Wearable devices for targeted peripheral stimulation

Abstract

In one embodiment, a wearable device for targeted peripheral stimulation is presented. The wearable device includes a sensor configured to receive data and generate a sensor output. The wearable device includes a processor that communicates with the sensor. The wearable device includes a memory communicably connected to the processor. The memory stores instructions that configure the processor to receive the sensor output from the sensor, the sensor output indicating one or more motor impairment symptoms of the user. The processor is configured to determine the disease state of the one or more motor impairment symptoms and generate a stimulation output based on the one or more motor impairment symptoms and the disease state of the motor impairment symptoms.

Description

Cross-reference of related applications

[0001] This application claims priority to U.S. Provisional Application No. 63 / 512,803, filed on 10 July 2023, which is incorporated herein by reference in its entirety. [Technical Field]

[0002] This disclosure relates to wearable devices. In particular, this disclosure relates to wearable devices for targeted peripheral stimulation. [Overview of the project] [Means for solving the problem]

[0003] In one embodiment, a wearable device for targeted peripheral stimulation is presented. The wearable device includes a sensor configured to receive data and generate a sensor output. The wearable device includes a processor that communicates with the sensor. The wearable device includes a memory communicably connected to the processor. The memory stores instructions that constitute the processor, which configure the processor to receive a sensor output from the sensor, the sensor output indicating one or more motor impairment symptoms of the user. The processor is configured to determine the onset stage of one or more motor impairment symptoms. The processor is configured to generate a stimulation output based on one or more motor impairment symptoms and the onset stage of the motor impairment symptoms. The processor is configured to instruct a stimulator communicating with the processor to apply the stimulation output to the user's peripheral nervous system to alleviate one or more motor impairment symptoms.

[0004] In another embodiment, a method for targeted peripheral stimulation is presented. The method includes attaching a wearable device to a user. The method includes detecting one or more motor impairment symptoms of the user through sensors on the wearable device. The method includes calculating the onset stage of one or more motor impairment symptoms. The method includes stimulating the user's peripheral nervous system through a stimulator on the wearable device in response to one or more motor impairment symptoms. The method includes detecting the user's responsiveness through sensors on the wearable device. The method includes stimulating the user's peripheral nervous system based on the detected responsiveness and the onset stage of one or more motor impairment symptoms.

[0005] The above and other preferred features (including various details and combinations of elements of the embodiments) will be described in more detail with reference to the accompanying drawings and will be expressed in the claims. It should be understood that the specific methods and apparatus described herein are illustrative and not limiting. As will be understood by those skilled in the art, the principles and features described herein can be employed in a variety and numerous embodiments. [Brief explanation of the drawing]

[0006] The disclosed embodiments have advantages and features that will become more readily apparent from the detailed description, the accompanying claims, and the accompanying figures (or drawings). A brief introduction to the figures is given below.

[0007] [Figure 1] This is a block diagram of a wearable device for targeted peripheral stimulation. [Figure 2] This is a block diagram of waveform parameter selection for a wearable device. [Figure 3] This is a block diagram of waveform parameter selection via a smartphone application that communicates with a wearable device. [Figure 4] This is a block diagram of a feature extraction process that can be performed by a wearable device. [Figure 5] This diagram shows a flowchart of the method for target peripheral stimulation. [Figure 6] This graph shows the baseline Unified Parkinson's Disease Rating Scale (UPDRS) scores of the subjects. [Figure 7] This graph shows the median and absolute percentage changes in symptoms for subjects with early-onset Parkinson's disease (EOPD) and late-onset Parkinson's disease (LOPD). [Figure 8] This graph shows baseline and stimulation-induced results for EOPD subjects. [Figure 9] This graph shows baseline and stimulation-induced results for LOPD subjects. [Figure 10] This graph shows the improvement in BF-ADL scores in subjects of various ages. [Figure 11] This is an illustration of a wearable device. [Figure 12] Figure 11 is an exploded view of the wearable device. Detailed description of the invention

[0008] The figures (or multiple figures) and the following description relate to preferred embodiments for illustrative purposes only. It should be noted from the following discussion that alternative embodiments of the structures and methods disclosed herein are readily recognizable as viable alternatives that can be adopted without departing from the principles of the claims.

[0009] Several embodiments are described in detail below, examples of which are shown in the accompanying drawings. Where practically possible, similar or identical reference numerals are used in the drawings to indicate similar or identical functions. The drawings show embodiments of systems (or methods) disclosed for illustrative purposes only. Those skilled in the art will readily recognize from the following description that alternative embodiments of the structures and methods described herein can be adopted without departing from the principles described herein.

[0010] Aspects of the present disclosure may be used to provide interchangeability of one or more stimulators for wearable devices, such as wearable neurostimulators. In some embodiments, the assemblies, systems, and methods of the present specification may result in improved durability of wearable neurostimulators, including against mechanical stress, moisture, temperature changes, repeated electrical or vibrational stimulation, and / or increasing other parameters. Embodiments of the present disclosure may be used to provide low-profile electrical connector systems that can enable long-term electrical connections between stimulator assemblies and / or control / power supply assemblies.

[0011] Figure 1 shows a system 100 for targeted peripheral stimulation according to one embodiment of the present invention. The system 100 may include a wearable device 100. The wearable device 100 may include a processor, such as a processing unit 104, and memory communicably connected to the processing unit 104. The memory of the wearable device 100 may store instructions that configure the processing unit 104 of the wearable device 100 to perform various tasks. The wearable device 100 may include a communication module 108. As used throughout this disclosure, “communication module” refers to any form of software and / or hardware capable of transmitting electromagnetic energy. For example, the communication module 108 may be configured to send and receive radio signals, Wi-Fi signals, Bluetooth® signals, cellular signals, etc. The communication module 108 may include a transmitter, a receiver, and / or other components. The transmitter of the communication module 108 may include, but is not limited to, an antenna. The antenna of the communication module 108 may include, but is not limited to, a dipole, monopole, array, loop, and / or other antenna types. The receiver of the communication module 108 may include, but is not limited to, an antenna as described above. The communication module 108 may communicate with the processing unit 104. For example, the processing unit 104 may be physically connected to the communication module 108 through one or more wires, circuits, etc. The processing unit 104 may instruct the communication module 108 to send or receive data to one or more other devices. For example, but is not limited to, the communication module 108 may transmit vibration stimulus data, motion data of the user's body 150, electrical activity of the user's muscles 164, etc. In some embodiments, the communication module 108 may transmit therapeutic data. Therapeutic data may include, but is not limited to, the severity of symptoms, the type of symptoms, the frequency of vibration stimuli 13, data from the sensor suite 112, etc. The communication module 108 can communicate with one or more external computing devices, including but not limited to smartphones, tablets, laptops, desktops, servers, and cloud computing devices.The wearable device 100 may be as described below with reference to Figure 9.

[0012] Continuing to refer to Figure 1, the wearable device 100 may include one or more sensors. As used throughout this disclosure, “sensor” is an element capable of detecting physical properties. Physical properties include, but are not limited to, kinematics, electrical, magnetic, radiant, and thermal energy. In some embodiments, the wearable device 100 may include a sensor suite 112. As used throughout this disclosure, “sensor suite” is a combination of two or more sensors. A sensor suite 112 may have multiple sensors, such as two or more sensors. A sensor suite 112 may have two or more sensors of the same type. In other embodiments, a sensor suite 112 may have two or more sensors of different types. For example, a sensor suite 112 may include an electromyography sensor (EMG) and an inertial measurement unit (IMU). The IMU may be configured to detect and / or measure the specific force, angular velocity, and / or posture of the body. Other sensors that a sensor suite 112 may include are, but are not limited to, accelerometers, gyroscopes, impedance sensors, temperature sensors, and / or other sensor types. The sensor suite 112 can communicate with the processing unit 104. The communication between the sensor suite 112 and the processing unit 104 may be an electrical connection that allows data to be shared between the sensor suite 112 and the processing unit 104. In some embodiments, the sensor suite 112 may use Wi-Fi, Bluetooth, etc. (R) The wearable device 100 may be wirelessly connected to the processing unit 104 via a wireless or other connection. In some embodiments, the wearable device 100 may be identical to the wearable device described in U.S. Patent Application No. 16 / 563,087, filed on September 6, 2019, entitled “Apparatus and Method Using a Wearable Device for Alleviating Symptoms of Neuromotor Disorders.” The entire contents of that application are incorporated herein by reference.

[0013] One or more sensors in the sensor suite 112 may be configured to receive data from a user (e.g., the user's body). Data received by one or more sensors in the sensor suite 112 may include, but are not limited to, motion data, electrical data, etc. Motion data may include, but are not limited to, acceleration, velocity, angular velocity, and / or other types of kinematics. In some embodiments, the IMU of the sensor suite 112 may be configured to receive movement from the user's body. Movement may include, but are not limited to, vibration, acceleration, muscle contraction, and / or other aspects of movement. Movement may be generated from one or more muscles in the user's body. Muscles may include, but are not limited to, wrist muscles, hand muscles, forearm muscles, and / or other muscles. In one embodiment, movement generated from one or more muscles in the user's body may be involuntarily generated by one or more symptoms of a motor disorder in the user's body. Motor disorders may include, but are not limited to, Parkinson's disease (PD), recovery after stroke, etc. Symptoms of motor impairment include, but are not limited to, rigidity, gait freeze, tremor, shaking, involuntary muscle contractions, and / or other symptoms. In other embodiments, movements generated from the user's body muscles may be voluntary. For example, a user may actively control one or more of their muscles, thereby generating movements that can be detected and / or received by the sensors of the sensor suite 112.

