Method and system for obtaining a measure of cognitive performance - Patents.com

Abstract

A method and system for obtaining a measure of an individual's cognitive performance is provided to obtain a measure of at least one of the following activity parameters for an individual: 1) spatial memory accuracy; 2) planning accuracy; 3) ability to perform dual task interactions while navigating to a goal, where deficiencies in dual task interactions are measured; 4) perseveration to incorrect dual task interactions while navigating to a goal; 5) total time taken by the individual to complete a navigation path; 6) upper limb neuromotor parameters; 7) dual task interaction reaction time; and 8) idle reaction time of the individual; receiving the obtained measures into an algorithm; and calculating an impairment score for the individual based on baseline measurements obtained from a population of healthy individuals. The measurements are obtained using an app on an electronic handheld device. The system and method includes an application executable by a user device to generate a gamified environment, receive a first user input or set of user inputs at a first time point and convert the first user input or set of user inputs into a first measurement or set of measurements, and receive a second user input or set of user inputs at a second time point and convert the second user input or set of user inputs into a second measurement or set of measurements; configured to receive the first measurement or set of measurements and calculate a first impairment score, and receive the second measurement or set of measurements and calculate a second impairment score; and configured to compare the second impairment score to the first impairment score to determine a magnitude and / or rate of change in the impairment score.

Description

[Technical field]

[0001] The present invention relates to a method for obtaining a measure of an individual's cognitive performance, and to a computer-implemented system for obtaining a measure of an individual's cognitive performance. [Background technology]

[0002] Today, over 50 million people worldwide have dementia, most of whom have Alzheimer's disease (AD). The impact of AD on individuals, their caregivers, and society is enormous in both developed and developing countries.

[0003] Dementia can be defined as a clinical syndrome characterized by a constellation of symptoms and signs manifested by memory impairment, disruptions in language and other cognitive functions, behavioral abnormalities, and impairment in activities of daily living. AD is the most common cause of dementia, accounting for up to 75% of all dementia cases, and is a progressive neurodegenerative disorder.

[0004] AD is a degenerative brain disease caused by changes in the brain, resulting in symptoms of dementia that gradually worsen over time. Early symptoms include difficulty remembering information. As AD progresses, symptoms become more severe and can include ataxia, confusion, and behavioral changes. Eventually, people have difficulty speaking, swallowing, and walking. Although prescription medications exist to treat the symptoms of AD, there is currently no way to prevent, cure, or slow AD, which ultimately leads to death.

[0005] AD is characterized by a presymptomatic phase lasting many years, during which progressive neurodegeneration in the brain occurs before typical clinical symptoms (e.g., cognitive impairment and mild cognitive impairment) are detectable (Backman et al., 2001). In theory, detection of AD at an early stage may provide an opportunity to implement therapeutic interventions that may more effectively delay the progression to clinical dementia.

[0006] However, despite the examination of several clinical, neuroimaging, and biochemical markers, challenges remain as to how to identify patients during the presymptomatic stages of the disease (DeKosky and Marek, 2003).

[0007] First, many studies suggest that deficits in certain cognitive domains, such as episodic memory and language abilities, can be noticeable up to a decade before dementia symptoms are clinically diagnosed, with more pronounced decline occurring over the last few years. In clinical practice, the term "mild cognitive impairment" is used to identify patients with isolated memory loss (i.e., "amnestic" MCI), which is more likely to represent a preclinical stage of AD. However, population-based follow-up studies often show that patients with MCI represent a very heterogeneous group with regard to prognosis (Palmer et al. (2002)); although older adults with MCI are at high risk of progressing to dementia, a significant proportion remain stable or may even return to normal for several years. When mild cognitive impairment is actually due to AD, it is known as presymptomatic AD.

[0008] Second, biochemical markers such as β-amyloid and tau protein in serum and cerebrospinal fluid have been proposed for the early detection of AD, but these markers are not reliable enough to diagnose AD at the preclinical stage (Blennow et al., 2006; DeKosky and Marek, 2003).

[0009] And in the last decade, brain imaging has emerged as a useful tool to diagnose AD, both in its preclinical and early clinical stages. For example, amyloid PET (positron emission tomography) imaging tracer ligands provide the opportunity to measure β-amyloid in the brain in vivo, offering the possibility of early diagnosis of AD and monitoring the course of anti-amyloid treatment in AD (Nordberg (2007); Forsberg et al. (2008)). Furthermore, medial temporal lobe atrophy, as seen by MRI volumetric measurements, has been used to distinguish MCI from early AD and to assess the progression of MCI and early AD (Dubois et al. (2007); Ridha et al. (2007)). However, these tests are currently limited to research use due to their cost and invasive nature. These limitations make it impossible to use them repeatedly to test individuals, especially in the early presymptomatic stages (Kourtis et al. (2019)).

[0010] Mobile and wearable digital consumer technologies have the potential to overcome the above limitations, and the application of this technology to AD detection has become an area of ​​interest. For example, the applicant's previous patent applications (published as WO2010 / 075481, WO2016 / 157093, and WO2020 / 049470, the contents of which are incorporated herein by reference) disclose the use of mobile devices to enable tests to determine a user's cognitive status.

[0011] Longitudinal measurements of cognitive performance are important to assess preclinical markers and presymptomatic stages of cognitive impairment and dementia, as well as to monitor disease progression. Current techniques for assessing cognitive decline are often based on cross-sectional assessments (i.e., observations at a specific point in time). However, cross-sectional assessments have limited value in capturing an individual's overall cognitive function, and cannot accurately predict future cognitive performance and risk of cognitive decline due to the high intraindividual variability of cognitive performance (Mungas et al. (2010)).

[0012] Traditional cross-sectional neuropsychological cognitive assessments are susceptible to several confounding factors, such as motivation, attention, mood, and testing environment, that affect an individual's assessment behavior. The uncertain nature of such neuropsychological assessments then has negative consequences for clinical care, as they are used to prognose, diagnose, and ultimately treat brain-related illnesses such as a range of dementia disorders (e.g., AD). Traditional neuropsychological assessments for AD are time-consuming, unreliable, and inaccurate in capturing MCI, and they also show large variations in different contexts and time points, especially after repeated measurements. The reasons for such variations are manifold, including the subject's motivation, attention, mood, anxiety level, sleep quality the night before the assessment, and testing environment. Such variations may lead to inaccurate diagnoses and inappropriate treatment, for example, by giving the false impression that a patient's cognition has improved at a later visit. The limitations of traditional cross-sectional neuropsychological assessments highlight major clinical and research gaps in conducting cognitive assessments of individuals across the full spectrum from healthy cognitive function to dementia. Summary of the Invention

[0013] The present invention seeks to provide an improved method for obtaining a measure of an individual's cognitive performance, and an improved computer-implemented system for obtaining a measure of an individual's cognitive performance.

[0014] According to an embodiment of the present invention there is provided a method for obtaining a measure of cognitive performance of an individual, the method comprising obtaining for the individual a measure of at least one of the following activity parameters: 1) spatial memory accuracy; 2) accuracy of planning; 3) the ability to perform dual-task interactions during navigation to a goal, where deficits in dual-task interactions are measured; 4) perseveration on incorrect dual-task interactions during navigation to the goal; 5) the total time taken by the individual to complete the navigation route; 6) upper limb neuromotor parameters; 7) Dual-task interaction reaction time; and 8) individual idle reaction time; receiving the obtained measurements into an algorithm; and An impairment score for the individual is calculated based on baseline measurements obtained from a population of healthy individuals.

[0015] The method is preferably computer-implemented and may be performed using a computer-implemented system or a computer system as described below.

[0016] The information required to obtain the measurements is preferably received via an input interface of the mobile device. The measurements are preferably received by a processor configured to execute an algorithm that uses the measurements to calculate an impairment score indicative of the individual's cognitive performance. The impairment score is preferably remotely accessible by a third party and displayable on an information output device.

[0017] The measurements may be taken using an application on a portable electronic device, which may for example be a smartphone or a tablet.

[0018] According to another embodiment of the present invention there is provided a computer implemented system for obtaining a measure of cognitive performance of an individual, the system comprising: an input interface configured to receive measurements from a remote source regarding at least one of the following activity parameters for the individual: 1) spatial memory accuracy; 2) accuracy of planning; 3) the ability to perform dual-task interactions during navigation to a goal, where deficits in dual-task interactions are measured; 4) perseveration on incorrect dual-task interactions during navigation to the goal; 5) the total time taken by the individual to complete the navigation route; 6) upper limb neuromotor parameters; 7) Dual-task interaction reaction time; and 8) individual idle reaction time; and a processor configured to receive the measurements and to execute computer program code that uses the measurements to calculate an impairment score indicative of cognitive performance in the individual.

[0019] The system: an input interface configured to receive a first measurement or set of measurements taken at a first time point and a second measurement or set of measurements taken at a second, different time point for the activity parameter or multiple activity parameters; may include a processor configured to receive a first measurement or set of measurements and to execute computer program code using the first measurement or set of measurements to calculate a first impairment score indicative of cognitive performance in the individual, and a processor configured to receive a second measurement or set of measurements and to execute computer program code using the second measurement or set of measurements to calculate a second impairment score; The processor is configured to compare the second impairment score to the first impairment score to determine a magnitude and / or rate of change in the impairment score.

[0020] The processor may be configured to determine both the magnitude and rate of change in the impairment score for the individual and calculate a composite (or total) score.

[0021] According to another embodiment of the present invention there is provided a computer system for obtaining a measure of cognitive performance of an individual, the system comprising: The gamified environment includes an application executable by a user device to generate a gamified environment, receive user input, and convert the input into a measurement of at least one of the following activity parameters for an individual: 1) spatial memory accuracy; 2) accuracy of planning; 3) the ability to perform dual-task interactions during navigation to a goal, where deficits in dual-task interactions are measured; 4) perseveration on incorrect dual-task interactions during navigation to the goal; 5) the total time taken by the individual to complete the navigation route; 6) upper limb neuromotor parameters; 7) Dual-task interaction reaction time; and 8) individual idle reaction time; The system is configured to receive the measurements and calculate an impairment score indicative of cognitive performance in the individual.

