Systems, devices, and methods for using quantitative digitography to measure and / or evaluate neurological function

Abstract

Digitography data may be analyzed to assess neurological health and a plurality of sets of digitography data may be analyzed to, for example, track disease progression and / or treatment responsiveness over time. In particular, when analysis of digitography data yields higher than normal rigidity, freezing, bradykinesia, and / or tremor scores a diagnosis of a neurological condition such as depression, Parkinson's disease, and / or traumatic brain injury may be indicated. Additionally, or alternatively, changes in digitography data over time may indicate changes (e.g., improvements or declines) in neurological health and / or responsiveness to treatment.

Description

SYSTEMS, DEVICES, AND METHODS FOR USING QUANTITATIVE DIGITOGRAPHY TO MEASURE AND / OR EVALUATE NEUROLOGICAL FUNCTIONRELATED APPLICATIONS

[0001] This application is an INTERNATIONAL (PCT) application of, and claims priority to, United States Provisional Patent Application Number: 63 / 741,970, filed on 05 January 2025 and entitled “SYSTEMS, DEVICES, AND METHODS for USING QUANTITATIVE DIGITOGRAPHY TO MEASURE AND / OR EVALUATE NEUROLOGICAL FUNCTION,” and United States Provisional Patent Application Number: 63 / 741,964, filed on 05 January 2025 and entitled “SYSTEMS, DEVICES, AND METHODS FOR USING QUANTITATIVE DIGITOGRAPHY TO QUANTIFY, MEASURE, AND / OR EVALUATE INDICATIONS OF PARKINSON'S DISEASE AND / OR RESPONSIVENESS TO TREATMENT,” both of which are incorporated herein by reference in their respective entireties.FIELD OF DISCLOSURE

[0002] The present disclosure relates to quantitative digitography (QDG) motion capture devices and systems and methods for processing digitography data recorded and / or measured using a digitography device so that depression may be measured and evaluated.BACKGROUND

[0003] Currently, diagnosis of neurological conditions and tracking disease progression and / or responsiveness to treatment is subjective and not easily quantifiable. This is particularly true for treatments that take weeks or months to become effective. Thus, implementation of the standard of care for performing neurological assessment and monitoring response to treatment often leads to inaccurate, inconclusive, and / or conflicting diagnosis of patients and treatment recommendations for them. In addition, it is difficult to quantify small changes in neurological conditions using traditional methods. This makes it difficult to determine a rate of improvement and / or decline, pinpoint anunderlying neurological condition that may be contributing to symptoms, and / or assess the effectiveness of treatment at arresting and / or reversing neurological conditions.

[0004] For example, Parkinson’s disease (PD) is the fastest growing neurological disorder and has been called an emerging pandemic. Diagnosing and / or evaluation of PD, particularly in the early stages of the disease is difficult and often subjective.Making matters worse, few doctors are trained in PD diagnosis and disease management, which makes it difficult for patients to receive the care they need in a timely manner. Typically, people with PD (PWP) are usually evaluated in person by a neurologist or doctor every three to six months. As PD is a progressive disease, the treatment plan set by the neurologist at one visit may become subtherapeutic by the next, which leaves PWP to adjust their medications themselves; a practice that results in unstable dopamine levels and swings from under- to over-treatment, which leads to an increased incidence of falls, fractures, and neuropsychiatric complications such as confusion and hallucinations, the complications of which can lead to death.Furthermore, the Movement Disorder Society-Unified Parkinson’s Disease Rating Scale (MDS-UPDRS) motor examination (Part III) is comprehensive but subjective and variable within and among raters or clinicians. Most health care providers are neither trained nor have time to administer it during short visits, and consequently PWP lack objective, comprehensive motor monitoring in between visits and instead must rely on subjective recall rather than objective data about symptoms between visits can also lead to suboptimal medication management and treatment adjustments.

[0005] A known treatment for people with PD (PWP) is the taking of multiple time-critical medications throughout the day to maintain dopamine levels in affected brain networks. Optimizing such complicated medication schedules to individual patients and so that personalized care with actionable insights may be delivered to patients requires careful management by a neurologist but access to neurologists is limited due to scarcity of qualified doctors. For example, over 40% of PWP in the United States do not have access to neurological care. Even for PWP who have access to a neurologist, there are usually three to six month intervals between in-person visits and there is no remote, real-time, comprehensive system to monitor the effects of therapy and / or symptom progression.SUMMARY

[0006] The digitographic measurement devices and systems disclosed herein may include a base, a first lever, which may be embodied as, for example, a key and / or a tensioned engineered lever, a second lever, which may be embodied as, for example, a key and / or a tensioned engineered lever, an axis, one or more sensors, and a communication interface configured to receive data from the sensor and communicate the data to an external computing device. The first lever may have a first end in communication with an axis and a second end configured to physically rotate around the axis toward the base in response to a force exerted on the second end of the first lever. The second lever may include a first end in communication with the axis and a second end configured to physically rotate around the axis toward the base in response to a force exerted on the second end of the second lever. On some occasions, the second end(s) of the first and / or second levers may include a finger placement indentation. Additionally, or alternatively, the first lever may include and / or be in communication with a first axis and the second lever may include and / or be in communication with a second axis that is physically separate from the first axis.

[0007] The axis and / or first and / or second axis may be in communication with the first ends of the first and second levers and directly, or indirectly in communication with the base. The axis and / or first and / or second axis may be configured to allow rotation of the second ends of the first and second levers in response to a force exerted thereon. In some embodiments, a degree of tension exerted by the axis on the second end of the first lever and / or second lever is adjustable to, for example, exert more, or less, resistance to movement of the second ends of the first and / or second levers.Additionally, or alternatively, the first and / or second lever(s) may be tensioned by a resistance device to mechanically resist movement of one or both of the first lever or the second lever. In these embodiments, the resistance device may be, for example, a spring, a foam, and / or a magnetic or electromagnetic device.

[0008] The sensor may be communication with one or both of the first lever and the second lever and may be configured to sense movement of the one or both of the first lever and the second lever and / or provide quantitative digitography (QDG) motion datawhen, for example, the patient or subject performs a rapid alternating finger tapping (RAFT) task. Exemplary sensors include, but are not limited to, a force meter, a magnet, a clock, a Hall effect sensor, an optical sensor, an infrared sensor, a magnetic sensor, a potentiometer, a displacement measurement sensor, an inertial movement sensor, a strain gauge, an accelerometer, and any combination thereof and data from the sensors may be used (e.g., an external computing device) to, for example, determine at least one of a QDG motion metrics, a tremor metric, a FoRAFT metric, a bradykinetic frequency metric, a bradykinetic sequence effect metric, a bradykinetic amplitude metric, a bradykinesia speed metric, a freezing behavior metric, a rigidity metric, a key press amplitude, a key press amplitude coefficient of variation, an inter-strike interval, an inter-strike interval coefficient of variation, a release slope, a press speed, a dwell time, a rest tremor, any average thereof, and any combination thereof. Data (e.g., QDG data and / or RAFT data) from the digitography devices and / or systems disclosed herein may be used to execute one or more of the methods disclosed herein.

[0009] Systems, methods, and devices for assessing depression, depression symptom progression, and / or depression responsiveness to treatment may utilize a depression assessment model configured to determine one or more indications for and / or relating to a depression diagnosis and / or a depression disorder using digitography data by, for example, inputting a set of digitography data received from a patient into the depression assessment model. The digitography data may correspond to the patient’s performance of a repetitive alternating finger tapping (RAFT) task by one, or both (i.e., left and right) hand(s) performed using, for example, a digitography device like the ones disclosed herein.

[0010] An output may then be received from the depression assessment model. The output may include an indication regarding, for example, a depression diagnosis and / or depression disorder for the patient determined using digitography data. The indication regarding the depression diagnosis may be provided to, for example, a display device or other user communication device and / or interface.

[0011] In some embodiments, the indication may be a rigidity score, a bradykinesia score, a number of taps per minute, a freezing behavior score, and / or a tremor score. In some cases, the indication may be accompanied by a positive ornegative depression diagnosis and / or an indication of a type of depression the patient may be suffering from. In these cases, the indication may correspond to a rigidity score above a threshold value, a bradykinesia score above a threshold value, a freezing behavior score above a threshold value, a tremor score that may be above a threshold value, and / or a number of taps per minute below a threshold value (e.g., 105 taps per minute). In many cases, a threshold value will be a value that corresponds to healthy, age-matched, controlled scores for the relevant metric(s).

[0012] In some embodiments, the method (or portions thereof) may be a number of times (e.g., 2-500) over time to, for example, assess changes in the patient’s digitography data and / or symptoms and / or responsiveness to treatment over time (e.g., days, weeks, months, and / or years). In these embodiments, subsequently received sets of digitography data may be input into the depression assessment model. A subsequent output from the depression assessment model may be received and provided to the display device. Optionally, two or more sets of digitography data, characteristics thereof, and / or indications determined therefrom may be compared with one another to, for example, assess a change therein over time to, for example, assess responsiveness to treatment. For example, if a baseline number of taps per minute determined from a first set of digitography data for a patient is 90 (which is below a 105 taps per minute threshold and therefore indicates the patient is depressed) and they undergo a treatment for depression (e.g., medication and / or cognitive behavior therapy) for a month and a second set of digitography data indicates the number of taps per minute is 102, it may be determined that the treatment is working but that the patient is still depressed and a recommendation that further modification to the treatment may be helpful may be provided to the display device and / or user interface.

[0013] In some embodiments, an indication of a treatment provided to the patient may be input into the depression assessment model along with the digitography data and a treatment-responsive output may be from the depression assessment model and provided to the display device.

[0014] Additionally, or alternatively, systems, methods, and devices may be configured to receive a set of digitography data corresponding to the patient’s performance of aRAFT task using for example, a digitography device like the onesdisclosed herein and determine a characteristic therefrom. The characteristic may then be compared to, for example, a threshold value and / or target value for the characteristic and an indication of whether the patient has depression responsively to a result of the comparison may then be determined and provided to a display device. The characteristic may be, for example, a rigidity score, a bradykinesia score, an amplitude, a frequency, a freezing behavior score, a mobility score, a number of taps per minute, a degree of arrhythmicity, a degree of irregularity, a degree of asynchronicity between the digitography data of the patient’s right hand and the patient’s left hand, a tremor score, and an ability to do alternate fingers correctly.

[0015] In some embodiments, the method may be performed a plurality (e.g., 2-500) times over time on, for example, a periodic (e.g., every day, week, or month) and subsequently received sets of digitography data and / or characteristics determined therefrom may be compared with one another to, for example, determine an indication of a change (or a lack of a change) in the patient’s condition over time. The indication of the change may then be provided to a display device. In some cases, determining the indication of the change in the patient’s condition includes determining an indication of how the patient may be responding to a treatment. The digitography data may be generated via the patient’s performance of RAFT.

[0016] Additionally, or alternatively, systems, methods, and devices may be configured to input a set of digitography data received from a patient using, for example, a digitography device like the ones disclosed herein into a traumatic brain injury assessment model configured to determine one or more indications for a traumatic brain injury diagnosis and / or conditions (e.g., neurological conditions, cognitive decline, mood changes, etc.) that may be directly and / or indirectly related to a traumatic brain injury using digitography data.

[0017] An output may then be received from the traumatic brain injury assessment model. The output may include, for example, an indication regarding a traumatic brain injury diagnosis for the patient and / or a condition that may be indirectly, or directly, related to traumatic brain injury determined using digitography data. The indication may then be provided to a display device or other user interface.

[0018] The indication may be, for example, a rigidity score, a bradykinesia score, an amplitude, a frequency, a freezing behavior score, a mobility score, a number of taps per minute, a degree of arrhythmicity, a degree of irregularity, a degree of asynchronicity between the digitography data of the patient’s right hand and the patient’s left hand, a tremor score, and an ability to do alternate fingers correctly. In some cases, the indication may include a determination that, for example, the rigidity score, bradykinesia score, amplitude, frequency, freezing behavior score, mobility score, number of taps per minute, degree of arrhythmicity, degree of irregularity, degree of asynchronicity between the digitography data of the patient’s right hand and the patient’s left hand, tremor score, and ability to do alternate fingers correctly falls above and / or below a threshold value. The threshold value may correspond to a value for the characteristic and / or indication that corresponds to healthy, age-matched controls.

[0019] In some embodiments, the indication may corresponds to a risk indication for the patient developing Parkinson’s disease. In these embodiments, the digitography data may include RAFT movements for the patient’s left and right hands on levers of a digitography device and the risk indication for Parkinson’s disease may be an asymmetry between the RAFT movements of the patient’s left hand and right hand. Additionally, or alternatively, the indication may be at least one of a low number of taps per minute, irregular amplitude changes of the RAFT movements, speed of pressing and / or releasing the lever or key of a digitography device, and arrhythmic performance of RAFT movements.

[0020] Additionally, or alternatively, a series (e.g., 2-500) of sets of digitography data may be received and / and / or analyzed using the traumatic brain injury assessment model overtime (e.g., days, weeks, months, and / or years) to, for example, see changes to the data, characteristics of the data, and / or scores determined from the data over time in order to, for example, track disease progression and / or responsiveness to treatment. Additionally, or alternatively, a result of the comparison and / or the changes may be used to determine a

[0021] On some occasions, a result of the comparison may be an indication of a risk that the patient will develop Parkinson’s disease and / or used to determine by, for example, the model or otherwise, a risk that the patient will develop Parkinson’sdisease. Additionally, or alternatively, a recommendation may be determined by the model or otherwise responsively to the result of the comparison and provided to the display device. In some instances, the recommendation may include recommendation that the patient begin a treatment for Parkinson’s disease and / or that the treatment should be adjusted.

[0022] In some embodiments, an indication that the patient is receiving a treatment may be input into the traumatic brain injury assessment model and a treatment-responsive output from the traumatic brain injury assessment model may be received therefrom. The treatment-responsive output may be responsive to the indication of the treatment.

[0023] Additionally, or alternatively, systems, methods, and devices may be configured to input a set of digitography data received from a patient using, for example, a digitography device like the ones disclosed herein into a Parkinsonism assessment model configured to determine one or more indications for a Parkinson’s disease using digitography data. An output from the Parkinsonism assessment model may be received. The output may include an indication regarding a Parkinsonism diagnosis for the patient determined using digitography data. The indication may then be provided to a display device and / or user interface. This may be done to, for example, to monitor the patient for the onset of Parkinsonism, monitor Parkinsonism progression, and / or track the patient’s responsiveness to a treatment for Parkinsonism. In some instances, the patient may have been diagnosed with traumatic brain injury, obstructive sleep apnea, depression, cognitive decline, and / or mood changes.

[0024] The Parkinsonism model may be configured to analyze the digitography data to, for example, determine one or more of a rigidity score, a bradykinesia score, an amplitude, a frequency, a freezing behavior score, a mobility score, a number of taps per minute, a degree of arrhythmicity, a degree of irregularity, a degree of asynchronicity between the digitography data of the patient’s right hand and the patient's left hand, a tremor score, and an ability to do alternate fingers correctly. The Parkinsonism assessment model may be configured to determine that the patient has Parkinson’s disease responsively to detecting, for example, an asymmetrical performance of a RAFT task corresponding to the digitography data between thepatient's left and right hands, a tremor score above a threshold, and / or a rigidity score above a threshold.

[0025] Additionally, or alternatively, systems, methods, and devices may be configured to receive a first set of digitography data corresponding to the patient’s performance of a RAFT task using, for example, a digitography device like the ones disclosed herein and, after a duration of time (e.g., day, week, month, year, etc.), a second set of digitography data corresponding to the patient’s performance of the RAFT task may be received. The first and second sets of digitography data, characteristics of the first and second sets of digitography data and / or scores determined using the first and second sets of digitography data may be compared with one another to, for example, determine the patient’s responsiveness to treatment using a result of the comparison. The determination of the patient’s responsiveness to treatment may then be provided to a display device and / or user interface. Exemplary scores and / or characteristics include, but are not limited to, a rigidity score, a bradykinesia score, a amplitude, a frequency, a freezing behavior score, a mobility score, a number of taps per minute, a degree of arrhythmicity, a degree of irregularity, a degree of asynchronicity between the digitography data of the patient’s right hand and the patient’s left hand, a tremor score, and an ability to do alternate fingers correctly.Exemplary treatments may be for a neurological condition and / or a condition that impacts motor skills (e.g., arthritis) and may include, for example, a pharmaceutical, surgery, behavior therapy, and / or physical therapy.

[0026] On some occasions, the treatment may be provided via a brain-computer interface and / or a deep brain stimulation device. In these instances, it may be determined where and / or how to stimulate the brain using the brain-computer interface and a deep brain stimulation device responsively to the determination of the patient’s responsiveness to treatment provided by the respective brain-computer interface and / or a deep brain stimulation device. In some embodiments, a recommendation for where and / or how to stimulate the brain using the wherein the at least one brain-computer interface and a deep brain stimulation device may be determined responsively to the determination and provided to a display device and / or an interface in communication with the respective brain-computer interface and / or deep brain stimulation device.

[0027] Durations of time between subsequent digitography data sets described herein may be, for example, 6 hours, 24 hours, a week, two weeks, a month, two months, three months, a year, 2 years, 5 years, and 10 years.