[0014] Continuing to refer to Figure 1, one or more sensors in the sensor suite 112 may be configured to receive electrical data (e.g., electrical activity that may be generated by one or more muscles of the user). Electrical data may include, but is not limited to, voltage, impedance, current, resistance, reactance value, waveform, etc. For example, electrical activity may include an increase in current and / or voltage of one or more muscles during the contraction of those muscles. The EMG of the sensor suite 112 may be configured to receive and / or detect electrical activity generated by one or more muscles of the user. In some embodiments, one or more sensors in the sensor suite 112 may be configured to generate sensor outputs. As used in this disclosure, “sensor output” is information generated by one or more sensing devices. Sensor outputs may include, but are not limited to, voltage, current, acceleration, velocity, and / or other outputs. Sensor outputs generated from one or more sensors in the sensor suite 112 may be communicated to a processing unit 104 via wired, wireless, or other connections, etc. The processing unit 104 may be configured to determine symptoms of a motor impairment based on the sensor outputs received from one or more sensors. The processing unit 104 may be configured to determine symptoms such as rigidity, tremor, and gait freezing, but is not limited to these. Gait freezing is a symptom of Parkinson's disease in which a person with Parkinson's disease experiences episodes in which they suddenly and temporarily become unable to take a step forward despite their intention to walk. Abnormal gait patterns can range from mere inconvenience to potentially dangerous and may increase the risk of falls. Rigidity may refer to the involuntary contraction and rigidity of the muscles of a person with Parkinson's disease. The processing unit 104 may compare one or more values ​​of sensor outputs from the sensor suite 112 to one or more values ​​associated with one or more symptoms of motor impairment. For example, the processing unit 104 may compare the sensor output of one or more sensors in the sensor suite 112 to one or more stored values ​​already associated with one or more symptoms of motor impairment. As a non-limiting example, an acceleration of the user's arm from approximately 1 inch / second to approximately 3 inches / second may correspond to a symptom of mild tremor.

[0015] In some embodiments, processing unit 104 may utilize a classifier or other machine learning model that classifies sensor outputs into categories of movement disorder symptoms. As used herein, a "classifier" is a machine learning model (such as a mathematical model, neural network, or program) generated by a machine learning algorithm called a "classification algorithm" that classifies inputs into categories or bins of data and outputs data for that category or bin and / or labels associated therewith. The classifier may be configured to output at least one data that identifies or labels a set of data that has been clustered or found to be proximate under a distance metric described below. The processor 104 and / or another device may generate the classifier using a classification algorithm (defined as the process by which the processor derives the classifier from training data). Classification may be performed using, but is not limited to, linear classifiers such as logistic regression and / or naive Bayes classifiers, nearest neighbor classifiers such as k-nearest neighbor classifiers, support vector machines, least squares support vector machines, Fisher's linear discriminant, quadratic classifiers, decision trees, boosted trees, random forest classifiers, kernel estimation, learning vector quantization, and / or neural network-based classifiers.

[0016] Continuing to refer to FIG. 1, the classifier may be generated using, as a non-limiting example, the Naive Bayes classification algorithm. The Naive Bayes classification algorithm generates a classifier by assigning class labels to problem cases represented as vectors of element values. The class labels are drawn from a finite set. The Naive Bayes classification algorithm may include generating a family of algorithms that assume that the value of a particular element is independent of the values of any other elements when the class variable is given. The Naive Bayes classification algorithm may be based on Bayes' theorem expressed as P(A / B)=P(B / A) P(A)÷P(B). Here, P(A / B) is the probability of hypothesis A when data B is given (also called the posterior probability), P(B / A) is the probability of data B when hypothesis A is true, P(A) is the probability that hypothesis A is true independent of the data (also called the prior probability of A), and P(B) is the probability of data independent of the hypothesis. The Naive Bayes algorithm may be generated by first converting the training data into a frequency table.

[0017] The processor 104 may calculate a likelihood table by calculating the probabilities of different data entries and classification labels. The processor 104 may calculate the posterior probability of each class using the Naive Bayes equation. The class containing the highest posterior probability becomes the result of the prediction. The Naive Bayes classification algorithm may include a Gaussian model that follows a normal distribution. The Naive Bayes classification algorithm may include a multinomial model used for discrete counts. The Naive Bayes classification algorithm may include a Bernoulli model that may be used when the vector is binary.

[0018] Continuing to refer to Figure 1, a classifier may be generated using the K-Nearest Neighbors (KNN) algorithm. As used in this disclosure, the “K-Nearest Neighbors” algorithm includes a classification method that utilizes feature similarity to analyze how close out-of-sample features are to the training data and classifies the input data into one or more clusters and / or categories of features represented in the training data. This may be performed by representing both the training and input data in vector form and using one or more vector similarity measures to identify classifications within the training data and to determine the classification of the input data. The K-Nearest Neighbors algorithm may include specifying a K value (a number that instructs the classifier to select the k most similar entries from the training data for a given sample), determining the most common classifier among the entries in the database, and classifying known samples. This may be performed recursively and / or iteratively to generate classifiers that can be used to classify the input data as further samples. For example, an initial set of samples may be run to cover initial heuristics and / or “initial estimates” about outputs and / or relationships, which may be seeded with expert input received by any process described herein, but are not limited to such inputs. As a non-restrictive example, early heuristics may include ranking the relevance between elements of the input and training data. Heuristics may include selecting some of the highest-ranking relevances and / or elements of the training data.

[0019] The classifier can be trained with training data that correlates motor data and / or electrical data to symptoms of motor impairment. Training data can be received through user input, an external computing device, and / or past training iterations. As a non-limiting example, the IMU of the sensor suite 112 may receive motor data generated by one or more muscles of the user and generate a sensor output including acceleration values ​​that are communicated to the processing unit 104. The processing unit 104 may classify and / or categorize the sensor output into symptoms of gait freezing (FOG).

[0020] Continuing to refer to Figure 1, the processing unit 104 may train a classifier with training data that correlates motor and / or electrical data with symptoms of motor impairment. In other embodiments, the training of the classifier and / or other machine learning models may be performed remotely from the processor 104, to which the classifier, trained models such as machine learning models, weights, etc., may be transmitted. The training data may be received through user input, one or more external computing devices, and / or past iterations of processing. The classifier may, but is not limited to, take sensor outputs, such as the output of the sensor suite 112, as input and classify the outputs into one or more groups such as tremor, rigidity, gait freeze, etc.

[0021] The processing unit 104 may calculate a stimulation output 128 based on sensor outputs generated by one or more sensors of the wearable device 100. As used in this disclosure, “stimulation output” is a signal having frequency. The stimulation output 128 may be generated as vibration, electrical, audio, and / or other outputs. The stimulation output 128 may include one or more waveform outputs. A waveform output may include one or more parameters such as frequency, phase, amplitude, and channel index. The channel index may include channels of the mechanoreceptor used and / or actuators. For example, the channel index may include one or more channels of a mechanoreceptor, actuators that stimulate the mechanoreceptor, and / or a combination thereof. The processing unit 104 may select one or more parameters of the waveform output based on sensor outputs received from one or more sensors of the sensor suite 112. In other embodiments, the waveform parameters of the stimulation output 128 may be selected by a user. As a non-limiting example, a user may select the stimulation output 128 and / or waveform parameters from a predefined waveform list using buttons or other interactive elements on the wearable device 100. The predefined list of stimulus outputs 128 may include, but is not limited to, one or more waveforms having various frequencies, amplitudes, etc. The predefined list of stimulus outputs 128 may be generated through past iterations of stimulus output 128 generation. In other embodiments, the predefined list of stimulus outputs 128 may be input by one or more users. In some embodiments, the predefined list of stimulus outputs 128 may include, but is not limited to, stimulus outputs 128 for specific symptoms such as gait freeze, tremor, and rigidity. In some embodiments, the user may select specific waveform parameters using an external computing device, including, but not limited to, a smartphone, laptop, tablet, desktop, or smartwatch. The external computing device may communicate with the processing unit 104 through a communication module 108. The generation of stimulus outputs 128 will be further detailed below with reference to Figures 2-3.

[0022] In some embodiments, the processing unit 104 may communicate a stimulus output 128 to one or more stimulators 124 of the wearable device 100. As used in this disclosure, “stimulator” is any device capable of generating a stimulus output. For example, the stimulators 124 may include electrical, mechanical, thermal, acoustic, and / or other types of stimulators 124. The wearable device 100 may include one or more stimulators 124. For example, the wearable device 100 may include two or more stimulators 124. In some embodiments, the wearable device 100 may include two or more stimulators 124 of different types, such as a mechanical stimulator and an electrical stimulator, or an electrical stimulator and an acoustic stimulator. The stimulators 124 of the wearable device 100 may be arranged to provide stimulation to specific parts of the user’s body, such as through a stimulus output 128. For example, the wearable device 100 may include one or more stimulators 124 that can be arranged to stimulate one or more parts of the user’s peripheral nervous system. As used in this disclosure, “peripheral nervous system” refers to the part of the nervous system that is outside the central nervous system (CNS). The peripheral nervous system may include one or more nerves and / or tissues. The peripheral nervous system may include one or more ganglia. “Ganglia” refers to a collection of nerve cell bodies in the peripheral nervous system. Ganglia may include the dorsal root ganglia and / or trigeminal ganglia. Nerves and / or tissues of the peripheral nervous system may be referred to as “peripheral nerves” and “peripheral tissues,” respectively. The processing unit 104 may be configured to target peripheral nerves and / or tissues of the user’s peripheral nervous system. Peripheral nerves and / or tissues may be located in the user’s wrist, arm, neck, and / or other areas. In some embodiments, the stimulation output 128 may be delivered to one or more peripheral nerves and / or tissues of the user. In some embodiments, the stimulation output 128 may be delivered to one or more mechanoreceptors in the user’s body. As used throughout this disclosure, “mechanoreceptor” refers to cells of the human body that respond to mechanical stimuli. Mechanoreceptors may include proprioceptors and / or somatosensory receptors. Proprioceptors may include the muscle spindle heads of muscles innervated by the trigeminal nerve.Proprioceptors may be part of one or more regions of the user's limbs, including but not limited to the wrist, hand, leg, foot, and arm. Somatosensory receptors 160 may include cells having receptor neurons located in the dorsal root ganglia.

