Systems and processes for cognitive assessment

Abstract

A medical process, an assessment tool and a system are provided. The medical process may comprise: administering a first series of user tasks to a user and measuring user data points for one or more task performance parameters. The first series of user tasks are administered by displaying a first group of elements on a display and prompting the user to perform a first user task of selecting a first sub-group of elements from the first group and arranging the first sub-group in a first sequence; displaying a second group of elements on the display and prompting the user to perform a second user task of arranging one or more elements of the second group based on a predefined sequence; and displaying a third group of elements on the display, the third group of elements including the first sub-group, and prompting the user to perform the third user task.

Description

SYSTEMS AND PROCESSES FOR COGNITIVE ASSESSMENT RELATED APPLICATIONS

[0001] This Application claims priority to US provisional application No.63 / 526,847 filed July 14, 2023, and Canadian patent application No.3, 230,700 filed February 29, 2024, each of which are incorporated herein in their entirety. FIELD

[0002] This application relates to systems and processes for cognitive assessment of individuals. BACKGROUND

[0003] The human population is aging worldwide. By 2050, the number of individuals over 60 years old is expected to double, increasing from 962 million to 2.1 billion, and the number of individuals over the age of 80 years is expected to triple from 137 million to 425 million. Furthermore, it is estimated that 40 million individuals aged 60 years and older are diagnosed with dementia worldwide, and it is projected to multiply at least three-fold by 2050, with direct and indirect healthcare costs up to $9.1 trillion.

[0004] Alzheimer’s dementia (AD) treatments can be most successful when the individual is identified in the earliest stages of the disease. The continuously increasing prevalence of dementia and the rising awareness of the importance of early diagnosis can add to the large existing demand for cognitive assessment by healthcare professionals. However, due to the costs, wait times, and burden on the healthcare systems, individuals may not be diagnosed early enough for treatments to be most successful. SUMMARY

[0005] The following summary is provided to introduce the reader to the more detailed discussion to follow. The summary is not intended to limit or define any claimed or as yet unclaimed invention. One or more inventions may reside in any combination or sub-combination of the elements or process steps disclosed in any part of this document including its claims and figures.

[0006] According to some aspects, a medical process is provided. The medical process comprises: administering a first series of user tasks to a user and measuring user data points for one or more task performance parameters. The first series of user tasks are administered by displaying a first group of elements on a display and prompting the user to perform a first user task of selecting a first sub-group of elements from the first group and arranging the first sub- group in a first sequence; displaying a second group of elements on the display and prompting the user to perform a second user task of arranging one or more elements of the second group based on a predefined sequence, the second user task providing a time interval between the first user task and a third user task; and displaying a third group of elements on the display, the third group of elements including the first sub-group, and prompting the user to perform the third user task of selecting and arranging elements from the third group to reproduce the first sequence. The task performance parameters include task times associated with completing each of the first user task, the second user task and the third user task; a total task time associated with completing the first series of user tasks; a number of user interactions associated with completing each of the first user task, the second user task and the third user task; a total number of user interactions associated with completing the first series of user tasks; a number of elements selected in the third user task; a number of matching elements between the first sub-group and elements selected in the third user task; a number of elements correctly arranged to reproduce the first sequence in the third user task; and a number of elements correctly arranged to match the predefined sequence in the second user task.

[0007] In at least one embodiment, the medical process further comprises determining a user cognition score based on the measured user data points; and assessing cognition of the user by comparing the user cognition score with one or more threshold values.

[0008] In at least one embodiment, determining the user cognition score is based on an algorithm having the one or more task performance parameters and / or one or more user demographic characteristics (for example age or education), number of times the user underwent the medical process, or period of time since the user last underwent the medical process, as predictor variables and a total Montreal Cognitive Assessment (MoCA) score as response variable.

[0009] In at least one embodiment, the algorithm is based on a regression model, for example a logistic regression model or a lasso regression model.

[0010] In at least one embodiment, the algorithm is based on a machine learning model, for example an unsupervised machine learning model e.g. a Gaussian Mixture Model, cluster analysis, or manifold learning.

[0011] In at least one embodiment, the response variable is a binary variable defined as 1 if the total MoCA score is smaller or equal to a predefined cutoff score; and 0 if the total MoCA score is greater than the predefined cutoff score.

[0012] In at least one embodiment, the predefined cutoff score is 23, 24, or 25.

[0013] In at least one embodiment, the user cognition score is a scaled probability output value of the regression model, optionally the logistic regression model, corresponding to the measured user data points and optionally user demographic characteristics being inputs to the regression model.

[0014] In at least one embodiment, the one or more threshold values includes a first threshold value and a second threshold value, and assessing cognition of the user comprises: assessing cognition of the user to correspond to total MoCA score smaller or equal to the predefined cutoff score if the user cognition score is below the first threshold value; and assessing cognition of the user to correspond to total MoCA score greater than the predefined cutoff score if the user cognition score is above the second threshold value.

[0015] In at least one embodiment, the predefined sequence is a logical sequence based on one or more of type, color and size of the second group of elements.

[0016] In at least one embodiment, the user interactions include click and drag interactions of the user with displayed elements.

[0017] In at least one embodiment, the medical process is self-administered by the user.

[0018] In at least one embodiment, the first series of user tasks is administered using a personal computer, a tablet device or a smartphone that comprises the display.

[0019] In at least one embodiment, the method further comprises administering one or more additional series of user tasks, each additional series of user tasks comprising three user tasks correspond to the first user task, the second user task and the third user task.