[0028] Additionally, or alternatively, the systems, devices, and methods disclosed herein may be configured to, for example, input a set of digitography data received from a patient into a gait assessment model configured to determine a gait characteristic for the patient using digitography data and an output may be received and provided to a display device and / or user interface. The output may be, for example, a gait characteristic determined using digitography data.

[0029] The method of claim 46 or 47, wherein the indication may be a freezing behavior score, a freezing of gate score, a mobility score, and / or a gait speed. In some embodiments, a plurality of sets of digitography data may be input into the gait assessment model over time to, for example, determine changes therebetween and / or monitor changes to the patient’s gait over time and / or the patient’s responsiveness to treatment. At times, a recommendation for the patient may be determined responsively to the result of the comparison and provided to the display device, in some cases, the recommendation may include recommending a treatment for Parkinson’s disease.BRIEF DESCRIPTION OF THE FIGURES

[0030] The present disclosure is illustrated by way of example, and not limitation, in the figures of the accompanying drawings in which:

[0031] FIG. 1A is a top perspective view of an exemplary digitography device, in accordance with some embodiments of the present disclosure;

[0032] FIG. 1 B is a side view of the digitography device of FIG. 1 A, in accordance with some embodiments of the present disclosure;

[0033] FIG. 2 is a block diagram of exemplary internal components of an exemplary digitography device, in accordance with some embodiments of the present disclosure;

[0034] FIG. 3 is a block diagram of an exemplary networked computer system configured to perform one or more of the methods disclosed herein, in accordance with some embodiments of the present disclosure;

[0035] FIG. 4A is a flowchart showing a method for using digitography data to assess a degree of depression for a patient, in accordance with some embodiments of the present disclosure;

[0036] FIG. 4B provides a labeled graph of lever position in mm as a function of time, in accordance with some embodiments of the present disclosure;

[0037] FIG. 4C provides a screen shot of a panel showing four different graphs of digitography data for a healthy control, in accordance with some embodiments of the present disclosure;

[0038] FIG. 4D provides a screen shot of a panel showing four different graphs of QDG RAFT data for a person with Parkinson’s Disease, in accordance with some embodiments of the present disclosure;

[0039] FIG. 4E provides a screen shot of an exemplary interface showing exemplary QDG RAFT data analysis results and, in particular, a statistical method for calculating a mobility score, in accordance with some embodiments of the present disclosure;

[0040] FIG. 5A provides a screen shot of a first exemplary graphic user interface (GUI) showing digitography data and evaluation results for the digitography data, in accordance with some embodiments of the present disclosure;

[0041] FIG. 5B provides a screen shot of a second exemplary GUI showing digitography data and evaluation results for the digitography data, in accordance with some embodiments of the present disclosure;

[0042] FIG. 5C provides a screen shot of a third exemplary graphic user interface reporting QDG RAFT data analysis results to a user on a display device, in accordance with some embodiments of the present disclosure;

[0043] FIG. 6A provides a first exemplary screen shots of exemplary GUI that display QDG RAFT data and analysis results for a person with Parkinson’s disease (PWP) both on and off medication, in accordance with some embodiments of the present disclosure;

[0044] FIG. 6B provides a second exemplary screen shots of exemplary GUI that display QDG RAFT data and analysis results for a person with Parkinson’s disease(PWP) both on and off medication, in accordance with some embodiments of the present disclosure;

[0045] FIG. 60 provides a third exemplary screen shots of exemplary GUI that display QDG RAFT data and analysis results for a person with Parkinson’s disease (PWP) both on and off medication, in accordance with some embodiments of the present disclosure;

[0046] FIG. 6D provides a fourth exemplary screen shots of exemplary GUI that display QDG RAFT data and analysis results for a person with Parkinson’s disease (PWP) both on and off medication, in accordance with some embodiments of the present disclosure;

[0047] FIG. 7A provides a flowchart showing a process for remotely monitoring a patient using QDG motion capture data, in accordance with some embodiments of the present disclosure;

[0048] FIG. 7B provides a screen shot of a QDG web dashboard that displays values for bradykinesia metrics over a single day of testing for a PWP along with an indication of a prescribed medication time, an indication of when the patient actually took the medication, and an indication of a value for a bradykinesia metric for 7am and 11am, in accordance with some embodiments of the present disclosure;

[0049] FIG. 7C provides a screen shot of an interface showing remotely obtained QDG metrics for one participant’s left hand over a 30-day period., in accordance with some embodiments of the present disclosure;

[0050] FIG. 7D provides a screen shot of a GUI of a QDG web dashboard tracking QDG mobility score for both hands of a PWP over time, in accordance with some embodiments of the present disclosure;

[0051] FIG. 7E provides a screen shot of a GUI of a QDG web dashboard tracking QDG mobility score for two different PWP over time, in accordance with some embodiments of the present disclosure;

[0052] FIG. 8 is a flowchart providing an exemplary process for identifying and removing tremor data from QDG RAFT data, in accordance with some embodiments of the present disclosure;

[0053] FIG. 9A provides a screen shot of an exemplary panel providing an exemplary tremor-labeled QDG RAFT dataset for emergent tremor in a tremor-dominant PD phenotype, in accordance with some embodiments of the present disclosure;

[0054] FIG. 9B provides a screen shot of an exemplary panel providing a plurality of scatter plots of percent duration of tremor in trial (%T) and change in metrics measuring bradykinesia (ISI, press amplitude, and press amplitude CV), rigidity (release slope), arrhythmicity (ISI CV) and dwell time after the exclusion of tremor in TD Trials (n = 85), in accordance with some embodiments of the present disclosure;

[0055] FIG. 10 is a flowchart showing a method for training a depression assessment model, in accordance with some embodiments of the present disclosure;

[0056] FIG. 11 is a flowchart showing a method for using a depression assessment model, in accordance with some embodiments of the present disclosure;

[0057] FIG. 12 is a flowchart showing a method for training a traumatic brain injury assessment model, in accordance with some embodiments of the present disclosure;

[0058] FIG. 13 is a flowchart showing a method for using a traumatic brain injury assessment model, in accordance with some embodiments of the present disclosure;

[0059] FIG. 14 is a flowchart showing a method for training a Parkinsonian assessment model, in accordance with some embodiments of the present disclosure;

[0060] FIG. 15 is a flowchart showing a method for using a Parkinsonian assessment model, in accordance with some embodiments of the present disclosure.

[0061] FIG. 16 is a flowchart showing a method for training a gait assessment model, in accordance with some embodiments of the present invention;

[0062] FIG. 17 is a flowchart showing a method for using a gait assessment model, in accordance with some embodiments of the present invention; and

[0063] FIG. 18 is a flowchart showing a method for developing and updating a digitography exercise program, in accordance with some embodiments of the present disclosure.

[0064] Throughout the drawings, the same reference numerals and characters, unless otherwise stated, are used to denote like features, elements, components, or portions of the illustrated embodiments. Moreover, while the subject disclosure will nowbe described in detail with reference to the drawings, the description is done in connection with the illustrative embodiments. It is intended that changes and modifications can be made to the described embodiments without departing from the true scope and spirit of the subject disclosure as defined by the appended claims.WRITTEN DESCRIPTION

[0065] Currently, assessments of depression type and / or severity are subjective and not easily quantifiable. In addition, responsiveness to treatment is also difficult to assess and measure quantifiably, particularly because antidepressants can take weeks or months become effective. Thus, implementation of the standard of care for performing depression assessment and monitoring response to treatment often leads to inaccurate, inconclusive, and / or conflicting depression diagnosis of patients. In addition, it is difficult to quantify small changes in depression using traditional methods. This makes it difficult to determine a rate of improvement and / or decline, pinpoint an underlying neurological condition that may be contributing to depression, and / or assess the effectiveness of treatment at arresting and / or reversing depression.

[0066] At times, people with depression may experience cognitive inflexibility or rigidity in their thinking and a sense of inner or psychic tension. They may also experience psychomotor retardation and / or psychomotor slowness, which may manifest itself as, for example, slowness of movement, speech, and / or thinking. Other physical, or motor, symptoms noted in people experiencing depression include loss of spontaneous facial expression, a slow gait, and / or lethargy when compared with nondepressed healthy controls. In some circumstances, depression symptoms have been associated with structural defects, degeneration, and / or atrophy in brain regions such as the prefrontal cortex and the limbic circuitry. For example, four different biotypes of depression have been identified, with each of these biotypes having distinct brain network involvement and distinct therapeutic profiles. However complex psychological behavior patterns may not be, in themselves, correlated to a particular biotype of depression and / or dysfunction of a particular region or feature of the brain to predict a biotype therapeutic strategy. Disclosed herein are systems, devices, and methods for recording, measuring, and / or assessing patient fine motor control using quantitativedigitography (QDG) and using this data to quantifiably measure motor indications that may be used to represent aspects of depression and / or determine one or more biotypes of depression the patient may be exhibiting so that, for example, an effective therapeutic strategy may be implemented. In addition, QDG metrics may provide an objective, quantifiable, manner in which to evaluate the function of regions of the brain affected in depression and may be useful to monitor the effect of therapeutic strategies and / or predict which therapeutic strategies may be effective for a particular patient. In some circumstances, QDG tasks may be performed remotely with real time feedback to the health care provider so that, for example, a patient may be monitored inside and / or outside (e.g., home, nursing facility, etc.) of a medical facility and / or neurologist’s office.

[0067] In some instances, different biotypes of depression may have different QDG metric profiles. For example, QDG metrics for patients who have bipolar depression may be associated with more impulsive choices of tapping and inaccuracies than healthy controls and / or patients who have a different biotype of depression (e.g., major depression or postpartum depression). In another example, QDG metrics for patients with major depression may be associated with more rigidity, slower press speeds and / or slower inter-strike intervals (i.e., a time duration between lever presses and / or releases) than healthy controls and / or patients who have a different biotype of depression.

[0068] Analysis of digitography data (also referred to herein as digitography data) accurately measures slowness of movement, which may be correlated with psychomotor slowness and / or depression severity and or a type of depression.Digitography data also provides a unique and robust metric of rigidity or stiffness which may correlate with psychic tension and other depression characteristics. The accuracy, reaction time, time between different finger strikes (inter-digit interval) and / or variability of finger tapping included in digitography data may also be abnormal in people with depression of different types compared to healthy controls. In addition, QDG metrics before, during, and / or after administration and / or participation in therapies may provide indications of whether a patient is responsive to a therapy aimed at arresting and / or reversing depression and / or improving symptoms associated with depression.Additionally, or alternatively, analysis of digitography data may show, for example,correlations between the patient’s performance of the motor exercise and a level of depression determined using other clinical scales for measuring depression and / or with atrophy of one or more brain regions as may be determined via, for example, depression-related patient reported outcome measures (PROM) such as the Computerized Adaptive Testing - Mental Health (CAT-MH) PROM or Patient Health Questionnaire 9 (PHQ-9) PROM.

[0069] The systems, devices, and method disclosed herein may be used to accurately and precisely capture various aspects (e.g., movement patterns, frequency, amplitude, pressure, reaction time, variability, dwell time, accuracy, inter-digit interval etc.) of QDG motion for patients and these measurements and / or inferences or models made therefrom may be used to provide one or more indications of one or more aspects of a severity and / or type of depression a patient may be suffering from and / or the patient’s responsiveness to treatment. Exemplary digitography exercises include, but are not limited to, RAFT of a plurality (e.g., 2-10) levers provided by a digitography device such as the digitography devices disclosed herein and exemplary digitography data includes lever speed, lever velocity, force exerted on a lever, a duration of time between alternating lever motions, an amplitude of lever motion, and / or a duration of a lever motion measured and / or recorded while the patient is performing digitography exercises (e.g., RAFT). These measurements and / or recordings may then be analyzed to determine one or more characteristics thereof such as a value for a digitographic metric that may be used to assess a neurological condition such as depression.Exemplary digitographic metrics for which values may be calculated include, but are not limited to, a tremor metric, a rigidity metric, a freezing of RAFT (FoRAFT) metric, a bradykinetic sequence effect metric (deterioration of amplitude, speed of press and release, and / or frequency overtime), an entropy metric, a bradykinetic amplitude metric, a bradykinetic frequency metric, a speed of pressing and / or releasing a lever or key of a digitography device, an accuracy metric, a reaction time metric, a flexibility metric, and a freeze behavior metric. In some cases, patients exhibiting depression and / or psychomotor slowness may have fewer lever taps within a given time period when compared with healthy controls. Additionally, or alternatively, patients exhibiting depression and / or psychomotor slowness may have a slower frequency of taps, asmaller amplitude for taps of the levers, and / or slower press and release times for releasing the levers when compared with healthy controls.

[0070] Digitography data may also be used to assess, evaluate, and / or diagnose other impairments and / or deficits including, but not limited to, cognitive impairment, essential (action) tremor, stroke, and / or muscle weakness. Currently, assessments of cognitive impairment are performed by providing patients with complex questionnaires (e.g., PROMs), the answers to which are interpreted by neurologists in a scientific, but subjective, manner such that results of cognitive impairment tests may vary from neurologist to neurologist and / or from patient to patient. In addition, inherent limitations of the questionnaires and the required subjective analysis of answers to the questionnaires make it difficult to pinpoint sources and / or degrees of neurological disfunction and cognitive impairment. Thus, implementation of the standard of care for performing cognitive impairment assessment often leads to inaccurate, inconclusive, and / or conflicting cognitive impairment diagnosis of patients. In addition, it is difficult to detect small changes in cognitive impairment using traditional methods, which makes it difficult to determine a rate of cognitive decline, pinpoint an underlying neurological condition that may be contributing to cognitive impairment, and / or assess the effectiveness of treatment at arresting and / or reversing cognitive impairment.

[0071] At times, patients with, or who are susceptible to cognitive impairment ((e.g., patients diagnosed with mild cognitive impairment) present with physical, or motor, symptoms (e.g., stiffness, a slow, variable gait, etc.) when compared with age-matched healthy controls. These motor symptoms may indicate, for example, a structural defect, degeneration, and / or atrophy in a brain region such as the nucleus basalis of Meynert, an important brain structure in cognitive circuitry. Thus, measurement and / or evaluation of these motor symptoms may provide an objective, measurable, manner in which to evaluate the function of cognition-related regions of the brain so that, for example, cognitive impairment and / or decline may be objectively, quantifiably, measured. One way to measure, observe, and / or evaluate motor symptoms that may be associated with cognitive impairment is the analysis of a motor exercise performed by a patient, such as a repetitive alternating finger tapping using quantitative digitography (QDG-RAFT) motor exercises. Analysis of QDG motioncapture information or digitography data may, for example, indicate different types and / or degrees of cognitive impairment and / or a response of the brain to a therapy aimed at arresting and / or reversing cognitive impairment. Additionally, or alternatively, analysis of digitography data may show, for example, correlations between the patient’s performance of the motor exercise and a level of cognitive impairment determined using other clinical scales for measuring cognitive impairment and / or with atrophy of one or more brain regions (e.g., nucleus basalis of Meynert). At times, this written description refers to a “patient.” It is to be understood that a “patient” may be, for example, a person who is under the care of a physician, a person receiving medical care, a person contemplating receiving medical care, and / or a healthy control subject of, for example, a study or clinical validation procedure.

[0072] In addition, disclosed herein are systems, devices, and methods that provide a comprehensive connected care platform for people with Parkinson’s Disease (PWP) that delivers validated, quantitative metrics of all motor signs for PWP in real time, monitors medication adherence and the effects of adjusting therapy, integrates with patient electronic medical records, and / or provides actionable data with which patients and clinicians may make decisions about, for example, treatment management, symptom management, disease progression, and goal-setting.

[0073] In some embodiments, the systems, devices, and method disclosed herein may be used to accurately and precisely capture various aspects (e.g., movement patterns, frequency, amplitude, pressure, reaction time, etc.) of QDG motion for patients and these measurements and / or inferences made therefrom may be used to, for example, generate values for quantitative metrics for one or motor signs for PWP in real time (or nearly real time), which may provide actionable data with which patients and clinicians may make decisions about managing treatment for PD. For example, the system, devices, and / or methods disclosed herein may be used to monitor medication adherence, monitor the effects of a therapy and / or adjustments to the therapy, and / or make predictions and / or recommendations regarding PD management and disease progression. In some embodiments, raw and / or processed QDG data may be added to and / or integrated with patient electronic medical records and / or remote patientmonitoring software applications so that patients may be remotely monitored regarding, for example, treatment compliance, treatment efficacy, and / or disease progression.

[0074] Exemplary QDG tasks performed by PWP include, but are not limited to, repetitive alternating finger tapping (RAFT) of a plurality (e.g., 2-10) of adjacent tensioned engineered levers provided by a digitography device and / or a QDG RAFT device such as the digitography devices and / or QDG RAFT devices disclosed herein. Exemplary QDG RAFT data includes lever speed, press speed, release speed, lever velocity, force exerted on a lever, a duration of time between alternating lever motions, an amplitude of lever motion, arrhythmicity (regularity of frequency), regularity of amplitude, taps per minute, and / or a duration of a lever motion measured and / or recorded while the patient is performing QDG tasks. These measurements, recordings, and / or raw data may then be analyzed to determine one or more characteristics thereof such as a value for a digitographic metric that may be used to assess a patient’s condition and / or changes in patient condition. Exemplary digitographic metrics for which values may be calculated include, but are not limited to, a tremor metric, a rigidity metric, a freezing of RAFT (FoRAFT) metric, a bradykinetic sequence effect metric, a bradykinetic metric, a bradykinetic amplitude metric, a bradykinetic frequency metric, a bradykinetic press speed metric, a bradykinetic sequence effect metric, a freeze behavior metric, a tremor score, a mobility score, and / or an arrhythmicity metric.