[0022] The system: may include an application executable by the user device to generate a gamified environment, receive a first user input or set of user inputs at a first time and convert the first user input or set of user inputs into a first measurement or set of measurement values, and receive a second user input or set of user inputs at a second time and convert the second user input or set of user inputs into a second measurement or set of measurement values; The system is configured to receive a first measurement or set of measurements and calculate a first impairment score, and to receive a second measurement or set of measurements and calculate a second impairment score; The system is configured to compare the second impairment score to the first impairment score to determine a magnitude and / or rate of change in the impairment score.

[0023] The system may be configured to determine both the magnitude and rate of change in impairment score for the individual, and calculate a composite (or total) score.

[0024] The system may be configured to receive measurements remotely from an electronic portable device or user device and calculate the impairment score and / or composite score, for example, the electronic portable device or other user device may upload measurements over the internet to the remote system, where processing / calculation is performed.

[0025] Preferably, a number of activity parameters are measured.

[0026] In certain embodiments, at least upper extremity neuromotor parameters are measured, for example agility of movement, speed of movement, and smoothness of movement may be measured.

[0027] Preferably, at least three activity parameters are measured, or at least four activity parameters are measured, or at least five activity parameters are measured. Advantageously, the accuracy of the impairment score is improved by including the measurement of additional activity parameters.

[0028] In certain embodiments, particularly useful when prediction of conversion from MCI to AD is the goal, at least the following activity parameters are measured: spatial memory accuracy; the ability to perform dual-task interactions during navigation to a goal, where deficits in dual-task interactions are measured; Perseveration to incorrect dual-task interactions during navigation to a goal; Upper limb neuromotor parameters; and Individual idle reaction time.

[0029] In the most preferred embodiment, all eight activity parameters are measured.

[0030] An algorithm is executed to calculate a metric belonging to the activity parameters.

[0031] In one embodiment, multiple metrics pertaining to activity parameters are calculated; these metrics are mapped to multiple cognitive domains; and a percentile rank score is calculated for each cognitive domain.

[0032] The metric is generally calculated based on a predefined algorithm, which may be or include one or more of signal analysis, sensor fusion, algebraic integration, Fourier analysis, or wavelet analysis.

[0033] The cognitive domains to which the metrics are mapped may include at least one of: sensorimotor coordination, complex attention, cognitive processing speed, inhibitory function, cognitive flexibility, visual perception, planning, prospective memory, and spatial memory.

[0034] The individual's hand movements may be evaluated to obtain at least one measurement, which may include testing the speed and / or accuracy of the individual's hand movements.

[0035] An individual's hand movements may be assessed by displaying an image to the individual and assessing the individual's ability to trace or tap the image, which may be displayed on a screen of a portable electronic device or other user device.

[0036] The individual's ability to navigate may be assessed to obtain at least one of the measurements, which may be accomplished by assessing the individual's navigational capabilities, including the individual's ability to locate and retrieve a number of objects.

[0037] The individual's ability to perform the task may be assessed to obtain at least one of the measurements.

[0038] Evaluating an individual's ability to perform a task may include evaluating their ability to perform subtasks in the correct order.

[0039] Evaluating an individual's ability to navigate or perform a task may include distracting the individual during the evaluation.

[0040] In one embodiment, the accuracy of spatial memory is determined by measuring the number of items an individual correctly selects in a navigation assessment, or by analyzing the complexity of the path an individual takes in a navigation assessment. For example, path complexity may be measured based on the number of turns a subject makes while performing a test: fewer turns indicate a more direct path to the goal, which corresponds to a better spatial memory.

[0041] Planning accuracy may be determined by measuring the individual's performance of correct prospective memory tasks during a task performance assessment.

[0042] The upper limb neuromotor parameters include movement agility, movement speed, and / or movement smoothness, which may be derived by signal processing of the 3D acceleration data provided on the portable electronic device.

[0043] Reaction time for a dual task interaction may be measured as the time elapsed between a stimulus being presented to an individual and a response from the individual.

[0044] Idle reaction time is measured as the time elapsed between the patient's idle state and the next immediate interaction response in the performance of the dual task. It may be considered as a measure of reaction time, e.g. the time taken to react to a distracting signal (such as a high-pitched sound) during the task.

[0045] The method may be performed multiple times by the individual, for example at about monthly intervals. The method is preferably performed at least three times, at least four times, at least five times, or at least six times.

[0046] A first impairment score obtained from an individual may be compared to a second impairment score obtained from that individual at another time, and the magnitude and / or rate of change in the impairment score for the individual may be determined.

[0047] In one embodiment, both the magnitude and rate of change in the impairment score for the individual are determined and a composite score is calculated therefrom.

[0048] The cognitive impairment score or composite score may be calculated by a system configured to receive the measurements remotely from the electronic portable device or user device and calculate the impairment score or composite score, where the system includes an information output accessible by a third party remote from the electronic portable device or user device.

[0049] The individual may have mild cognitive impairment, and a prediction may be made based on the cognitive impairment score or composite score whether the individual with mild cognitive impairment will convert to Alzheimer's disease. The individual may be diagnosed with mild cognitive impairment as a result of the test, or may have been diagnosed with mild cognitive impairment prior to taking the test.

[0050] The cognitive impairment score or composite score obtained by the above-described method or by the above-described system is used to predict conversion to Alzheimer's disease in an individual previously diagnosed with mild cognitive impairment or to diagnose mild cognitive impairment.

[0051] If an individual with mild cognitive impairment is predicted to convert to Alzheimer's disease based on the cognitive impairment score or composite score, information regarding pharmaceutical or other intervention may be provided by the information output.

[0052] The proposed intervention may be a pharmaceutical intervention, and the information may relate to the identity of a particular drug to be administered to the individual.

[0053] The agent may be a cholinesterase inhibitor (such as donepezil, rivastigmine, galantamine), memantine (optionally in combination with a cholinesterase inhibitor), a monoclonal antibody (such as aducanumab (Aduherm)), BAN2401, gantenerumab (optionally in combination with solanezumab), solanezumab (optionally in combination with gantenerumab), a sigma-1 receptor agonist (optionally also an M2 autoreceptor antagonist such as ANAVEX2 (bulcamesine), AVP-786 or AXS-05, or an NMDA receptor antagonist ), SV2A modulators (such as AGB101 (low dose levetiracetam)), mast cell stabilizers (such as ALZT-OP1 (cromolyn + ibuprofen)), anti-inflammatory agents (such as ALZT-OP1 (cromolyn + ibuprofen)), RAGE antagonists (such as azeliragon), glutamate modulators (such as BHV4157 (troriluzole)), D2 receptor partial agonists (such as brexpiprazole), serotonin dopamine modulators (such as brexpiprazole), amyloid vaccines (such as CAD106), bacterial Protease inhibitors (such as COR388), selective serotonin reuptake inhibitors (such as escitalopram), antioxidants (such as ginkgo), plant extracts (such as ginkgo), alpha-2 adrenergic agonists (such as guanfacine), omega-3 fatty acids (such as ethyl eicosapentaenoate (IPE), a purified form of eicosapentaenoic acid), angiotensin II receptor blockers (such as losartan), calcium channel blockers (such as amiodipine), cholesterol agents (such as atorvastatin), angiotensin I receptor blockers (such as losartan), calcium channel blockers (such as amiodipine), cholesterol agents (such as atorvastatin), angiotensin I receptor blockers (such as losartan), calcium channel blockers (such as losartan), angiotensin I receptor ... combinations of I receptor antagonists (such as losartan), calcium channel antagonists (such as amiodipine) and cholesterol agents (such as atorvastatin), tyrosine kinase inhibitors (such as masitinib), insulin sensitizers (such as metformin), dopamine reuptake inhibitors (such as methylphenidate), alpha-1 antagonists (such as mirtazapine), acetylcholinesterase inhibitors (such as octohydroaminoacridine succinate), ketogenic stimulants (such as tricaprylin), caprylic triglyceride (such as tricaprylin),The therapeutic agent may be a tau protein aggregation inhibitor (such as AADvac1 or TRx0237 (LMTX)), a positive allosteric modulator of the GABA-A receptor (zolpidem and zoplicone), or BPDO-1603, or any combination thereof administered together or separately.

[0054] If an individual scores low in visuospatial function, a prescription of memantine / donepezil may be suggested. If an individual scores low in executive function, a prescription of metformin may be suggested. If an individual scores low in perceptual-motor coordination, a prescription of TRx0237 may be suggested.

[0055] Prescription of aducanumab (Aduherm) may be suggested.

[0056] The proposed intervention may be a pharmaceutical intervention, and the information may relate to the frequency and / or dosage of the pharmaceutical intervention or a particular drug to be administered to the individual.

[0057] The individual may have previously been diagnosed with mild cognitive impairment, and the information regarding pharmaceutical or other interventions provided by the information output relates to whether a previously prescribed intervention was effective for the individual.

[0058] According to another embodiment of the present invention there is provided a method for diagnosing Alzheimer's disease comprising the method as described above, further comprising the step of diagnosing Alzheimer's disease based on the impairment score or the composite score.

[0059] According to another embodiment of the present invention there is provided a method for diagnosing mild cognitive impairment comprising the method as described above, further comprising the step of diagnosing Alzheimer's disease based on the impairment score or the composite score.

[0060] According to another embodiment of the present invention there is provided a system for diagnosing Alzheimer's disease comprising a system as described above, wherein the processor or system is operable to make a diagnosis of Alzheimer's disease based on the impairment score or the composite score.

[0061] According to another embodiment of the present invention there is provided a system for diagnosing mild cognitive impairment comprising a system as described above, wherein the processor or system is operable to make a diagnosis of Alzheimer's disease based on the impairment score or the composite score.

[0062] In practice, the method and system described herein are typically used on individuals who have previously been diagnosed with mild cognitive impairment. Its output is intended to be used as an adjunct to other diagnostic assessments to identify whether MCI is based on AD (i.e., whether the individual has pre-symptomatic AD). It may be used to predict whether individuals with mild cognitive impairment will progress to develop dementia, particularly dementia caused by Alzheimer's disease.