[0020] In at least one embodiment, the additional series of user tasks comprises: a second series of user tasks including a fourth user task corresponding to the first user task, a fifth user task corresponding to the second user task, and a sixth user task corresponding to the third user task; and a third series of user tasks including a seventh user task corresponding to the first user task, an eighth user task corresponding to the second user task, and a ninth user task corresponding to the third user task.

[0021] In at least one embodiment, the fifth user task corresponds to a higher task difficulty level compared with the second user task; the eighth user task corresponds to a higher task difficulty level compared with the fifth user task; the sixth user task corresponds to a higher task difficulty level compared with the third user task; and the ninth user task corresponds to a higher task difficulty level compared with the sixth user task.

[0022] In at least one embodiment, the task performance parameters further comprise: an average task time associated with completing the third user task, the sixth user task, and the ninth user task; an average task time associated with completing the second user task, the fifth user task, and the eighth user task; an average number of user interactions associated with completing the third user task, the sixth user task, and the ninth user task; an average number of user interactions associated with completing the second user task, the fifth user task, and the eighth user task; an average number of elements selected in the third user task, the sixth user task, and the ninth user task; an average number of matching elements selected in the third user task, the sixth user task, and the ninth user task; an average number of elements correctly arranged in the third user task, the sixth user task, and the ninth user task; and an average number of elements correctly arranged in the second user task, the fifth user task, and the eighth user task.

[0023] In at least one embodiment, the task performance parameters further comprise: an average task time associated with completing the first user task, the third user task, the fourth user task, the sixth user task, the seventh user task and the ninth user task; and an average number of user interactions associated with completing the first user task, the third user task, the fourth user task, the sixth user task, the seventh user task and the ninth user task.

[0024] In at least one embodiment, the user is aged 50 years or older.

[0025] In at least one embodiment, the method further comprises assessing cognition of the user by comparing the user cognition score with one or more historical user cognition scores determined based on previously administered user tasks.

[0026] According to some aspects, a cognition and / or early dementia assessment tool for a user is provided. The cognition and / or early dementia assessment tool comprises performance of the medical process described herein for the user and identifying the user for medical intervention according to their user cognition score.

[0027] According to some aspects, a method for selecting participants for a clinical trial, for example a dementia treatment or assessment clinical trial, is provided. The method comprises performance of the medical process described herein for a user, and selecting the user to be or not be a participant according to their user cognition score.

[0028] According to some aspects, a system is provided. The system comprises a memory storing program instructions and a processor that is coupled to the memory to read and execute the program instructions that configure the processor to perform a medical process described herein.

[0029] According to some aspects, a non-transitory computer readable medium is provided. The non-transitory computer readable medium stores thereon program instructions that are executable by a processor for performing a medical process described herein. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The drawings included herewith are for illustrating various examples of systems, tools, and processes of the present specification and are not intended to limit the scope of what is taught in any way. In the drawings:

[0031] FIG. 1 is a schematic illustration of a system for assessing cognition of a user, in accordance with an embodiment;

[0032] FIG.2 is a flowchart illustrating an example medical process for assessing cognition of a user;

[0033] FIGS.3A-3C show example graphical displays provided to a user during the example medical process of FIG.2;

[0034] FIGS.4A-4C show additional example graphical displays provided to a user during the example medical process of FIG.2;

[0035] FIGS. 5A-5C show additional example graphical displays provided to a user during the example medical process of FIG.2;

[0036] FIG.6 is a block diagram of the example system of FIG.1;

[0037] FIG.7 is a graph showing a receiver operating characteristic (ROC) curve for a logistic regression model implemented in an example study based on the disclosed systems and processes;

[0038] FIG. 8 is a graph showing sensitivity and specificity of determined user cognition scores in the example study of FIG. 7 for predicting a user’s Montreal Cognitive Assessment (MoCA) score;

[0039] FIG. 9 is a histogram showing MoCA scores of users corresponding to different ranges of determined user cognition scores in the example study of FIGS.7 and 8;

[0040] FIGS.10A-B are histograms of the participants who underwent an XpressO cognitive assessment (“XpressO” or “XpressO test”) in an example study based on the disclosed systems and processes, FIG.10A displaying a histogram of participants’ age and FIG.10B a histogram of the participants’ education level;

[0041] FIG.11 is a histogram of XpressO scores of participants in the example study of FIGS. 10A-B;

[0042] FIG.12 is a diagram comparing the paper MoCA score against the XpressO score of FIGS. 10A-B. The results of the generalized Gaussian mixture (GGM) classifier the following: circles classified as cognitively normal and triangles as cognitively impaired; and

[0043] FIGS. 13A-B are graphs showing proportion of correct answers in the recall (FIG. 13A) and logical (FIG.13B) user tasks within the XpressO test, in accordance with an embodiment herein described. In FIG.13A, “Animals” corresponds to the first memory recall task (or third user task), “Objects” corresponds to the second memory recall task (or sixth user task), and “Symbols” corresponds to the third memory recall task (or ninth user task). In FIG. 13B, “Animals” corresponds to the first logical task (or second user task), “Objects” corresponds to the second logical task (or fifth user task), and “Symbols” corresponds to the third logical task (or eighth user task).DETAILED DESCRIPTION

[0044] Numerous embodiments are described in this application and are presented for illustrative purposes only. The described embodiments are not intended to be limiting in any sense. The invention is widely applicable to numerous embodiments, as is readily apparent from the disclosure herein. Those skilled in the art will recognize that the present invention may be practiced with modification and alteration without departing from the teachings disclosed herein. Although particular features of the present invention may be described with reference to one or more particular embodiments or figures, it should be understood that such features are not limited to usage in the one or more particular embodiments or figures with reference to which they are described.