[0075] Turning now to the figures, FIG. 1A is a top perspective view and FIG. 1B is a side view of an exemplary QDG motion capture and / or digitography device 100 that may be used by a patient to perform a digitography task (e.g., RAFT) as described herein. Digitography device 100 may also configured to measure, or otherwise capture, data regarding movement of the levers of digitography device 100 as, for example, described herein.

[0076] Digitography device 100 includes a first lever 110A that includes a first finger placement indentation 115A, a second lever 110B that includes a second finger placement indentation 115B, an axis 120, a base 125, and a bumper 130. As shown in FIGS. 1A and 1B, first and second levers 110A and 110B are in an initial, orat-rest, position. First and second levers 110A and 110B may be configured to rotate around axis 120 responsively to a downward (as oriented in FIG. 1A) force exerted thereonfrom, for example, a patient’s finger while the patient is performing a digitography task. First and / or second levers 110A and / or 110B may be configured to move, for example 3-25mm, 10-15mm, or approximately 15mm downward when pressed, or tapped, by a patient (or a healthy control subject) and then return to a neutral, or starting, position when the patient or healthy control subject releases the lever. A downward motion of first and / or second levers 110A and 110B may terminate when a portion of a lower surface of first and / or second levers 110A and 110B touches bump stop 130. A degree of tension for first and / or second levers 110A and / or 110B may be adjustable to, for example, control an amount of force required to depress first and / or second levers 110A and / or 110B and / or how quickly first and / or second levers 110A and / or 110B returns from a depressed position to the at-rest position shown in FIG. 1A.

[0077] Digitography device 100 may be configured so that first and / or second levers 110A and 110B rotate about axis 120 to return to their initial, at-rest, position with, or without, the patient’s assistance. Automatic rotation (i.e., the returning from the depressed position to the initial position) of first and / or second levers 110A and 110B may be achieved via, for example, a deformed (e.g., stretched / expanded or compressed) resistance device (e.g., a spring, foam, magnet, etc.) mechanically coupled to first and / or second levers 110A and 110B returning to its undeformed (e.g., contracted or expanded, respectively) state. Conversely, automatic rotation of first and / or second levers 110A and 110B may be achieved via, for example, an undeformed resistance device mechanically coupled to first and / or second levers 110A and 110B being deformed (e.g., contracted or expanded, respectively).

[0078] At times, a magnitude of force needed to depress first and / or second levers 110A and 110B from the initial, at-rest, position to the depressed position may be variable via, for example, adjustment of a level, or magnitude, of resistance provided by the first and / or second levers 110A and 110B to the movement of the respective lever by the patient’s fingers. This variable resistance may be provided by, for example, one or more resistance device(s) mechanically, electrically, and / or magnetically coupled to first and / or second levers 110A and 110B. Additionally, or alternatively, the variable resistance may be provided by a tension / resistance adjusting device 220, which is discussed below with regard to FIG. 2.

[0079] Often times, digitography device 100 is configured so that first and second levers 110A and 110B move independently of one another and a patient may use digitography device 100 in a manner where he or she alternates moving two fingers (e.g., index finger and middle finger) up and down so that first and second levers 110A and 110B move up and down in a corresponding manner. A patient may be directed to where to place the tips of each finger on first and second levers 110A and 110B by first and second finger placement indentations 115A and 115B, which may be configured as, for example, depressions that hold the patient’s fingertips therein when digitography device 100 is being used to conduct a digitography exercise.

[0080] FIG. 2 is a block diagram of a system 200 of exemplary internal components of exemplary digitography device 100. The internal components of system 200 may reside in, for example, base 125, first lever 110A, second lever 110B, and / or axis 120 and may be configured to be electrically, communicatively (e.g., wired and / or wireless communication), and / or physically coupled to one another.

[0081] System 200 includes an indication display device 205, a processing device 210, a memory 215, an optional tension / resistance adjusting device 220, a communication interface 225, a port 230, a power source 235, and one or more sensor(s) 240. Indication display device 205 may be any device configured to provide feedback to the patient regarding an operation (e.g., on / off, functioning properly, ready to record motion data, etc.) of digitography device 100. Exemplary indication display devices 205 include, but are not limited to indicator lights (e.g., diodes or LEDs) and display devices or screens that may, at times, be touch-sensitive.

[0082] Processing device 210 may be a device configured and / or programmed to operate digitography device 100, record motion using digitography device 100, process and / or pre-process data generated by digitography device 100, and / or execute one or more methods or method steps disclosed herein. Exemplary processing devices include, but are not limited to processors, application specific integrated circuits (ASICs), controllers, and the like. Memory 215 may be configured and / or programmed to store one or more sets of instructions executable by processing device 210.Additionally, or alternatively, memory 215 may be configured to store one or moreindications, measurements, and / or metrics of motion of first and / or second lever 110A and / or 11 OB.

[0083] Tension / resistance adjusting device 220 may be a device physically, mechanically, and / or magnetically coupled to first and / or second lever 110A and / or 110B and may be configured to, for example, adjust a level of resistance to movement provided by first and / or second lever 110A and / or 110B and / or set a rate of movement of first and / or second lever 110A and / or 11 OB from a depressed position to the first, at-rest, position.

[0084] Communication interface 225 may be configured and / or programmed to communicate (send and / or receive) with an external device. In some embodiments, communication interface 225 may be a wireless transceiver. Additionally, or alternatively, communication interface 225 may be a wired, or wireless, communication port and, on some occasions, may act to provide power to digitography device 100 and / or recharge power source 235. For example, communication interface 225 may be configured to communicate measurements of one or more sensors 240 to an external computing device (e.g., computer system 330 of system 300) for additional processing according to, for example, one or more methods disclosed herein. Communication interface 225 may also be configured to receive information, such as instructions or operation parameters for storage in memory 215 and / or execution by processing device 210. Additionally, or alternatively, data may be received from and / or communicated to the external device via port 230, which may be any port configured for acceptance of a cable for communication of data and / or electricity (which may be sent to power source 235). Power source 235 may be a battery that, in some cases, may be rechargeable via connection of power cord to port 235 and an electrical main.

[0085] One or more sensors 240 may be configured to measure or otherwise capture movement of first and / or second levers 110A and / or 110B during use by a patient (e.g., the patient is performing RAFT). Exemplary sensors 240 include force meters, clocks, Hall effect sensors, optical sensors, infrared sensors, magnetic sensors, potentiometers, displacement measurement sensors, inertial movement sensors, strain gauges, and accelerometers. Sensors 240 may be configured to capture data that may be converted (e.g., by processing device 210 and / or computer system 330) intomeasurements for one or more types of metrics such as the metrics disclosed herein (e.g., a rigidity metric, a bradykinetic amplitude metric, a bradykinetic frequency metric, a bradykinetic sequence effect metric, a tremor metric, a freeze behavior metric, and / or a FOUL metric).

[0086] FIG. 3 is a block diagram of an exemplary networked computer system 300 configured to communicate with digitography device 100 and / or perform one or more of the methods disclosed herein. System 300 includes a cloud computing platform 310, a communication network 320, a computer system 330, a digitography device 100, and a database 340. It will be appreciated that in some embodiments, system 300 may not include all the components shown in FIG. 3 and / or may include additional components other than those shown in FIG. 3. At times, the components of system 300 may form an integrated connected care platform.

[0087] In some instances, communication network 320 is the Internet.Additionally, or alternatively, communication network 320 may be a private network within, for example, an institution (e.g., a hospital or system of medical treatment facility). The components of system 300 may be coupled together via wired and / or wireless communication links. In some instances, wireless communication of one or more components of system 300 may be enabled using short-range wireless communication protocols designed to communicate over relatively short distances (e.g., BLUETOOTH™, near field communication (NFC), radio-frequency identification (RFID), and Wi-Fi) with, for example, a computer or personal electronic device (e.g., tablet computer or smart phone) as described below. Often times, communication between components of system 300 may be compliant with one or more security protocols, laws, and / or policies that may protect sensitive personally identifying and / or healthcare data.

[0088] Cloud computing platform 310 may be any cloud computing platform 310 configured to store data and / or execute one or more processes described herein.Computer system 330 may be configured to act as a communication terminal to cloud computing platform 310 via, for example, communication network 320 and may communicate (directly and / or indirectly) measurements taken by digitography device 100 to cloud computing platform 310. Cloud computing platform 310 may be any cloud computing platform 310 configured to run a machine learning and / or artificialintelligence software program and / or support a machine learning and / or artificial intelligence architecture configured to build, tune, update, and / or validate machine learning models such as TensorFlow. Exemplary cloud computing platforms 310 include, but are not limited to, Amazon Web Service (AWS), Rackspace, and Microsoft Azure. Exemplary machine learning and / or artificial intelligence architectures include neural networks, deep neural networks, artificial neural networks, Bayesian networks, and / or software or hardware that utilizes artificial intelligence. The machine learning models disclosed herein may incorporate a variety of models such as decision trees, linear regression models, logistic regression models, neural networks, classifiers, support vector machines (SVMs), inductive logic programming, ensembles of models (e.g., using techniques such as bagging, boosting, random forests, etc.), genetic algorithms, Bayesian networks. Examples of neural networks can include convolutional neural networks (CNNs) such as Il-Net architectures and Residual Networks (Res-Net). The machine learning models may be configured to perform a variety of tasks including, for example, a regression, a classification, a clustering, or a segmentation. The machine learning models can be trained using a variety of approaches, such as deep learning, association rules, inductive logic, clustering, maximum entropy classification, learning classification, etc. In some cases, the machine learning models may use supervised learning. In other cases, the machine learning models use unsupervised learning.

[0089] Exemplary computer systems 330 include desktop and laptop computers, servers, tablet computers, personal electronic devices, mobile devices (e.g., smart phones), and the like. In some instances, computer system 330 may include a display device and / or a user interface by which information may be displayed to a user and / or input from a user may be received.

[0090] Computer system 330 may be communicatively coupled to database 340, which may be configured to store data received from, for example, digitography device 100 and / or sets of instructions for execution by computer system 330 and / or cloud computing platform 310. One or more components (e.g., database 340, computer system 330, and / or cloud computing platform 310) of system 300 may store machine-readable instructions and / or receive machine-readable instructions via, for example, communication network 320, that when executed by a processor (e.g., a processor ofcomputer system 330, and / or cloud computing platform 310) may perform one or more methods, processes, and / or method steps and / or generate measurement data disclosed herein.

[0091] The digitography data and / or patient data may be mined and / or analyzed to, for example, determine patterns and correlations therein and / or develop models that may be used to, for example, recognize, monitor, and / or diagnose depression, a depression disorder, and / or depression types and / or predict treatment outcomes.Additionally, or alternatively, the digitography data and / or patient data may be mined and / or analyzed to, for example, determine patterns and correlations therein and / or develop models that may be used to, for example, recognize, monitor, and / or diagnose cognitive impairment, essential (action) tremor, stroke, and / or weakness.

[0092] FIG. 4A is a flowchart showing a method 400 for using digitography data to assess and / or evaluate a degree of depression, cognitive impairment, essential (action) tremor, stroke, and / or weakness for a patient using a motion capture device like digitography device 100. Method 400 may be executed by, for example, digitography device 100, system 200, system 300, and / or components thereof.

[0093] Initially, digitography data may be received (step 405) by, for example, processing device 210 and / or computer system 330. The digitography data received in step 405 may include, for example, measured and / or recorded movement of a plurality of levers (e.g., first and second levers 110A and 110B) of a motion capture device like digitography device 100 over a time period (e.g., 30 seconds, 2 minutes, 5 minutes, etc.) while the patient is, for example, performing a RAFT task. The movement of the plurality of levers may be initiated by a patient pressing down on one or more of the plurality of levers, a patient pulling up on one or more of the plurality of levers, and a response of the motion capture device or a component thereof (e.g., tension / resistance adjusting device 220) to the patient-initiated movement (e.g., a rate of the lever’s return from a depressed to an initial, rest position).

[0094] Exemplary measurements that may be received in step 405 include, but are not limited to, a magnitude of lever displacement, a magnitude of force exerted upon a lever, a rate at which the patient pushes down and / or releases / pulls up on one or more of the plurality of levers, a rate at which the lever responds to a downward orupward force exerted thereon by returning to the initial position, a magnitude of an interstrike interval of time (also called an “inter-strike interval” and “ISI” herein) between two or more consecutive patient-initiated movements of one or more of the plurality of levers, an amplitude of patient-initiated movements of one or more of the plurality of levers (also referred to herein as “press amplitude”), press speed, release speed, number of taps per minute, time the patient froze or didn’t strike a lever, arrhythmicity, and sequence effect. An amplitude of a patient-initiated movement of a lever may be a measurement of how far down the patient has depressed one or more of the plurality of levers and it may be determined by measuring a distance between an initial resting state and a depressed state of one or more of the levers of a digitography measurement device. In some embodiments, the data received in step 405 may include metrics that provide an indication of bradykinesia such as a number of taps per minute, press speed, sequence effect, press amplitude of taps, press speed, and / or a metric reflective of the sequence effect in tap amplitude (the coefficient of variation of press amplitude); metrics that include an indication of rigidity, such as release speed, rest and action tremor, arrhythmicity, and / or gait impairment.

[0095] In some embodiments, the data received in step 405 may be raw data and in other embodiments, it may be pre-processed and / or filtered to, for example, remove noise and / or outlying measurements. The pre-processing may be performed by, for example, processing device 210 prior to communication of data to an external computing device like computer system 330.

[0096] In step 410, the digitography data received in step 405 may be processed and / or analyzed to determine one or more characteristics thereof and / or a value for one or more metrics that may be indicated by the digitography data. The characteristics and / or metrics may correspond to raw data and / or may be a mean, or average, value. Exemplary characteristics include, but are not limited to, a count of how many times within a given period the patient depressed the one or more levers, an amplitude of lever movement, whether indications of tremors or other unintentional movements of the one or more levers are detected, and / or a force exerted on the one or more levers.Exemplary metrics include, but are not limited to, a tremor metric, a FreezingT metric, a bradykinetic frequency metric, a bradykinetic sequence effect metric, a bradykineticamplitude metric, a bradykinesia speed metric, a freezing behavior metric (i.e., arrhythmicity), and / or a rigidity metric. Additionally, or alternatively, the characteristics and / or metrics calculated and / or determined via execution of step 410 may include 1) press amplitude, 2) press amplitude coefficient of variation (CV: standard deviation / mean), 3) inter-strike interval (ISI: time to complete one cycle of finger movement), 4) inter-strike interval CV (ISI CV), 5) release slope (i.e., ratio of the amplitude of the lever release compared to duration of release), 6) press speed (i.e., ratio of the amplitude of the lever press compared to duration of press), 7) dwell time (i.e., duration at bottom of the press), 8) rest tremor: average amplitude and frequency and % (RT%: percent of QDG trace with rest tremor) and / or 9) action tremor: average amplitude and frequency and % (RT%: percent of QDG trace with action tremor), press freezes, release freezes, amplitude freezes. At times, execution of step 410 may also include calculation of the average for each of these metrics for each finger and / or averaging these values across fingers for each hand.

[0097] In some embodiments, execution of step 410 may include calculation of a QDG mobility score using, for example, ISI, ISI CV, press speed, press amplitude, press amplitude CV, release speed, and / or dwell time. FIGs. 4B-4E provides examples of digitography data that may be received, wherein FIG. 4B provides a graph 402 of lever position in mm as a function of time, wherein labels for press amplitude, dwell time, release slope, release amplitude, and inter-strike interval (ISI) are superimposed thereon. FIG. 4C provides a screen shot of a panel 403 showing four different graphs of QDG RAFT / digitography data alternating between an index finger (shown in black) and a middle finger (shown in blue), wherein the data displayed in panel 403 corresponds to data collected from a health control. The first graph of panel 403 plots raw RAFT / digitography data lever position / displacement by the index and middle fingers in mm as a function of time over a 30 second interval, the second graph of panel 403 plots lever strike amplitude values in mm as a function of time over the 30 second interval, the third graph of panel 403 plots ISI values for each press of by the middle finger in milliseconds as a function of time over the 30 second interval, and the fourth graph of panel 403 plots dwell time (DT) values for each press by the middle finger in milliseconds as a function of time over the 30 second interval.