[0063] However, broader uses may also be envisaged: for example, they could be used to identify MCI (e.g. MCI due to AD) in individuals who had not noticed any disorder. [Brief description of the drawings]

[0064] A preferred embodiment is now described, by way of example only, with reference to the accompanying drawings, in which: Figures 1 to 6 show examples of user interfaces for exercise testing; Figures 7 to 16 show examples of user interfaces for the Back-in Time task; Figures 17 to 23 show examples of user interfaces for the Day-Out task; FIG. 24 illustrates an exemplary login screen of an embodiment of a dashboard for accessing test results; FIG. 25 shows an exemplary search field for subject test results; FIG. 26 shows an exemplary overview of test results for subjects; FIG. 27 shows an example PDF report for subject 2 in FIG. 26; Figure 28 shows the receiver operating characteristic (ROC) curves of the classifier; Figure 29 shows the dependencies between variables identified in the selected data set; Figure 30 shows the importance of MMSE, FAQ and DM features in ADNI data for the best logistic regression estimator for classifying subjects into cognitive normal and MCI; FIG. 31 shows the ROC curve of the classifier for another embodiment; Figure 32 shows the operation of SHAP (effect on output); Figure 33 presents an illustration of variance. Left: longitudinal data of an individual patient. Right: variance (dots) of the performance of the patient at different time points (A, B, C) represented by the population mean (line) picked using the neuropsychological assessment taught in this application (upper curve) and the traditional neuropsychological assessment (lower curve). The SD is related to the variance over time (LTRS) of a given subject. Dotted line: indicates the true variance; Figure 34 shows a schematic illustration of LTRS (top) and LDVS (bottom) (numbers 17.3 and 41.5 are random examples). The left third of the line indicates low risk, the middle third indicates medium risk, and the right third indicates high risk; Figure 35 shows the combined longitudinal risk matrix obtained from the two measures shown in Figure 34 (the overlapping areas allow for a more nuanced interpretation); Figure 36 shows exemplary intrapersonal variability scores; Figure 37 shows the dispersion indices plotted for the three different groups based on the LTRS and neuropsychological tests and converted to standard deviations; FIG. 38 shows the indices of dispersion plotted across tasks, showing the intra-individual standard deviation (iSD) for the healthy control group (A), the MCI group (B) and the AD group (C); and FIG. 39 is a schematic diagram of an embodiment of an apparatus configured to implement the systems and methods taught herein. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0065] Early clinical recognition of AD is important so that physicians can treat subjects with prescription medications to alleviate the symptoms and associated burden of the disease, and so that caregivers can address changes in cognitive function, mood, and personality. Early detection also creates opportunities to participate in clinical trials. However, currently, there is a lack of tools to help physicians assess cognitive function when diagnosing AD.

[0066] Currently, doctors rely on a number of mental and neuropsychological tests to assess symptoms associated with AD, such as declines in memory, abstract thinking, problem solving, language use, and other cognitive skills. For example, doctors use techniques such as the Alzheimer's Disease Assessment Scale-Cognitive Behavior (ADAS-Cog), the Mini-Mental State Examination (MMSE), or the Clock Drawing Test to assess the level of cognitive impairment in subjects with AD. Furthermore, meta-analysis data from longitudinal studies shows that a complete neuropsychological assessment can significantly contribute to predicting dementia while an individual is still in the MCI stage.

[0067] Although early clinical recognition of AD is important, there are currently no tools to help assess cognitive impairment, especially in individuals with MCI, predict progression to AD, or assist physicians in making a diagnosis of AD. Current assessment methods (such as those described above) are cumbersome and often burdensome for subjects.

[0068] This application describes a computerized cognitive assessment support device that provides measurements of cognitive performance to aid in the assessment of impaired cognitive function and assist physicians in predicting and diagnosing AD. The device is used to identify potential cognitive decline in adult subjects by comparing it with baseline test performance of other adults without AD, and allows cognitively impaired subjects to undergo further testing if necessary. The system disclosed in this application is an algorithm-based software application that runs on a variety of hardware platforms, typically portable electronic devices such as tablets and smartphones. In a preferred embodiment, the device includes functionality for (1) a graphical user interface (GUI); (2) to manage power for motor, visual, perceptual, and memory testing; and (3) to assist in generating, printing, and archiving test reports in real time.

[0069] A preferred embodiment is configured as an application (app) designed to run on a portable electronic device such as a tablet or smartphone. The app can perform a series of tests to be performed by the subject, for example evaluating perceptual-motor coordination, complex attention, cognitive processing speed, inhibitory function, cognitive flexibility, visual perception, planning, prospective memory, and / or spatial memory. Such tests may include motor tests to evaluate the subject's hand movements. These tests may also further include so-called backtracking and day-out tasks, evaluating the subject's ability to navigate and / or perform tasks in a predefined order.

[0070] The system is configured to request the user to carry out various tests on his / her portable electronic device, presented to him / her by an app, which records the results of the tests in the form of a set of activity parameters including at least one of the following: 1) spatial memory accuracy; 2) accuracy of planning; 3) the ability to perform dual-task interactions during navigation to a goal, where deficits in dual-task interactions are measured; 4) perseveration on incorrect dual-task interactions during navigation to the goal; 5) the total time taken by the individual to complete the navigation route; 6) upper limb neuromotor parameters; 7) Dual-task interaction reaction time; and 8) Individual idle reaction time.

[0071] These results are then provided to a processor, which may be remote from the individual's device. An algorithm is executed to calculate metrics pertaining to the measured activity parameters. The metrics are mapped to various cognitive domains, and percentile rank scores may be calculated for each cognitive domain. From these, an impairment score is calculated that indicates the individual's cognitive performance. This score (and other relevant information, e.g., the scores for each individual cognitive domain) can then be accessed remotely by a physician or other healthcare professional, such as from a desktop computer at a medical facility.

[0072] The system provides healthcare professionals with an objective measure of cognitive performance and can be used as an adjunct tool to help evaluate an individual's sensory and memory function.

[0073] For individuals, the system would provide a personalized cognitive profile, which could also be applicable to family members, allowing time to explore options to help mitigate the risk of cognitive decline and also identifying subjects early for participation in clinical trials.

[0074] The preferred system further provides the ability to measure cognitive function using a non-invasive handheld software device, aiding in the diagnostic evaluation of certain diseases such as AD, facilitating early intervention and management of AD with available pharmaceutical options. The non-invasive nature of the system allows frequent assessments and allows for multiple measurements to be taken over time, which can better reflect the overall status of the subject, as opposed to a snapshot in time.

[0075] Such longitudinal use of the system can assist in monitoring the brain health of individuals over time. For example, healthy individuals can be monitored for the onset of MCI. Individuals with MCI can be monitored for cognitive decline. Preferred embodiments of the system have also been shown to be highly predictive of individuals with MCI who subsequently convert to AD, allowing for interventions to prevent or delay the onset of dementia. The system can thus be used to predict conversion from MCI to AD, helping physicians determine and prescribe medications or other interventions. Given the detailed information the system can obtain from the user, the system can also be used to suggest specific medications for a given individual based on the results obtained.

[0076] In one embodiment, an individual can perform the test at home using a portable electronic device, such as a smartphone. The performance results in a score. By repeating the test, for example, daily, weekly, or monthly, the brain health of the individual can be monitored. Both the magnitude and rate of any decline can be monitored over time. For an apparently healthy individual, signs of mild cognitive impairment can be detected, and the system can suggest appropriate interventions to the individual's doctor, for example, to improve / prevent further decline in a particular cognitive domain. Furthermore, the system can be useful for monitoring the effectiveness of drug treatments for individuals previously diagnosed with MCI. The system can quickly identify therapeutic procedures or other interventions that are no longer effective, and improved drugs or other treatments can be suggested.

[0077] Drugs that may then be prescribed to slow or prevent further deterioration or to treat the condition include cholinesterase inhibitors (such as donepezil, rivastigmine, galantamine), memantine (optionally in combination with a cholinesterase inhibitor), monoclonal antibodies (such as aducanumab (Aduherm)), BAN2401, gantenerumab (optionally in combination with solanezumab), solanezumab (optionally in combination with gantenerumab), sigma-1 receptor agonists (optionally also ANAVEX2 (bulcamesin), AVP-786 or These include M2 ​​autoreceptor antagonists or NMDA receptor antagonists such as AXS-05, SV2A modulators (such as AGB101 (low dose levetiracetam)), mast cell stabilizers (such as ALZT-OP1 (cromolyn + ibuprofen)), anti-inflammatory agents (such as ALZT-OP1 (cromolyn + ibuprofen)), RAGE antagonists (such as azeliragon), glutamate modulators (such as BHV4157 (troriluzole)), D2 receptor partial agonists (such as brexpiprazole), serotonin dopamine modulators (such as serotonin and dopamine modulators), and serotonin and dopamine modulators. Antioxidants (such as brexpiprazole), amyloid vaccines (such as CAD106), bacterial protease inhibitors (such as COR388), selective serotonin reuptake inhibitors (such as escitalopram), antioxidants (such as ginkgo), plant extracts (such as ginkgo), alpha-2 adrenergic agonists (such as guanfacine), omega-3 fatty acids (such as ethyl eicosapentaenoate (IPE), a purified form of eicosapentaenoic acid), angiotensin II receptor blockers (such as losartan), calcium channel blockers (such as amiodipine), ), cholesterol agents (such as atorvastatin), combinations of angiotensin II receptor antagonists (such as losartan) and calcium channel blockers (such as amiodipine) and cholesterol agents (such as atorvastatin) with or without exercise, tyrosine kinase inhibitors (such as masitinib), insulin sensitizers (such as metformin), dopamine reuptake inhibitors (such as methylphenidate), alpha-1 antagonists (such as mirtazapine), acetylcholinesterase inhibitors (such as octohydroaminoacridine succinate),These may include ketone stimulants (such as tricaprylin), caprylic triglyceride (such as tricaprylin), tau protein aggregation inhibitors (such as AADvac1 or TRx0237 (LMTX)), positive allosteric modulators of the GABA-A receptor (zolpidem and zoplicone), or BPDO-1603, or any combination thereof administered together or separately.

[0078] Depending on the results, the system may suggest pharmaceutical intervention, may suggest changes to an already implemented pharmaceutical intervention (such as a change in dosage or form of administration), and / or may indicate whether the intervention should continue to be effective.