[0045] The terms “an embodiment,” “embodiment,” “embodiments,” “the embodiment,” “the embodiments,” “one or more embodiments,” “some embodiments,” and “one embodiment” mean “one or more (but not all) embodiments of the present invention(s),” unless expressly specified otherwise.

[0046] The terms “including,” “comprising” and variations thereof mean “including but not limited to,” unless expressly specified otherwise. A listing of items does not imply that any or all of the items are mutually exclusive, unless expressly specified otherwise. The terms “a,” “an” and “the” mean “one or more,” unless expressly specified otherwise.

[0047] In addition, as used herein, the wording “and / or” is intended to represent an inclusive- or. That is, “X and / or Y” is intended to mean X or Y or both, for example. As a further example, “X, Y, and / or Z” is intended to mean X or Y or Z or any combination thereof.

[0048] As used herein and in the claims, two or more parts are said to be “coupled”, “connected”, “attached”, “joined”, “affixed”, or “fastened” where the parts are joined or operate together either directly or indirectly (i.e., through one or more intermediate parts), so long as a link occurs. As used herein and in the claims, two or more parts are said to be “directly coupled”, “directly connected”, “directly attached”, “directly joined”, “directly affixed”, or “directly fastened” where the parts are connected in physical contact with each other. None of the terms “coupled”, “connected”, “attached”, “joined”, “affixed”, and “fastened” distinguish the manner in which two or more parts are joined together.

[0049] Further, although method steps may be described (in the disclosure and / or in the claims) in a sequential order, such methods may be configured to work in alternate orders. In other words, any sequence or order of steps that may be described does not necessarily indicate a requirement that the steps be performed in that order. The steps of methods described herein may be performed in any order that is practical. Further, some steps may be performed simultaneously.

[0050] As used herein and in the claims, a group of elements are said to ‘collectively’ perform an act where that act is performed by any one of the elements in the group, or performed cooperatively by two or more (or all) elements in the group.

[0051] Some elements herein may be identified by a part number, which is composed of a base number followed by an alphabetical or subscript-numerical suffix (e.g., 112a, or 1121). Multiple elements herein may be identified by part numbers that share a base number in common and that differ by their suffixes (e.g., 1121, 1122, and 1123). All elements with a common base number may be referred to collectively or generically using the base number without a suffix (e.g., 112).

[0052] It should be noted that terms of degree such as "substantially", "about" and "approximately" when used herein mean a reasonable amount of deviation of the modified term such that the end result is not significantly changed. These terms of degree should be construed as including a deviation of the modified term if this deviation would not negate the meaning of the term it modifies.

[0053] The embodiments of the systems and processes described herein may be implemented in hardware or software, or a combination of both. These embodiments may be implemented in computer programs executing on programmable computers, each computer including at least one processor, a data storage system (including volatile memory or non-volatile memory or other data storage elements or a combination thereof), and at least one communication interface. For example and without limitation, the programmable computers (referred to below as computing devices) may be a server, network appliance, embedded device, computer expansion module, personal computer, laptop, personal data assistant, cellular telephone, smart-phone device, tablet computer, wireless device or any other computing device capable of being configured to carry out the processes described herein.

[0054] Each program may be implemented in a high-level procedural or object-oriented programming and / or scripting language, or both, to communicate with a computer system. However, the programs may be implemented in assembly or machine language, if desired. In any case, the language may be a compiled or interpreted language. Each such computer program may be stored on a storage media or a device (e.g. ROM, magnetic disk, optical disc) readable by a general or special purpose programmable computer, for configuring and operating the computer when the storage media or device is read by the computer to perform the procedures described herein. Embodiments of the system may also be considered to be implemented as a non-transitory computer-readable storage medium, configured with a computer program, where the storage medium so configured causes a computer to operate in a specific and predefined manner to perform the functions described herein.

[0055] Furthermore, the systems, processes and methods of the described embodiments are capable of being distributed in a computer program product comprising a computer readable medium that bears computer usable instructions for one or more processors. The medium may be provided in various forms, including one or more diskettes, compact disks, tapes, chips, wireline transmissions, satellite transmissions, internet transmission or downloads, magnetic and electronic storage media, digital and analog signals, and the like. The computer useable instructions may also be in various forms, including compiled and non-compiled code.

[0056] The disclosed systems and processes can provide a simple, accessible, low-cost pre- screening tool for cognitive assessment of individuals. A cognition score can be determined for an individual and appropriate action can be taken based on the cognition score. For example, if the cognition score is below a threshold score, the individual may be selected for further cognition assessment.

[0057] The disclosed systems and processes can enable the pre-screening tool to be self- administered. This can enable the pre-screening to be performing without a clinic appointment and the long wait times often associated with securing clinic appointments. Timely pre-screening may enable early detection of dementia.

[0058] Early recognition of individuals at high risk for dementia progression and requiring further cognition assessment can help identify individuals who may benefit from treatment with disease-modifying therapies or may be interested in participating in clinical trials. For example,an individual may be selected to be or not be a participant according to their user cognition score determined by the disclosed systems and processes.

[0059] The disclosed systems and processes may also enable reduction in burden on healthcare systems (e.g., cognitive assessment clinics) by identifying individuals who are not at or at lower risk for dementia. For example, an individual may be identified as not needing further assessment if their determined cognition score is above a threshold score. This may reduce the demand for cognitive assessment clinic appointments, thereby reducing the appointment wait times for individuals identified as needing further cognitive assessment.