[0023] In some embodiments, the stimulator 124 may be positioned along the wristband of the wearable device 100. In one embodiment, the wearable device 100 may include more than one stimulator 124 positioned within the wristband of the wearable device 100, spaced equally apart from each other. In other embodiments, the stimulator 124 may be positioned on the surface of the housing of the wearable device 100. The stimulator 124 includes, but is not limited to, piezoelectric motors, electromagnetic motors, linear resonant actuators (LRAs), and eccentric rotating mass motors (ERMs). In one embodiment, the stimulator 124 may be configured to vibrate at a frequency of 200 kHz or higher. The stimulator 124 may draw energy from one or more batteries of the wearable device 100. For example, the stimulator 124 may draw about 5 W of power from the battery of the wearable device 100. In some embodiments, the stimulator 124 may have a maximum current draw of approximately 90 mA, a current draw of approximately 68 mA, and a current draw of 34 mA at a 50% duty cycle, and the voltage may be approximately 0 V to approximately 5 V, but is not limited to these. In some embodiments, the acceleration of extrasensory vibration may be 50 mGrms or more. In some embodiments, the acceleration of extrasensory vibration generated by one or more stimulators 124 may be between 180 mGrms and 1.8 Grms. In some embodiments, the acceleration of subthreshold vibration generated by one or more stimulators 124 may be between 0 and 50 mGrms.

[0024] Continuing to refer to Figure 1, the processing unit 104 may be configured to instruct the stimulator 124 to apply a stimulation output 128 to one or more mechanoreceptors in the user's body. The stimulation output 128 may include a waveform output calculated by the processing unit 104 and may be applied to the user's body through the stimulator 124. The stimulation output 128 may be applied to mechanoreceptors or other peripheral nerves and / or tissues, thereby causing the mechanoreceptors to generate one or more afferent signals. As used in this disclosure, “afferent signal” is a neuronal signal in the form of an action potential transmitted toward a target neuron. Afferent signals may be transmitted to the peripheral nervous system (PNS) of the user's body. The user's brain may transmit efferent signals to the PNS 172 through the spinal cord. As used in this disclosure, “efferent signal” is a signal that transmits motor information for a muscle to perform an action. Efferent signals may include one or more electrical signals that can cause one or more muscles to contract or perform other actions. For example, the PNS can receive afferent signals and transmit them to the brain via the spinal cord. The brain can generate one or more efferent signals and transmit them to the PNS via the spinal cord. The PNS can then transmit these efferent signals to the muscles.

[0025] Continuing to refer to Figure 1, the processing unit 104 may operate in a closed-loop system. For example, the processing unit 104 may operate in a feedback loop between data generated from one or more muscles of the user and a stimulus output 128 generated by the stimulator 124. Furthermore, the closed-loop system may be extended through and to the user's body's PNS, central nervous system (CNS), brain, etc., based on afferent and efferent signals. In some embodiments, the processing unit 104 may be configured to operate in one or more modes. For example, the processing unit 104 may operate in a first mode and a second mode. The first mode may include passively monitoring the user's body movements to detect one or more motor impairment symptoms beyond a threshold. In one embodiment, the threshold may include a root mean square (RMS) acceleration of 100 mG or 500 mGA. The threshold may be set by the user and / or determined by the processing unit 104 based on past data. Past data may include, but are not limited to, data from the user's sensor and / or stimulus output 128 over a period of time, such as minutes, hours, weeks, months, or years. The threshold may include, but is not limited to, one or more acceleration, pressure, current, and / or voltage values. In some embodiments, when the threshold is reached, the processing unit 104 may be configured to operate in a second mode, in which the processing unit 104 commands the stimulator 124 to provide a stimulus output 128 to one or more peripheral nerves and / or tissues of the user.

[0026] In some embodiments, the processing unit 104 may utilize a stimulus selection algorithm. The stimulus selection algorithm may take the current stimulus parameters of the stimulus output 128 and / or extracted features of sensor data as input and generate new stimulus parameters through a model-free policy optimization algorithm. Model-free policy optimization includes, but is not limited to, Argmin, Q-learning, neural networks, genetic algorithms, differential dynamic programming, iterative quadratic regulators, and / or guided policy search. The processing unit 104 may continuously update the stimulus parameters of the stimulus output 128 using the stimulus selection algorithm. For example, the new stimulus parameters may become the current stimulus parameters in the next cycle, and the processing unit 104 may iterate through the stimulus selection algorithm.

[0027] In some embodiments, the processing unit 104 may operate in a third mode. The third mode may include a diagnostic mode. The diagnostic mode may be a mode in which the processing unit 104 is configured to detect the user's responsiveness to a stimulation therapy (such as a stimulation output 128). For example, the user's responsiveness may be determined through sensor data generated by the sensor suite 112. The sensor data may be generated from the user's physical response to the stimulation output 128. For example, the severity of one or more of the user's motor impairment symptoms may be reduced as a response to the stimulation output 128. In some embodiments, the processing unit 104 may be configured to calculate the severity level of one or more of the patient's motor impairment symptoms. As used in this disclosure, “severity level” refers to a classification of the intensity of one or more motor impairment symptoms. For example, but not limited to, severity levels may include mild, moderate, severe, or critical. The severity level may be determined by the amplitude, frequency, and / or other parameters of one or more motor impairment symptoms. For example, but not limited to, one or more motor impairment symptoms may include tremor, and tremor may have amplitude. Normal to moderate severity levels may include tremor amplitudes of less than approximately 1 cm. Mild to severe severity levels may include tremor amplitudes of approximately 1 cm or more. Severe severity levels may include tremor amplitudes of approximately 2 cm or more. Severity levels may be determined according to baseline tremor scores, which are further detailed below with reference to Figures 6-9. Severity levels may include, but not limited to, any type of motor impairment symptom described throughout this disclosure. Severity may be reduced by approximately 10%, 20%, 30%, 40%, 50%, 60%, 70%, 80%, or more. In some embodiments, the reduction in severity may be correlated by the treatment unit 104 to determine the level of the user's responsiveness to stimulation therapy. Responsiveness levels may include, but are not limited to, low responsiveness, low to average responsiveness, average responsiveness, average to high responsiveness, or high responsiveness.For example, but not limited to, a reduction of approximately 10% to 30% in the severity of one or more motor impairment symptoms may be classified as low responsiveness, a reduction of approximately 30% to 60% in the severity of one or more motor impairment symptoms may be classified as average responsiveness, and a reduction of approximately 60% or more in the severity of one or more motor impairment symptoms may be classified as high responsiveness. In some embodiments, average responsiveness may include a reduction of less than approximately 30% to approximately 60% in the severity of one or more motor impairment symptoms, such as approximately 10% to 20%, approximately 10% to 30%, approximately 10% to 40%, or any range within these limits. Low responsiveness may include a reduction of approximately 5% to 10%, approximately 5% to 15%, approximately 5% to 20%, or any range within these limits. In some embodiments, high responsiveness may include a reduction of more than approximately 70% in the severity of one or more motor impairment symptoms. In some embodiments, responsiveness may correlate with the onset stage of one or more motor impairment symptoms. For example, users in the early onset stage of one or more motor impairment symptoms may be higher responders than users in the late onset stage. In some embodiments, responsiveness may correlate with patient data and / or demographic data. Patient data, including demographic data, may include, but are not limited to, age, sex, weight, height, muscle mass, skeletal muscle mass, body fat percentage, age of initial onset of one or more motor impairment symptoms, and / or other data. In some embodiments, younger patients may be more responsive to stimuli than older patients, while older patients may be less responsive to stimuli than younger patients. In some embodiments, responsiveness may correlate with the time elapsed since the onset of one or more motor impairment symptoms. For example, but are not limited to, a shorter time elapsed from the initial onset of one or more motor impairment symptoms to stimulation may correlate with a higher responsiveness to stimuli in the user, while a longer time elapsed from the initial onset of one or more motor impairment symptoms to stimulation may correlate with a lower responsiveness to stimuli in the user. Responsiveness may correlate, at least partially, with the user's current age and / or the user's initial age at the onset of one or more motor impairment symptoms. Differences in responsiveness may be as shown below, with reference to Figures 4-7.

[0028] Continuing to refer to Figure 1, in some embodiments, the processing unit 104 may be configured to determine the user's disease state. As used in this disclosure, “disease state” refers to the overall progression and / or severity of one or more motor impairment symptoms of an individual. For example, but not limited to, a disease state may include the onset stage of one or more motor impairment symptoms, the severity level of one or more motor impairment symptoms, and / or the stage of one or more motor impairment symptoms. In some embodiments, the processing unit 104 may be configured to determine the user's disease state based on locally generated sensor data and / or sensor data received via one or more external computing devices. In some embodiments, the processing unit 104 may be configured to determine the user's disease state based on the user’s motor and / or electrical activity or other data that can be measured by the sensor suite 112. For example, the processing unit 104 may determine a disease state that includes an early stage, an intermediate stage, or a late stage of one or more motor impairment symptoms, or any range between these stages. In some embodiments, the processing unit 104 may determine the disease state locally. In other embodiments, the processing unit 104 may communicate sensor data to an external computing device, including but not limited to a laptop, server, desktop, smartphone, or other device. The external computing device may calculate the user's disease state and communicate the calculated stage to the processing unit 104 via a communication module 108 or the like. The processing unit 104 may adjust one or more parameters of the stimulation output 128 based on the user's calculated disease state. For example, for users with a disease state that includes a late-onset stage of one or more motor impairment symptoms, a higher amplitude and / or frequency of the waveform of the stimulation output 128 may be used because they are less responsive to the stimulation output 128. For users with a disease state that includes an early-onset stage of one or more motor impairment symptoms, a lower amplitude and / or frequency of the waveform of the stimulation output 128 may be used because they are more responsive to the stimulation output 128.In some embodiments, a machine learning model may be used to compute the adjusted parameters of the stimulus output 128. For example, the machine learning model may be trained with training data that correlates one or more parameters of the disease state with one or more parameters of the stimulus output 128. The training data may be received through user input, an external computing device, and / or past iterations of processing. In some embodiments, a classifier may be used to classify sensor data generated by the sensor suite 112 into different stages of the disease state. The classifier may be trained with training data that correlates sensor data, such as motor and electrical activity, with the disease state. The training data may be received through user input, an external computing device, and / or past iterations of processing. The processing unit 104 may operate one or more machine learning models and / or classifiers locally. In other embodiments, the processing unit 104 may communicate with one or more external computing devices via a communication module 108. The external computing device 108 may operate one or more machine learning models and / or classifiers. In some embodiments, parameters of one or more machine learning models or classifiers may be sent from one or more external computing devices to the processing unit 104 via the communication module 108. The processing unit 104 may utilize one or more parameters of the machine learning model and / or classifier to run a local version of the machine learning model and / or classifier.