[0098] In some embodiments, execution of step 410 may include calculation of a mobility score may be calculated using Equation 1:1nMobility Scare ~ 100 — 14 x -tj<t V. / i -" J *.■nmlEquation 1 where z is the observed z-score for a given metric for the data point and n represents the total number of QDG metrics. In some embodiments, the mobility score may be normalized and / or ranged from 0 to 100, with 100 representing perfect mobility. At times, a sign of the z-score may be flipped in, for example, cases where a negative z-score would indicate worse performance (e.g., press amplitude, press speed, and release slope). In some embodiments, negative values (i.e., above average performance) may be capped at 0 so that above average performance in any metric does not artificially inflate the overall score. Given the tightly clustered distribution of press amplitudes around full amplitude in healthy controls (mean: 8.67 ± 0.12 mm), a calculation of the mobility score may have lower press amplitudes that may be primarily dominated by a high absolute press amplitude z-score value, which may diminish the impact of other metrics. In some embodiments, when an absolute press amplitude z-score value is greater than 10, which corresponded to a press amplitude below 7.5 mm, the press amplitude z-score value may be transformed using a power law equation to progressively decrease the impact of lower press amplitude values on the overall mobility score. In some embodiments, the press amplitude z-score may be adjusted using Equation 2:— A x f iVZpres& AmpJEquation 2 where A = 3.2 and k = 0.495. The equation parameters may be defined to ensure that a maximum transformed z-score value does not exceed 20. A continuous transition of transformed values may be maintained at a press amplitude z-score of 10, mitigating any potential discontinuities in the transformed values.

[0099] Additionally, or alternatively, execution of step 410 may include determining a tremor severity score, which classifies the presence of tremor on a per-strike basis using one or more of the QDG metrics described herein. To determine a tremor severity score, the strikes indicating tremor in a set of digitography data may be identified and the average amplitude of the tremor strikes may be determined and / or extracted from the data and scored based on a combination of the percent duration of tremor in the trial and the average amplitude of tremor using, for example, Equation 3, below:%Rest Tremor 4~ 100xTremor Severity — - - - ~ -Equation 3where Amp is the observed press amplitude for a given tremor strike, n represents the total number of identified tremor strikes, and AmpMax is the maximum possible amplitude on the digitography device (e.g., device 100). For trials with a low percent tremor (e.g., < 10%), the amplitude component may be transformed in order to suppress its impact on the overall tremor severity score using, for example, Equation 4, below:J DXTX gyftp _ Tremor),Equation 4 where A = 4, k = 0.05, and b = -1 and RTamp is the transformed normalized rest tremor amplitude. Additionally, or alternatively, execution of step 410 may include analyzing digitography data to isolate and / or remove data corresponding to emergent tremor data (e.g., strikes corresponding to tremor as opposed to voluntarily made strikes) so that accurate analysis of the digitography data may occur. At times, emergent tremor data may be identified within digitography data. Further information regarding the calculation of a tremor score and the identification of tremors within digitography data is provided in the figures and discussed below.[000100] In step 415, the digitography data, a characteristic of the digitography data, and / or a determined QDG metric value may be evaluated to determine one or more indications of a neurological condition such as depression, cognitive impairment, essential (action) tremor, stroke, traumatic brain injury, and / or weakness. Additionally, or alternatively, the analysis and / or evaluation of step 415 may determine if thedigitography data or features of it may be correlated with a neurological symptom such as brain injury, brain atrophy, brain degeneration, Parkinson’s disease, and / or depression. In some instances, step 415 may be performed by using a machine learning process and / or model trained using, for example, digitography data and / or patient data as, for example, described herein. Other characteristics may be evaluated to determine other musculoskeletal conditions, such as arthritis. In step 420, a result of executing step(s) 405, 410, and / or 415 may be provided to a user via, for example, a display device provided by, for example, computer system 330 the evaluation of step 415 and / or the indication(s) of depression and / or motion of the patient’s fingers that may be correlated with a neurological symptom may be provided to a user such as a clinician, attending physician, and / or neurologist.[000101] FIG. 4D provides a screen shot of a panel 404 showing four different graphs of QDG RAFT data for data collected from a PWP. The first graph plots raw QDG RAFT data lever position / displacement by the index and middle fingers in mm as a function of time over a 30 second interval with movement of the index finger shown in black and movement of the middle finger shown in dark grey. The second graph of panel 404 plots lever strike amplitude values in mm as a function of time over the same 30 second interval, the third graph of panel 404 plots ISI values for each press by the middle finger in milliseconds as a function of time over the 30 second interval, and the fourth graph of panel plots dwell time (DT) values for each press by the middle finger in milliseconds as a function of time over the 30 second interval.[000102] FIG. 4E provides a screen shot of an exemplary interface 405 showing exemplary analysis results for execution of step 410. In particular, FIG. 4E provides a graph showing raw QDG RAFT trace data from index and middle finger from a PWP (as may be received in step 405) in the form of amplitude changes of the index finger (shown in black) and middle finger (shown in dark grey) and an analysis of that data represented as histograms and accompanying normal distribution fits for data from the healthy control cohort for a plurality of different QDG metrics including press amplitude in mm as a function of count, ISI in ms as a function of count, press speed as a function of count, press amplitude CV as a function of count, ISI CV as a function of count, and release slope as a function of count. The vertical dashed line shown on each of the sixhistograms represents a value from the QDG RAFT trace data and its corresponding Z-score.[000103] FIGs. 5A and 5B provide screen shots of a first exemplary graphic user interface (GUI) 503 and a second GUI 502, respectively, that provides an example of the how the data, evaluation, data analysis, and reporting of step(s) 405, 410, and / or 415 may be provided to a user on a display device in step 420 for a patient with depression. First GUI 501 and second GUI 502 provide a mobility score, a graph of raw data wherein showing lever position in mm for a first (shown in red) and a second (shown in blue) lever as a function of time over a 30 second interval and values for taps per minute, rigidity (correlated to release speed), values for fast and action tremor, values for metrics that may indicate a degree of bradykinesia (correlated to lever press amplitude, lever press speed, and sequence effect), values for metrics that may indicate freezing behavior (correlated to arrhythmicity and percent time freezing), and values that indicate a percentage of time, a frequency, and a height of tremors for rest tremors and essential / action tremors. Values shown in green indicate values that are within the range of age-matched healthy controls, whereas the values in orange or red correspond to values that are outside the healthy control range.[000104] As may be seen in GUI 501 the patient demonstrates a low and / or out of normal range values for taps per minute (49), press speed (9.3 cm / sec), with normal release speed. These values and, in particular the low values for taps per minute and press speed while values for amplitude and release speed are closer to normal may indicate that the patient has depression. The patient also has fairly high symmetry between the lever strikes of the first and second levers, which may be an indication that the patient is not suffering from Parkinson’s Disease.[000105] As may be seen in GUI 502, the patient demonstrates a low and / or out of normal range values for taps per minute (47), and press speed (6.4 cm / sec) with normal release speed. These values and, in particular the low values for taps per minute and press speed while values for amplitude and release speed are closer to normal may indicate that the patient has depression. The patient also has fairly consistent high amplitude taps with each finger and does not show evidence of the sequence effect(progressive loss of amplitude and / or frequency of taps), which is more indicative of a movement disorder or neurological impairment such as Parkinson’s disease.[000106] FIG. 5C provides a screen shot of an exemplary graphic user interface (GUI) 503 that provides an example of the how the evaluation, data analysis, and / or reporting of step 415 may be provided to a user on a display device in step 420. GUI 503 provides patient bibliographic data such as patient name, test information, and an indication of whether the data corresponds to RAFT measurements for the left or right hand. In addition, GUI 503 provides a mobility score (in this case, 61), a tremor severity score (in this case, 1), and values for taps per minute, rigidity (correlated to release speed), values for fast and action tremor, values for metrics that may indicate a degree of bradykinesia (correlated to lever press amplitude, lever press speed, and sequence effect), and values for metrics that may indicate freezing behavior (correlated to arrhythmicity and percent time freezing). Values shown in green indicate that values are within the range of age-matched healthy controls, whereas the values in orange or red correspond to values that are outside the healthy control range. Optionally, GUI 503 may include a graph plotting lever position measurements in mm as a function of time.[000107] In some embodiments, method 400 may be executed repeatedly (e.g., periodically or on an as-needed basis) with a patient over time to, for example, monitor the patient’s psychological and / or neurological health, mood, energy level, and / or responsiveness to treatment over time. Additionally, or alternatively, method 400 may be executed before, during, and / or after an event (e.g., treatment with a medication or course of therapy, neurosurgery, or occurrence of an injury) to determine any differences in the digitography data from before, during, and / or after the event. In some embodiments, results and / or indications provided to the user in step 420 may be cumulatively evaluated in order to, for example, adjust a treatment regimen and / or digitography motion task routine performed by the patient and / or provide a recommendation regarding same.[000108] Method 400, or portions thereof, may be executed to assess, monitor, and / or diagnose neurological health and / or neurological disease progression for conditions such as depression, psychic tension that may be related to depression, psychomotor slowness that may be related to depression, cognitive impairment,essential (action) tremor, stroke, and / or weakness. For example, a sense of psychic tension that feels ‘heavy’ or restrictive is a very debilitating symptom of depression. However, there is currently no objective way to measure psychic tension. However, in some cases, depressive psychic tension may be the mood equivalent of muscular rigidity because the sense of psychic tension limits the person’s mood and thinking in a manner similar to how muscular rigidity limits the person’s movement of any part of the body that requires coordination of muscles. Thus, patients with psychic tension may produce digitography data showing more rigidity than age-matched healthy controls, thereby providing an objective way to measure psychic tension as well as responsiveness of the patient to one or more therapies (e.g., medication, deep brain stimulation, etc.) and, for these patients, improvements in psychic tension may be mirrored by an improvement in RAFT metrics indicating rigidity. Thus, method 400, and in particular RAFT rigidity measurements may be used to characterize people with different types and degrees of depression and their response to therapies.[000109] Additionally, or alternatively, method 400 may be executed to characterize and / or monitor psychomotor slowness for patients with depression. Psychomotor slowness may manifest as slowness of speech, thinking, and / or movement and, traditionally, there is no way to objectively measure psychomotor slowness. However, in some cases, psychomotor slowness may be the mood equivalent of bradykinesia (i.e., slowness of movement) and these patients may exhibit slower repetitive alternating finger tapping when performing RAFT than healthy controls. For example, patients with psychomotor slowness may have a number of taps in a given time period, a frequency of tapping, and / or an amplitude of press and / or release phases of the strikes / finger taps that differs from healthy controls. Thus, method 400, and in particular QDG RAFT metrics and / or values for bradykinesia, counted number of taps, frequency, and / or amplitude measurements may be used to characterize people with different types and degrees of depression and their response to therapies.[000110] Additionally, or alternatively, method 400 may be executed to characterize and / or monitor cognitive impairment and / or dementia, wherein digitography data generated by patients may be analyzed to determine correlations within the data and atrophy of the nucleus basalis of Meynert, an important brain structure in cognitivecircuitry thereby providing an objective metric with which to characterize people with different types and varying degrees of cognitive impairment and their response to therapies. In some embodiments, cognitive impairment may manifest in digitography data as slow (or low) values for taps per minute when, for example, compared with healthy age-matched controls, difficulty in alternating between fingers (e.g., consecutive taps of the same finger and / or double taps of both fingers striking their respective levers at the same (or nearly the same) time), galloping (e.g., longer interval between fingers 1 to 2 than between fingers 2 to 1), freezing behavior, and / or the presence of FoRAFT (freezing events) within the data.[000111] Additionally, or alternatively, method 400 may be executed to characterize and / or monitor working memory impairment, which may manifest within digitography data as changes in patterns present within the digitography data over the course of a digitography data recording session. For example, a patient with a working memory impairment may begin performing RAFT but after a number (e.g., 5, 10, 20, etc.) of cycles may lose the alternating pattern and deteriorate into one or more “non- RAFT” types of tapping (e.g., consecutive taps of the same finger and / or double taps of both fingers striking their respective levers at the same (or nearly the same) time).[000112] Additionally, or alternatively, method 400 may be executed to characterize and / or monitor concussion, which may manifest within digitography data as increased arrhythmicity and / or amplitude variability, slow taps per minute with compared with healthy age-matched controls, and other aspects of disordered cognition (e.g., non-RAFT types of tapping, irregular inter-strike intervals, etc.)[000113] Additionally, or alternatively, method 400 may be executed to characterize and / or monitor essential action tremor. People with essential action tremor have great difficulty performing tasks such as feeding themselves, using a toothbrush, putting on makeup, doing up buttons, and writing due to tremor that largely occurs during action. Currently tremor is assessed using a visual observation of how the person draws a spiral and a straight line. Wearable sensors can measure tremor if and when it occurs but need to be working for long periods of time to gather data. However, in some cases, patients with essential tremor may generate digitography data that differs from healthycontrols. The involuntary action tremor may result in loss of the alternating pattern and instead show synchronous, simultaneous tapping with both fingers / levers depressing and releasing at the same time. Thus, execution of method 400, may be used to measure and / or characterize the severity, frequency, type, degree, and duration of essential action tremor as well as patient response to one or more treatments and / or therapies.[000114] Additionally, or alternatively, method 400 may be executed to characterize and / or monitor fine motor control impairment and / or weakness that may be caused by, for example, concussion, stroke and / or traumatic head injury. Rehabilitation regimes and assessment for these conditions usually focuses on strength and exercises involving limb movement and gait but it is difficult to assess a patient’s responsiveness to these therapies because there are limited assessment tools for fine motor control to follow to determine the response to therapies. However, analysis of digitography data from these patients and, in particular, a resistance overcome by the patients when using the digitography device 100, system 200, and / or system 300 may be used to quantify fine motor control and weakness and measure changes in fine motor control and weakness over time. Thus, execution of method 400 may be used to characterize people with different types and degrees of stroke and their response to therapies.Weakness may manifest within digitography data as, for example, low amplitude tapping, difficulty performing press amplitude to the bottom of the lever excursion, increased sequence effect, slow taps per minute, and / or slow press speed.[000115] Additionally, or alternatively, method 400 may be executed to characterize and / or monitor disease progression and / or responsiveness to treatment for patients diagnosed with multiple sclerosis. In particular, digitography data and / or metrics for these patients of interest may be arrhythmicity and stiffness (slow release speed), low amplitude tapping, difficulty performing press amplitude to the bottom of the lever excursion, increased sequence effect, slow taps per minute, slow press speed, difficulty in alternating between fingers (e.g., consecutive taps of the same finger and / or double taps of both fingers striking their respective leversat the same (or nearly the same) time), galloping (e.g., longer interval between fingers 1 to 2 than between fingers 2 to 1 ), freezing behavior, and / or the presence of freezing behavior and events within the data[000116] Additionally, or alternatively, method 400 may be executed in response to, for example, an adverse event (e.g., fall or faint), head injury when, for example, concussion is suspected, and / or as a vital sign to perform an assessment of neurological health upon, for example, admittance to an emergency room and / or during a visit to a doctor’s office to avoid missing a potential underlying and / or asymptomatic neurological diagnosis that may, for example, have directly and / or indirectly lead to the adverse event. In these embodiments, a patient may perform QDG-RAFT for a time period (e.g., 30 or 60 seconds) and analysis of the resulting data may be used to provide, in real time or nearly real time, an accurate assessment of motor function as well as a probability of an underlying neurological diagnosis (e.g., Parkinsonian syndrome, stroke, etc.). This can be completed along with the other vital signs and will be available for the emergency clinician and / or attending caregiver, which may aid in determining whether or not to call a consultant with neurological expertise which may increase earlier access to neurological care for patients, especially patients not living close to a neurologist.