[0060] The disclosed systems and processes may also provide an automated report of the results, which may be beneficial in several settings: (1) interpretation of the results by the individual, for personal monitoring of their cognitive function, for example, the individual may perform periodic assessments of their cognitive function; (2) increase accessibility to healthcare settings, by pre-screening referrals: results may identify individuals who are either at high risk for cognitive impairment who need further cognitive evaluation, or that present high probability for the MoCA range of intact cognition, and not needing further cognitive evaluation; or (3) in screening for clinical trials according to specific inclusion criteria of cognitive scores: a prerequisite of the online, self-administered test provided by the disclosed systems and processes may reduce the number of participants screened, therefore providing efficient recruitment.

[0061] Referring now to FIG.1, shown therein is a schematic illustration of a system 100 for assessing cognition of user 20. For assessing cognition, system 100 may administer a series of user tasks to user 20. For example, system 100 may administer the series of user tasks by displaying groups of elements on a display 30 and prompting user 20 to perform user tasks related to the displayed elements.

[0062] Display 30 may be any suitable display for presenting visual information to user 20. For example, display 30 can be a computer monitor, a laptop screen, a phone display, a tablet display, a projector display, a flatscreen display, a display panel, etc.

[0063] In some embodiments, display 30 may include a touchscreen display and user 20 may interact with displayed elements using a touch input. In other embodiments, display 30 may not include a touchscreen display and user 20 may interact with displayed elements using any suitable i / o device, for example, a mouse, a stylus, etc.

[0064] In the illustrated example, display 30 is incorporated into a user device 40 associated with user 20. User device 40 can be, for example, a tablet or a smartphone. In some embodiments, user device 40 can be a gaming device or any suitable hand-held device.

[0065] In some embodiments, display 30 may not be incorporated into a user device, for example, display 30 may be associated with system 100 and may be temporarily used by user 20 to perform the user tasks.

[0066] System 100 and user device 40 may be communicatively coupled using a network 50. Network 50 may include a communication network such as the Internet, a Wide-Area Network (WAN), a Local-Area Network (LAN), or another type of network.

[0067] System 100 may perform one or more medical processes. For example, system 100 may perform a medical process for assessing cognition of user 20. Reference is now also made to FIG.2 showing a flowchart illustrating an example medical process 200 for assessing cognition of a user. Medical process 200 may be performed, for example, by system 100.

[0068] In some examples, medical process 200 may be self-administered by a user. For example, user 20 may access a webpage or use an application on user device 40 to launch medical process 200, perform the user tasks and receive a user cognition score. In some examples, medical process 200 may be administered based on a remote input provided by a healthcare practitioner or may be automatically administered based on a stored schedule.

[0069] At 204, a first series of user tasks may be administered to the user. In some embodiments, the first series of user tasks may include three user tasks. For example, the first series of user tasks may include a first user task, a second user task and a third user task.

[0070] For the first user task, a first group of elements may be displayed on a display and the user may be prompted to perform a first user task of selecting a first sub-group of elements from the first group and arranging the first sub-group in a first sequence. Each element can be a graphical representation or an icon that is displayed on display 30.

[0071] The first group of elements can include any suitable number of elements. For example, the first group of elements may include five elements. In other examples, the first group of elements may include a different number of elements (e.g., 3 to 20). The first sub-group of elements may include any suitable number of elements. For example, the first sub-group ofelements may include any number of elements from 1 to the total number of elements in the first group of elements.

[0072] Reference is now made to FIG. 3A showing an example graphical display 304 provided to a user. For example, graphical display 304 may be provided to user 20 on display 30. In the illustrated example, graphical display 304 includes a first group of elements 308a-308e and a user prompt 312.

[0073] User prompt 312 may prompt the user to select a first sub-group of elements (in the illustrated example, the first sub-group includes all elements 308a-308e from the first group) and arrange the first sub-group in a first sequence. In the illustrated example, the first sequence includes a horizonal row of boxes 316a-316e to arrange the first sub-group of elements into. In other examples, the first sequence may use other graphical forms, for example, circles instead of square boxes, a vertical arrangement instead of a horizontal arrangement, etc.

[0074] In some embodiments, the elements may be designed for accessible use by older individuals (e.g., users aged 50 years or older) who may be more likely to use the cognitive pre- screening tool. For example, the elements may be sized for ease of viewing and interaction actions like clicking and dragging.

[0075] In some embodiments, graphical display 304 may include a timer 320. Timer 320 may display a time associated with the first user task. For example, timer 320 may display the time elapsed since beginning the first user task. In some examples, timer 320 may be a countdown timer that displays the maximum time remaining for completing the first user task.

[0076] Referring back to FIGS.1 and 2, for the second user task at 204, a second group of elements may be displayed on the display and the user may be prompted to perform a second user task of arranging one or more elements of the second group based on a predefined sequence.

[0077] Reference is now made to FIG. 3B showing an example graphical display 324 provided to a user. For example, graphical display 324 may be provided to user 20 on display 30. In the illustrated example, graphical display 324 includes a second group of elements 328a-328f, a predefined sequence including multiple elements displayed in a display portion 332 and a user prompt 336.

[0078] The second group of elements can include any suitable number of elements. For example, the second group of elements may include six elements. In other examples, the second group of elements may include a different number of elements (e.g., 3 to 20).

[0079] The predefined sequence may include multiple initial elements (e.g., 340a, 340h) arranged based on a logical sequence. In some embodiments, the predefined sequence can be a logical sequence based on one or more of type, color and size of the initial elements and the second group of elements.

[0080] The logical sequence may include missing elements (e.g., 344b, 344c) corresponding to second group of elements 328a-328f. In the illustrated example, missing elements 344 are graphically represented as empty boxes. In other examples, any other suitable graphical representation may be used, e.g., an empty space corresponding to the size of an elements, an empty space with an underscore, etc. The total number of missing elements 344 may be equal to total number of elements 328 in the second group.