[0079] The system also provides the physician with the opportunity to examine the scores obtained by an individual in the test domains and can determine the most appropriate intervention for that individual.

[0080] Described below are possible implementations of the method and system, which may be implemented using a user's portable electronic device, such as a smartphone or tablet. Example 1 A. User Tasks

[0081] The user is presented with a series of visual and auditory stimuli, both sequentially and simultaneously, to measure the user's ability to respond to a variety of auditory and visual stimuli. The subject is asked to perform three tasks: a motor test, a back-tracking, and a day-out task. These three types of tests, with different levels of difficulty, characterize the subject's performance in each of the functional domains tested. The tests are performed in one session, with a short break (30 seconds) between tests. a. Exercise test:

[0082] The motor test includes three successive types of tasks that require the subject to perform hand movement tests on a screen. Figures 1 to 6 show an exemplary representation of the tests on the screen of a portable electronic device. The first type asks the subject to trace a colored path (Figures 1 and 2) as accurately and quickly as possible. The second type (Figures 3 and 4) imposes a time limit. The third type asks the subject to tap on a target object as accurately and quickly as possible as soon as it appears in the presence of distractors (green and grey circles in Figures 5 and 6). b. Backwards:

[0083] In the "retracing" test, augmented reality is used to test the subject's ability to place and retrieve a series of virtual objects while being perturbed by audio signals. Figures 7 to 16 show examples of what the subject sees on the screen of his or her portable electronic device.

[0084] The subject is instructed to use augmented reality to place three virtual objects in the appropriate locations in his / her real environment (see Figures 7 and 8). To initialize the virtual reality tracking, the subject is asked to walk around the room a few steps while holding the device at an angle of approximately 60 degrees (see Figure 9). After successfully placing all three objects (see Figures 10 and 11), the subject is instructed to pick up the objects again by pointing the device's camera at the location where he / she placed them (see Figure 12). Before the objects can be picked up, the subject is asked to walk back to the location where the object placement scene started (see Figure 13).

[0085] To pick up an object, the subject must respond to an audio signal (such as a high-pitched beep) that prompts the subject to press a button at the bottom of the screen (see instructions in Figures 14 and 15). The order in which the subject is asked to pick up the objects is randomized each time, ensuring that the last object placed is never the first object found. If the subject cannot remember where they placed one of the objects, they can skip that object using the skip button (see Figure 15). Once all objects have been found or skipped, or three minutes have elapsed, the test ends and the subject must answer two questions about the first object placed and the first object looked for (see Figure 16). a. Day out tasks:

[0086] The Day Out task uses augmented reality features similar to the Backwards task described above. The subjects are confronted with a situation where they need to escape from a fire, where three actions are performed in a set order: 1) the alarm is activated, 2) the fire department is called, and 3) important documents are rescued (Figures 17 and 18). To do this, the subjects need to use augmented reality to place three objects around them that represent these actions. Specifically, the subjects need to use augmented reality to place 1) an alarm button, 2) a phone, and 3) documents around them, just like in the Backwards task described above (see Figure 19). The subjects then pick up these three objects and perform the task.

[0087] The order in which the subject is asked to place the objects is randomized, but subjects are not allowed to place the alarm button last. The order of actions to pick up the objects (perform the task) is fixed as above (see Figure 20). Again, the subject is asked to respond to an audio signal (such as a beep) while performing the sequence of actions (see Figure 21). Unlike the backtracking task, the subject is shown high and low tone signals, but is asked to respond only to the high-pitched audio signal (the beep) (see instructions in Figure 21). While the object needs to be found, the screen is engulfed in an animation of a fire, mimicking the urgency of a fire drill situation (see Figure 22).

[0088] Once the entire task has been completed, skipped, or the three minutes have elapsed, the test ends with two questions about the first item placed and the first item found (see Figure 23). The answer to the second question about which item was found first is always the alert button (unlike the situation for the retroactive task).

[0089] The system (preferably a software application) tracks the subject's response errors and reaction times. As described above, the device presents a combination of visual and auditory stimuli, either sequentially or simultaneously, depending on the task.

[0090] Participants are scored based on the timing and accuracy of their responses, as well as movement data, such as hand movements and walking patterns, as they place and pick up items in real space, which is generated based on data from the device's sensors. B. Principle of Action

[0091] The system described above allows for the automated characterization of aspects of perceptual, neuromotor, and memory function associated with human cortical information processing. This assessment is accomplished by tracking the subjects' response errors and reaction times, and recording the subjects' ability to respond to changes in auditory and visual stimuli. The tests are rapid (taking only 10 minutes), comprehensive (including many brain functional domains), and non-invasive (subject contact is limited to a portable electronic device).

[0092] The above tasks define a set of performance measurements (k1 through k8). These measurements include: (k1) spatial memory accuracy, measured as the number of correct items selected; (k2) Planning accuracy, measured as accurate prospective memory task execution (correct ordering of subtasks); ● (k3) Lack of dual task interaction between start and goal; ● (k4) Perseveration on incorrect dual-task interactions during navigation to the goal; ● (k5) the total time to complete navigation for each item; ● (k6) Upper limb neuromotor parameters, i.e. movement agility, movement speed, and movement smoothness to task completion (derived from signal processing of 3D acceleration data provided by the iPad's sensors); ● (k7) reaction time of a “dual-task” interaction, measured as the time elapsed between the stimulus and the response; and ● (k8) There is an “idle state” reaction time (e.g. an individual’s reaction time to an appropriate auditory signal) measured as the time elapsed between the subject’s idle state and the next immediately following interaction response for the performance of the “dual task.”

[0093] In this embodiment, measurements k1 to k8 are used in a scoring algorithm to calculate a functional impairment score. Specifically, a total of 660 metrics are calculated from the data generated during the administration of the test, which belong to a set of activity parameters (k1-k8 above). The calculations involved are algorithm-based and include, but are not limited to, signal analysis, sensor fusion, algebraic integration, Fourier analysis, and wavelet analysis. Given a database of metrics for multiple subjects, an algorithm can be trained to score new subjects based on the 660 metrics.

[0094] The resulting metrics are mapped to a total of nine cognitive domains (see Table 1). [Table 1]

[0095] For each cognitive domain, a percentile rank score is calculated and adjusted for age and sex. The percentile of a cognitive domain describes what percentage of a healthy population of the same age group and sex performs worse than the subject. Thus, a value of 50% suggests average performance, and higher values ​​suggest above average performance.

[0096] In addition, a single output measure or score is presented: a score of 0-50 suggests that the subject belongs to the "disabled" class, whereas a score above 50 suggests that the subject belongs to the "non-disabled" class. Information about percentiles of cognitive domains may in some cases be useful for interpreting scores, for example explaining why scores may be very low in individual cases. C. Display of results

[0097] The test results for each subject can be accessed and reviewed by medical personnel using a dashboard (an example of which will be provided by the applicant). An example is shown in FIG. 24.

[0098] When the healthcare professional enters the “My Patients” tab, a search field is presented as shown in Figure 25. Once the user enters the patient ID, the test results for each of the subject's sessions are presented.

[0099] FIG. 26 presents example results for subjects. On the right side of the heading, circles (red or green) are shown next to the items. If the score is greater than 50, a green circle is shown (subject 1). If the score is less than 50, a red circle is shown (subject 2). A score greater than 50 indicates that the subject's performance does not correlate with the biological signs of pre-symptomatic AD based on β-amyloid aggregation (Aβ42 / 40 ratio) and therefore there is no possibility of cognitive impairment related to AD. A score less than or equal to 50 indicates that the subject's performance correlates with the biological signs of pre-symptomatic AD based on β-amyloid aggregation (Aβ42 / 40 ratio) and therefore there is a possibility of cognitive impairment related to AD.

[0100] As shown in Figure 26, once an item in the heading (in this case Subject 2) is selected, further information is presented as a radar chart below the heading, with the scores shown above and each of the cognitive domain percentiles surrounding the chart.

[0101] Next to the circle (red or green as appropriate) is a PDF download icon that provides a downloadable PDF report. Figure 27 shows an example of such a report (for subject 2 in Figure 26). If the score is less than 50, the report states "AD-related cognitive impairment: likely." D. Statistical performance

[0102] This classifier tests whether it is possible to separate MCI subjects into either MCI / Ab- or MCI / Ab+, in other words whether it is possible to detect amyloid beta status in MCI subjects. The performance of this classifier is plotted in Figure 28. The model is built using the following data of MCI patients: Full dataset: 120 subjects, 426 data points MCI / Ab-: 42 subjects, 101 data points MCI / Ab+: 78 subjects, 325 data points

[0103] Statistics at Youden's optimal cutoff (0.81 + / - 0.15) are as follows (Table 2): [Table 2] E. Validators

[0104] To evaluate the technical performance of the software, the machine learning algorithms were cross-validated using nested k-fold techniques, demonstrating robust performance. Additionally, data collected to date shows promise for clinical success in providing a measure of cognitive performance and helping physicians assess cognitive impairment for use in diagnosing AD. Specifically, scores (impaired / not impaired) are correlated with readings from the MMSE using a bootstrap Bayesian network.

[0105] The link between the acquired digital measurements and cognitive characteristics such as the MMSE was analyzed via a recently developed artificial intelligence (AI) methodology called the Variational Autoencoder Modular Bayesian Network (VAMBN) (Gootjes-Dreesbach et al. (2020), the contents of which are incorporated herein by reference), which is a hybrid of a Variational Autoencoder and a Modular Bayesian Network. In addition, the possibility of accurately predicting MMSE subitem scores from the digital measurements and vice versa via machine learning was also tested.

[0106] We simulated digital measurements within the AD Neuroimaging Initiative (ADNI) cohort and ran VAMBN again. Applying VAMBN to data from the virtual reality game resulted in a network that included digital measurements, MMSE subitem scores, and demographic characteristics. Figure 29 shows the variable dependencies identified for the dataset in 1000 bootstrap Bayesian network (BN) (strength ≧ 0.5 and direction ≧ 0.5) reconstructions. These edges show the variable dependencies typically seen in bootstrap Bayesian network reconstructions.