[000117] Additionally, or alternatively, method 400 may be executed to determine a responsiveness of a patient or study subject to a treatment and / or medical intervention. For example, process 400 may be executed prior to treatment or at a baseline time during receipt of treatment to obtain a baseline set of digitography data and / or evaluations of digitography data (e.g., one or more of a rigidity score, a bradykinesia score, a amplitude, a frequency, a freezing behavior score, a mobility score, a number of taps per minute, a degree of arrhythmicity, a degree of irregularity, a degree of asynchronicity between the digitography data of the patient’s right hand and the patient’s left hand, a tremor score, and / or an ability to do alternate fingers correctly). Then, method 400 may be executed at one or more later point(s) in time (e.g., minutes, hours, days, weeks, months, and / or years) to receive subsequently performed digitography data and / or subsequently perform evaluation(s) (step 415) that may be compared with the baseline value to determine differences therebetween. Thesedifferences may be used to, for example, determine disease progression and / or responsiveness to treatment. In one example, repeated execution of process 400 over time may be performed to evaluate a patient’s responsiveness to arthritis treatment, wherein pre-treatment data for the patent may have a relatively low number taps per minute, relatively high freezing and / or rigidity scores, and / or a relatively low amplitude when compared to healthy controls and improvements of any of these metrics may indicate that the treatment is effective.[000118] In another example, method 400 may be executed over time to evaluate the effectiveness of treatment with a brain-computer interfaces and / or deep brain stimulation devices. In these embodiments, process 400 may be executed a plurality of times over relatively short intervals (e.g., seconds, minutes, hours, days) to, for example, determine where (e.g., different brain regions) and / or how (e.g., type, frequency, and / or intensity of stimulation) to stimulate the brain and / or regions of the brain. For example, different manners of stimulating a patient’s brain may be tried with a brain-computer interfaces and / or deep brain stimulation devices until an evaluation of the digitography data via execution of process 400 indicates an improvement in one or more metrics and / or a metric that approaches a “normal” value for an age matched healthy control.[000119] FIGs. 6A-6D provide screen shots of GUI 601, 602, 603, and 604, respectively, that include values for a mobility score both on (in green) and off (in red) medication, graphs showing a QDG-RAFT data trace when a PWP is on (in green) and off medication (in red) along with graphs that show values for press amplitude, ISI, press speed, press amplitude CV, ISI CV, arrhythmicity, and rigidity on and off medication. In particular, GUI 601 of FIG. 6A shows a first QDG-RAFT trace for a first PWP off medication with large (close to normal) amplitude presses but a slow speed of tapping and a first QDG-RAFT for the first PWP on medication trace wherein it may be seen that the speed of tapping (both the press speed and tap duration (ISI)) improved and this was reflected in an improvement of the QDG Mobility Score from 68 off medication to 86 on medication. GUI 602 of FIG. 6B provides a second QDG-RAFT trace for a second PWP off medication with low, varied amplitude RAFT, with slow press and release speeds and low frequency, off medication and a second QDG-RAFTtrace for the second PWP on medication, wherein the mean press amplitude and speed of tapping improved, alongside improvements in sequence effect and rigidity so that the mobility score increased from 41 while off-medication to 90 while on medication. GUI 603 of FIG. 6C provides a third QDG-RAFT trace for a third PWP who is tremor dominant off medication. Their performance off medication revealed full amplitude strikes and only mildly impaired voluntary tapping, as demonstrated by a mobility score of 86. However, this individual demonstrated tremor for 9% of the trial with an average amplitude of 7.1 mm. This corresponded to a tremor severity score of 40. On medication (see e.g., third QDG-RAFT trace on medication), there was a small improvement in the already high mobility score of 91 and a noticeable reduction in tremor, which was now only present for 3% of the trial and the tremor severity score reduced to 11. GUI 604 of FIG. 6D provides a fourth QDG-RAFT trace for a fourth PWP off medication and a fourth QDG-RAFT trace for the fourth PWP on medication, wherein the tremor of the fourth PWP did not respond to medication. Off medication, the fourth PWP showed significantly impaired voluntary tapping marked by low amplitude presses and loss of amplitude overtime (i.e., sequence effect) resulting in a mobility score of 26. This individual also had tremor for 18% of the trial with an average amplitude of 5.7 mm, resulting in a tremor severity score of 41. On medication, the mobility score of the fourth PWP improved to a 59 due to improvements in amplitude, press speed, and sequence effect. However, they still showed tremor for 20% of the task with a tremor severity score of 49.[000120] FIG. 7A is a flowchart showing a process 700 for analyzing a plurality of sets of QDG motion capture data (e.g., QDG RAFT data) generated by a PWP using a motion capture device like digitography device 100 to measure, evaluate, and / or assess one or more characteristics of PD. The plurality of sets of QDG RAFT data may be received over time (e.g., days, weeks, and / or months) to, for example, remotely monitor the PWP to, for example, monitor disease progression, compliance with treatment and / or responsiveness to treatment. Process 700 may be executed by, for example, digitography device 100, and / or system(s) 200 and / or 300.[000121] Initially, a plurality of sets of QDG motion capture data and / or QDG RAFT data may be received (step 705) by, for example, processing device 210 and / orcomputer system 330. Each set of the plurality of sets may be associated with a different QGD RAFT session, which may be associated with the QDG RAFT data as, for example, a timestamp (e.g., day, date, time of day, etc.). In some embodiments, the plurality of QDG RAFT data sets may be received one at a time (e.g., as they are captured or recorded), or in bulk (e.g., a plurality of sets captured over a period of time (e.g., day, week, or month). Each set of the QDG RAFT may be similar to the QDG RAFT data received in step 405 as discussed above with regard to FIG. 4.[000122] In some embodiments, the data of one or more of the plurality of sets of QDG motion capture data received in step 705 may be raw data and in other embodiments, it may be pre-processed and / or filtered to, for example, remove noise and / or outlying measurements. The pre-processing may be performed by, for example, processing device 210 prior to communication of data to an external computing device like computer system 330.[000123] In step 710, each set of the QDG RAFT data received in step 705 may be processed and / or analyzed to determine one or more characteristics thereof and / or a value for one or more metrics that may be indicated by the QDG RAFT data of each respective set. Execution of step 710 may be similar to execution of step 410 and the characteristic(s) determined via execution step 710 may be similar to those determined via execution of step 410.[000124] Optionally, in step 715, treatment information for the patient may be received. Treatment information may include, but is not limited to, a type, dosage, and / or time of day a medication is taken by the patient and / or a type and / or time of day a PWP participated in a physical therapy regimen (e.g., daily walk or lifting weights).[000125] In step 720, sets of the QDG RAFT data, a characteristic of the sets QDG RAFT data, treatment information, and / or a determined QDG metric value may be evaluated individually, and / or in combination, to determine an indication of a motor and / or neurological impairment, a trend for the PWP, and / or a responsiveness of the patient to the treatment. In step 725, the data received in step 705, a result of the evaluation of step 720 and / or the indication(s) of motor impairment and / or motion of the patient’s fingers that may be correlated with one or more neurological symptom(s) may be provided to a user (e.g., a clinician, attending physician, and / or neurologist). In someembodiments, process 700 may be executed remotely from, for example, a patient’s home or workplace, thereby enabling remote monitoring of the patient’s PD symptoms and / or responsiveness to treatment.[000126] FIG. 7B provides a screen shot of a QDG analysis results web dashboard, or GUI, 701 that may be provided to the user via execution of process 700 and / or step 725. QDG web dashboard 701 provides information (e.g., evaluations of step 720 and treatment information of step 715) for a plurality sets of QDG RAFT data taken or recorded over a single day of testing for a PWP and, in particular, plots data for the metrics (evaluated / determined in step 720) of bradykinesia, specifically press amplitude (a), press speed (b), and sequence effect (c). On the day represented, the PWP completed a first test when he was feeling poorly (e.g., the worst he felt all day) at 7 am and a second test when the PWP was feeling better (e.g., the best the PWP felt all day) at 11 am as denoted by the circular data points on the chart. The red circles correspond to QDG metric values that deviate from the range of metric values for healthy controls, while the green circles correspond to metric values that fall within the range for healthy controls. The ‘Rx’ markings designate time points when the PWP is prescribed to take PD medications as decided by their neurologist, while filled ‘Rx’ markings with a solid line indicating when the PWP participant actually took the medication. As may be seen in FIG. 7B, the participant’s metrics of bradykinesia improved after they took medication and the values moved from the abnormal to normal range. The data plots of FIG. 7B demonstrate that QDG metrics reflect changes in motor symptoms in relation to medication intake over the course of a single morning while also providing the time the PWP took medication compared to the time it was prescribed to gauge their ability to adhere to the frequent dosing schedule. Additionally, the data shown in FIG. 7B may provide insight into how small changes in medication dosing can impact motor symptoms on a longer-term scale for the PWP.[000127] Figure 7C provides a screenshot of an exemplary QDG web dashboard, or GUI, 702 that may be provided to the user via execution of process 700 and / or step 725. GUI 702 provides data (in this case, values for mobility score, amplitude, and arrhythmicity determined in step 720) corresponding to a plurality sets of QDG motion capture data remotely obtained for one participant’s left hand over a 32-day period (i.e.,one set of QDG RAFT data received each day during the 32-day period). This PWP, in the early stages of PD, experienced gait as the most bothersome symptom. Their MDS-UPDRS III gait sub-score improved from 2 to 1 after starting a regimen of immediate-release carbidopa / levodopa (CD / LD) taken three times a day. This was matched by the PWP’s and their family’s perception that their gait and facial expression improved in response to the medication in general, although they did not notice any specific difference in symptom severity correlated to specific and / or individual doses, as is typical in early stage PD. The participant took the first medication dose at 6:00 am. The second dose was taken at approximately 9:30 am, preceding a daily walk roughly 30 min later. They decided to try taking an extra dose of CD / LD at the second prescribed time to see if it would improve their walking further (dashed line Fig. 7C). This resulted in noticeable improvements in the QDG metrics, wherein the PWP’s QDG-mobility score (see first graph “a” of FIG. 7C), bradykinesia-amplitude (see second graph “b” of FIG.7C), and arrhythmicity (see third graph “c” of FIG. 7C), scores for the left hand improved from abnormal to within the normal range over time. This improvement was accompanied by a reduction in day-to-day variability, suggesting a more consistent response to the extra dose of medication.[000128] FIG. 7D provides a screen shot of a GUI 703 of a QDG web dashboard tracking QDG mobility score for a PWP over time that may be prepared and / or provided to a user via execution of process 700 and / or step 725, wherein a first graph of GUI 703 shows QDG mobility scores for the PWP’s right hand and a second graph shows data for the PWP’s left hand over a time period of 26 days following a probable PD diagnosis and before initiation of therapy, wherein red circles represent abnormal values and green circles represent normal values. As may be seen in the graphs of FIG. 7D, the progression of Parkinsonian motor disability is more severe for this participant’s left hand within the first month after receiving the clinical diagnosis of probable PD and before any treatment was initiated. Throughout the study period, the PWP’s right (lesser affected) hand consistently maintained a QDG Mobility Score of 100 (maximum score). In contrast, the left (more affected) hand showed a significant decline in the QDG mobility score over time (FIG. 7C, linear regression: = -1.18 [-1.70 -0.67], R2=-0.74, p = 1.2e-4).[000129] FIG. 7E provides a screen shot of a GUI 704 of a QDG web dashboard tracking QDG mobility score for a PWP over time (in this case, 26 days) that may be prepared and / or provided to a user via execution of process 700 and / or step 725 for two PWP who are being remotely monitored. A first graph of GUI 704 shows QDG mobility scores for a first PWP’s left hand over 26 days and a second graph shows data for a second PWP’s left hand over a time period of 26 days, wherein green circles indicate normal (e.g., associated with healthy controls) values and red circles indicate abnormal values. The dashed lines of the first and second graphs indicate when an adjustment in therapy was made during the 26 day interval.[000130] In some embodiments, process(es) 400 and / or 700 may be executed repeatedly (e.g., periodically or on an as-needed basis) with a patient over time to, for example, monitor the patient’s neurological health, motor skills, and / or responsiveness to treatment over time. Additionally, or alternatively, process(es) 400 and / or 700 may be executed before and after an event (e.g., neurosurgery, change in treatment, and / or an injury) to determine any differences in the QDG RAFT data from before and after the event. In some embodiments, results and / or indications provided to the user in step 420 may be cumulatively evaluated in order to, for example, adjust a treatment regimen and / or QDG motion exercise routine performed by the patient and / or provide a recommendation regarding same. In some embodiments, raw data and / or analysis of the QDG RAFT data may be added and / or inserted into the participant’s electronic medical record on a periodic and / or as-needed basis so that, for example, the PWP may be remotely monitored to, for example, determine treatment compliance and / or symptom severity.[000131] In some instances, evaluation of QDG RAFT data may be impaired and / or confounded by a PWP’s tremor. For example, rest tremor is present in over 70% of PWP and often occurs at frequencies between 4 and 7 Hz. Rest tremor is usually suppressed with the onset of action but can emerge during sustained movement (such as walking or performing QDG RAFT exercises) and when a posture of the hand or limb is sustained.[000132] In particular, the emergence of tremor can confound the clinical assessment of bradykinesia. For example, while performing a QDG RAFT exercise, thethumb may be held in a fixed posture, and regular amplitude, high-frequency finger movement that is actually tremor can be interpreted as voluntary movement, leading to an underestimated bradykinesia score. Conversely, bradykinesia may be overestimated when intermittent tremor interrupts voluntary movement and causes irregularities in tapping, which may be interpreted as hesitations. On the clinical scale, there is no way to isolate involuntary emergent tremor from voluntary movements which is crucial to ensure a more accurate and dependable measurement of Parkinsonian symptom severity.[000133] Analysis of QDG RAFT data to identify instances and / or periods of tremor may allow for identifying and / or capturing unique temporal characteristics of tremor so that emergent tremor may be accurately identified and, consequently, indications for bradykinesia and rigidity may be more reliably based on voluntary tapping only (e.g., not confounded by tremor).[000134] In some embodiments, the QDG RAFT data may be analyzed to isolate tremor data so that, for example, a tremor score may be determined and / or lever strikes made as a result of tremor(s) are removed from the data used to calculate values for one or more metrics disclosed herein. FIG. 8 is a flowchart providing an exemplary process 800 for identifying and removing tremor data from QDG RAFT data.Additionally, or alternatively, process 800 may be executed to identify a unique digital signature for emergent tremor(s) during QDG-RAFT, which could be used to reliably identify, isolate, and / or remove strikes induced by tremor(s) within QDG RAFT data and assist with distinguishing involuntary tremor-based movement from voluntary strikes, thereby enabling a more representative measurement of voluntary motor signs such as bradykinesia and rigidity based on voluntary strikes only. Process 800 may be executed by, for example, system(s) 200 and / or 300.[000135] Initially, a plurality of tremor-labeled QDG RAFT datasets may be received. The tremor-labeled QDG RAFT datasets may be generated via, for example, visual observation of a PWP while they generate a QDG RAFT dataset to determine when tremor is observed and then labeling the QDG RAFT dataset with the times at which and / or durations over which the PWP demonstrated tremor. The visual observation and / or labeling may be performed by, for example, a blinded movementdisorders specialist who is, for example, in the room while the PWP generates the QDG RAFT dataset, is remotely observing the PWP, and / or watches a video recording of the PWP while he or she notates when, during the generation of the QDG RAFT tremor occurred, thereby generating tremor-labeled QDG RAFT dataset(s). In some embodiments, one or more of the plurality of tremor-labeled QDG RAFT datasets received in step 805 may include subsets of tremor-labeled QDG RAFT data relating to, for example, raw QDG RAFT data, amplitude (Amp), inter-strike-distance (ISI), and / or dwell time (DT). FIG. 9A provides a screen shot of an exemplary panel 901 providing an exemplary tremor-labeled QDG RAFT dataset for emergent tremor in a tremor-dominant PD phenotype that includes various tremor-labeled subsets of data labeled to indicate when tremor and / or emergent tremor occurs and / or is a cause for movement present within the QDG RAFT dataset, wherein the dashed blue lines represent exemplary ISI (225 ms) and dwell time (85 ms) thresholds investigated to classify tremor strikes.[000136] In step 810, each tremor-labeled QDG RAFT dataset may be analyzed to, for example, identify one or more characteristics of the tremor(s) included therein and / or determine how tremor may be distinguished from voluntary movement with each respective tremor-labeled QDG RAFT dataset and / or the plurality of tremor-labeled QDG RAFT dataset(s). The results of the analysis of each tremor-labeled QDG RAFT dataset may then be aggregated or otherwise combined to, for example, statistically identify markers, or characteristics, of tremor present within the plurality of tremor-labeled QDG RAFT datasets and / or determine how tremor strikes differ from voluntary strikes within the QDG RAFT datasets. Table 1 provides exemplary data that demonstrates differences between ISI, DT, peak duration, release duration, release slope, press duration, release amplitude, and press amplitude for tremor lever strikes and voluntary lever strikes in terms of D, P-value, median of tremor strikes and median of no-tremor strikes. The values of Table 1 may be used to differentiate between tremor-induced lever strikes and voluntary lever strikes within QDG RAFT data as, for example, described herein.Metric D P-value Median of Tremor Median of NonStrikes Tremor Strikes ISI 0.88 <0.001 186 [163.25207] 491 [341 654]Dwell Time 0.64 <0.001 46