[0081] User prompt 336 may prompt the user to arrange elements 328 of the second group based on the predefined sequence. A user may interact with the elements to perform the user task. For example, the user may click and drag elements 328 into the boxes corresponding to missing elements 344.

[0082] For the third user task at 204, a third group of elements may be displayed on the display, the third group including elements of the first sub-group. Further, the user may be prompted to perform a third user task of selecting and arranging elements from the third group to reproduce the first sequence.

[0083] Reference is now made to FIG. 3C showing an example graphical display 348 provided to a user. For example, graphical display 348 may be provided to user 20 on display 30. In the illustrated example, graphical display 348 includes a display portion 352 displaying a third group of elements, a display portion 356 for reproduction of the first sequence and a user prompt 360.

[0084] The third group of elements may include all the elements of the first sub-group (e.g., 308a-308e) and any suitable number of additional elements (e.g., 364a, 364b).

[0085] User prompt 360 may prompt the user to select and arrange elements from the third group to reproduce the first sequence in display portion 356. In the illustrated example, display portion 356 includes a horizontal row of boxes to arrange elements into. In other examples, display portion 356 may include other graphical forms. The graphical forms used in display portion 356 may match the graphical forms used in the first sequence of graphical display 304 (shown in FIG. 3A).

[0086] The second user task may provide a time interval between the first user task and the third user task. The time interval can introduce a delay time between a user arranging elements in the first sequence (during the first user task) and recalling from memory the first sequence during the third user task. A longer time interval may increase the difficulty level of the third user task.

[0087] The time interval may be a variable delay time based on the task time taken by a user to complete the second user task. In some embodiments, a maximum time value may be defined for the time interval. The maximum time value may correspond to a maximum time allocated for completing the second user task. For example, the maximum time value can be 2.5 minutes. In other examples, the maximum time value may be larger or smaller than 2.5 minutes (e.g., 1 minute to 4 minutes).

[0088] In some embodiments, a minimum time value may be defined for the time interval. The minimum time value may be defined to maintain the third user task at a suitable difficulty level. For example, the minimum time value may be defined as 30 seconds. In other examples, the minimum time value may be larger or smaller than 30 seconds (e.g., 20 seconds to 45 seconds). If a user performs the second user task in a time less than the minimum time value, then a delay may be introduced before the third user task is administered to the user.

[0089] Referring back to FIGS.1 and 2, at 204, one or more additional series of user tasks may be administered to the user. Each additional series of user tasks may include any suitable number of user tasks. In some embodiments, each additional series of user tasks may include the same number of user tasks as the first series of user tasks.

[0090] In some embodiments, two additional series of user tasks (a second series of user tasks and a third series of user tasks) may be administered to the user at 204. Each of the second series and the third series may include three user tasks.

[0091] The second series of user tasks may include a fourth user task corresponding to the first user task, a fifth user task corresponding to the second user task, and a sixth user task corresponding to the third user task. Reference is now made to FIGS.4A-4C showing example graphical displays 404, 408, and 412 respectively that are provided to the user for administering the fourth, fifth and sixth user tasks.

[0092] For the fourth user task, a fourth group of elements may be displayed in display portion 416 and the user may be prompted to perform a fourth user task of selecting a second sub-group of elements from the fourth group and arranging the second sub-group in a second sequence in display portion 420.

[0093] The elements of the fourth group may be same or different compared with the elements of the first group (during the first user task). In some embodiments, there may be one or more common elements between the first group and the fourth group. In the illustrated example, there are no common elements between the first group and the fourth group.

[0094] The fourth group of elements can include any suitable number of elements. The number of elements in the fourth group may be same or different compared with the number of elements in the first group (during the first user task). In the illustrated example, the fourth group of elements includes seven elements. In other examples, the fourth group of elements may include a different number of elements (e.g., 3 to 20).

[0095] The second sub-group of elements may include any suitable number of elements. The number of elements in the second sub-group may be same or different compared with the number of elements in the first sub-group (during the first user task). For example, the second sub-group of elements may include any number of elements from 1 to the total number of elements in the fourth group of elements. In the illustrated example, the second sub-group of elements includes five elements.

[0096] In the illustrated example, the second sequence includes a horizonal row of boxes in display portion 420 for the user to arrange the second sub-group of elements into, similar to the graphical form used for the first sequence in graphical display 304 (shown in FIG.4A). In other examples, the second sequence may use different graphical forms compared with the first sequence.

[0097] For the fifth user task, a fifth group of elements may be displayed in display portion 424 and the user may be prompted to perform a fifth user task of arranging one or more elements of the fifth group based on a predefined sequence including multiple elements displayed in display portion 428.

[0098] The fifth group of elements can include any suitable number of elements. For example, the fifth group of elements may include seven elements. In other examples, the fifth group of elements may include a different number of elements (e.g., 3 to 20).

[0099] The elements of the predefined sequence displayed in display portion 428 may be based on a similar or different logical sequence compared with the second user task. In the illustrated example, the predefined sequence displayed in display portion 428 is a logical sequence based on color, shape and proportion of colored region of the elements. The logical sequence may include one or more missing elements corresponding to the fifth group of elements.

[0100] In some embodiments, the fifth user task may correspond to a higher difficulty level compared with the second user task. The difficulty level of the fifth user task may correspond to one or more of a number of elements in the fifth group of elements (e.g., 7 elements in the fifth group compared with 6 elements in the second group), a number, proportion and location of initial elements provided in the predefined sequence (e.g., 9 / 16 initial elements provided in the fifth user task compared with 10 / 16 initial elements provided in the second user task), and the underlying logical sequence (e.g., based on proportion of colored region of the elements in the fifth user task compared with size of elements in the second user task). In other embodiments, the fifth user task may correspond to an equal or lower difficulty level compared with the second user task.

