality of electrodes are connected sequentially.

9. The device of claim 1, wherein the first connector and the second connector are magnetic.

10. The apparatus of claim 1, wherein the first item has a first item shape and the second item has a second item shape, wherein the first item shape and the second item shape substantially overlap when the first item and the second item are operably connected.

11. The apparatus of claim 1, wherein the first bottom surface has a width of at least 25 cm 2 surface area.

12. The device of claim 1, wherein the circuit board is flexible.

13. The apparatus of claim 1, wherein the circuit board comprises a conductor.

14. The apparatus of claim 13, wherein the conductor is gold-plated copper.

15. The apparatus of claim 13, wherein the conductor is bonded to a plating layer.

16. The apparatus of claim 13, wherein the conductor is bonded to a nickel-copper-nickel plating.

17. The apparatus of claim 1, wherein the second article is durable.

18. The apparatus of claim 1, wherein the first article is disposable.

19. The apparatus of claim 1, wherein the first article is configured to contact human skin.

20. The apparatus of claim 1, wherein the first article comprises a bottom layer, a middle layer, and a top layer, wherein the middle layer is stacked on top of the bottom layer, in contact with the bottom layer, and operably connected to the bottom layer, and wherein the top layer is stacked on top of the middle layer, in contact with the middle layer, and operably connected to the middle layer.

21. The device of claim 20, wherein the bottom layer comprises the plurality of electrodes.

22. The device of claim 20, wherein the bottom layer comprises a hydrogel and the plurality of electrodes.

23. The apparatus of claim 20, wherein the intermediate layer comprises a dielectric material.

24. The apparatus of claim 20, wherein the top layer comprises the set of first connectors.

25. The device of claim 20, wherein the bottom layer has a bottom layer shape, the middle layer has a middle layer shape, and the top layer has a top layer shape, wherein when the bottom layer and the middle layer are operably connected, and the middle layer and the top layer are operably connected, the bottom layer shape, the middle layer shape, and the top layer shape substantially overlap.

26. The apparatus of claim 1, further comprising: c) a control system operably connected to the second item, wherein the control system comprises: 1) Power supply; 2) a processor operably connected to the power source and configured to operate the device; and 3) A stimulator operably connected to the processor, operably connected to the power source, and configured to deliver electrical stimulation to the circuit board.

27. The device of claim 26, wherein the power supply, the processor and the stimulator are in a common housing.

28. The apparatus of claim 26, wherein the control system further comprises a wireless receiver operably connected to the processor and configured to receive instructions from a user to deliver electrical stimulation to the circuit board.

29. The device of claim 26, wherein the control system further comprises a memory system operably connected to the processor and configured to record information regarding usage of the device.

30. The device of claim 26, wherein the control system further comprises a transmitter operably connected to the processor and configured to wirelessly transmit information regarding usage of the device to a receiver external to the device.

31. A device according to claim 30, wherein the information about the use of the device is stimulation provided to a human body part in physical contact with the device and a record of the movement of the human body part in response to the stimulation.

32. The device of claim 26, wherein the control system further comprises a motion detector operably connected to the processor and configured to detect motion of a human body part in physical contact with the device.