[0029] Referring to Figure 2, a block diagram of the waveform parameter selection system 220 is presented. The system 220 may be local to the wearable device 100 and processed by, for example, a processor 104. In other embodiments, the system 220 may run through an external computing device, including but not limited to a smartphone, tablet, desktop, laptop, server, or cloud computing device. The processing unit 104 may be configured to process raw sensor inputs 604 received from the sensor suite 112 based on the activity of one or more of the user's muscles 200. The raw sensor inputs 204 may include unprocessed and / or unfiltered sensor data collected and / or generated by the sensor suite 112. In some embodiments, the processing unit 104 may pass the raw sensor inputs 204 through one or more filters. Filters may include, but are not limited to, noise filters. Filters may include nonlinear, linear, time-varying, time-invariant, causal, non-causal, discrete-time, continuous-time, passive, active, infinite impulse response (IIR), finite impulse response (FIR), and the like. The processing unit 104 may remove noise from the sensor output using a noise filter 208, for example. Noise may include unwanted modifications to the signal (such as irrelevant sensor outputs from one or more sensors in the sensor suite 112). The noise filter 208 may either subtract from the sensed waveform using knowledge of the output waveform, or limit the sensed state to the "off" phase of the pulsed stimulus using knowledge of the timing of the output waveform. In some embodiments, the processing unit 104 may use filters, such as a motion impairment filter 212, to remove all information irrelevant to motion impairment. Information irrelevant to motion impairment may include certain frequencies and / or frequency ranges that may be outside the range of the motion impairment indicator. As a non-limiting example, tremors may have frequencies from approximately 3 Hz to approximately 15 Hz, and frequencies outside this range are irrelevant to the tremor and can be removed through one or more filters.As another non-limiting example, classical resting tremor, isolated postural tremor, and motion tremor during slow movement may be approximately 3 Hz to 7 Hz, 4 Hz to 9 Hz, and 7 Hz to 12 Hz, respectively. The processing unit 104 may be configured to filter frequencies outside any of the above ranges. In some embodiments, the processing unit 104 may be configured to extract the fundamental tremor frequency through spectral analysis. The fundamental tremor frequency may be used in one or more filters as a digital bandpass filter with cutoff frequencies around and below the fundamental frequency. The processing unit 104 may be configured to implement and / or generate one or more filters based on a patient's specific fundamental tremor frequency. The motion impairment filter 212 can be any type of filter. In some embodiments, the motion impairment filter 212 may include a 0-15 Hz bandpass filter configured to remove all other signal components not caused by motion impairment. In other embodiments, the motion impairment filter 212 may include, but is not limited to, a bandpass filter with an upper limit greater than 15 Hz. The processing unit 104 may determine the user's excess motion by using a motion impairment filter 212 to remove noise irrelevant to the user's excess motion. In one embodiment, the processing unit 104 may utilize three or more filters. The processing unit 104 may first use a noise filter 208 to remove noise from the raw sensor input 204, and then use a second filter, such as a motion impairment filter 212, to remove all information irrelevant to motion impairment. In some embodiments, filtered sensor data 216 may be generated after processing the sensor output through one or more filters. In some embodiments, one or more features may be extracted from the filtered sensor data 216. Extraction may include obtaining temporal, spectral, or other features of the filtered sensor data 216. Temporal features may include, but are not limited to, minimum values, maximum values, the first three standard deviations, signal energy, root mean square (RMS) amplitude, zero crossover ratio, principal component analysis (PCA), kernel or wavelet convolution, or self-convolution.Spectral features may include, but are not limited to, the Fourier transform, fundamental frequency, (Mel-frequency) cepstrum coefficients, spectral centroid, and bandwidth. The processing unit 104 may input the extracted features of the filtered sensor data 216 and / or filtered sensor data 616 to the waveform parameter algorithm 220.

[0030] The waveform parameter selection algorithm 220 may be a parameter selection algorithm. The parameter selection algorithm may include an algorithm for determining one or more parameters of an output. The waveform parameter selection algorithm 220 may include, but is not limited to, classification algorithms such as logistic regression, naive Bayes, decision trees, support vector machines, neural networks, random forests, and / or other algorithms. In some embodiments, the waveform parameter selection algorithm 220 may be an argmax(FFT) algorithm. The waveform parameter selection algorithm 220 may include the calculation of the mean, median, interquartile range, X-percentile signal frequency, root mean square (RMS) amplitude, power, log(power), and / or a linear or nonlinear combination thereof. For example, but is not limited to, the waveform parameter selection algorithm 220 may modify the frequency, amplitude, inter-peak values, etc., of one or more waveforms. The waveform parameter algorithm 220 may modify one or more parameters of a waveform output (such as a stimulus output 128) applied to the peripheral nervous system 232. In some embodiments, the waveform parameter algorithm 220 may be configured and / or programmed to determine a waveform parameter set based on the current waveform parameter set and / or filtered sensor data 216. In a non-limiting example, the filtered sensor data 216 may include tremor amplitude. The waveform parameter algorithm 220 may determine which waveform parameter set yields the lowest tremor amplitude by comparing the tremor amplitude observed with the current waveform parameter set with the tremor amplitude observed with previous waveform parameter sets. The set yielding the lowest tremor amplitude may be used as a baseline for the waveform parameter selection 220 for the next iteration, which may then compare this baseline with a new waveform parameter set. The waveform parameter selection 220 may utilize one or more of the following: a Q-learning model, one or more neural networks, a genetic algorithm, differential dynamic programming, an iterative quadratic regulator, and / or a guided policy search.The waveform parameter selection 220 may determine one or more new waveform parameters from the currently applied waveform parameter set in order to minimize the user's symptom severity based on an optimization model. The optimization model may include, but is not limited to, discrete optimization or continuous optimization. For example, the waveform parameter selection 220 may utilize an optimization model configured to take the current waveform parameters of filtered sensor data 216 and / or vibration stimulation 13 as input and output a selection of new waveform parameters that can minimize the user's symptom severity. Symptom severity may include, but is not limited to, gait freeze, rigidity, and tremor.

[0031] In some embodiments, the stimulation output 128 may, but is not limited to, target afferent nerves selected from a set consisting of somatosensory cutaneous afferent nerves of the C5-T1 dermatomes and proprioceptive afferent nerves of the muscles and tendons of the wrist, fingers, and thumb. In one embodiment, the stimulation output 128 may be applied around the user's wrist, thereby enabling stimulation of five different somatosensory channels via the C5-T1 dermatomes and an additional fifteen proprioceptive channels via tendons passing through the wrist, for a total of twenty different channels. The waveform parameter selector 220 may be configured to generate one or more waveform parameters specific to one or more proprioceptive and / or somatosensory channels. For example, but is not limited to, the waveform parameter selector 220 may select a single proprioceptive channel for which to apply the stimulation output 128, via the C5 dermatome. As another example, but is not limited to, the waveform parameter selector 220 may select a combination of C5 dermatome and T1 dermatome channels. In some embodiments, the waveform parameter selector 620 may be configured to generate a multichannel waveform by generating one or more waveform parameters for one or more proprioceptive and / or somatosensory channels. The channels of the multichannel waveform may be specific to one or more proprioceptive and / or somatosensory channels. In some embodiments, each transducer of a plurality of transducers may generate a waveform output for a specific proprioceptive and / or somatosensory channel, and each channel may be different from, identical, or a combination thereof. The waveform parameter selector 220 may select any combination of proprioceptive and / or somatosensory channels, but is not limited to that. The waveform parameter selector 220 may select one or more proprioceptive channels to target based on one or more symptoms of motor impairment. For example, but is not limited to, the waveform parameter selector 220 may select both the T1 channel and the C5 channel as targets for stimulation based on a symptom of muscle rigidity. In some embodiments, the waveform parameter selector 220 may include a stimulus machine learning model. The stimulus machine learning model may include any machine learning model described throughout this disclosure, but is not limited to that.In some embodiments, a stimulus machine learning model may be trained with training data that correlates sensor data and / or waveform parameters to optimal waveform parameters. Training data may be received through user input, an external computing device, and / or past iterations of processing. The stimulus machine learning model may be configured to take filtered sensor data 216 and / or a current set of waveform parameters as input and to output a new set of waveform parameters. The stimulus machine learning model may, but is not limited to, outputting specific targets of vibration stimuli (such as one or more proprioceptive and / or somatosensory channels), as described above. As a non-limiting example, the stimulus machine learning model may take filtered sensor data 216 as input and output a set of waveform parameters specific to the C6 and C8 proprioceptive channels. The stimulus output 128 may be applied to one or more mechanoreceptors. In some embodiments, if this process is performed outside the wearable device 100, the computing device may communicate one or more waveform parameters to the wearable device 100.

[0032] The waveform parameter selector 220 may generate a series of waveform outputs. The series of waveform outputs may include two or more waveform outputs applied sequentially to the user. The time between two or more waveform outputs in the series may be, but is not limited to, milliseconds, seconds, minutes, etc. Each waveform output in the series may have various parameters, including, but not limited to, amplitude, frequency, and peak-to-peak value. In some embodiments, the series of waveform outputs may include multiple waveform outputs, each having a higher frequency than the previous waveform output. In some embodiments, each waveform output may have a lower or the same frequency as the previous waveform output. The waveform parameter selector 220 may provide a series of waveform outputs until the waveform outputs reach a frequency that results in a suppressed output of the user's excess motion.