[0101] For the sixth user task, a sixth group of elements may be displayed in display portion 432, the sixth group including elements of the second sub-group. Further, the user may be prompted to perform a sixth user task of selecting and arranging elements from the sixth group to reproduce the second sequence in display portion 436.

[0102] The graphical forms used in display portion 436 may match the graphical forms used in the second sequence of display portion 420 (e.g., a horizontal row of boxes to arrange elements into). The sixth group of elements may include all the elements of the second sub-group and any suitable number of additional elements.

[0103] As described herein above with reference to the second user task providing a time interval between the first user task and the third user task, the fifth user task may provide a time interval between the fourth user task and the sixth user task. The time interval can introduce a delay time between a user arranging elements in the second sequence (during the fourth user task) and recalling from memory the second sequence during the sixth user task. A longer time interval may increase the difficulty level of the sixth user task.

[0104] In some embodiments, the sixth user task may correspond to a higher difficulty level compared with the third user task. The difficulty level of the sixth user task may correspond to one or more of a total number of elements to be selected and arranged to reproduce the sequence, a total number of elements of the sixth group of elements and the ease associated with memorization of the specific graphical symbols representing the elements.

[0105] The third series of user tasks may include a seventh user task corresponding to the first user task and the fourth user task, an eighth user task corresponding to the second user task and the fifth user task, and a ninth user task corresponding to the third user task and the sixth user task. Reference is now made to FIGS.5A-5C showing example graphical displays 504, 508, and 512 respectively that are provided to the user for administering the seventh, eighth, and ninth user tasks.

[0106] For the seventh user task, a seventh group of elements may be displayed in display portion 516 and the user may be prompted to perform a seventh user task of selecting a third sub- group of elements from the seventh group and arranging the third sub-group in a third sequence in display portion 520.

[0107] The elements of the seventh group may be same or different compared with the elements of the first group (during the first user task) and the fourth group (during the fourth user task). In some embodiments, there may be one or more common elements between the seventh group and the first / fourth group. In the illustrated example, there are no common elements between the seventh group, the first group and the fourth group.

[0108] The seventh group of elements can include any suitable number of elements. The number of elements in the seventh group may be same or different compared with the number of elements in first group (during the first user task) and the fourth group (during the fourth user task). In the illustrated example, the seventh group of elements includes eight elements. In otherexamples, the seventh group of elements may include a different number of elements (e.g., 3 to 20).

[0109] The third sub-group of elements may include any suitable number of elements. The number of elements in the third sub-group may be same or different compared with the number of elements in the first group (during the first user task) or the fourth group (during the fourth user task). For example, the third sub-group of elements may include any number of elements from 1 to the total number of elements in the seventh group of elements. In the illustrated example, the third sub-group of elements includes five elements.

[0110] For the eighth user task, an eighth group of elements may be displayed in display portion 524 and the user may be prompted to perform an eighth user task of arranging one or more elements of the eighth group based on a predefined sequence including multiple elements displayed in display portion 528.

[0111] The eighth group of elements can include any suitable number of elements. For example, the eighth group of elements may include ten elements. In other examples, the eighth group of elements may include a different number of elements (e.g., 3 to 20).

[0112] The elements of the predefined sequence displayed in display portion 528 may be based on a similar or different logical sequence compared with the second user task and the fifth user task. In the illustrated example, the predefined sequence displayed in display portion 528 is a logical sequence based on color, size and numbering of the elements. The logical sequence may include one or more missing elements corresponding to the eighth group of elements.

[0113] In some embodiments, the eighth user task may correspond to a higher difficulty level compared with the fifth user task. The difficulty level of the eighth user task may correspond to one or more of a number of elements in the eighth group of elements, a number, proportion and location of initial elements provided in the predefined sequence, and the underlying logical sequence. In other embodiments, the eighth user task may correspond to an equal or lower difficulty level compared with the fifth user task.

[0114] For the ninth user task, a ninth group of elements may be displayed in display portion 532, the ninth group including elements of the third sub-group. Further, the user may be prompted to perform a ninth user task of selecting and arranging elements from the ninth group to reproduce the third sequence in display portion 536.

[0115] The graphical forms used in display portion 536 may match the graphical forms used in the third sequence of display portion 520 (e.g., a horizontal row of boxes to arrange elements into). The ninth group of elements may include all the elements of the third sub-group and any suitable number of additional elements.

[0116] As described herein above with reference to the second user task providing a time interval between the first user task and the third user task, the eighth user task may provide a time interval between the seventh user task and the ninth user task. The time interval can introduce a delay time between a user arranging elements in the third sequence (during the seventh user task) and recalling from memory the third sequence during the ninth user task. A longer time interval may increase the difficulty level of the ninth user task.

[0117] In some embodiments, the ninth user task may correspond to a higher difficulty level compared with the sixth user task. The difficulty level of the ninth user task may correspond to one or more of a total number of elements to be selected and arranged to reproduce the sequence, a total number of elements of the ninth group of elements and the ease associated with memorization of the specific graphical symbols representing the elements (e.g., abstract graphical symbols of the ninth user task compared with familiar object symbols of the sixth user task).

[0118] Referring back to FIGS. 1 and 2, at 208, user data points for one or more task performance parameters may be measured. User data points may be measured during each user task administered at 204. A first series of user tasks may be administered to the user. The user data points may be measured, for example, at user device 40. In some embodiments, system 100 may measure one or more user data points based on input received from user device 40.