[0107] This network thus allows disentangling and quantifying the relationship between the digital measurements and the obtained clinical scores. Simulation of the digital measurements in the ADNI cohort and application of the VAMBN further allows predicting the connectivity of the digital measurements to features reflecting functional activities of daily life, such as the FAQ (Functional Assessment Questionnaire), or even molecular mechanisms. To evaluate the sensitivity of the digital measurements to classify subjects into cognitively normal (CN) and mild cognitive impairment (MCI), two logistic regression binary classifiers were trained on data from the virtual reality game and the ADNI cohort.

[0108] These results show that there is a strong dependency between digital measures and clinical scores such as MMSE and FAQ. Therefore, digital measures have the potential to act as crucial measures in predicting AD at the presymptomatic stage. Evaluation of the diagnostic merits of digital measures led to the realization that digital measures rank higher in the performance of classifying subjects into CN and MCI than some of the features such as MMSE and FAQ. Figure 30 shows the importance of MMSE, FAQ and DM features in ADNI data for the best logistic regression estimator for classifying subjects into CN and MCI.

[0109] In addition, studies have shown that scores in MCI subjects detect biological signatures of pre-symptomatic AD based on β-amyloid aggregation (Aβ42 / 40 ratio) with ROC-AUC>94% (Bugler et al. (2020) and Tsnanas et al. (2015); the contents of which are incorporated herein by reference). This signature of β-amyloid aggregation has been suggested to predict MCI subjects who will convert to AD (Sorensen et al. (2020)). Example 2

[0110] In the above embodiment, cognitive impairment is obtained by measuring eight activity parameters. In other embodiments, it is not necessary to measure all eight activity parameters. In one embodiment, a single parameter can be measured, and it can be an upper limb neuromotor parameter (for example, the agility, speed, and smoothness of movement to complete the task as defined in k6 of embodiment 1).

[0111] Figure 31 shows the ROC curve of the classifier for this example, and Figure 32 shows the behavior of SHAP (effect on output). It can be seen that even when a single activity parameter is measured, a useful impairment score can be obtained.

[0112] Statistics at Youden's optimal cutoff (0.20 + / - 0.12) are as follows (Table 3): [Table 3]

[0113] Healthy controls were shown to be distinguishable from AD, pre-symptomatic AD and MCI / amyloid beta positive individuals. Example 3

[0114] The above methods and systems (composite scores) were used in studies to measure individual-level changes in AD. Variance measured with the above-mentioned scoring systems was compared to traditional neuropsychological assessments to monitor the disease, characterize longitudinal risk trajectories, and predict cognitive transition events (healthy to MCI, and / or MCI to AD). method Research Structure

[0115] Two experiments (Study A and Study B) were conducted to evaluate the obtained scores against a set of established neuropsychological assessments as baseline. Study A (ClinicalTrials.gov identification number: NCT02050464) was a semi-naturalistic observational study including 29 participants, over 65 years old, diagnosed with mild to moderate AD, and recruited at the Hirschlanden Clinic in Zurich, Switzerland. Study B (ClinicalTrials.gov identification number: NCT02843529) was also a semi-naturalistic observational multicenter study including 496 participants (213 MCI and 283 healthy controls (HC)) and was conducted in 10 memory clinics and primary care centers in Europe and two primary care community centers in the United States. Thus, a total of 525 participants were enrolled in the two studies. These participants were cognitively healthy (n=283) or had been diagnosed with MCI (n=213) or AD (n=29). The studies had similar inclusion criteria (acceptance / rejection) and clinical scales, and we characterized AD biomarkers using the same criteria as in the analysis. Both studies were approved and initiated by the local Institutional Review Board (IRB), i.e., the Bioethical Committee of the Ionian University of Corfu, Greece.

[0116] In these studies, cognitive performance of three groups of participants, i.e., HC, MCI and AD, was measured using a composite score as described above, and a series of conventional paper-and-pencil neuropsychological assessments. Thus, in this retrospective observational analysis, the independent variable is the test method, either the composite score as described above or the neuropsychological assessment (detailed in the Materials section), and our key dependent variable is variance. participants

[0117] In both studies A and B, participants with any serious neurological illness (e.g., Parkinson's disease, Huntington's disease, normal pressure hydrocephalus, brain tumor, progressive supranuclear palsy, seizure disorder, subdural hematoma, multiple sclerosis, or a history of significant head trauma followed by persistent neurological normality or known structural brain abnormality) were excluded at the recruitment stage. In study B, further inclusion criteria were: (1) age between 55 and 90 years, (2) fluency in English, French, Spanish, Greek, German, or Italian, and (3) familiarity with digital devices, including current ownership and active use of an iPad Pro or iPhone and having a Wi-Fi network at home for remote assessment. Using these criteria, a group of 283 cognitively healthy individuals was initially recruited through the same procedure at the Global Brain Health Institute (GBHI), Trinity College Dublin. Biomarkers (CSF, brain MRI and ApoE genotype) were used as criteria to recruit participants with cognitive impairment, and cognitive deficits compatible with a diagnosis of MCI were found in 213 subjects: 170 from memory clinics and primary care centers in different European countries (detailed in the procedure section below) and 43 from community centers in the United States. Seven participants were excluded from the data analysis due to poor data quality. The study B cohort consisted of HCs (n = 283) and patients with MCI at high risk of developing AD within 18–40 months (n = 213), assessed every 6 months. The MCI and AD cohorts were included independently based on their respective biomarker status if the respective diagnoses were consistent with a diagnosis of MCI and Alzheimer's dementia according to the major criteria of the revised NIA-AA guidelines (Jack et al. (2011)). The cohort of participants in Study B is further detailed in Bugler et al. (2020). A cohort from Study A (symptomatic AD patients from the Hirschlanden Clinic, Zurich, Switzerland) was added for control and comparison (n = 29).Participants were matched for gender and education level, with no statistically significant differences in cognitive performance between age groups for education (p = 0.43, Cohen's d = 0.4), or gender (p = 0.68, Cohen's d = 0.3) variables. procedure

[0118] Upon enrollment, all participants provided written informed consent to participate in the study and to reuse of their data. In all groups (HC, MCI, and AD), the composite score test as described above was administered over 2 days every 6 to 8 months; day 1 included practice and the first measurement, and day 2 included a "refresher practice" followed by the second measurement. One hundred participants used the composite score method described above at home on day 2 (their measurements were validated against measurements obtained in the clinic before being included in the analysis).

[0119] In general terms, the procedure included the following: 1) Smart devices incorporating the system disclosed in this application were given to primary care physicians and memory clinics and evaluated in their clinics. 2) The method was carried out over two days at baseline: Day 1 (practice and first measurement); Day 2 (refresher practice and second measurement). 3) In some locations (study B with healthy controls and participants with MCI), the second day was conducted unsupervised at home for a total of n=100 subjects. These assessments showed the same performance as the clinic visit assessments on day 1. 4) Neuropsychological tests as disclosed herein were administered at baseline and at follow-up intervals of 6 months.

[0120] The duration of the first composite score test was 20 min including practice (10 min practice, 2 min rest, 8 min measurement). After establishing this baseline, the composite score test, administered every 6 to 8 months, took an average of 8 min. Traditional neuropsychological assessments take 120–140 min with rest per visit. Every 6 to 8 months, participants were also assessed for clinical and neuropsychological status using the Mini-Mental State Examination (MMSE) or Montreal Cognitive Assessment (MOCA), and clinically examined for conversion from MCI to dementia (due to AD or not related to AD) based on the core diagnostic criteria of the NIA-AA (Jack et al. (2011)). Clinical diagnoses of MCI / dementia / AD were confirmed by researchers blinded to the predictor variables of this study.

[0121] Participants in Study A were tested over a total period of 48 months between 2013 and 2017, and participants in Study B were tested over a total period of 40 to 42 months between 2017 and 2020. Participating memory clinics were located in Greece, Italy, Spain, Ireland, Switzerland, and the United States. In detail, the following facilities enabled data collection for Study B: Greek Alzheimer and Related Diseases Association "Ag. Giannis", "Ag. Eleni" Memory Clinic, Thessaloniki, Greece; La Sapienza Memory Clinic, University of Rome, Rome, Italy; IRCCS Centro San Giovanni di Diofate Benefratelli Memory Clinic, Brescia, Italy; Neuromudo IRCCS Memory Clinic, Naples, Italy; Fundación Clinic Perala Recerca Biomedica Memory Clinic, Barcelona, ​​Spain; St. James Memory Clinic, Trinity College Dublin, Dublin, Ireland; BiHELab - a network of bioinformatics and human electrophysiology laboratories and associated attending physicians on the island of Corfu, Greece; two offices of the Personalized Medicine Practice Department at Hirslanden Private Hospital, Zurich and Aarau, Switzerland; Scripps Health, La Jolla, CA, USA; and The University of Texas Brain Health Center, Dallas, TX, USA. material

[0122] Baseline neuropsychological (NP) assessment. The baseline NP assessment included a comprehensive battery of tests: the WMS-R Wechsler Memory Scale (adjusted for education) (WMS-IV (2009)), the MMSE (Folstein et al. (1975)) or MOCA (Nasreddine et al. (2005)), the Clinical Dementia Rating Scale (CDR) Memory box score (Morris (1993)), and a full neuropsychological battery (WMS-IV (2009)) including assessments of forward digit span, backward digit span, Trail Making Test A, Trail Making Test B (Butler et al. (1991)), Rey 15-word Auditory Verbal Learning Test (RAVLT) total, RAVLT A6, RAVLT B7, RAVLT C8, RAVLT D9, RAVLT E10, RAVLT F11, RAVLT F12, RAVLT F13, RAVLT F14, RAVLT F15, RAVLT F16, RAVLT F17, RAVLT F18, RAVLT F19, RAVLT F19, RAVLT F20, RAVLT F21, RAVLT F18, RAVLT F19, RAVLT F22, RAVLT F19, RAVLT F23, RAVLT F19, RAVLT F24, RAVLT F19, RAVLT F25, RAVLT F30, RAVLT F40, RAVLT F16, RAVLT F17, RAVLT F18, RAVLT F19, RAVLT F25, RAVLT F19, RAVLT F19, RAVLT F25, RAVLT F19, RAVLT F19, RAVLT F20, RAVLT F19, RAVLT F21, RAVLT F19, RAVLT F19, RAVLT F21, RAVLT F19, RAVLT F19, RAV A7 (RAVLT (1996)), Benton VRT (Benton Visual Retention Test, 5th edition (1991)), Digit Symbol (Kaufman (1983)), Block Design (Corsse Cube Combination Test, PsycNET (1932)), Similarity (Drozdick et al. (2018)), and Animal Name Recall Test (Benton (1968)). Collectively, these tests address 13 cognitive domains.