[0033] Continuing to refer to Figure 2, the wearable device 100 may be configured to operate in one or more settings. The settings of the wearable device 100 may include one or more operating modes. The user may be configured to select one or more settings of the wearable device 100 (but not limited to) through interactive elements such as buttons and touchscreens, and / or via a remote computing device through applications, etc. Interactive elements and applications are described in further detail below with reference to Figure 3.

[0034] The settings for the wearable device 100 may include automatic settings, tremor reduction settings, gait freeze settings, rigidity settings, and / or adaptive mode settings. The automatic settings for the wearable device 100 may include the processing unit 104 automatically selecting the optimal waveform output based on data generated from one or more sensors of the sensor suite 112. For example, waveform parameter selection 220 may select one or more waveform parameters that are generally optimal for the current sensor data, such as filtered sensor data 216. The automatic modes of the wearable device 100 may determine one or more mean values, standard deviations, etc., of the stimulus output 128 based on multiple data generated from multiple users of the wearable device 100. In some embodiments, the generation of the automatic modes of the wearable device 100 may include crowdsourcing from one or more users. A cloud computing system may be implemented to collect data from one or more users.

[0035] Continuing to refer to Figure 2, the wearable device 100 may be configured to operate in a tremor reduction setting. The tremor reduction setting may include the waveform parameter selection 220 assigning higher weights or values ​​to filtered sensor data 216 corresponding to tremor and reducing the weights or values ​​of other symptoms. The waveform parameter selection 220 may be configured to generate one or more waveform parameters that optimize the user's tremor reduction. Optimizing the user's tremor reduction may include minimizing the weights, values, and / or waveform parameters of other symptoms such as gait freezing and rigidity. Similarly, a gait freezing setting may optimize the user's gait freezing reduction, and a rigidity setting may optimize the user's rigidity reduction. Each setting may be iteratively updated based on data received from crowdsourcing, the user's historical data, etc. For example, each setting may be continuously updated to optimize symptom reduction for the most users from a group of multiple users. In some embodiments, the settings of the wearable device 100 may include an adaptive mode. The adaptive mode may include the waveform parameter selection 220 continuously searching for the highest weight and / or most severe symptom in the sensor data 616 and generating one or more waveform parameters to mitigate that symptom and / or weight. In some embodiments, the adaptive mode of the wearable device 100 may utilize a machine learning model. The adaptive mode machine learning model may be trained with training data that correlates the sensor data and / or the weights of the sensor data to one or more waveform parameters. The training data may be received through user input, an external computing device, and / or past iterations of processing. The adaptive mode machine learning model may be configured to take filtered sensor data 216 and one or more optimal waveform parameters 220 to mitigate the most severe symptom as input. In some embodiments, the adaptive mode machine learning model may be trained remotely, and the weights of the trained model may be communicated to the wearable device 100, thereby reducing the processing load on the wearable device 100.

[0036] Referring to Figure 3, a block diagram of the waveform parameter selection process 300 via a mobile device is presented. Process 300 may, but is not limited to, be executed by a processor such as the processing unit 104 described above with reference to Figure 1. Process 300 may include waveform parameter selection 304. Waveform parameter selection 304 may be identical to waveform parameter selection 220 described above with reference to Figure 6. In some embodiments, application 308 may be configured to run on a computing device. Application 308 may, but is not limited to, a laptop, desktop, tablet, smartphone, etc. In some embodiments, application 308 may take the form of a web application. Application 308 may be configured to display data to the user through a graphical user interface (GUI). The GUI may include one or more text, pictures, or other icons. The GUI generated by application 308 may include one or more windows that can display data (images, text, etc.). The GUI generated by application 308 may be configured to display sensor data, stimulus data, etc. In some embodiments, the GUI generated by application 308 may be configured to receive user input 312. User input 312 includes, but is not limited to, keystrokes, mouse input, and touch input. For example, a user may trigger an event handler of application 308 by clicking on a GUI icon generated by application 708, which may perform one or more actions, including, but is not limited to, displaying data through a window or communicating data to another device. In some embodiments, user input 312 received through application 708 may generate smartphone application data 316. Smartphone application data 316 may include one or more selections of one or more waveform parameters.In some embodiments, smartphone application data 316 may include, but are not limited to, patient data such as age, onset of one or more motor disorders, comorbidities, activity level, body fat percentage, and / or other patient data. Patient data may be received by user input through application 308. In some embodiments, patient data may be received through one or more external computing devices and communicated to a processor running process 300 via Wi-Fi, Bluetooth, cellular, or other signals. Waveform parameters may include, but are not limited to, amplitude frequency. In some embodiments, one or more waveform parameters may be generated based on patient data such as, but are not limited to, age, onset of one or more motor disorders, comorbidities, patient activity level, body fat percentage, and / or other patient data. Process 300 may automatically input patient data and select one or more optimal waveform parameters based on the patient data. Waveform parameters may be as described above with reference to Figures 1-2. As a non-limiting example, smartphone application data 316 may include the selection of higher frequencies of waveform outputs generated by user input through application 308.

[0037] Furthermore, and / or alternatively, the user may generate user input 312 through one or more interactive elements of the wearable device. The wearable device may, but is not limited to, those described above with reference to Figure 1. The wearable device may include one or more interactive elements, including, but not limited to, knobs, switches, buttons, sliders, etc. Each interactive element of the wearable device may correspond to a function. For example, one button on the wearable device may correspond to an increase in the frequency of a waveform output, and another button may correspond to a decrease in the frequency of a waveform output. The user may generate device button data 320 through user input 312 of the wearable device. In some embodiments, the wearable device may include a touchscreen or other interactive display through which the user may generate device button data 320. In one embodiment, the wearable device may be configured to run an application 308 locally and receive smartphone application data 316 through a touchscreen or other input device which may be part of the wearable device. The waveform parameter selection 304 may be run locally on the wearable device and / or offloaded to one or more computing devices. In some embodiments, the waveform parameter selection 304 may be configured to receive smartphone application data 316 and / or device button data 320. Based on the smartphone application data 316 and / or device button data 320, the waveform parameter selection 304 may be configured to generate a waveform output, such as a stimulation output 128. The user may adjust the stimulation output 128 by generating the smartphone application data 316 and / or device button data 320. The stimulation output 128 may be communicated to one or more sites of the user's peripheral nervous system 328 through one or more stimulators, etc., as described above with reference to Figure 1.

[0038] Referring to Figure 4, a feature extraction process 400 is presented. Process 400 may include an input of a filtered signal 424. The filtered signal 424 can be any filtered signal, such as those described above with reference to Figure 3. Process 400 may extract temporal features, or one or more sets of temporal features. For example, a first set of temporal features 404 may include, but are not limited to, minimum, maximum, first three standard deviations, signal energy, root mean square (RMS), and zero crossing rate. A second set of temporal features 408 may include, but are not limited to, principal component analysis (PCA) and kernels. A third set of temporal features 412 may include, but are not limited to, wavelet convolution or self-convolution. In some embodiments, each temporal feature may be extracted as a single set. Process 400 may extract spectral features 416. Examples of spectral features include the Fourier transform, fundamental frequency, (Mel frequency) cepstrum coefficients, spectral centroid, and bandwidth. Features can be extracted on a wearable device 100 using standard digital signal processing techniques. The collected set of features can then be input into a stimulus selection algorithm 420.

[0039] Referring to Figure 5, a method 500 for targeted peripheral stimulation is presented. In step 505, the method 500 includes attaching a wearable device to the user. The wearable device includes, but is not limited to, a wristband or strap and may include an attachment mechanism. The wearable device may include one or more sensors, stimulators, etc., as described above with reference to Figure 1.

[0040] In step 510, method 500 includes detecting one or more motor impairment symptoms. Detection of one or more motor impairment symptoms may be performed through sensors of a wearable device. For example, the sensors may include, but are not limited to, an EKG, an accelerometer, or other sensors. In one embodiment, one or more motor impairment symptoms may be detected based on a change in the value of an accelerometer. One or more motor impairment symptoms may include, but are not limited to, rigidity, stiffness, freezing, paralysis, paresis, dyskinesia, tremor, or a combination thereof. Detection of one or more motor impairment symptoms may include detecting the amplitude of a tremor. This step may be carried out as described above with reference to Figures 1-4, without being limited thereto.

[0041] In step 515, method 500 includes calculating a disease status for one or more motor impairment symptoms. The disease status may include, but is not limited to, a severity level, an onset stage, and / or a stage for one or more motor impairment symptoms. In some embodiments, the calculation of a disease status for one or more motor impairment symptoms may include the calculation of each of the severity level, onset stage, and / or a stage for one or more motor impairment symptoms. In some embodiments, the calculation of a disease status for one or more motor impairment symptoms may be performed locally on the processor of the wearable device. In some embodiments, sensor data may be communicated to an external computing device via the communication module of the wearable device. The external computing device may calculate the disease status for one or more motor impairment symptoms and communicate the calculated disease status to the wearable device via the communication module of the wearable device. In some embodiments, the calculation of a disease status for one or more motor impairment symptoms may include the calculation of a user's baseline UPDRS score based on the detection of one or more motor impairment symptoms. In some embodiments, the calculation of a disease status for one or more motor impairment symptoms may include performing a static sitting test and / or an arm extension test. For example, the user's baseline severity may be calculated. Baseline severity may include the amplitude of tremor displacement in the user's body parts. Normal to slight baseline tremor may include tremor amplitudes of less than approximately 1 cm. Mild to severe baseline tremor may include tremor amplitudes of approximately 1 cm or more.

[0042] In some embodiments, calculating the disease status of one or more motor impairment symptoms may involve the use of a machine learning model. For example, a machine learning model may be trained with training data that correlates one or more motor impairment symptoms with their disease status. The training data may be received through user input, an external computing device, and / or past iterations of the process. In some embodiments, parameters of a machine learning model trained to determine the disease status of one or more motor impairment symptoms may be communicated to the wearable device's processor via the wearable device's communication module. The wearable device's processor may execute one or more machine learning processes using one or more machine learning parameters. In some embodiments, data may be communicated to an external computing device via the wearable device's communication module. The external computing device may train and / or deploy one or more machine learning models to determine or predict the disease status of one or more motor impairment symptoms. The determination or prediction may be transmitted from the external computing device to the wearable device's processor via the wearable device's communication module.