[2070] 140

[90207] Peak Duration 0.45 <0.001 68 [33.2597] 148

[69294] Release 0.44 <0.001 38

[3049] 63 [45 105] DurationRelease Slope 0.30 <0.001 0.20 [0.130.26] 0.13 [0.070.19] Press Duration 0.19 <0.001 27

[1942] 37

[2464] Release 0.18 <0.001 8.72 [6.168.83] 8.78 [8.678.83] AmplitudePress 0.18 <0.001 8.72 [6.498.83] 8.78 [8.678.83] AmplitudeTABLE 1[000137] Optionally, in step 815, tremor percentage within the datasets of step 805 may be correlated with clinical ratings of tremor severity and / or persistence using, for example, the MDS-UPDRS III for each PWP and their respective tremor-labeled QDG RAFT dataset and a result of this correlation may be used to validate tremor characteristics within QDG-RAFT datasets. In some instances, the correlation between tremor percentage and the weighted overall MDS-UPDRS III tremor score (postural + kinetic tremor + 0.5(rest tremor severity + constancy of rest tremor); rho = 0.50, p = 2.34e-4 may be strongest. Percent tremor may also be significantly correlated with the sum of rest tremor severity and consistency scores ((rho = 0.45, p = 0.0012), with the constancy score itself (rho = 0.43, p = 0.0019), and with the sum of rest + postural tremor scores (rho = 0.35, p = 0.0068).[000138] In step 820, a set of tremor characteristics as they appear in QDG RAFT datasets may be finalized and optionally used to analyze new sets of QDG RAFT data that are not tremor-labeled. For example, in step 825 a new set of QDG RAFT data may be received from a PWP and analyzed for the presence of tremor using the finalized tremor characteristics of step 820 (step 830). If no tremor is present, then process 800 may proceed to step 410 for further analysis of the QDG RAFT data received in step 825. If tremor is present, data corresponding to tremor strikes may be removed from theQDG RAFT dataset received in step 825 and then process 800 may proceed to step 410 for further analysis.[000139] Table 903 provides data that demonstrates a change in the values for the QDG metrics of bradykinesia, rigidity, and arrhythmicity after exclusion of tremor strikes in trials performed by tremor dominant (TD) individuals over 85 trials. The data of table 903 shows that values for metrics related to bradykinesia, rigidity, and arrhythmicity are more accurate after exclusion of tremor strikes via execution of process 800.Metric z p-Value Dwell Time 6.90 5.17e-12ISI 6.27 3.50e-10ISI CV -6.04 1,56e-09 Press Amplitude 3.92 9.00e-05 Release Slope -3.35 8.15e-04 Press Amplitude CV -3.12 0.0018TABLE 2[000140] FIG. 9B provides a screen shot of an exemplary panel 904 providing a plurality of scatter plots of percent duration of tremor in trial (%T) and change in metrics measuring bradykinesia (ISI, press amplitude, and press amplitude CV), rigidity (release slope), arrhythmicity (ISI CV) and dwell time after the exclusion of tremor in TD Trials (n = 85), wherein blue markers are indicative of the trials with >5%T (n = 26) and the grey markers indicate trials with <5%T (n = 59). The Rho and p-values reported in panels a-f indicate that the correlation between %T and change in metrics after the exclusion of tremor strikes in TD trials with >5% %T (n = 26). It may be seen in the data of panel 904 that the change in metrics (press amplitude, press amplitude CV, and release slope, in particular) was non-uniform and dependent on the prevalence of tremor (e.g., %T) in the trial. Although there was no significant correlation between the change in press amplitude, press amplitude CV, and %T when all TD trials were included (n = 85), there was a significant correlation between the change in press amplitude (Rho = -0.69, p = 1,17e-4) and press amplitude CV (Rho = 0.63, p = 6.53e-4) when trials with <5% %T were excluded from the analysis (n = 26). Further information about this is providedTable 3, which provides data regarding sensitivity and false-positive rates of different temporal threshold combinations and XGBoost, a machine learning architecture used to perform some (or all) of the analysis and calculations of process 800.Dataset Tested ISI Dwell Time Sensitivity False- Threshold Threshold (%) Positive (ms) Rate (%) Dataset 1, evaluated using 216 70 50.00 4.30 temporal thresholdsDataset 1, evaluated using 225 80 68.19 6.82 temporal thresholdsDataset 1, evaluated using 225 85 73.45 7.49 temporal thresholdsDataset 1, evaluated using 230 85 75.61 8.72 temporal thresholdsTest set (25% of Data set 2) 225 85 79 6.7 evaluated using temporalthresholdsTest set (25% of Data set 2) 98 2.7 evaluated using XGBoostClassifierTABLE 3[000141] In some embodiments, some, or all, of the steps of process 800 and, in particular, execution of steps 805-820, may be performed as part of a machine learning routine and / or via a machine learning and / or artificial intelligence computer system and / or architecture including, but not limited to XGBoost.[000142] FIG. 10 is a flowchart showing a method 1000 fortraining and using a depression assessment model. Method 1000 may be executed by, for example, digitography device, system 200, system 300, and / or components thereof.[000143] Initially, in step 1005, a plurality (e.g., 100-10,000,000) of sets of digitography data and corresponding depression diagnosis, depression symptomology,and / or additional patient information may be received by, for example, a processor and / or computer such as computing system 330, and / or cloud computing platform 310. In some embodiments, the digitography data may include and / or be used to determine one or more of a mobility score, a rigidity score, a freezing behavior score, a tremor severity score, a taps per minute value, a bradykinesia scores, an indication of arrhythmicity between fingers and / or left and right hands of a person contributing the digitography data, and / or a frequency and / or amplitude of key strikes within a set of digitography data.[000144] One or more of the plurality of sets of digitography data and / or corresponding additional information may be received from a database like cloud-based database 350, local database 340, and / or an electronic medical record database populated and / or maintained by a medical facility (e.g., hospital or medical treatment provider). The corresponding additional information received in step 1005 may be, for example, medical and / or demographic information about the patient, a diagnosis of the patient, a type of depression the patient is diagnosed with, a treatment the patient is, or has, received, and / or an outcome of treating the patient. The sets of digitography data received in step 1005 may include digitography data for individuals diagnosed with varying types of depression with varying degrees of severity and symptomology. In addition, the sets of digitography data received in step 1005 may include digitography data generated by health controls with varying ages, demographic details, medical histories, and / or comorbidities.[000145] In step 1010, the plurality of sets of digitography data and corresponding additional information may be divided into a training set of data and a testing set of data. The additional data may be, for example, depression diagnoses, symptoms, medication, treatment, lab tests, images (e.g., MRI and / or ultrasound), co-morbidities, electronic medical records, and the like. In many instances, the additional data may be correlated with a patient / participant identifier and / or a timestamp (e.g., date, time of day, location, etc.), and / or a source (e.g., electronic medical record, digitography device 100, computer 330, local database 340, and / or cloud-based database 350) of the respective set (or plurality of sets) of digitography data. A set of machine learning inputs and / or parameters for a machine learning architecture for the generation of a depressionassessment model may then be selected, set, and / or determined (step 1015).Exemplary inputs and / or parameters include one or more QDG metrics and correlations between QDG metrics and depression, psychomotor symptoms, and / or the additional information. In some embodiments, the inputs received in step 1015 may select a machine learning, or model, architecture that may be, for example, a deep neural network (DNN), a convolutional neural network (CNN) tailored for temporal signal features, and / or a robust ensemble classifier such as a random forest and / or a gradient boosting machine (e.g., XGBoost). In some implementations, recurrent neural networks (RNNs) and / or long short-term memory networks (LSTMs) may be used.[000146] In step 1020, a depression assessment model may be generated and / or trained by running the training set through the machine learning architecture of step 1015. In some embodiments, execution of step 1020 may include training a model to understand relationships and / or correlations between digitography data and / or analysis of digitography data (e.g., mobility scores, rigidity scores, freezing behavior scores, tremor severity scores, taps per minute, and / or bradykinesia scores) and depression diagnosis, depression symptomology, and / or additional patient information so that, for example, a set of a patient’s digitography data (or a series of sets of digitography data for a patient) may be input into the depression assessment model to, for example, determine characteristics of the patient’s neurological health and, in particular, determine whether the patient may be suffering from depression and, if so, what may be causing the depression and / or how the patient may be expected to respond to one or more different types of treatment. Additionally, or alternatively, the depression assessment model may be configured to evaluate a patient’s digitography data and / or scores (e.g., mobility scores, rigidity scores, freezing behavior scores, tremor severity scores, taps per minute, and / or bradykinesia scores) determined therefrom over time to, for example, determine treatment effectiveness and / or disease progression over time.[000147] Once training is complete (step 1025), the depression assessment model may be tested using the testing data set. Testing of the depression assessment model may involve, for example, inputting one or more sets of digitography data into the depression assessment model of step 1020 and comparing an output of the depression assessment model to a known output (e.g., diagnosis or treatment outcome) associatedwith the input digitography data. Results of the testing of the depression assessment model may then be evaluated (step 1030) and if the results of the testing are sufficiently accurate (e.g., within a margin of error or a standard of deviation of error) or otherwise in line with expectations (step 1035), the testing and / or training of the depression assessment model may be complete and method 1000 may end. When the results of the testing are not sufficiently accurate or otherwise in line with expectations, the depression assessment model may be tuned, updated, or otherwise adjusted responsively to the evaluation (step 1040) and steps 1020, 1025, 1030, and / or 1035 may be iteratively repeated.[000148] FIG. 11 is a flowchart showing a method for using a depression assessment model to evaluate a set of digitography data for a patient according to, for example, step 415 of method 400. Method 1100 may be executed by, for example, digitography device 100, system 200, system 300, and / or portions or components thereof.[000149] In step 1105, a set of digitography data for a patient may be received by, for example, a processor and / or computer such as processing device 210, computing system 330, and / or cloud computing platform 310. The set of digitography data for the patient may be received from, for example, digitography device 100, computer 330, local database 340, and / or cloud-based database 350. Optionally, additional information about the patient as, for example, described herein may also be received in step 1105. A depression assessment model similar to the depression assessment model generated via method 1000 may be accessed (step 1110) and the received set of digitography data and additional information about the patient (when received) may be input into the depression assessment model (step 1115). Then, an output of the depression assessment model may be determined (step 1120) and provided (step 1125) to a user (e.g., the patient and / or a care giver of the patient). Exemplary outputs determined in step 1120 include, but are not limited to, a diagnosis, a diagnosis of a particular type of depression the patient may be suffering from, a treatment recommendation, and a prediction for responsiveness of the patient to a treatment.[000150] Process(es) 1000 and / or 1100 may be adapted to train and / or use an assessment model for one or more neurological conditions (e.g., working memoryimpairment, essential action tremor, fine motor control impairment, cognitive impairment, weakness, multiple sclerosis, and / or concussion) in addition to, and / or instead of, depression.[000151] FIG. 12 is a flowchart showing a method 1200 for training a traumatic brain injury assessment model. Exemplary traumatic brain injuries include, but are not limited to, injuries caused by, for example, stroke, physical trauma (e.g., blunt and / or acute trauma) and may manifest as, for example, concussion, altered states of consciousness, paralysis, intellectual problems, pain, neurodegenerative diseases (e.g., Parkinson's disease, Alzheimer’s disease, dementia, etc.), and other symptoms.Method 1200 may be executed by, for example, digitography device 100, system 200, system 300, and / or portions or components thereof.[000152] In step 1205, a plurality (e.g., 100-10,000,000) of sets of digitography data and corresponding traumatic brain injury diagnoses, traumatic brain injury related symptomology, and / or additional information may be received by, for example, a processor and / or computer such as computing system 330, and / or cloud computing platform 310. One or more of the plurality of sets of digitography data and / or corresponding additional information may be received from a database like cloud-based database 350, local database 340, and / or an electronic medical record database populated and / or maintained by a medical facility (e.g., hospital or medical treatment provider). The corresponding additional information received in step 1205 may be, for example, medical and / or demographic information about the patient, a diagnosis of the patient (e.g., whether the patient has sustained a traumatic brain injury, when the traumatic brain injury was sustained, symptoms associated with the traumatic brain injury, etc.), a treatment the patient is, or has, received for the traumatic brain injury and / or a symptom of the traumatic brain injury, and / or an outcome of treating the patient. The sets of digitography data received in step 1205 may include digitography data for individuals diagnosed with varying types of traumatic brain injury with varying degrees of severity and symptomology. In addition, the sets of digitography data received in step 1205 may include digitography data generated by health controls with varying ages, demographic details, medical histories, and / or comorbidities.[000153] In step 1210, the plurality of sets of digitography data and corresponding additional information may be divided into a training set of data and a testing set of data. The additional data may be, for example, traumatic brain injury diagnoses, symptoms, medications, treatments, lab tests, images (e.g., MRI and / or ultrasound), comorbidities, electronic medical records, and the like. In many instances, the additional data may be correlated with a patient / participant identifier and / or a timestamp (e.g., date, time of day, location, etc.), and / or a source (e.g., electronic medical record, digitography device 100, computer 330, local database 340, and / or cloud-based database 350) of the respective set (or plurality of sets) of digitography data. A set of machine learning inputs and / or parameters for a machine learning architecture for the generation of a traumatic brain injury assessment model may then be selected, set, and / or determined (step 1215). Exemplary inputs and / or parameters include one or more QDG metrics and correlations between QDG metrics and traumatic brain injury, or symptoms of traumatic brain injury (e.g., short-term symptoms, long-term symptoms, and / or long-term risk factors), psychomotor symptoms, and / or the additional information. In some embodiments, execution of step 1215 may resemble execution of step 1015.[000154] In step 1220, a traumatic brain injury assessment model may be generated and / or trained by running the training set through the machine learning architecture of step 1215. In some embodiments, execution of step 1220 may include training a model to understand relationships and / or correlations between digitography data and / or analysis of digitography data (e.g., mobility scores, rigidity scores, freezing behavior scores, tremor severity scores, taps per minute, and / or bradykinesia scores) and one or more traumatic brain injury diagnosis, traumatic brain injury symptomology, and / or additional patient information so that, for example, a set of a patient’s digitography data (or a series of sets of digitography data for a patient) may be input into the traumatic brain injury assessment model to, for example, determine characteristics of the patient’s neurological health and, in particular, determine whether the patient may be suffering from traumatic brain injury, a condition that may be resultant from and / or otherwise correlated to traumatic brain injury (e.g., Parkinson’s disease, stroke, etc.), and / or evaluate risk factors for a patient diagnosed with traumatic brain injury developing other conditions, and / or how the patient may be expected torespond to one or more different types of treatment. Additionally, or alternatively, the traumatic brain injury assessment model may be configured to evaluate a patient’s digitography data over time to, track symptom progression, determine trends or other indications with the digitography data and / or scores (e.g., mobility scores, rigidity scores, freezing behavior scores, tremor severity scores, taps per minute, and / or bradykinesia scores) determined therefrom, and / or determine treatment effectiveness and / or disease progression over time.[000155] Once training is complete (step 1225), the traumatic brain injury assessment model may be tested using the testing data set. Testing of the traumatic brain injury assessment model may involve, for example, inputting one or more sets of digitography data into the traumatic brain injury assessment model of step 1220 and comparing an output of the traumatic brain injury assessment model to a known output (e.g., diagnosis or treatment outcome) associated with the input digitography data. Results of the testing of the traumatic brain injury assessment model may then be evaluated (step 1230) and if the results of the testing are sufficiently accurate (e.g., within a margin of error or a standard of deviation of error) or otherwise in line with expectations (step 1235), the testing and / or training of the traumatic brain injury assessment model may be complete and method 1200 may end. When the results of the testing are not sufficiently accurate or otherwise in line with expectations, the traumatic brain injury assessment model may be tuned, updated, or otherwise adjusted responsively to the evaluation (step 1240) and steps 1220, 1225, 1230, and / or 1235 may be iteratively repeated.[000156] FIG. 13 is a flowchart showing a method for using a traumatic brain injury assessment model like the traumatic brain injury assessment model generated via execution of method 1200 to evaluate a set of digitography data for a patient. Method 1300 may be executed by, for example, digitography device 100, system 200, system 300, and / or portions or components thereof.[000157] In step 1305, a set of digitography data for a patient may be received by, for example, a processor and / or computer such as processing device 210, computing system 330, and / or cloud computing platform 310. The set of digitography data for the patient may be received from, for example, digitography device 100, computer 330,local database 340, and / or cloud-based database 350. Optionally, additional information about the patient as, for example, described herein may also be received in step 1305. A traumatic brain injury assessment model similar to the traumatic brain injury assessment model generated via method 1200 may be accessed (step 1310) and the received set of digitography data and additional information about the patient (when received) may be input into the traumatic brain injury assessment model (step 1315). Then, an output of the traumatic brain injury assessment model may be determined (step 1320) and provided (step 1325) to a user (e.g., the patient and / or a care giver of the patient). Exemplary outputs determined in step 1320 include, but are not limited to, a diagnosis, a diagnosis of a particular type of traumatic brain injury the patient may be suffering from, a treatment recommendation, a prediction for responsiveness of the patient to a treatment, and / or a potential risk factor (e.g., percentage) for a developing Parkinsonism.[000158] FIG. 14 is a flowchart showing a method 1400 for training a Parkinsonism assessment model configured to, for example, assess progression of Parkinson’s disease, evaluate risk factors for developing Parkinson’s disease, and detect and / or diagnose Parkinson’s disease using digitography data. Method 1400 may be executed by, for example, digitography device 100, system 200, system 300, and / or portions or components thereof.[000159] In step 1405, a plurality (e.g., 100-10,000,000) of sets of digitography data and corresponding additional information may be received by, for example, a processor and / or computer such as computing system 330, and / or cloud computing platform 310. One or more of the plurality of sets of digitography data and / or corresponding additional information may be received from a database like cloud-based database 350, local database 340, and / or an electronic medical record database populated and / or maintained by a medical facility (e.g., hospital or medical treatment provider). The corresponding additional information received in step 1405 may be, for example, medical and / or demographic information about the patient, a diagnosis of the patient (e.g., whether the patient has Parkinsonism, when the Parkinsonism was diagnosed, symptoms associated with the Parkinsonism, contributing Parkinsonism risk factors (e.g., traumatic brain injury, obstructive sleep apnea, arthritis, etc.) associated with theprovider of the digitography information, a treatment the patient is, or has, received for the Parkinsonism, a symptom of the Parkinsonism, and / or an outcome of treating the patient. The sets of digitography data received in step 1405 may include digitography data for individuals diagnosed with varying types of Parkinsonism with varying degrees of severity and symptomology. In addition, the sets of digitography data received in step 1405 may include digitography data generated by health controls with varying ages, demographic details, medical histories, and / or comorbidities.