[0119] The user data points may be measured for task performance parameters including task times associated with completing each user task (e.g., one or more of the first, second, third, fourth, fifth, sixth, seventh, eighth and ninth user tasks), a total task time associated with completing the series of user tasks (e.g., one or more of the first, second and third series of user tasks), a number of user interactions (e.g., a drag interaction where a user drags a selected element to a different location) associated with completing each user task, a total number of user interactions associated with completing the series of user tasks, and a number of elements selected, matched and / or correctly arranged in the various user tasks.

[0120] In some embodiments, user data points may be measured for all the task performance parameters described above. In other embodiments, user data points may be measured for a subset of the task performance parameters. For example, only the user data points for the total task time associated with completing the series of user tasks, the number of user interactions associated with completing the second user task and the third user task, and the number of elements correctly arranged in the second user task and the third user task may be measured at 208. The user data points selected for measurement at 208 may be based on the model used to determine the user cognition score, as described herein below with reference to 212.

[0121] The task time for any user task may be measured as the time duration beginning at a time when the user task is first administered and ending at a time when the user completes the user task. For example, the task time for the first user task may be measured as the time duration beginning at a time when the first group of elements is first displayed to the user and ending at a time when the user completes arrangement of the first sub-group in the first sequence.

[0122] The total task time associated with completing a series of user tasks may be measured as a sum of the task times associated with each user task included in that series of user tasks. For example, the total task time associated with completing the first series of user tasks may be measured as a sum of the task times associated with completing the first, second and third user tasks.

[0123] The measured number of elements selected in a user task can include, for example, the number of elements selected in the third user task (or similarly the number of elements selected in the sixth user task or the ninth user task). For the example illustrated in FIG.3C, the number of elements selected by a user in the third user task can be any number from 0 to 5.

[0124] The number of matched elements can include, for example, the number of selected elements in the third user task that correctly match the elements selected as the first sub-group in the first user task. Referring to the examples illustrated in FIGS.3A and 3C, the first sub-group of elements includes five elements 308a-308e. The number of matched elements can be 4 if a user correctly selects elements 308a, 308b, 308c, and 308e in the third user task. In some embodiments, any of the measured numbers of correctly matched or correctly arranged elements may be measured as a proportion or percentage (instead of an absolute number). For example, the number of matched elements may be measured as 4 of 5 or 80%.

[0125] The number of correctly arranged elements can include, for example, the number of matched elements that are also correctly arranged in the third user task to reproduce the first sequence from the first user task. Continuing with the above example, the number of correctly arranged elements can be 2 if the user correctly arranged elements 308a and 308e, but incorrectly arranged elements 308b and 308c.

[0126] In some cases, the number of correctly arranged elements can include, for example, the number of elements correctly arranged to match the predefined sequence in the second user task (or similarly the number of correctly arranged elements in the fifth user task or the eighth user task). For the example illustrated in FIG.3B, the number of correctly arranged elements can be any number from 0 to 6. The number of correctly arranged elements can be 6 if all elements 328a-328f are correctly arranged by a user into boxes corresponding to missing elements 344.

[0127] In some embodiments, multiple tasks may be grouped together, and the task performance parameters may include averaged values for the groups. For example, the second user task, the fifth user task and the eighth user task may be grouped into a logic group. An average task time may be determined for the logic group by determining an average of the task times associated with completing the second user task, the fifth user task and the eighth user task. An average number of user interactions may be determined for the logic group by determining an average of the number of user interactions associated with completing the second user task, the fifth user task and the eighth user task. An average number of elements correctly arranged to match the corresponding predefined sequence may be determined for the logic group by determining an average of the number of elements correctly arranged in the second user task, the fifth user task and the eighth user task.

[0128] In some embodiments, the third user task, the sixth user task and the ninth user task may be grouped into a memory group. An average task time may be determined for the memory group by determining an average of the task times associated with completing the third user task, the sixth user task and the ninth user task. An average number of user interactions may be determined for the memory group by determining an average of the number of user interactions associated with completing the third user task, the sixth user task and the ninth user task. An average number of elements selected for the memory group may be determined by determining an average of the number of elements selected in the third user task, the sixth user task and the ninth user task. An average number of matching elements selected for the memory group may be determined by determining an average of the number of matching elements selected in the thirduser task, the sixth user task and the ninth user task. An average number of elements correctly arranged for the memory group may be determined by determining an average of the number of elements correctly arranged in the third user task, the sixth user task and the ninth user task.

[0129] In some embodiments, a second memory group may be formed that includes the first memory task, the third user task, the fourth memory task, the sixth user task, the seventh memory task and the ninth user task. An average task time may be determined for the second memory group by determining an average of the task times associated with completing the first memory task, the third user task, the fourth memory task, the sixth user task, the seventh memory task and the ninth user task. An average number of user interactions may be determined for the second memory group by determining an average of the number of user interactions associated with completing the first memory task, the third user task, the fourth memory task, the sixth user task, the seventh memory task and the ninth user task.

[0130] Referring back to FIGS.1 and 2, at 212, a user cognition score may be determined based on the measured user data points. The determined user cognition score may be highly associated with a total MoCA score of the user. The user cognition score may be determined, for example, by system 100. System 100 may communicate the determined user cognition score to user 20 or another authorized individual. In some embodiments, the user cognition score may be locally determined by user device 40.

[0131] The user cognition score may be determined using any suitable model. For example, the user cognition score may be determined based on a regression model. For example, the user cognition score may be determined based on a logistic regression model having one or more task performance parameters and / or one or more user demographic characteristics as predictor variables and a total Montreal Cognitive Assessment (MoCA) score as response variable. For example, the user cognition score may be determined based on a lasso regression model having one or more task performance parameters and / or one or more user demographic characteristics predictor variables and a total Montreal Cognitive Assessment (MoCA) score as response variable.