[0043] In step 520, method 500 includes stimulating the user's peripheral nervous system through a stimulator of a wearable device. The stimulator may be of the vibratory, electrical, ultrasonic, or other stimulator type. In some embodiments, the stimulator of the wearable device may be positioned to contact the surface of a part of the user's body including peripheral nerves and / or tissues. For example, but not limited to, one or more stimulators of the wearable device may be positioned and / or embedded in a wristband of the wearable device so as to contact one or more areas of the user's wrist including peripheral nerves and / or tissues when worn by the user. In some embodiments, stimulation of the user's peripheral nervous system may include providing a stimulatory output to one or more parts of the user's body including the peripheral nervous system. The stimulatory output may be as described above with reference to Figure 1. This step may be carried out as described above with reference to Figures 1-4, but not limited to this.

[0044] In step 525, method 500 includes detecting the user's responsiveness. Responsiveness may be detected via one or more sensors of the wearable device. Responsiveness may be calculated locally on the processor of the wearable device. In some embodiments, sensor data may be communicated to an external computing device via a communication module of the wearable device. The external computing device may calculate responsiveness based on the sensor data received by the wearable device. Responsiveness may be calculated by changes in the UPDRS score, the root mean square of the tremor amplitude, a static sitting test, and / or an arm extension test. Responsiveness may be categorized into various categories. For example, a decrease of one or more points in the UPDRS score may be classified as high responsiveness. In some embodiments, the user's responsiveness may be calculated by comparing the reduction of one or more motor impairment symptoms to the average reduction of one or more motor impairment symptoms across a cohort of similar individuals. For example, mean responsiveness may be calculated for specific age groups, including but not limited to individuals approximately 18–25 years old, 26–35 years old, 36–50 years old, and 50 years and older. Mean responsiveness may be generated for individuals with specific body types, such as body fat percentage, muscle mass, skeletal muscle mass, height, weight, and / or other characteristics. For example, individuals with more muscle mass may show greater reduction in one or more motor impairment symptoms than individuals with less muscle mass. In some embodiments, correlations of various responsiveness and / or demographic data across multiple patients may be used to calculate one or more stimulus and / or waveform parameters of the stimulus output. Demographic data may include the aforementioned patient data. For example, but not limited to, age, muscle mass, age of onset of one or more motor impairment symptoms, skeletal muscle mass, height, weight, and / or other characteristics may correlate with various responsiveness levels, including but not limited to low responsiveness, mean responsiveness, high responsiveness, and / or other responsiveness levels. Responsiveness and / or correlation between responsiveness and demographic data may be calculated locally and / or received via an external computing device. This step may be carried out as described above with reference to Figures 1-4, but is not limited thereto.

[0045] In step 530, method 500 includes stimulating the user's peripheral nervous system based on detected responsiveness and the disease status of one or more motor impairment symptoms. For example, the stimulation output as described above with reference to Figure 1 may be adjusted and / or modulated to take into account the responsiveness and / or disease status of one or more motor impairment symptoms. As a non-limiting example, a user classified as having a mild severity level and / or an early onset stage of one or more motor impairment symptoms may experience reduced severity of one or more motor impairment symptoms with a stimulation output of lower amplitude and / or frequency than a user classified as having a severe severity level and / or a late onset stage. In some embodiments, a machine learning model may be implemented to adjust one or more parameters of the stimulation output based on the user's responsiveness and / or disease status of one or more motor impairment symptoms. The machine learning model may be trained with training data that correlates the responsiveness and / or disease status of one or more motor impairment symptoms with one or more stimulation parameters. The training data may be received through user input, an external computing device, and / or past iterations of the process. A machine learning model can be trained to take sensor data, the responsiveness of one or more motor impairment symptoms, and / or disease states as input, and to output a stimulus output and / or its parameters. The machine learning model can be trained outside the wearable device, such as an external computing device that can communicate with the wearable device via the wearable device's communication module. The wearable device can receive one or more outputs of the machine learning model from the external computing device, such as the wearable device's communication module, and adjust one or more stimulus parameters of the stimulus output. In some embodiments, the wearable device can communicate recommended stimulus parameters to the user via a mobile application on a smartphone. Recommendations may include increasing or decreasing the frequency, pulse width, amplitude, duration, and / or other parameters of the stimulus output.

[0046] In some embodiments, Method 500 includes calculating a correlation between responsiveness and a disease state of one or more motor impairment symptoms. The calculation of the correlation may be performed locally, such as in the processor of the wearable device. In some embodiments, the wearable device may communicate sensor data to an external computing device via the wearable device's communication module. The external computing device may calculate the correlation between responsiveness and one or more disease states of one or more motor impairment symptoms. In some embodiments, a correlation between the user's physiological characteristics and / or responsiveness may be calculated. For example, but not limited to, users with higher muscle mass may show increased reduction in one or more motor impairment symptoms, while users with lower muscle mass may show less increased reduction in one or more motor impairment symptoms compared to users with higher muscle mass. The correlation may be calculated using any user data, including but not limited to height, weight, age, muscle mass, body fat percentage, skeletal muscle mass, exercise habits, bone density, and / or other user data. A machine learning model may be trained to take user data as input and output stimulus outputs and / or their parameters based on training data that correlates various user data with stimulus outputs and / or their parameters. Training data can be received through user input, external computing devices, and / or past iterations of processing.

[0047] Referring to Figure 6, a graph showing the baseline UPDRS scores of the subjects is illustrated. In Figures 6-9, the study was conducted on 17 patients with tremor-dominant Parkinson's disease. The baseline demographics of the 17 patients were 59% male and 41% female, with an age range of 43-79 years (mean 66.9 years), an age of onset of motor symptoms of 29-76 years (mean age of onset 59.6 years), and a mean baseline UPDRS tremor subscore of approximately 5.4 (range 4-8).

[0048] Graphs 600A and 600B further show the percentage improvement in root mean square (RMS) tremor displacement in both the static sitting test and the arm extension test. The results are shown on the baseline Unified Parkinson's Disease Rating Scale (UPDRS). The UPDRS consists of four parts: Part I assesses mental, behavioral, and mood; Part II assesses activities of daily living; Part III assesses motor function; and Part IV assesses motor and non-motor complications related to treatment. Each part consists of various sub-items, all scored on a scale of 0 to 4, where 0 indicates no impairment and 4 indicates severe impairment. The arm extension test for postural tremor and the static sitting test for resting tremor are part of the motor tests in Part III. Specifically, they are included in the assessment of rigidity and postural stability.

[0049] The Tremor Research Group's Essential Tremor Assessment Scale (TETRAS) is divided into four performance sections. Section A assesses resting tremor, Section B assesses motor tremor, Section C assesses postural tremor, and Section D assesses voice. Each of these sections includes various sub-items scored on a scale of 0 to 4, similar to the UPDRS. In addition, the TETRAS includes a performance test (Section E) that examines writing and drawing abilities. The arm extension test is used in Section C to assess postural tremor, and the static sitting test is used in Section A to assess resting tremor. By referring to these sub-tests, clinicians can derive a comprehensive view of the patient's tremor severity, effectively monitor changes, and adjust treatment plans as needed. Arm Extension Test for Postural Tremor - The arm extension test is an important component of Section III of the UPDRS and Section C of the TETRAS. This test specifically assesses postural tremor that appears when maintaining posture against gravity. During the test, the patient holds their arms extended forward at shoulder height for a set period of time. The clinician then observes the frequency and amplitude of the tremor. This non-invasive and simple test allows for the identification and evaluation of conditions such as essential tremor and Parkinson's disease, and can provide an indicator of their severity and progression.

[0050] As part of UPDRS Part III and TETRAS Part A, the resting seated test is used to measure resting tremor. This type of tremor occurs when muscles are relaxed and supporting against gravity. In the test, the patient is instructed to sit quietly with their hands on their knees. The presence, frequency, and amplitude of tremor are then observed and evaluated. This easily administered test is essential in the diagnosis and monitoring of Parkinson's disease, as resting tremor is a characteristic symptom of the disease. By observing changes over time, clinicians can understand the progression of the disease and adjust treatment as needed.

[0051] Both the arm extension test (postural tremor) and the seated test (resting tremor) in the UPDRS are scored using a scale from 0 to 4. The score generally correlates with the specific amplitude range observed during the test. In the UPDRS, a score of 0 indicates no tremor visible to the naked eye (amplitude 0 cm). A score of 1 indicates a slight tremor with an amplitude of less than 1 cm. A score of 2 indicates a mild but visible tremor with an amplitude of 1 cm to 3 cm. A score of 3 indicates a moderate tremor with an amplitude of 3 cm to 10 cm, which usually interferes with daily activities. Finally, a score of 4 is given for a severe tremor with an amplitude of more than 10 cm, which significantly impairs the performance of daily work.

[0052] Similar to the UPDRS, the arm extension test (postural tremor) and the resting seated test (resting tremor) in the TETRAS scale are also scored using a scale from 0 to 4. In TETRAS, a score of 0 indicates no tremor visible to the naked eye (amplitude 0 cm). A score of 1 indicates a tremor that is barely visible to the naked eye. A score of 1.5 indicates a slight tremor with an amplitude of less than 1 cm. A score of 2 indicates a mild but visible tremor with an amplitude of 1 cm to 3 cm. A score of 2.5 is given for tremors of 3 cm to 5 cm. A score of 3 indicates a moderate tremor with an amplitude of 5 cm to 10 cm, which usually interferes with daily activities. A score of 3.5 indicates a tremor of 10 cm to 20 cm. Finally, a score of 4 is given for a severe tremor with an amplitude of more than 20 cm, which significantly impairs the performance of daily work. These scores provide an objective and quantitative measure of tremor severity, enabling monitoring of disease progression and treatment effectiveness.