33. An apparatus comprising: a) a first article, wherein the first article is disposable, wherein the first article comprises: 1) A bottom layer, wherein the bottom layer comprises: A) a hydrogel; and B) a plurality of electrodes in contact with the hydrogel, wherein the plurality of electrodes are connected sequentially, wherein the plurality of electrodes are flexible, wherein the plurality of electrodes are silver ink, wherein the plurality of electrodes are configured to stimulate the muscle tissue and the neural target when the plurality of electrodes provide electrical stimulation to the muscle tissue and the neural target; 2) an intermediate layer, wherein the intermediate layer comprises a dielectric material, wherein the intermediate layer is laminated on top of the bottom layer, contacts the bottom layer, and is operably connected to the bottom layer; and 3) a top layer, wherein the top layer includes a set of first connectors, wherein the first connectors are magnetic, wherein the top layer is laminated on top of the middle layer, contacts the middle layer, and is operably connected to the middle layer, wherein the bottom layer has a bottom layer shape, the middle layer has a middle layer shape, and the top layer has a top layer shape, wherein when the bottom layer and the middle layer are operably connected, and the middle layer and the top layer are operably connected, then the bottom layer shape, the middle layer shape, and the top layer shape substantially overlap; b) a second article, wherein the second article is durable, wherein the second article comprises: 1) a second top surface, wherein the second top surface includes a plurality of visualization aids, wherein each visualization aid of the plurality of visualization aids independently corresponds to one of the plurality of electrodes, wherein the plurality of visualization aids are LEDs, wherein each visualization aid is configured to provide a visual signal when the electrode corresponding to the visualization aid emits an electrical signal; 2) a flexible circuit board including a conductor, the flexible circuit board being operably connected to the plurality of electrodes; and 3) a second bottom surface, wherein the second bottom surface includes a set of second connectors, wherein the second connectors are magnetic, wherein each of the first connectors is independently configured to couple to one of the second connectors; and c) a control system operably connected to the second item, wherein the control system comprises: 1) Power supply; 2) a processor operably connected to the power source and configured to operate the device; 3) a stimulator operably connected to the processor, operably connected to the power source, and configured to deliver electrical stimulation to the flexible circuit board; 4) a wireless receiver operably connected to the processor and configured to receive instructions from a user for delivering electrical stimulation to the flexible circuit board; 5) a memory system operably connected to the processor and configured to record information about the use of the device; 6) a transmitter operably connected to the processor and configured to wirelessly transmit to a receiver external to the device a stimulus provided to a human body part in physical contact with the device and a record of movement of the human body part in response to the stimulus; and 7) a motion detector operably connected to the processor and configured to detect motion of a human body part in physical contact with the device, wherein the power supply, the processor, the stimulator, the wireless receiver, the memory system, the transmitter, and the motion detector are in a common housing, wherein the first connector and the second connector are configured to form a connection that holds the first item and the second item together when the first connector is coupled to the second connector, wherein when the first article and the second article are operably connected, the first article and the second article together form a wearable object, wherein the wearable object has a wearable size and a wearable shape suitable for being mounted on the human body part, wherein the first article has a first article shape and the second article has a second article shape, wherein when the first article and the second article are operably connected, the first article shape and the second article shape substantially overlap, wherein the bottom layer has at least 25 cm 2 surface area.

34. A system comprising a device according to any one of claims 1-33 and a telecommunication apparatus configured to wirelessly operate the device.

35. The system of claim 34, wherein the telecommunications device includes non-transitory computer executable code encoded on a computer readable medium, wherein the non-transitory computer executable code is configured to operate the device based on instructions provided by a user.

36. The system of claim 35, wherein the non-transitory computer executable code is configured to use the device to monitor the performance of a human subject in physical therapy.

37. A system according to claim 35, wherein the non-transitory computer executable code is configured to provide an analysis of the performance of a human subject using the device in therapy, and to determine a proposed therapy regimen based on the analysis, wherein the proposed therapy regimen includes activating the plurality of electrodes in a pattern determined to be likely to provide an improvement in physical therapy based on the analysis.

38. The system of claim 35, wherein the telecommunications instrument comprises a touch screen that displays a grid, wherein the grid corresponds to the layout of the plurality of electrodes.

39. A system according to claim 35, wherein the telecommunications instrument includes a touch screen that displays a grid, wherein the grid corresponds to the layout of the plurality of electrodes, wherein touching the touch screen at a point on the grid activates an electrode of the plurality of electrodes corresponding to the point on the grid.

40. A method comprising contacting a human subject with the device of any one of claims 1-33.

41. A method comprising: a) contacting a body part of a human subject with a plurality of electrodes, wherein the plurality of electrodes are operably connected to a flexible circuit board, wherein the body part has a shape; b) manipulating said flexible circuit board to substantially conform to said shape of said body part; c) operatively connecting a plurality of visualization aids to the flexible circuit board, wherein each of the plurality of visualization aids independently corresponds to one of the plurality of electrodes; as well as d) applying an electric current to the plurality of electrodes, whereby the plurality of electrodes provide electrical stimulation to the body part.