[000160] In step 1410, the plurality of sets of digitography data and corresponding additional information regarding Parkinsonism associated with the provider of the digitography information may be divided into a training set of data and a testing set of data. The additional data may be, for example, Parkinsonism diagnoses, symptoms, medications, treatments, lab tests, images (e.g., MRI and / or ultrasound), comorbidities, electronic medical records, contributing factors, risk factors, and the like. In many instances, the additional data may be correlated with a patient / participant identifier and / or a timestamp (e.g., date, time of day, location, etc.), and / or a source (e.g., electronic medical record, digitography device 100, computer 330, local database 340, and / or cloud-based database 350) of the respective set (or plurality of sets) of digitography data. A set of machine learning inputs and / or parameters for a machine learning architecture for the generation of a Parkinsonism assessment model may then be selected, set, and / or determined (step 1415). Exemplary inputs and / or parameters include one or more QDG metrics and correlations between QDG metrics and Parkinsonism, or symptoms of Parkinsonism (e.g., short-term symptoms, long-term symptoms, and / or long-term risk factors), psychomotor symptoms, and / or the additional information. In some embodiments, execution of step 1415 may resemble execution of step 1015.[000161] In step 1420, a Parkinsonism assessment model may be generated and / or trained by running the training set through the machine learning architecture of step 1415. In some embodiments, execution of step 1420 may include training a model to understand relationships and / or correlations between digitography data and / or analysis of digitography data (e.g., mobility scores, rigidity scores, freezing behavior scores, tremor severity scores, taps per minute, and / or bradykinesia scores) and a diagnosis ofParkinson's disease, one or more symptoms of Parkinson’s disease, and / or additional patient information so that, for example, a set of a patient’s digitography data (or a series of sets of digitography data for a patient) may be input into the traumatic brain injury assessment model to, for example, determine characteristics of the patient’s neurological health and, in particular, determine whether the patient may be suffering from Parkinson’s disease, is at risk for developing Parkinson’s disease and / or a symptom of Parkinsonism that may be resultant from and / or otherwise correlated to another diagnosis or comorbidity (e.g., obstructive sleep apnea, traumatic brain injury, stoke, etc.), and / or how the patient may be expected to respond to one or more different types of treatment. Additionally, or alternatively, the Parkinsonism assessment model may be configured to evaluate a patient’s digitography data over time to, for example, track symptom progression, determine trends or other indications with the digitography data and / or scores (e.g., mobility scores, rigidity scores, freezing behavior scores, tremor severity scores, taps per minute, and / or bradykinesia scores) determined therefrom, and / or determine treatment effectiveness and / or disease progression over time.[000162] Once training is complete (step 1425), the Parkinsonism assessment model may be tested using the testing data set. Testing of the Parkinsonism assessment model may involve, for example, inputting one or more sets of digitography data into the Parkinsonism assessment model of step 1420 and comparing an output of the Parkinsonism assessment model to a known output (e.g., diagnosis or treatment outcome) associated with the input digitography data. Results of the testing of the Parkinsonism assessment model may then be evaluated (step 1430) and if the results of the testing are sufficiently accurate (e.g., within a margin of error or a standard of deviation of error) or otherwise in line with expectations (step 1435), the testing and / or training of the Parkinsonism assessment model may be complete and method 1400 may end. When the results of the testing are not sufficiently accurate or otherwise in line with expectations, the Parkinsonism assessment model may be tuned, updated, or otherwise adjusted responsively to the evaluation (step 1440) and steps 1420, 1425, 1430, and / or 1435 may be iteratively repeated.[000163] FIG. 15 is a flowchart showing a method for using a Parkinsonism assessment model like the Parkinsonism assessment model generated via, for example, execution of method 1400 to evaluate a set of digitography data for a patient. Method 1500 may be executed by, for example, digitography device 100, system 200, system 300, and / or portions or components thereof.[000164] In step 1505, a set of digitography data for a patient may be received by, for example, a processor and / or computer such as processing device 210, computing system 330, and / or cloud computing platform 310. The set of digitography data for the patient may be received from, for example, digitography device 100, computer 330, local database 340, and / or cloud-based database 350. Optionally, additional information about the patient as, for example, described herein may also be received in step 1505. Often times, the additional information may include an indication of whether the patient has been diagnosed with Parkinson’s disease and / or is associated with a risk factor for developing Parkinson’s disease (e.g., obstructive sleep apnea, traumatic brain injury, A Parkinsonism assessment model similar to the Parkinsonism assessment model generated via method 1400 may be accessed (step 1510) and the received set of digitography data and additional information about the patient (when received) may be input into the Parkinsonism assessment model (step 1515). Then, an output of the Parkinsonism assessment model may be determined (step 1520) and provided (step 1525) to a user (e.g., the patient and / or a care giver of the patient). Exemplary outputs determined in step 1520 include, but are not limited to, a diagnosis, a diagnosis of a particular type of Parkinsonism the patient may be suffering from, a treatment recommendation, a prediction for responsiveness of the patient to a treatment, and / or a potential risk factor (e.g., percentage) for a developing Parkinsonism.[000165] In some embodiments, methods 1100, 1300, and / or 1500 may be performed multiple times (e.g., 2-2,000 times) by a particular patient and / or cohort of patients over a period of time extending for days, weeks, months, and / or years. In some cases, digitography data for a particular patient and / or health control may be received in step 1105, 1305, and / or 1505 at, for example, periodic, irregular, and / or as-needed intervals to, for example, assess disease progression, symptom severity, and / or responsiveness to treatment. For example, a patient may provide digitography datareceived in step 1105 to diagnose depression and / or provide specific information on a type of depression the patient has and / or a region of the brain impacted by the depression. Additionally, or alternatively, this patient may provide digitography data received in step 1105 prior to, during, and / or following administration of a treatment for depression (or another medical condition) to, for example, assess the patient’s response to the treatment (e.g., have depressive symptoms present in the digitography data decreased in severity). For example, patient responsiveness to treatment may be measured by, for example, determining if the number of taps per minute and / or press speed have increased across serial sets of digitography data received over time. For example, if the digitography data for the patient who provided the digitography data used to generate GUI 501 has a baseline number of 49 taps per minute (as shown in GUI) prior to starting treatment and that value increases to 52 taps per minute seven days after treatment commences and then 60 taps per minute 30 days after treatment commences, it may be deduced that the treatment is effective. Likewise, if the number of taps per minute over the same 30 day period shows little change, it may be deduced that the treatment is not effective and this may prompt a recommendation from the depression assessment model to, for example, increase a dosage of the treatment and / or change the treatment.[000166] An example of how method 1300 may be used includes receiving initial and / or baseline digitography data for a patient diagnosed with traumatic brain injury (and, ideally for the patient prior to the traumatic brain injury) in step 1305. This digitography data may be input into the traumatic brain injury model (step 1315) and an output may be received (step 1320) and provided to the user (step 1325) via, for example, a GUI like GUI 501, 502, and / or 503. Method 1300 may be performed a series of times over a time period (e.g., weeks, months, or years) to, for example, monitor the brain function of the patient and / or assess whether the patient is developing a neurological condition like Parkinson’s disease, which may be indicated by, for example, increases in rigidity score, freezing behavior score, bradykinesia score, and / or tremor score and / or a decrease in taps per minute over time.[000167] An example of how method 1500 may be used includes receiving initial and / or baseline digitography data for a subject in step 1505. This digitography data maybe input into the Parkinsonism assessment model (step 1515) and an output may be received (step 1520) and provided to the user (step 1525) via, for example, a GUI like GUI 501, 502, and / or 503. Method 1500 may be performed a series of times over a time period (e.g., weeks, months, or years) to, for example, monitor the brain function of the patient and / or assess whether the patient is developing Parkinson’s disease, and / or whether the severity of their Parkinson’s disease is increasing both of which may be indicated by, for example, increases in rigidity score, freezing behavior score, bradykinesia score, and / or tremor score and / or a decrease in taps per minute over time.[000168] FIG. 16 is a flowchart showing a method 1600 for training a gait assessment model configured to, for example, assess a patient’s gait characteristics, and / or determine gait speed, gait freezing, progression of a neurological condition that presents with gait-related symptoms (e.g., Parkinson’s disease, stroke, etc.) using digitography data. Method 1600 may be executed by, for example, digitography device 100, system 200, system 300, and / or portions or components thereof.[000169] In step 1605, a plurality (e.g., 160-10,000,000) of sets of digitography data (e.g.,. QDG RAFT data) and corresponding freezing of gait information, gait speed, and / or additional information for the patients and / or healthy controls providing the digitography data may be received by, for example, a processor and / or computer such as computing system 330, cloud computing platform 310. In some embodiments, one or more set(s) of digitography data received in step 1605 may be used to determine a freezing behavior score and / or a mobility score for the respective set of digitography data as, for example, described herein. Additionally, or alternatively, a plurality (e.g., 100-10,000,000) of freezing behavior scores and / or mobility scores and corresponding freezing of gait information, gait speed, and / or additional information for the patients and / or healthy controls providing the digitography data may be received in step 1605.[000170] One or more of the plurality of sets of digitography data and / or corresponding additional information may be received from a database like cloud-based database 350, local database 340, and / or an electronic medical record database populated and / or maintained by a medical facility (e.g., hospital or medical treatment provider). The corresponding additional information receive step 1605 may be, for example, medical and / or demographic information about the patient, a diagnosis of thepatient (e.g., whether the patient has gait, when the gait was diagnosed, symptoms associated with the gait, contributing gait risk factors (e.g., traumatic brain injury, obstructive sleep apnea, arthritis, etc.) associated with the provider of the digitography information, a treatment the patient is, or has, received for the gait, a symptom of the gait, and / or an outcome of treating the patient. The sets of digitography data received in step 1605 may include digitography data for individuals diagnosed with varying types of gait with varying degrees of severity and symptomology. In addition, the sets of digitography data received in step 1605 may include digitography data generated by health controls with varying ages, demographic details, medical histories, and / or comorbidities.[000171] In step 1610, the plurality of sets of digitography data and corresponding additional information regarding gait associated with the provider of the digitography information may be divided into a training set of data and a testing set of data. The additional data may be, for example, gait diagnoses, symptoms, medications, treatments, lab tests, images (e.g., MRI and / or ultrasound), comorbidities, electronic medical records, contributing factors, risk factors, and the like. In many instances, the additional data may be correlated with a patient / participant identifier and / or a timestamp (e.g., date, time of day, location, etc.), and / or a source (e.g., electronic medical record, digitography device 100, computer 330, local database 340, and / or cloud-based database 350) of the respective set (or plurality of sets) of digitography data. A set of machine learning inputs and / or parameters for a machine learning architecture for the generation of a gait assessment model may then be selected, set, and / or determined (step 1615). Exemplary inputs and / or parameters include one or more QDG metrics and correlations between QDG metrics and gait, or symptoms of gait (e.g., short-term symptoms, long-term symptoms, and / or long-term risk factors), psychomotor symptoms, and / or the additional information. In some embodiments, execution of step 1615 may resemble execution of step 615.[000172] In step 1620, a gait assessment model may be generated and / or trained by running the training set through the machine learning architecture of step 1615. Once training is complete (step 1625), the gait assessment model may be tested using the testing data set. Testing of the gait assessment model may involve, for example,inputting one or more sets of digitography data into the gait assessment model of step 1620 and comparing an output of the gait assessment model to a known output (e.g., diagnosis or treatment outcome) associated with the input digitography data. Results of the testing of the gait assessment model may then be evaluated (step 1630) and if the results of the testing are sufficiently accurate (e.g., within a margin of error or a standard of deviation of error) or otherwise in line with expectations (step 1635), the testing and / or training of the gait assessment model may be complete and method 1600 may end. When the results of the testing are not sufficiently accurate or otherwise in line with expectations, the gait assessment model may be tuned, updated, or otherwise adjusted responsively to the evaluation (step 1640) and steps 1620, 1625, 1630, and / or 1635 may be iteratively repeated.[000173] FIG. 17 is a flowchart showing a method 1700 for using a gait assessment model like the gait assessment model generated via, for example, execution of method 1600 to evaluate a set of digitography data for a patient. Method 1700 may be executed by, for example, digitography device 100, system 200, system 300, and / or portions or components thereof.[000174] In step 1705, a set of digitography data for a patient may be received by, for example, a processor and / or computer such as processing device 210, computing system 330, and / or cloud computing platform 310. The set of digitography data for the patient may be received from, for example, digitography device 100, computer 330, local database 340, and / or cloud-based database 350. Optionally, additional information about the patient as, for example, described herein may also be received in step 1705. Often times, the additional information may include an indication of whether the patient has been diagnosed with Parkinson’s disease and / or is associated with a risk factor for developing Parkinson’s disease (e.g., obstructive sleep apnea, traumatic brain injury, A gait assessment model similar to the gait assessment model generated via method 1600 may be accessed (step 1710) and the received set of digitography data and additional information about the patient (when received) may be input into the gait assessment model (step 1715). Then, an output of the gait assessment model may be determined (step 1720) and provided (step 1725) to a user (e.g., the patient and / or a care giver of the patient). Exemplary outputs determined in step 1720 include, but arenot limited to, a diagnosis, a diagnosis of a particular type of gait the patient may be suffering from, a treatment recommendation, a prediction for responsiveness of the patient to a treatment, and / or a potential risk factor (e.g., percentage) for a developing gait.[000175] An example of how method 1700 may be used includes receiving initial and / or baseline digitography data for a subject in step 1705. This digitography data may be input into the gait assessment model (step 1715) and an output may be received (step 1720) and provided to the user (step 1725) via, for example, a GUI like GUI 501, 502, and / or 503. Method 1700 may be performed a series of times over a time period (e.g., weeks, months, or years) to, for example, monitor the brain function of the patient and / or assess whether the patient is developing Parkinson’s disease, and / or whether the severity of their Parkinson's disease is increasing both of which may be indicated by, for example, increases in rigidity score, freezing behavior score, bradykinesia score, and / or tremor score and / or a decrease in taps per minute over time.[000176] FIG. 18 is a flowchart showing a method for developing and updating a digitography task routine, for a patient. Method 1800 may be executed by / using, for example, digitography device, system 200, system 300, and / or components thereof.[000177] In step 1805, a set of baseline digitography data for a patient may be received. In some embodiments, the baseline digitography data set may be, for example, a set of data captured the first time the patient uses a digitography device and, in other embodiments, the baseline digitography data set may be a prior-recorded set of digitography data. The received baseline digitography data may then be analyzed and / or used to generate a digitography routine for the patient (step 1810). The digitography routine for the patient may include, for example, target rates for inter-strike intervals, target magnitudes of force exerted on levers of a digitography device, a duration of a digitography session and / or a length of time over which the digitography routine extends (e.g., days, week, months, years, etc.), a magnitude of resistance provided by the levers of the digitography device, and / or a target amplitude for the movement of the levers of the digitography device.[000178] In step 1815, an indication that the patient is commencing a digitography session of the digitography routine may be received. The indication received in step1815 may be, for example, an indication that the patient has depressed one or more levers of the digitography device and / or turned on the digitography device. Optionally, in step 1820, a tension and / or resistance to movement provided by one or more levers of the digitography device may be adjusted according to, for example, the training routine of step 1810.[000179] In step 1825, digitography data from the digitography session may be received. The digitography data received in step 1825 may be similar to the digitography data received in step 405. In step 1830, the received digitography data may then be analyzed and / or compared with the baseline digitography data of step 1805 to determine whether any adjustments to the digitography routine may be needed (step 1835) and, if so, one or more aspects of the digitography routine may be updated responsively to the analysis of step 1835 and / or the comparison of step 1830 (step 1840). Exemplary updates to the training routine include, but are not limited to, adjusting target rates for inter-strike intervals, target magnitudes of force exerted on levers of a digitography device, a duration of the digitography routine, a magnitude of resistance provided by the levers of the digitography device, and a target amplitude for the movement of the levers of the digitography device to be more responsive and / or beneficial to the patient and / or the patient’s neurological and / or motor symptoms.[000180] In step 1845, an indication of the digitography data received in step 1825, the comparison of step 1830, and / or an adjustment to the training routine may be provided to the patient and / or a user (e.g., a neurologist, clinician, and / or attending physician) and method 1800 may end.[000181] In one example, method 1800 may be executed to develop and / or update a digitography program for patients suffering from weakness that may result from, for example, stroke or other neurological impairment. Rehabilitation strategies for these patients often involve a prescription of exercises, initially demonstrated by a physical therapist or health care provider and then performed by the patient in a home exercise program (HEP) and / or in a rehabilitation inpatient setting. Using traditional methods, it is challenging to monitor adherence and / or responsiveness to the home exercise programs by patients with weakness once they leave the clinic. However, by using a training routine such as the training routine generated and / or adapted via execution ofmethod 1800 the patient may be provided with a rehabilitation therapeutic device that is able to provide levels of resistance to RAFT that will help the person with weakness exercise and recover strength, help with adherence to the exercise program by proving an alert to the patient to do the task, and assist in recovery of fine motor control strength while also giving the patient direct feedback and providing interim reports to the heath care provider regarding, for example, adherence to the training routine and / or progress being made while using the training routine.