[0053] Continuing to refer to Figure 6, Graph 600A shows the baseline UPDRS scores for the static seated test. Graph 600B shows the baseline scores for the UPDRS arm extension test. In Graph 600A, patients with a baseline UPDRS score of 0.0 showed approximately 0% improvement in RMS tremor displacement. Patients with a baseline UPDRS score of 1.0 showed approximately 0% to -280% improvement in RMS tremor displacement. Patients with a baseline UPDRS score of 2.0 showed approximately 10% improvement in RMS tremor displacement. Patients with a baseline UPDRS score of approximately 3.0 showed approximately 20% improvement in RMS tremor displacement.

[0054] Referring to Graph 600B, the results of the arm extension test are presented. Patients with a baseline UPDRS score of 0.0 showed approximately 0% improvement in RMS tremor displacement. Patients with a baseline UPDRS score of 1.0 showed approximately 0% improvement in RMS tremor displacement. Patients with a UPDRS score of 2.0 showed approximately 5% to 10% improvement in RMS tremor displacement. Patients with a UPDRS score of 3.0 showed approximately 20% to 30% improvement in RMS tremor displacement.

[0055] Referring to Figure 7, graphs are shown illustrating the median percentage change and absolute change in symptoms for subjects with early-onset Parkinson's disease (EOPD) and late-onset Parkinson's disease (LOPD). In particular, the results for the sitting test and arm extension test for EOPD and LOPD patients are presented. Graph 700A shows the median percentage change (%) of maximum tremor power for both EOPD and LOPD patients. Graph 700B shows the absolute change in UPDRS scores for both the sitting test and arm extension test for EOPD patients. Referring to Graph 700A, the median percentage change in maximum tremor power for EOPD patients was approximately 40% in the sitting test and approximately 50% in the arm extension test. For LOPD patients, the median percentage change in maximum tremor power was approximately 0% in the sitting test and approximately -100% in the arm extension test.

[0056] Referring to Graph 700B, EOPD patients showed an absolute change of approximately 1 in their UPDRS score during the static sitting test and approximately 2 during the arm extension test, while LOPD patients showed no absolute change in their UPDRS score.

[0057] Referring to Figure 8, graphs showing baseline and stimulated results for EOPD and LOPD subjects are presented. In particular, graphs 800A and 800B show the results of the static sitting test and arm extension test for EOPD patients. Graph 800A shows the baseline scores for both the static sitting test and arm extension test for EOPD patients. Graph 800B shows the UPDRS score results comparing EOPD patients who received effective stimulation with those who did not.

[0058] Referring to Graph 800A, EOPD patients have a baseline peak tremor power of approximately 10 m / s² in the static seating test. 2 ) 2 The baseline peak tremor power in the arm extension test was approximately 125 m / s². 2 ) 2There was no distinguishable change in peak tremor power in EOPD patients who received stimulation. Referring to Graph 800B, the baseline UPDRS score of EOPD patients in the static sitting test was about 1 to about 2. The baseline UPDRS score of EOPD patients who received stimulation in the static sitting test was about 0 to about 1. In the arm extension test, the baseline UPDRS score of EOPD patients was about 1 to about 3, while the UPDRS score of EOPD patients who received stimulation was about 0 to about 1.

[0059] Referring to FIG. 9, graphs showing the baseline and stimulation results of LOPD subjects are presented. In particular, Graphs 900A - B present the results of the static sitting test and arm extension test of LOPD patients with and without stimulation. Graph 900A shows the peak tremor power, and Graph 900B shows the UPDRS score. Referring to Graph 900A, the baseline peak tremor power of LOPD patients in the static sitting test was about 0 to about 5 (m / s 2 ) 2 , and the baseline peak tremor power in the arm extension test was about 14 (m / s 2 ) 2 . The peak tremor power of LOPD patients who received stimulation in the static sitting test was about 0 to about 7.5 (m / s 2 ) 2 . In the arm extension test, the baseline UPDRS score of LOPD patients was about 1 to about 2, and no distinguishable difference was observed in LOPD patients who received stimulation.

[0060] Referring to Figure 10, a graph is presented showing the improvement in BF-ADL scores in subjects of various ages. Different stimulation parameters were used depending on the subjects' age. This data was extracted from a clinical trial involving 47 subjects defined as having definitive or stochastic essential tremor according to the Tremor Research Group (TRIG) criteria. 46% of the subjects were male and 54% were female. The mean age at the time of the trial was 65.71 ± 9.61 years. Graph 1000A shows the results for "high" and "low" stimulation levels in the cohort of subjects who were under 65 years old at the time of the trial. Graph 1000B shows the results in the cohort of subjects who were at least 65 years old at the time of the trial. In the younger cohort, the "high" stimulation level showed significantly better results than the "low" level (p=0.039), while the opposite was true in the older cohort (p=0.043). These results suggest the possibility of automatic adjustment of stimulation based on demographic characteristics.

[0061] The Bain & Findley Activities of Daily Living Scale (BF-ADL) is often used to measure patient-reported impairment. The BF-ADL scale is one such metric that includes a questionnaire-based assessment of the subject's impairment in certain common activities, such as eating soup or making a phone call. The scale is used in real time, and the subject is asked to complete a task and judge whether they (1) were able to perform the task without difficulty, (2) were able to perform the task with little effort, (3) were able to perform the task with much effort, or (4) were unable to perform the task on their own. The scale is intended to measure the subject's own assessment of impairment and was developed to assess the severity of tremor in patients with essential tremor and postural limb tremor (including those associated with dystonia).

[0062] Referring to Figure 11, an illustration of the wearable device 1100 is presented. In some embodiments, the wearable device 1100 may include a housing 1104 configured to house one or more components of the wearable device 1100. For example, the housing 1104 of the wearable device 1100 may include a material of a circular, elliptical, rectangular, square, or other shape. In some embodiments, the housing 1104 may have, but is not limited to, a length of approximately 5 inches, a width of approximately 5 inches, and a height of approximately 1.5 inches. The housing 1104 of the wearable device 1100 may have an interior and an exterior. The interior of the housing 1104 of the wearable device 1100 may include, but is not limited to, one or more sensors, stimulators, power supplies, processors, memory, etc., as described above with reference to Figure 1. In some embodiments, the wearable device 1100 may include one or more interactive elements 1116 outside the housing 1104. As used in this disclosure, “interactive element” is a component configured to respond to user input. Interactive elements 1116 include, but are not limited to, buttons, switches, and the like. In some embodiments, the wearable device 1100 may have a single interactive element 1116. In other embodiments, the wearable device 1100 may have two or more interactive elements 1116. In embodiments where the wearable device 1100 has multiple interactive elements 1116, each interactive element 1116 may correspond to a different function. For example, a first interactive element 1116 may correspond to a power function, a second interactive element 1116 may correspond to waveform adjustment, and a third interactive element 1116 may correspond to a mode of the wearable device 1100. In some embodiments, the wearable device 1100 may include a touchscreen display.

[0063] In some embodiments, the wearable device 1100 may include one or more batteries. For example, but not limited to, the wearable device 1100 may include one or more replaceable batteries such as lead-acid batteries, nickel-cadmium batteries, nickel-metal hydride batteries, lithium-ion batteries, and / or other battery types. The housing 1104 of the wearable device 1100 may include a charging port that allows access to the rechargeable battery of the wearable device 1100. For example, but not limited to, the wearable device 1100 may include one or more rechargeable lithium-ion batteries, and the charging port of the housing 1104 of the wearable device 1100 may be a USB-C, micro USB, and / or other type of port. The battery of the wearable device 1100 may be configured to charge at a rate of about 10 W / hour. The battery of the wearable device 1100 may be configured to charge at about 3.7 V with a current draw of about 630 mA. The battery of the wearable device 1100 may have a capacity of approximately 2.5 Wh, greater than 2.5 Wh, or less than 2.5 Wh, but is not limited thereto. In some embodiments, the wearable device 1100 may include one or more wireless charging circuits configured to receive power via electromagnetic waves. The wearable device 1100 may be configured to be wirelessly charged at a rate of approximately 5 W / hr through a charging pad or other wireless power transmission system. In some embodiments, the battery of the wearable device 1100 may be configured to be charged at approximately 460 mA, greater than 460 mA, or less than 460 mA.

[0064] Continuing to refer to Figure 11, the wearable device 1100 may include an attachment system. The attachment system may include any components configured to secure two or more elements. For example, but not limited to, the wearable device 1100 may include a wristband 1108. The wristband 1108 may include one or more layers of material. For example, but not limited to, the wristband 1108 may include multiple layers of a polymer such as rubber. The wristband 1108 may have an inner and an outer side. The inner and outer sides of the wristband 1108 may be made of the same material, texture, etc. In other embodiments, the inner side of the wristband 1108 may be softer and / or smoother than the outer side. As a non-limiting example, the inner side of the wristband 1108 may be made of a smooth rubber material and the outer side may be made of Velcro material. The wristband 1108 may have a thickness of about 2 mm. In other embodiments, the wristband 1108 may have a thickness greater than or less than about 2 mm. The wristband 1108 may be a rubber band, a Velcro strap, etc. In some embodiments, the wristband 1108 may be adjustable. For example, the wristband 1108 may be a flexible loop that can self-attach via a Velcro attachment system. In some embodiments, the wristband 1108 may be attached to one or more hooks 1112 on the outside of the housing 1104 of the wearable device 1100. In some embodiments, the wristband 1108 may be magnetic. In other embodiments, the wristband 1108 may include a row, grid, or other arrangement of holes that can receive fasteners from the hooks 1112.