42. The method of claim 41, wherein the body part comprises muscle tissue and a neural target.

43. The method of claim 41, wherein the plurality of electrodes are disposed in a hydrogel and the hydrogel is in contact with the body part.

44. The method of claim 41, wherein the plurality of electrodes are silver ink.

45. The method of claim 41, wherein each visualization aid is configured to provide a visual signal when an electrode corresponding to the visualization aid emits an electrical signal.

46. ​​The method of claim 45, wherein the plurality of visualization aids are LEDs.

47. The method of claim 41, further comprising operably connecting a current source to the flexible circuit board.

48. The method of claim 41, wherein the flexible circuit board is operably connected to a current source.

49. The method of claim 41, further comprising tracking movement of the body part in response to the electrical stimulation.

50. The method of claim 41, further comprising tracking movement of the body part in response to the electrical stimulation, and designing a physical therapy regimen based at least in part on the movement of the body part in response to the electrical stimulation, wherein the physical therapy regimen comprises a pattern of electrical signals applied via the plurality of electrodes.

51. A method comprising: a) contacting a body part of a human subject with a plurality of electrodes, wherein the plurality of electrodes are operably connected to a flexible circuit board, wherein the body part has a shape; b) manipulating said flexible circuit board to substantially conform to said shape of said body part; c) receiving instructions from a wireless user device for delivering electrical stimulation to the flexible circuit board; as well as d) selecting at least a portion of the plurality of electrodes and applying an electric current to the portion of the plurality of electrodes, whereby the portion of the plurality of electrodes provides the electrical stimulation to the body part.

52. The method of claim 51, wherein the body part comprises muscle tissue and a neural target.

53. The method of claim 51, wherein the plurality of electrodes are disposed in a hydrogel and the hydrogel is in contact with the body part.

54. The method of claim 51, wherein the plurality of electrodes are silver ink.

55. The method of claim 51, further comprising operably connecting a plurality of visualization aids to the flexible circuit board, wherein each of the plurality of visualization aids independently corresponds to one of the plurality of electrodes, wherein each visualization aid is configured to provide a visual signal when the electrode corresponding to the visualization aid emits an electrical signal.

56. The method of claim 51 , wherein the flexible circuit board is operably connected to a plurality of visualization aids, wherein each of the plurality of visualization aids independently corresponds to one of the plurality of electrodes, wherein each visualization aid is configured to provide a visual signal when the electrode corresponding to the visualization aid emits an electrical signal.

57. The method of claim 56, wherein the plurality of visualization aids are LEDs.

58. The method of claim 51, further comprising operably connecting a current source to the flexible circuit board.

59. The method of claim 51, wherein the flexible circuit board is operably connected to a current source.

60. The method of claim 51, further comprising tracking movement of the body part in response to the electrical stimulation.

61. The method of claim 51 , further comprising tracking movement of the body part in response to the electrical stimulation, and designing a physical therapy regimen based at least in part on the movement of the body part in response to the electrical stimulation, wherein the physical therapy regimen comprises a pattern of electrical signals applied via the plurality of electrodes.

62. An addressable electrode system comprising: power supply; and Articles, the articles comprising: (i) multiple electrodes connected in sequence; (ii) multiple indicators; and (iii) a plurality of switches, each switch independently comprising a first terminal, a second terminal and a third terminal; wherein the first terminal of the switch is electrically coupled to the power source; wherein the second terminal of the switch is electrically coupled to an indicator of the plurality of indicators; wherein the third terminal of the switch is electrically coupled to one electrode of the plurality of sequentially connected electrodes; and The switch is configured to simultaneously provide electrical power to the electrode and the indicator when power is supplied to the first terminal of the switch by the power source.