[0123] Global Score. Digital biomarker data on cognitive and functional performance is collected using the composite score described above. The composite score methodology selects the most promising indicators from previous work (such as those shown above) and reduces the test time from nearly 2 hours to 10 minutes. It also includes new measurements not used in the above context (e.g., measuring gait, touch pressure, walking path and tremor). This multivariate scoring increases the efficiency of digital phenotyping and allows for better evaluation of an individual's performance against their own unique history as well as against "normative" data based on others in the same cohort. The composite score described above captures over 320 individual characteristics such as reaction time, speed, attention and memory based assessments, and any and all device sensor inputs (or lack thereof) through accelerometer, gyroscope, magnetometer, camera, microphone, touch screen. The composite score methodology as described above was tested in an independent pilot study on a sample of young healthy controls across all cognitive domains described and the test-retest variability was found to be 0.156%. Such small variability indicates good internal validity of the composite score test and supports the representability and stability of the measure over time.

[0124] Additional biomarker testing. Additionally, AD biomarkers (cerebrospinal fluid (CSF) beta-amyloid and phosphorylated tau and total tau levels, brain MRI and ApoE genotype) were collected as specific baseline measurements for digital biomarkers obtained through composite score testing. To ensure a more nuanced understanding of the types of cognitive impairment; in the diagnosed population, classification into MCI and AD-based dementia (aMCI and ADD) or non-MCI and AD-related dementia (naMCI and nADD) was made based on CSF beta-amyloid and tau levels biomarkers. statistical analysis

[0125] To investigate the variability in the participants' cognitive abilities, a general and meaningful index was obtained that allows comparing the above-mentioned composite scores with the gold standard neuropsychological assessments. For this, the so-called dispersion index was used (e.g., Hultsch et al. (2008); Wojtowicz et al. (2012)). This was calculated for each individual based on their reaction times (including controls with a speed / accuracy trade-off), within each individual, and between healthy controls and the MCI and AD groups for the cognitive measures (Figure 33).

[0126] Dispersion indices are more reliable measures of central nervous system (CNS) integrity and individual cognitive structure than mean performance (Hultsch et al. (2008); Wojtowicz et al. (2012)). Individual dispersion profiles were obtained using regression techniques to calculate intrapersonal standard deviation (iSD) scores from standardized test scores. Dispersion profiles were obtained for all cognitive domains measured by the composite score tests described above and the neuropsychological test battery used in the study to make them directly comparable. Test scores from the neuropsychological assessment battery were first regressed for linear and quadratic age trends to control for between-group differences in mean performance. Controlling for between-group differences based on age is necessary because there tends to be a greater variability associated with larger mean and mean-level performances that are expected to differ across age groups, present in the study sample for participants with an age range of 55-90 years. Residuals from these linear and quadratic regression models were standardized as T-scores (M=50, SD=10), and then iSD was calculated for these residual test scores. The resulting dispersion estimates are indexed on a common metric and reflect the amount of variation across individuals' neuropsychological profiles relative to the group mean (Figure 33). The group mean is derived from the participants' performance levels across measures. Higher values ​​of the dispersion index reflect greater intraindividual variability in cognitive function.

[0127] We then calculated longitudinal risk trajectory scores (LTRS) and longitudinal decline velocity scores (LDVS) across the 11 composite scores and 13 traditional neuropsychological cognitive / functioning domains (see below).

[0128] For comparison of means between groups we used MANOVA (multivariate analysis of variance) and independent one-way ANOVA (analysis of variance) or T-tests, whereas for comparison of means within groups we used independent one-way ANOVA. Benjamin-Hochberg correction for multiple testing was applied for all statistical analyses, and an alpha value of 0.05 (p<0.05, two-tailed) was used. All statistical analyses were performed using the statistical software SPSS 22.0 for Mac. Longitudinal intraindividual variability related metrics

[0129] LTRS / LDVS. The Longitudinal Trajectory Risk Score (LTRS) quantifies the change for all cognitive domains, such as the amount of cognitive decline an individual suffers from, based on a multiple linear regression model (Figure 34, top). The LTRS does not take into account the length of time over which the decline occurs. It simply quantifies the magnitude of change captured by the observation. In contrast, the Longitudinal Decline Rate Score (LDVS) quantifies how quickly the change occurs and can therefore be used to assess whether the decline is occurring at a critical rate in each of the cognitive domains (Figure 34, bottom). The LDVS is also based on a multiple linear regression model. High values ​​of the LDVS suggest an unusually fast decline, and a weighted linear regression model is constructed for each cognitive domain of the composite score, using a simple linear regression with the rate of decline as the "weight". Preferably, participants undergo at least four complete tests over several weeks, and the LTRS and LDVS can be interpreted together in a risk matrix (Figure 35).

[0130] Intra-individual variability. Intra-individual variability quantifies fluctuations in an individual's cognitive performance and has been shown to sensitively detect neuropathology underlying cognitive and functional changes in the early stages of AD (Figure 36).

[0131] Intra-individual variability quantifies the variation over time in percentiles of cognitive domains. This value corresponds to the average variation of the subject's tests expressed as a multiple of the healthy subjects' variation in each domain. Preferably at least five tests are performed by the same participant. Intra-individual variability is a sensitive predictor of disease onset and conversion to AD. result

[0132] The variance score across the entire sample was 11.45 (SD=5.12) T-score units. Figure 37 shows the magnitude of variance within each cognitive status subgroup (healthy controls, MCI, AD) based on the LTRS and traditional neuropsychological assessments, indicating that digital biomarkers explain up to 2.6 times more intraindividual variability compared to traditional paper-and-pencil neuropsychological assessments.

[0133] Figure 37 shows the dispersion indices based on LTRS and neuropsychological tests, converted to standard deviations and plotted for the three different groups. These graphs show a nonlinear increase in standard deviation as a function of the disease trajectory. Comparing the overall means of LTRS and NP by group gives the following values: HC: t=10.00106, p<0.00001; MCI: t=7.02195, p<0.00001; AD: t=6.65272, p=0.000011, which are statistically significant at p<0.001. Details at the individual time points are shown in Table 4. [Table 4]

[0134] Estimation analysis for the comparison of values ​​shown in Figure 37 revealed that the intraindividual variability differed between groups (F(2,522)=34.252, p<001, η 2= 0.25), where the AD group (m = 23.78, SD = 4.54) showed the highest variability, followed by the MCI (m = 12.48, SD = 2.91), and HC (m = 8.09, SD = 1.64). Between-group differences across all domains were also observed based on the battery of 11 composite score domains (Table 4) versus 13 NP. The AD group showed greater variance than the MCI, which in turn was greater than the HC (Table 4), confirming the robustness of the measures.

[0135] Following the LTRS / LDVS analysis, longitudinal intraindividual variability for each group was also plotted, revealing a nonlinear increase in standard deviation as a function of disease trajectory (Figure 38). In Figure 38, intraindividual variability is consistently and significantly more sensitive than traditional neuropsychological assessments for detecting trends in disease trajectories, especially for preconversion events (the steep peaks in Figure 38B predict a higher likelihood of conversion from MCI to AD by the next assessment). The "distance" in the variance measures increases between the two assessment types (longitudinal intraindividual variability and neuropsychological assessment) as the disease progresses, indicating that longitudinal intraindividual variability is more sensitive to detect markers than neuropsychological assessments (Figure 38).

[0136] Figure 38 shows the indices of dispersion plotted for the task, showing the group intra-individual standard deviation (iSD) for the healthy control (A), MCI (B), and AD (C) groups. These graphs show a non-linear increase in SD as a function of disease trajectory. Intra-individual variability is consistently and significantly more sensitive than traditional neuropsychological assessments for trends in disease trajectories, especially for pre-conversion events (the steeper peaks in B predict a higher likelihood of conversion by the next assessment). LIIV is longitudinal intra-individual variability.

[0137] The results shown in Figures 37 and 38 provide evidence of the strength of the digital biomarkers, as the composite score domain includes measures of both LTRS and longitudinal intraindividual variability. Longitudinal intraindividual variability is a powerful preclinical risk predictor and determines conversion from MCI to AD (Figure 38B) through machine learning algorithms, while the LTRS shows higher sensitivity to changes in cognition than traditional neuropsychological assessments (Figure 37 and Table 4).

[0138] Taken together, these results indicate that the composite score dispersion metric is consistently and significantly more sensitive than traditional neuropsychological assessments in capturing trends in disease trajectories. In addition, the composite score assessment allows prediction of conversion events 6 to 8 months prior to the conversion event. These conversion predictors are characterized by a steep peak in intraindividual variability preceding the actual conversion, as shown in Figure 38B, and cannot be detected by traditional neuropsychological assessments. Consideration

[0139] In the above mentioned studies, we addressed a persistent problem in cognitive aging research: individual-level changes in cognition and function in dementia. Establishing when meaningful individual-level changes have occurred is useful for evaluating interventions for dementia and for preserving brain health throughout life (Livingston et al. (2017)). The two metrics considered in combination in this application (LTRS / LDVS and longitudinal intraindividual variability combined into a composite score) may provide a potential tool for medical practitioners. The LTRS / LDVS may be useful for evaluating the effectiveness of cognitive training, medication or therapy at the individual level, and it is a valuable alternative to the more frequently used reliability change index. Provided that the frequency of data collection is sufficient, the LTRS / LDVS allows individual changes in performance to be assessed more sensitively than in the case of traditional paper-and-pencil assessments, and without the inconvenience of having to contrast changes in a standard sample of subjects with the problem of intraindividual variability. Also, unlike traditional reliability change indexes, the longitudinal intraindividual variability provides a reliable tool for drawing conclusions based solely on individual performance. This is particularly valuable in the context of adaptive trials, which use information on an ongoing basis to maximise trial efficiency and to detect early disease progression events, including in the pre-symptomatic stages of dementia (Ritchie et al., 2016).