[0065] Referring to Figure 12, an exploded side view of the wearable device 1100 is shown. The wearable device 1100 may include a stimulator 1200. The mechanical transducer 1200 may be housed within a wristband 1208. The wristband 1208 may be configured to contact the user's wrist. The wearable device 1100 may have an upper half 1224 and a lower half 1220 of the housing. In some embodiments, a printed circuit board 1204 (PCB) may be positioned between the upper half 1224 and the lower half 1220. Furthermore, a silicone square may be positioned to insulate the bottom of the PCB 43, and the PCB may be positioned above a battery 1216. The battery 1216 may include protection circuits to protect against overcharging and unwanted discharge. In some embodiments, the wearable device 1000 may include a magnetic connector 1208. The magnetic connector 1208 may be configured to align the wearable device 1100 with a charging pad, station, etc. The magnetic connector 1208 may be configured to receive power wirelessly to recharge the battery 1216. The magnetic connector 1208 may be coupled to the battery 1216 and mounted on the housing 1220 and / or 1224. In some embodiments, the magnetic connector 1208 may be inserted into the PCB 1204. The magnetic connector 1208 may be configured to mate with a connector of an external charger.

[0066] This specification includes many specific implementation details, which should not be interpreted as limitations on the scope of the claims, but rather as descriptions of features that may be specific to particular embodiments. Certain features described in this specification in the context of separate embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may be implemented individually or in any suitable subcombination in multiple embodiments. Furthermore, features may be described above as functioning in a particular combination and initially claimed as such, but one or more features from a claimed combination may, in some cases, be excluded from that combination, and the claimed combination may be directed towards a subcombination or a variation of a subcombination.

[0067] Similarly, while actions are depicted in a specific order in the drawings, this should not be understood as requiring that such actions must be performed in a specific or sequential order, or that all illustrated actions must be performed to achieve a desired result. In certain situations, multitasking and parallel processing may be advantageous. Furthermore, the separation of various system components in the embodiments described above should not be understood as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated into a single software product or packaged into multiple software products.

[0068] Specific embodiments of the subject matter of the present invention have been described. Other embodiments are within the scope of the following claims. For example, the operations described in the claims may achieve the desired results even if they are performed in a different order. As an example, the process shown in the accompanying drawings does not necessarily require the specific order or sequence shown to achieve the desired results. In particular embodiments, multitasking and parallel processing may be advantageous. Other steps or stages may be added to the described process, or steps or stages may be omitted. Accordingly, other embodiments are within the scope of the following claims.

[0069] The usage and terminology used herein are for illustrative purposes only and should not be considered limiting.

[0070] The term “approximately,” the phrase “approximately equal to,” and other similar phrases, when used in the specification and claims (for example, as “X is approximately equal to the value of Y” or “X is approximately equal to Y”), should be understood to mean that one value (X) is within a given range of another value (Y). Unless otherwise specified, the given range may be ±20%, 10%, 5%, 3%, 1%, 0.1%, or less than 0.1%.

[0071] The indefinite articles "a" and "an" used in the specification and claims should be understood to mean "at least one" unless explicitly indicated otherwise. The phrase "and / or" used in the specification and claims should be understood to mean "either or both" of the elements thus combined; that is, elements that exist conjunctively in some cases and disjunctively in others. Multiple elements enumerated by "and / or" should be interpreted in the same manner; that is, "one or more" of the elements thus combined. Other elements may optionally exist, regardless of whether they relate to the elements specifically identified by the "and / or" clause. Thus, as a non-restrictive example, a reference to "A and B" when used in combination with open-ended language such as "including A and B" may, in one embodiment, refer to A only (optionally including elements other than B), in another embodiment to refer to B only (optionally including elements other than A), and in yet another embodiment to refer to both A and B (optionally including other elements).

[0072] As used in the specification and claims, “or” should be understood to have the same meaning as “and / or” as defined above. For example, when separating items in a list, “or” or “and / or” should be interpreted as inclusive; that is, including at least one from a list of numbers or elements, and including more than one, and optionally including items not in the additional list. Only explicitly opposite terms such as “only one” or “exactly one,” or, when used in the claims, “consisting of,” refer to including exactly one element from a list of numbers or elements. In general, as used herein, the term “or” should be interpreted as indicating an exclusive choice (i.e., “one or the other, but not both”) only when preceded by an exclusive term such as “either,” “one of,” “only one,” or “exactly one.” “Consisting of essentially being” should, when used in the claims, have its usual meaning as used in the field of patent law.

[0073] The phrase “at least one” as used in the specification and claims should be understood to mean at least one element selected from any one or more elements in a list of one or more elements, but not necessarily including at least one of each element specifically listed in the list, nor excluding any combination of elements in the list. This definition also allows for the optional presence of elements other than those specifically identified in the list, regardless of whether they relate to the specifically identified element of the element referred to by the phrase “at least one.” Therefore, as a non-limiting example, “at least one of A and B” (or equivalently “at least one of A or B” or equivalently “at least one of A and B”) may, in one embodiment, refer to at least one A (optionally including more than one A) in the absence of B (optionally including elements other than B), in another embodiment, refer to at least one B (optionally including more than one B) in the absence of A (optionally including elements other than A), and in yet another embodiment, refer to at least one A (optionally including more than one A) and at least one B (optionally including more than one B) (optionally including other elements).

[0074] The use of “include,” “equip,” “possess,” “contain,” “involve,” and variations thereof is intended to encompass the items and additional items listed thereafter.

[0075] The use of ordinal numbers such as "first," "second," and "third" in the claims modifies the elements of the claim and does not in itself imply priority, precedence, or order, or a temporal order in which an act of method is performed by an element of one claim relative to an element of another claim. Ordinal numbers are used merely as labels to distinguish one element of a claim having a particular name from another element having the same name (except for the difference in the use of ordinal numbers), and thus distinguish the elements of the claims.

[0076] Having described several aspects of at least one embodiment of the present invention, various modifications, alterations, and improvements will readily come to mind for those skilled in the art. Such modifications, alterations, and improvements are intended to be part of the present disclosure and within the spirit and scope of the invention. Accordingly, the foregoing description and drawings are for illustrative purposes only.

Claims

1. A wearable device for targeted peripheral stimulation, Processor and A memory that is communicably connected to the aforementioned processor, wherein the processor Determine the disease state of one or more motor impairment symptoms of the user. A stimulus output is generated based on one or more motor impairment symptoms and the disease state of the motor impairment symptoms. The stimulator communicating with the processor is instructed to apply the stimulus output to the user's peripheral nervous system in order to alleviate one or more of the motor impairment symptoms. A memory that stores instructions configured in this way, A wearable device equipped with [features / equipment].

2. A sensor that communicates with the aforementioned processor, Furthermore, The sensor outputs sensor data indicating one or more motor symptom disorders of the user. The aforementioned processor further, Based on the sensor data generated while the stimulus output is applied, the user's responsiveness level is calculated. The responsiveness is communicated to an external computing device via the wireless communication unit of the wearable device. The wearable device according to claim 1.

3. The user's responsiveness level is calculated as one of the following: low responsiveness, average responsiveness, or high responsiveness. The wearable device according to claim 4.

4. The reduction of one or more motor impairment symptoms is greater in users with a disease state including an early onset stage of one or more motor impairment symptoms than in users with a disease state including a late onset stage of one or more motor impairment symptoms. The wearable device according to claim 1.

5. The responsiveness is at least partially influenced by the user's demographic data. The wearable device according to claim 1.

6. The one or more motor impairment symptoms described above are tremor, rigidity, stiffness, freezing, paralysis, paresis, dyskinesia, or any combination thereof. The wearable device according to claim 1.

7. The aforementioned stimulus output is applied to one proprioceptive nerve or proprioceptive tissue of the user's peripheral nervous system, specifically to the flexor carpi radialis, flexor carpi ulnaris, extensor carpi radialis, extensor carpi ulnaris, or any combination thereof. The wearable device according to claim 1.

8. The aforementioned processor further, The stimulus output is adjusted based on the disease state of the aforementioned motor impairment symptoms. Command one or more of the stimulators to apply the adjusted stimulator output to the user's peripheral nervous system. The wearable device according to claim 1.

9. The processor further generates the stimulus output through a stimulus selection algorithm, The stimulus selection algorithm generates the stimulus output at least partially based on patient data communicated to the processor. The wearable device according to claim 1.

10. The disease state includes any one of the following: the severity level of one or more motor impairment symptoms, the onset stage of one or more motor symptoms, the stage of motor impairment of one or more motor impairment symptoms, or any combination thereof. The wearable device according to claim 9.

11. A method of targeting peripheral stimulation, Wearable devices are attached to the user, The wearable device's sensors detect one or more of the user's motor impairment symptoms. Based on the above detection, the disease state of one or more motor impairment symptoms is calculated. In response to one or more of the aforementioned motor impairment symptoms, the user's peripheral nervous system is stimulated through the stimulator of the wearable device. The user's responsiveness is detected through the sensors of the wearable device. The peripheral nervous system of the user is stimulated based on the detected responsiveness and the stage of the disease state of one or more motor impairment symptoms. A method that includes the act of doing so.

12. The disease state includes any one of the following: the severity level of one or more motor impairment symptoms, the onset stage of one or more motor symptoms, the stage of motor impairment of one or more motor impairment symptoms, or any combination thereof. The method according to claim 11.

13. The further includes calculating a correlation between the user's responsiveness and the disease state of one or more motor impairment symptoms. The method according to claim 11.

14. The further step includes adjusting one or more parameters of the stimulation output of the wearable device based on the correlation, The method according to claim 13.

15. The early stage of the onset of the aforementioned disease state correlates with a high response to the aforementioned stimulus. The method according to claim 13.

16. The mild or late stage of the onset of one or more motor impairment symptoms of the disease state correlates with a low response to the stimulus. The method according to claim 13.

17. The peripheral nerves or tissues of the user's wrist or arm are stimulated. The method according to claim 11.

18. Stimulating the body part further includes providing the peripheral nervous system with one or more or a combination thereof of vibration, electricity, or ultrasound output through the stimulator of the wearable device. The method according to claim 11.

19. The reduction of one or more of the aforementioned motor impairment symptoms is greater in users with a mild severity level than in users with a moderate or severe severity level of the aforementioned one or more of the aforementioned motor impairment symptoms. The method according to claim 11.

20. The responsiveness is at least partially influenced by the user's patient data. The method described in claim 11

Images