Claims

CLAIMSWhat is claimed is:

1. A method comprising:inputting, by a processor, a set of digitography data received from a patient into a depression assessment model configured to determine one or more indications for a depression diagnosis using digitography data;receiving, by the processor, an output from the depression assessment model, the output including an indication regarding a depression diagnosis for the patient determined using digitography data; andproviding, by the processor, the indication regarding the depression diagnosis to a display device.

2. The method of claim 1, wherein the indication is at least one of a rigidity score, a bradykinesia score, a number of taps per minute, a freezing behavior score, and a tremor score.

3. The method of claim 1 or 2, wherein indication corresponds to a positive depression diagnosis may be responsive to, for example, to at least one of a rigidity score that is above a threshold value, a bradykinesia score that is above a threshold value, a freezing behavior score that is above a threshold value, and a tremor score that is above a threshold value.

4. The method of claim 1, 2, or 3, wherein the indication corresponds to a number of taps per minute that is below a threshold value.

5. The method of claim 4, wherein the threshold value is 105 taps per minute.

6. The method of any of claims 1-5, wherein the set of digitography data is a first set of digitography data, the output is a first output, and the indication is a first indication, the method further comprising:inputting, by a processor, a second set of digitography data received from the patient into the depression assessment model;receiving, by the processor, a second output from the depression assessment model, the second output including a second indication regarding a depression diagnosis for the patient using digitography data; andproviding, by the processor, the second indication regarding a depression diagnosis for the patient to the display device.

7. The method of claim 6, further comprising:comparing, by the processor, the first and second indications; and providing, by the processor, a result of the comparison to the display device.

8. The method of claim 7, further comprising:determining, by the processor, a recommendation responsively to the result of the comparison; andproviding, by the processor, a recommendation to the display device.

9. The method of claim 7 or 8, further comprising:receiving, by the processor, an indication of a treatment provided to the patient, wherein a result of the comparison is an indication of how the patient is responding to the treatment.

10. The method of claim 9, further comprising:inputting, by the processor, the indication of the treatment into the depression assessment model;receiving, by the processor, a treatment-responsive output from the depression assessment model, the treatment-responsive output being responsive input indication of the treatment; andproviding, by the processor, an indication of the treatment-responsive output to a display device.

11. The method of any of claims 1-10, wherein the digitography data is generated using a digitography device comprising a first and a second lever, wherein each lever is configured to move downward from a starting position in response to the patient pressing on the lever and return to approximately the starting position when the patient releases the lever.

12. The method of claim 11, wherein the downward motion comprises rotation of the first and / or second lever around an axis, wherein an end of the first and / or second lever furthest from the axis moves downward by 3-20mm in response to being pressed by one of the patient’s fingers.

13. A computer-implemented method comprising:receiving a set of digitography data corresponding to the patient’s performance of a repetitive alternating finger tapping (RAFT) task;determining a characteristic of the set of digitography data;comparing the characteristic to a threshold value for the characteristic; determining an indication of whether the patient has depression responsively to a result of the comparison; andproviding the indication to a display device.

14. The method of claim 13, wherein the RAFT task is performed by the patient using a digitography data comprising a first and a second lever, wherein each lever is configured to move downward from a starting position in response to the patient pressing on the lever and return to approximately the starting position when the patient releases the lever.

15. The method of claim 14, wherein the downward motion comprises rotation of the first and / or second lever around an axis, wherein an end of the first and / or second lever furthest from the axis moves downward by 3-20mm in response to being pressed by one of the patient’s fingers.

16. The method of any of claims 13-15, wherein the characteristic is at least one of a rigidity score, a bradykinesia score, an amplitude, a frequency, a freezing behavior score, a mobility score, a number of taps per minute, a degree of arrhythmicity, a degree of irregularity, a degree of asynchronicity between the digitography data of the patient’s right hand and the patient’s left hand, a tremor score, and an ability to do alternate fingers correctly.

17. The method of any of claims 13-16, wherein the set of digitography data is a first set of digitography data, the characteristic is a first characteristic, and the result of the comparison is a first result, the method further comprising:receiving, after duration of time, a second set of digitography data corresponding to the patient’s second performance of the RAFT task;determining a second characteristic of the second set of digitography data; comparing the second characteristic to the first characteristic;determining an indication of a change in the patient’s condition over the duration of time responsively to a result of the comparison; andproviding the indication of the change to a display device.

18. The method of claims 17, wherein the determining of the indication of the change in the patient’s condition includes determining an indication of how the patient is responding to a treatment.

19. A method comprising:inputting, by a processor, a set of digitography data received from a patient into a traumatic brain injury assessment model configured to determine one or more indications for a traumatic brain injury diagnosis using digitography data;receiving, by the processor, an output from the traumatic brain injury assessment model, the output including an indication regarding a traumatic brain injury diagnosis for the patient determined using digitography data; andproviding, by the processor, the indication regarding the traumatic brain injury diagnosis for the patient to a display device.

20. The method of claim 19, wherein the digitography data is generated via the patient’s performance of repetitive alternating finger tapping (RAFT).

21. The method of claim 19 or 20, wherein the indication is at least one of a rigidity score, a bradykinesia score, a number of taps per minute, a freezing behavior score, and a tremor score.

22. The method of any of claims 19-21, wherein the indication corresponds to at least one of a rigidity score, a bradykinesia score, a freezing behavior score, and a tremor score that is above a threshold value.

23. The method of any of claims 19-22, wherein the indication corresponds to a number of taps per minute that is below a threshold value.

24. The method of any of claims 19-23, wherein the indication corresponds to a risk indication for the patient developing Parkinson’s disease.

25. The method of claim 24, wherein the digitography data includes repetitive alternating finger tapping (RAFT) movements for the patient’s left and right hands and the risk indication for Parkinson’s disease is an asymmetry between the RAFT movements of the patient’s left hand and right hand.

26. The method of any claims 19-25, wherein the indication is at least one of a low number of taps per minute, irregular amplitude changes of the RAFT movements, and arrhythmic performance of RAFT movements.

27. The method of any of claims 19-26, wherein the set of digitography data is a first set of digitography data, the output is a first output, and the indication is a first indication, the method further comprising:inputting, by a processor, a second set of digitography data received from the patient into a traumatic brain injury assessment model configured to determine one or more indications for a traumatic brain injury diagnosis using digitography data; receiving, by the processor, a second output from the traumatic brain injury assessment model, the second output including a second indication regarding a traumatic brain injury diagnosis for the patient using digitography data; and providing, by the processor, the second indication regarding a traumatic brain injury diagnosis for the patient to the display device.

28. The method of claim 27, further comprising:comparing, by the processor, the first and second indications; andproviding, by the processor, a result of the comparison to the display device.

29. The method of claim 28, wherein a result of the comparison is an indication of a risk that the patient will develop Parkinson’s disease.

30. The method of claim 28 or 29, further comprising:determining, by the processor, a recommendation responsively to the result of the comparison; andproviding, by the processor, a recommendation to the display device.

31. The method of claim 30, wherein the recommendation includes recommending a treatment for Parkinson’s disease.

32. The method of any of claims 28-31, further comprising:receiving, by the processor, an indication of a treatment provided to the patient, wherein a result of the comparison is an indication of how the patient is responding to the treatment.

33. The method of claim 32, further comprising:inputting, by the processor, the indication of the treatment into the traumatic brain injury assessment model;receiving, by the processor, a treatment-responsive output from the traumatic brain injury assessment model, the treatment-responsive output being responsive to the indication of the treatment; andproviding, by the processor, an indication of the treatment-responsive output to a display device.

34. The method of any of claims 19-33, wherein at least some of the sets of digitography data are generated using a digitography device comprising a first and a second lever, wherein each lever is configured to move downward from a starting position in response to the patient pressing on the lever and return to approximately the starting position when the patient releases the lever.

35. The method of claim 34, wherein the downward motion comprises rotation of the first and / or second lever around an axis, wherein an end of the first and / or second lever furthest from the axis moves downward by 3-20mm in response to being pressed by one of the patient’s fingers.

36. A method comprising:inputting, by a processor, a set of digitography data received from a patient into a Parkinsonism assessment model configured to determine one or more indications for a Parkinson’s disease using digitography data;receiving, by the processor, an output from the Parkinsonism assessment model, the output including an indication regarding a Parkinsonism diagnosis for the patient determined using digitography data; andproviding, by the processor, the indication regarding the Parkinsonism diagnosis for the patient to a display device.

37. The method of claim 36, wherein the method is executed to monitor the patient for the onset of Parkinsonism.

38. The method of claim 36 or 37, wherein the method is executed to monitor the patient’s responsiveness to a treatment for Parkinsonism.

39. The method of any of claims 36-38, wherein the patient has been diagnosed with traumatic brain injury, obstructive sleep apnea, depression, cognitive decline, or mood changes.

40. The method of any of claims 36-39, wherein the Parkinsonism model determines at least one of a rigidity score, a bradykinesia score, an amplitude, a frequency, a freezing behavior score, a mobility score, a number of taps per minute, a degree of arrhythmicity, a degree of irregularity, a degree of asynchronicity between the digitography data of the patient’s right hand and the patient’s left hand, a tremor score, and an ability to do alternate fingers correctly.

41. The method of claim 40, wherein the Parkinsonism model determines that the patient has Parkinson’s disease responsively to detecting at least one of an asymmetrical performance of a RAFT task corresponding to the digitography data between the patient’s left and right hands, a tremor score above a threshold, and a rigidity score above a threshold.

42. The method of any of claims 36-41, wherein the digitography data is generated using a digitography device comprising a first and a second lever, wherein each lever is configured to move downward from a starting position in response to the patient pressing on the lever and return to approximately the starting position when the patient releases the lever.

43. The method of claim 42, wherein the downward motion comprises rotation of the first and / or second lever around an axis, wherein an end of the first and / or second lever furthest from the axis moves downward by 3-20mm in response to being pressed by one of the patient’s fingers.

44. A computer-implemented method of monitoring a patient’s responsiveness to a treatment comprising:receiving a first set of digitography data corresponding to the patient’s performance of a repetitive alternating finger tapping (RAFT) task;receiving, after a duration of time, a second set of digitography data corresponding to the patient’s performance of the RAFT task;comparing the first and second sets of digitography data;determining the patient's responsiveness to treatment using a result of the comparing; andproviding a determination of the patient’s responsiveness to treatment to a display device.

45. The method of claim 44, further comprising:determining a first characteristic of the first set digitography data; determining a second characteristic of the second set digitography data, wherein the comparing comprises comparing the first and second characteristics.

46. The method of claim 45, wherein the first characteristic is at least one of a first rigidity score, a bradykinesia score, a first amplitude, a first frequency, a first freezing behavior score, a first mobility score, a first number of taps per minute, a first degree of arrhythmicity, a first degree of irregularity, a first degree of asynchronicity between the digitography data of the patient’s right hand and the patient’s left hand, a first tremor score, and a first ability to do alternate fingers correctly, and the second characteristic is at least one of a second rigidity score, a second bradykinesia score, a second amplitude, a second frequency, a second freezing behavior score, a second mobility score, a second number of taps per minute, a second degree of arrhythmicity, a second degree of irregularity, a second degree of asynchronicity between the digitography data of the patient’s right hand and the patient’s left hand, a second ability to do alternate fingers correctly, and / or a second tremor score.

47. The method of any of claims 44-46, wherein the treatment is for a neurological condition or a condition that impacts motor skills.

48. The method of any of claims 44-47, wherein the treatment is for arthritis.

49. The method of any of claims 44-48, wherein the treatment is a pharmaceutical, surgery, and physical therapy.

50. The method of any of claims 44-49, wherein the treatment is at least one of a braincomputer interface and a deep brain stimulation device.

51. The method of claim 50, further comprising:determining where and / or how to stimulate the brain using the at least one braincomputer interface and deep brain stimulation device responsively to thedetermination of the patient’s responsiveness to treatment provided by the at least one brain-computer interface and a deep brain stimulation device.

52. The method of claim 51, further comprising:providing a recommendation for where and / or how to stimulate the brain using the at least one brain-computer interface and a deep brain stimulation device responsively to the determination; andproviding the recommendation to at least one of the display device and an interface in communication with the at least one brain-computer interface and deep brain stimulation device.

53. The method of any of claims 44-52, wherein the duration of time is at least one of 6 hours, 24 hours, a week, two weeks, a month, two months, three months, a year, 2 years, 5 years, and 10 years.

54. The method of any of claims 44-53, wherein the RAFT task is performed by the patient using a digitography data comprising a first and a second lever, wherein each lever is configured to move downward from a starting position in response to the patient pressing on the lever and return to approximately the starting position when the patient releases the lever.

55. The method of claim 54, wherein the downward motion comprises rotation of the first and / or second lever around an axis, wherein an end of the first and / or second lever furthest from the axis moves downward by 3-20mm in response to being pressed by one of the patient’s fingers.

56. A method comprising:inputting, by a processor, a set of digitography data received from a patient into a gait assessment model configured to determine a gait characteristic for the patient using digitography data;receiving, by the processor, an output from the gait assessment model, the output including an indication regarding a gait characteristic determined using digitography data; andproviding, by the processor, the indication regarding the gait characteristic to a display device.

57. The method of claim 56, wherein the digitography data is generated via the patient’s performance of repetitive alternating finger tapping (RAFT), whereby the fingers press and release adjacent tensioned engineered levers in an alternating manner.

58. The method of claim 56 or 57, wherein the indication is at least one of a rigidity, bradykinesia and / or freezing behavior score, a freezing of gait score, a mobility score, a tremor severity score, percent time with tremor, tremor amplitude, tremor frequency, and / or a gait speed.

59. The method of any of claims 56-58, wherein the indication corresponds to at least one of a freezing behavior score above a threshold value or a mobility score below a threshold value.

60. The method of any of claims 56-59, wherein the set of digitography data is a first set of digitography data, the output is a first output, and the indication is a first indication, the method further comprising:inputting, by the processor, a second set of digitography data received from the patient into the gait assessment model;receiving, by the processor, a second output from the gait assessment model, the second output including a second indication determined using digitography data; andproviding, by the processor, the second indication to a display device.

61. The method of claim 60, further comprising:comparing, by the processor, the first and second indications; andproviding, by the processor, a result of the comparison to the display device.

62. The method of claim 61, wherein a result of the comparison is an indication of a change in the patient’s gait over time.

63. The method of claim 61 or 62, further comprising:determining, by the processor, a recommendation responsively to the result of the comparison; andproviding, by the processor, a recommendation to the display device.

64. The method of claim 63, wherein the recommendation includes recommending a treatment for Parkinson’s disease.

65. The method of any of claims 56-64, further comprising:receiving, by the processor, an indication of a treatment provided to the patient, wherein a result of the comparison is an indication of how the patient is responding to the treatment.

66. The method of any of claims 56-65, wherein the digitography data is generated using a digitography device comprising a first and a second lever, wherein each lever is configured to move downward from a starting position in response to the patient pressing on the lever and return to approximately the starting position when the patient releases the lever.

67. The method of claim 66, wherein the downward motion comprises rotation of the first and / or second lever around an axis, wherein an end of the first and / or second lever furthest from the axis moves downward by 3-20mm in response to being pressed by one of the patient’s fingers.

68. A digitographic measurement device comprising:a base;a first lever having a first end in communication with an axis and a second end including a first finger placement indentation, the first lever being configured to physically rotate around the axis toward the base in response to a force exerted on the second end of the first lever;a second lever having a first end in communication with the axis and a second end including a second finger placement indentation, the second lever being configured to physically rotate around the axis toward the base in response to a force exerted on the second end of the second lever;the axis being in communication with the first ends of the first and second levers and the base and configured to allow rotation of the second ends of the first and second levers in response to a force exerted thereon;a sensor in communication with one or both of the first lever and the second lever, the sensor being configured to sense movement of the one or both of the first lever and the second lever and provide quantitative digitography (QDG) motion data; anda communication interface configured to receive QDG motion data from the sensor and communicate the QDG motion data to an external computing device.

69. The digitographic measurement device of claim 68, wherein the force exerted on the first key occurs when a patient positions an index finger within the first indentation and presses downward and the force exerted on the second key occurs when a patient positions a middle finger within the second indentation and presses downward.

70. The digitographic measurement device of claim 68 or 69, wherein the first key and the second key are configured to rotate around the axis to move upward and return to an original position when the patient releases the respective first or second key.

71. The digitographic measurement device of any of claims 68-70, wherein a degree of tension exerted by the axis on the second end of the first lever and / or second lever is adjustable.

72. The digitographic measurement device of any of claims 68- 71, wherein each of the first lever and the second lever is tensioned by a resistance device to mechanically resist movement when one or both of the first lever or the second lever.

73. The digitographic measurement device of claim 62, wherein the resistance device is a spring, a foam, or a magnet.

74. The digitographic measurement device any of claims 68-73, wherein the second end of the first key and the second key are configured to move downward by 5-20mm, 10-20mm, 10-15mm or approximately 15mm.

75. The digitographic measurement device of any of claims 68-74, wherein the sensors is a force meter, a clock, a Hall effect sensor, an optical sensor, an infrared sensor, a magnetic sensor, a potentiometer, a displacement measurement sensor, an inertial movement sensor, a strain gauge, an accelerometer, and any combination thereof.

76. The digitographic measurement device of any of claims 68-75, wherein the external computing device is configured to determine at least one of a QDG motion metrics, a tremor metric, a FoRAFT metric, a bradykinetic frequency metric, a bradykinetic sequence effect metric, a bradykinetic amplitude metric, a bradykinesia speed metric, a freezing behavior metric, a rigidity metric, a key press amplitude, a key press amplitude coefficient of variation, an inter-strike interval, an inter-strike intervalcoefficient of variation, a release slope, a press speed, a dwell time, a rest tremor, any average thereof, and any combination thereof.

Images