[0140] In the context of AD, variance has been shown to be a sensitive marker to detect changes in cognitive and functional abilities even in the presymptomatic stage of the disease (Hultsch et al. (2008); Wojtowicz et al. (2012)). Since significant effects in group-level statistics do not indicate (or even suggest) what changes have occurred for any one individual (Murray et al. (2021)), it is informative to establish meaningful changes at the individual level. Taking both of these facts into account, we analyzed the differences in variance between traditional NP assessments of 13 cognitive domains over a total of 120–140 min and 10-min composite score assessments of 11 cognitive domains, and compared the variance over 40 months in groups of HC, MCI, and AD participants. The composite score consistently showed a significantly higher sensitivity in capturing these changes with respect to disease trajectory trends. As shown in the LTRS / LDVS results (Figure 2, Table 1), this was especially true in the later stages of the disease and may be due to the combined domain uniquely incorporating function and cognition in the composite score.

[0141] These findings indicate that the composite score methodology described above is a useful tool for monitoring disease progression and as an endpoint in clinical trials. Moreover, intra-individual variability was consistently more sensitive than traditional NP assessments for identifying markers of disease trajectory trends (Figure 38). Intra-individual variability is also a particularly powerful marker among the composite score metrics for detecting pre-conversion events, enabling a tool that can predict MCI to AD conversion 6-8 months before the actual event. Such predictions not only allow for lifestyle interventions to delay conversion and maintain a healthy brain for a long time, but also give patients and families time for preparation, care coordination, and pharmacological interventions when available. In addition, this approach allows for the prospective and longitudinal assessment of biological (imaging, genetic, biochemical) and functional markers involved in dementia pathophysiology. This should help provide a greater understanding of disease manifestation and onset. Until now, it has not been possible to predict MCI to symptomatic AD conversion events many months in advance.

[0142] The composite score methodology differs from traditional neuropsychological assessments in that it captures multidimensional digital biomarkers and is not limited to latency or accuracy-based measurements. It integrates several objectively measured features into a single task. This integration creates a more generalizable "real-world situation" than traditional laboratory testing settings, thus increasing the ecological validity of the observations. With both the novel combination of many variables addressing 11 cognitive domains in one embodiment, and the sensor data, it is not surprising that the wealth of data collected by the composite score methodology results in high sensitivity, especially when considering variability measurements. The composite score digital biomarker platform generates a large amount of high-resolution data, including cognitive and motor processing; voice-based data indicating emotional states; and micro-errors that reveal where, when, and how disease manifestations are affecting daily life functioning. These data may be further leveraged to model disease progression, more accurately predict conversion events, and model drug effects, resulting in large-scale, non-invasive, lifelong monitoring of brain health.

[0143] It is important to note that both variance and intraindividual variability increase nonlinearly with age. The current data pattern reveals that larger variance across domains is associated with lower cognitive performance, likely reflecting reduced cognitive control. The steeper peak in intraindividual variability in the MCI group may be explained by the demands of executive function, a domain that is particularly affected in MCI due to the complexity of the composite score, in addition to internal and external factors such as worry and depression that are particularly influential at this stage of the illness.

[0144] Another important feature of the composite score method described above is its efficiency: the composite score test takes 10 minutes to administer, as opposed to 120 minutes for traditional neuropsychological test batteries, and produces comparable results even when administered at home (versus during a clinic visit). The heterogeneity / homogeneity characteristics of the composite score and changes in LTRS / LDVS or longitudinal intraindividual variability in various cognitive abilities may also be useful tools for clinicians.

[0145] The findings in this study highlight the sensitivity of digital biomarkers for detecting cognitive change and also open interesting directions for research on heterogeneity in cognitive change.

[0146] This study shows that active biomarkers are useful tools for monitoring disease progression in cognitive aging. Such tools can be used by primary caregivers without requiring significant training in dementia testing, providing the necessary resources to refer patients for re-examination or mitigate the debilitating effects of cognitive decline. The findings of this study are also relevant for clinical trials, since predicting conversion to AD 6 to 8 months before the event allows for the detection of meaningful changes that may also affect medication dosage and allows for closer patient monitoring. In addition, observing such changes early allows for the study of underlying disease markers just prior to conversion, contributing to an improved understanding of the pathophysiological process of AD and the potential discovery of new phenotypes of cognitive decline. conclusion

[0147] This study represents the first attempt to explore active digital biomarkers, such as those included in the composite score method described above, to detect meaningful changes at the individual level based on the newly employed metrics. Although the average scores of cognitive tests are important to characterize the disease, the intra-individual variability between tests holds a great deal of information that can be easily captured. The novel metrics using sensors in smart devices show increased sensitivity compared to traditional neuropsychological assessments. The composite score method described above was found to be 2.6 times more sensitive than traditional batteries for dementia and only requires 10 minutes. This "better" and "faster" performance makes the composite score method an excellent tool for patient care and can be used to determine whether an individual's symptoms have undergone meaningful changes for monitoring pharmaceutical interventions. Example 4

[0148] The above tests were performed monthly at home by individuals previously diagnosed with MCI using a composite score system on their smartphone, or more frequently if desired or appropriate. Each performance resulted in a composite score assessment consisting of a Longitudinal Trajectory Risk Score (LTRS) and a Longitudinal Development Velocity Score (LDVS). The composite score measures the treatment response and how it translates into cognitive and functional improvements in daily life functioning. It can be calculated monthly immediately after therapeutic intervention with a drug such as Aduhelm (aducanumab), where the LTRS and LDVS scores are added together. The range is 0-200, and a proposed visualization of the composite score is shown in Figure 35.

[0149] In this embodiment, LTRS progresses longitudinally for each cognitive domain over a given time window of 6 months. A linear regression model is then constructed using simple linear regression for each cognitive domain. The result is a linear equation for each cognitive domain i, y=ax+b: y_i=m_i*t+b_i. For each cognitive domain i, initialize LTRS=0. If the slope of this linear model is negative (i.e., there is a decline), add the absolute value of the slope to LTRS. If LTRS>100, set LTRS=100. LTRS scores range from 0 to 100. If the window from therapeutic intervention is less than 6 months, LTRS scores are used for calibration. Similarly, LDVS in this embodiment progresses longitudinally for each cognitive domain over a given time window of 1 month. A linear regression model is then constructed using simple linear regression for each cognitive domain. The result is a linear equation for each cognitive domain i, y=ax+b: y_i=m_i*t+b_i. If the slope of this linear model is negative at the critical rate (i.e., there is a decline within 1 month), then the intraindividual standard deviation (iSD) is calculated as the standard deviation across the standardized scores of the cognitive domains calculated for a single individual as a multiplier to the absolute value of the LDVS slope. Both the LTRS and LDVS scores are added together to generate a composite score (0–200).

[0150] In this example, a composite score of 150-200 means that the therapeutic intervention is working and no adjustments need to be made.

[0151] A composite score between 100 and 150 alerts the physician to examine the calculated cognitive domain percentiles for different cognitive domains (e.g., the nine cognitive domains listed in Table 1), and the system suggests to the individual's physician appropriate interventions to improve / prevent further deterioration in that cognitive domain. For example, if the patient scores low in visuospatial function, the system may suggest prescribing memantine (donezepill).

[0152] If the composite score is between 50 and 100, the system may suggest increasing the therapeutic agent. In one example, the therapeutic agent may be Aduhelm (aducanumab), an amyloid beta-directed antibody used to treat AD. In another example, the therapeutic agent may be AADvac1, a compound effective against harmful tau protein aggregation in the brain that has been associated with slower accumulation of neurofilament light chain (NfL) protein in one placebo-controlled randomized phase 2 study, suggesting slower neurodegeneration compared to patients receiving a placebo (Novak et al. (2021)).

[0153] In addition to this, physicians are also encouraged to further examine the calculated cognitive domain percentiles for different cognitive domains (e.g., the nine cognitive domains listed in Table 1), and the system will suggest to the individual's physician appropriate interventions to improve / prevent further deterioration in that cognitive domain, e.g., for executive function, metformin, a metabolic / bioenergetic compound currently in phase 3, and for sensorimotor coordination, TRx0237, a tau protein-directed antibody compound currently in phase 3 (Cummings et al. (2020)).

[0154] Finally, if the composite score is below 50, the system may suggest that the therapeutic intervention is at a critical stage or is failing for that particular individual / patient.

[0155] The system can thus be used to diagnose individuals with mild cognitive impairment or AD, or to predict whether an individual with mild cognitive impairment will convert to AD in time. It can also be used to assist physicians in prescribing appropriate interventions and / or helping determine whether an already prescribed intervention is effective. The system may thus assist physicians by suggesting to start an intervention, stop an intervention, or change an intervention, pharmaceutical or otherwise. It may suggest the appropriate frequency and / or dosage of a pharmaceutical intervention or a particular drug to be administered to an individual, and / or may suggest the appropriate route of administration of a pharmaceutical intervention to that individual. This applies to the particular pharmaceutical interventions mentioned above, such as those in Example 4, and to all other potential drugs, whether or not disclosed in this application.

[0156] One significant advantage of the system described herein is that it allows for the assessment of cognitive ability in a single test, as compared to standard neuropsychological assessments currently used for the diagnosis of AD. As a result, the measurement of cognitive function can be performed in approximately 10 minutes, as compared to the 2 hours required for traditional neuropsychological assessments (e.g., MMSE, ADAS-Cog).

[0157] One example of an apparatus 300 that can be used to implement the teachings of the present application is shown in Figure 39. The apparatus 300 in this example includes a mobile device 302 equipped with first and second cameras 304, 306, typically one facing forward (away from the user) and the other facing backward (towards the user and on the same side as the display). The mobile device 300 also typically includes an output unit 310, a position sensor 312 (such as a GPS module, accelerometer, etc.), a microphone 320, a user input unit 322, and one or more processing units 330, 340, 360.

[0158] The mobile device 300 is preferably a handheld portable device such as a smartphone. However, the mobile device 302 may also be any other portable user device. It may be, for example, a wearable such as a smart watch or bracelet, smart glasses or the like. The mobile device 300 may be a single device or may be realized in multiple devices, such as a smartphone associated with a smart watch or bracelet, or smart glasses. FIG. 39 illustrates such a smart device 420 as an external accessory configured to communicate with the mobile device 300.