63. The system of claim 62, wherein the article is a textile.

64. The system of claim 62, wherein the item is subdivided into a plurality of patches.

65. The system of claim 64, wherein each indicator of the plurality of indicators independently corresponds to a patch of the plurality of patches.

66. The system of claim 65, wherein the indicator is disposed above the patch.

67. The system of claim 62, wherein the plurality of sequentially connected electrodes are connected in a daisy chain configuration.

68. The system of claim 62, wherein the switch comprises a solid state relay.

69. The system of claim 62, wherein the switch comprises a metal oxide semiconductor field effect transistor (MOSFET).

70. The system of claim 62, wherein an indicator of the plurality of indicators and a switch of the plurality of switches are incorporated into a single integrated circuit (IC).

71. The system of claim 62, wherein the second terminal of each switch is electrically coupled to at most one indicator.

72. The system of claim 62, wherein the second terminal of each switch is electrically coupled to at most one electrode.

73. The system of claim 62, wherein each electrode of the plurality of serially connected electrodes is electrically coupled to a return electrode.

74. A system according to claim 73, wherein each return electrode is integrated with one electrode of the plurality of sequentially connected electrodes.

75. The system of claim 62, wherein the plurality of sequentially connected electrodes comprises at least a first electrode and a second electrode, wherein the first electrode is connected to the second electrode via a coiled wire, wherein the coiled wire is flexible.

76. The system of claim 62, wherein each indicator produces visible light.

77. The system of claim 76, wherein each indicator is a light emitting diode (LED).

78. A method for providing neural stimulation, comprising: a) receiving a user gesture at a user interface (UI), wherein the gesture is a physical contact with the user interface; b) generating a control signal based at least in part on the gesture; c) generating a recommended spatial pattern of neural stimulation pulses for the subject from the control signal; as well as d) providing an electric current to at least one electrode of a plurality of electrodes in contact with the subject to provide the spatial pattern of the recommended neural stimulation pulses to the subject.

79. The method of claim 78, wherein the user interface comprises a graphical user interface (GUI).

80. The method of claim 79, wherein the GUI comprises a layout, wherein the layout corresponds to a spatial configuration of the plurality of electrodes.

81. The method of claim 80, wherein the layout comprises at least two dimensions.

82. The method of claim 80, wherein the layout is a grid.

83. The method of claim 78, further comprising displaying the user interface on a telecommunications device.

84. A method according to claim 78, wherein the physical contact with the user interface occurs at a portion of the user interface, wherein the portion of the user interface corresponds to the position of at least one of the plurality of electrodes on the subject.

85. The method of claim 78, wherein the plurality of electrodes are embedded in an article.

86. The method of claim 85, wherein the article is a textile.

87. The method of claim 86, wherein the textile is incorporated into a wearable device.

88. The method of claim 78, wherein said generating said recommended spatial pattern of neural stimulation pulses is performed by a processor.

89. The method of claim 88, wherein the control signal provides a set of instructions that, when executed by the processor, generate the recommended spatial pattern of neural stimulation pulses.

90. A system for providing neural stimulation, comprising: a) telecommunications equipment; b) Stimulation module; c) electrode array; as well as d) Power supply; The telecommunications equipment comprises: 1) a software application configured to provide a user interface, the user interface configured to accept a gesture from a user, wherein the gesture is physical contact with the user interface, and to generate a control signal based at least in part on the gesture; and 2) a transmitter, the transmitter being configured to send the control signal to the stimulation module; The electrode array comprises: a plurality of electrodes, wherein each electrode is independently electrically coupled to the power source via a switch, wherein each switch is configured to connect or disconnect a corresponding electrode from the power source; and The stimulation module comprises: 1) a receiver, the receiver being configured to receive the control signal; 2) a processor operably coupled to the receiver, the processor configured to generate a recommended pattern of neural stimulation pulses from the control signal; and 3) A switch unit configured to configure each switch to connect or disconnect the corresponding electrode in response to the recommended pattern of neural stimulation pulses.

Images