[0159] The output unit 310 may include a display 316, which in some implementations may be a projector such as an eye projector in smart glasses. This output may also include an audio unit 318, such as a loudspeaker and / or an audio output port for earphones or headphones.

[0160] An internal device 400, typically a processing unit, advantageously an artificial neural network, may be provided for performing computing tasks remotely from the mobile device 300, including but not limited to the computation of data from multiple different subjects as presented in the teachings above. The processing unit 400 is typically coupled to the mobile device 300 to exchange data remotely, such as via the Internet, a wireless network or a GSM network. In some embodiments, the processing unit 400 may include a central processing computer. As will be appreciated, in some embodiments, all processing is performed within the device 300.

[0161] The device may also include an external optical sensor, such as a smart home camera or other camera 430, as described above, that is configured to capture images of the subject and transmit them to the mobile unit 300 or the external processing unit 400, or both. As will be appreciated, the external optical unit 430 may include an array of cameras or the like, capable of capturing multiple images of the subject, either sequentially or simultaneously.

[0162] As will be appreciated by those skilled in the art, this is just one example of a device for implementing the teachings of the present application, and those skilled in the art will understand from these teachings how to configure or create different electronic devices to perform the same tasks.

[0163] The above-mentioned methods and systems provide measurements of cognitive ability to assist physicians in assessing impaired cognitive function, and are used in diagnosing AD.They are intended to be preferably used as assessment aids, and are not intended to perform differential diagnosis of the presence or absence of AD.In particular, they may be used as an adjunct to other diagnostic assessments, and are intended to predict the conversion of MCI to AD in subjects previously diagnosed with MCI.However, they may find use in assessing cognitive function and / or predicting the onset of dementia due to other conditions.

[0164] Those skilled in the art will appreciate that changes may be made to the embodiments and examples described above without departing from the broader concept of the present invention, and it is therefore understood that the invention is not limited to the particular embodiments disclosed, but it is intended to cover modifications within the spirit and scope of the present invention as defined by the appended claims.

[0165] All features disclosed and described for the method may be used for the system and vice versa.

[0166] The disclosures of US Patent Application No. US63 / 211,953 from which this application claims priority, and in the Abstract accompanying this application, are hereby incorporated by reference. References Backman et al. (2001) Brain 124, 96-102 Benton (1968) Neuropsychology 6, 53-60 Benton VRT (1991) Benton Visual Retention Test, 5th edition Blennow et al. (2006) Lancet 368, 387-403 Bugler et al. (2020) Alzheimer's Disease 12, e12073 Butler et al. (1991) Professional Psychology: Research and Practice 22, 510-512 Cummings et al. (2020) Alzheimer's Disease 6, e12050 DeKosky & Marek (2003) Science 302, 830-4 Drozdick et al. (2018) Wechsler Adult Intelligence Scale-4th Edition and Wechsler Memory Scale-4th Edition. Modern Intelligence Testing: Theory, Tests, and Issues, 4th Edition (pp. 486-511) Guilford Press Dubois et al. (2007) Lancet Neurology 6, 734-46 Folstein et al. (1975) Journal of Psychiatry 12, 189-98 Forsberg et al. (2008) Neurobiology of Aging 29, 1456-65 Gootjes-Dreesbach et al. (2020) Big Data Frontiers 3, 16 Hultsch et al. (2008) Handbook of Aging and Cognition, 3rd Edition Jack et al. (2011) Alzheimer's and Dementia 7, 257-62 Kaufman (1983) Journal of Psychological and Educational Evaluation 1, 309-13 Kourtis et al. (2019) NPJ Digital Medicine 2, 9 Livingston et al. (2017) Lancet 390, 2673-734 Morris (1993) Neurology 43, 2412 Mungas et al. (2010) Psychology and Aging 25, 606-619 Murray (2021) Alzheimer's Research and Treatment 13, 26 Nasreddine et al. (2005) Journal of the American Geriatrics Society 53, 695-9 Novak et al. (2021) Nature Ageing 1, 521-34 Nordberg (2007) Current Opinion in Neurology 20, 398-402 Palmer et al. (2002) American Journal of Psychiatry 159, 436-42 RAVLT: Rey 15-word Auditory Verbal Learning Test (1996) WPS Ridha et al. (2007) Archives of Neurology 64, 849-54 Ritchie et al. (2016) Lancet Psychiatry 3, 179-86 Sorensen et al. (2020) Alzheimer's Research and Treatment 12, 155. Tarnanas et al. (2015) Alzheimer's and Dementia: Diagnosis, Assessment and Monitoring of the Disease 1, 521-32 Coase Cube Combination Test (1932) Revised for Clinical Use - PsycNET Wechsler Memory Scale-IV, 4th edition (2009) Wojtowicz et al. (2012) International Journal of Multiple Sclerosis Care 14, 77-83 International Publication No. 2010 / 075481 International Publication 2016 / 157093 International Publication 2020 / 049470

Claims

**Claim 1** A system, implemented on a computer, for obtaining a measurement of an individual's cognitive ability, comprising: an input interface configured to receive measurements from a remote source regarding at least the following activity parameters for the individual: 1) the accuracy of spatial memory; 2) the ability to perform a dual-task interaction during navigation to a target, where the absence of a dual-task interaction is measured; 3) the persistence in an incorrect dual-task interaction during navigation to a target; 4) upper limb neuromotor parameters derived by signal processing 3D acceleration data provided on a portable electronic device; and 5) the reaction time of a dual-task interaction; a processor configured to receive the measurements and to use the measurements to calculate a plurality of metrics belonging to the activity parameters, the metrics being mapped to a plurality of cognitive domains, to calculate a percentile rank score for each cognitive domain based on baseline measurements obtained from a population of healthy individuals, and therefrom to calculate a dysfunction score indicative of the individual's cognitive ability based on the percentile rank score of the individual for the cognitive domain, and executing computer program code for doing so. **Claim 2** The system of claim 1, wherein: the input interface is further configured to receive a first measurement or set of measurements obtained at a first time point and a second measurement or set of measurements obtained at a second different time point regarding the activity parameter or parameters; the processor is configured to receive the first measurement or set of measurements and to use the first measurement or set of measurements to execute computer program code to calculate a first dysfunction score indicative of the individual's cognitive ability, and is further configured to receive the second measurement or set of measurements and to use the second measurement or set of measurements to execute computer program code to calculate a second dysfunction score; and the processor is configured to compare the second dysfunction score with the first dysfunction score to determine the magnitude and / or rate of change in the dysfunction score. **Claim 3** A computer system for obtaining measurement values of an individual's cognitive ability, the system comprising: An application executable by a user device that generates a gamified environment, receives user input, and converts the input into a measurement value of at least one of the following activity parameters for the individual: 1) Accuracy of spatial memory; 2) The ability to perform a dual-task interaction during navigation to a target, where the absence of a dual-task interaction is measured; 3) Persistence in incorrect dual-task interactions during navigation to a target; 4) Upper limb nerve movement parameters derived by signal processing 3D acceleration data provided on a portable electronic device; and 5) Reaction time of a dual-task interaction; A system configured to receive the measurement values and calculate a plurality of metrics belonging to the activity parameters; the metrics are mapped to a plurality of cognitive domains; calculate percentile rank scores for each cognitive domain based on baseline measurement values obtained from a group of healthy individuals; and therefrom calculate a dysfunction score indicating the cognitive ability in the individual based on the percentile rank score of the individual for the cognitive domain.

4. The system comprises: An application executable by a user device that generates a gamified environment, receives a first user input or a set of user inputs at a first point in time, and converts the first user input or the set of user inputs into a first measurement value or a set of measurement values, and also receives a second user input or a set of user inputs at a second point in time, and converts the second user input or the set of user inputs into a second measurement value or a set of measurement values; The system is configured to receive the first measurement value or the set of measurement values and calculate a first dysfunction score, and also receive the second measurement value or the set of measurement values and calculate a second dysfunction score; The computer system of claim 3, wherein the system is configured to compare the second dysfunction score with the first dysfunction score to determine the magnitude and / or speed of the change in the dysfunction score.

5. The system of claim 2 or 3, wherein the processor or system is configured to determine both the magnitude and rate of change in the disability score for the individual and calculate a composite score. **Claim 6** The measured activity parameter further 6) Accuracy of planning; 7) Total time taken by the individual to complete the navigation route; and 8) Response time of the individual's idle state; The system of claim 1 or 3, comprising. **Claim 7** The system of claim 1 or 3, wherein the cognitive domain includes at least one of sensorimotor coordination, divided attention, cognitive processing speed, inhibitory function, cognitive flexibility, visual perception, planning, prospective memory, and spatial memory. **Claim 8** The movement of the individual's hand is evaluated to obtain at least one measurement by displaying an image to the individual and testing the speed and / or accuracy of the individual's hand movement by evaluating the individual's ability to trace or tap the image. The system of claim 1 or 3. **Claim 9** The system of claim 1 or 3, wherein the ability of an individual to perform navigation by placing and retrieving a plurality of objects is evaluated to obtain at least one of the measurements. **Claim 10** The ability of an individual to perform a task is evaluated to obtain at least one of the measurements, and the evaluation of the ability of an individual to perform a task includes evaluating the ability to perform subtasks in the correct order. The system of claim 1 or 3. **Claim 11** The accuracy of spatial memory is determined by measuring the number of items correctly selected by the individual in a navigation assessment or by analyzing the complexity of the route taken by the individual in a navigation assessment. The system of claim 1 or 3. **Claim 12** The accuracy of planning is determined by measuring the performance of a correct prospective memory task by the individual in a task execution assessment. The system of claim 1 or 3. **Claim 13** The system of claim 1 or 3, wherein the upper limb nerve movement parameters include movement agility, movement speed, and / or movement smoothness. **Claim 14** The system of claim 1 or 3, wherein the reaction time of the dual-task interaction is measured as the elapsed time from the stimulus given to the individual to the response from the individual. **Claim 15** The reaction time in the idle state is measured as the elapsed time between the patient's idle state and the next immediate interaction response in the execution of the dual task, for the system of claim 1 or 3.

Images