[0132] In some embodiments, all the task performance parameters described herein may be used as predictor variables in the regression model. In some embodiments, all the task performance parameters described herein and user demographic characteristics of age and / or education may be used as predictor variables in the regression model. In other embodiments, asmaller subset of task performance parameters may be selected as predictor variables. This may reduce model complexity, computational resource requirements and / or overfitting of the model to training data that is used for generating the model. The model used at 212 may be selected from among many trained models based on the performance of the models during validation tests. The model performance may be evaluated based on factors including area under the ROC curve (AUC), sensitivity, specificity, etc.

[0133] In some embodiments, the number of times the user underwent the medical process, and / or the period of time since the user last underwent the medical process may be used as predictor variables in the regression model.

[0134] The response variable of the logistic regression model can be a binary variable defined as “1” if the total MoCA score is smaller or equal to a predefined cutoff score and “0” if the total MoCA score is greater than the predefined cutoff score. Any suitable MoCA score may be used as the predefined cutoff score based on the requirements of the medical process. For example, the predefined cutoff score may be in a range from 10 to 26. In some embodiments, predefined cutoff scores in a range from 23 to 25 may be used in scenarios where medical process 200 is being used as a pre-screening tool to identify users at risk of dementia and where a follow- up cognitive screening may be conducted based on the determined cognition score. For example, a predefined cutoff score of 24 may be used.

[0135] At 212, the measured user data points, user demographic characteristics, number of times the user underwent the medical process, and / or period of time since the user last underwent the medical process corresponding to the predictor variables may be provided as inputs to the regression model. The output of the regression model can be a probability value between 0 and 1 indicating probability of the corresponding total MoCA score being less than or equal to the predefined cutoff score (e.g., being less than or equal to 24). In an embodiment, the regression model is a logistic regression model. In another embodiment, the regression model is a lasso regression model.

[0136] The probability value may be scaled to a number between 0 and 100 to generate the user cognition score. In some embodiments, the scaling may also be performed such that a low probability value (of MoCA score being less than or equal to 24) corresponds to a high user cognition score and a high probability value corresponds to a low user cognition score.

[0137] At 216, the cognition of the user may be assessed by comparing the user cognition score determined at 212 with one or more threshold values. For example, the threshold values may include a low threshold value and a high threshold value. The cognition of the user may be assessed to correspond to total MoCA score smaller or equal to the predefined cutoff score (corresponding to the response variable of the model used at 212, for example, the predefined cutoff score may be 24, 25 or 26) if the determined user cognition score is below or equal to the low threshold value. The cognition of the user may be assessed to correspond to total MoCA score greater than the predetermined cutoff score (e.g.9 or 10) if the determined user cognition score is above or equal to the high threshold value.

[0138] In some embodiments, the cognition assessment may be provided to the user or another authorized individual using any suitable method, e.g., as a notification, a report, etc. The cognition assessment may include one or more of the determined cognition score, associated MoCA score, and / or recommended actions based on the determined cognition score. In some cases, the user may self-administer the medical process at periodic intervals (e.g., annually or at any other suitable interval) and the cognition assessment may include historical data of determined user cognition scores.

[0139] In some embodiments, medical process 200 may further include one or more actions based on the cognition assessment. For example, a scan (e.g., a positron emission tomography (PET) scan) or a blood / cerebrospinal fluid (CSF) biomarker test (e.g., for amyloid beta, tau) may be performed based on the cognition assessment. In some embodiments treatments may be provided based on the cognition assessment and / or the results of the scan / test. The treatments can include, for example, a cholinesterase inhibitor (e.g. galantamine, rivastigmine, donepezil), aducanumab or lecanemab.

[0140] Referring now to FIG.6, shown therein is a block diagram of system 100 for assessing cognition of user. In some embodiments, system 100 may be implemented as a server device (e.g., as illustrated in FIG.1). In other embodiments, system 100 may be implemented using any other suitable hardware components. For example, system 100 may be implemented as a mobile device.

[0141] For the example embodiment illustrated in FIG. 6, system 100 includes a memory 608, an application 612, an output device 616, a display device 620, a secondary storage device 624, a processor 628, an input device 632, and a communication device 636. One or more (or all)of memory 608, application 612, output device 616, display device 620, secondary storage device 624, processor 628, input device 632, and communication device 636 may be communicatively coupled by wire and / or wirelessly.

[0142] In some embodiments, system 100 includes multiple of any one or more of memory 608, application 612, output device 616, display device 620, secondary storage device 624, processor 628, input device 632, and communication device 636. In some embodiments, system 100 does not include one or more of applications 612, secondary storage devices 624, network connections, input devices 632, output devices 616, display devices 620, and communication devices 636.

[0143] In at least one embodiment, system 100 includes a connection with a network 604 such as a wired or wireless connection to the Internet or to a private network. In some cases, network 604 includes other types of computer or telecommunication networks. System 100 may receive, over network 604, measured user data point for one or more task performance parameters and may provide, over network 604, user cognition score and / or cognition assessment to a user or authorized individual.

[0144] Memory 608 can include one or more of random-access memory (RAM) and read- only memory (ROM). In some embodiments, memory 608 stores one or more applications 612 for execution by processor 628. Applications 612 correspond with software modules including computer executable instructions to perform processing for the functions and methods described herein.

[0145] Memory 608 may store one or models used to determine cognition scores. In some embodiments, memory 608 may also store historical data corresponding to determined cognition scores and / or cognition assessments.

[0146] Secondary storage device 624 may include any suitable non-transitory computer- readable medium including instructions executable by a processor (e.g., processor 628). For example, secondary storage device 624 can include a hard drive, floppy drive, CD drive, DVD drive, Blu-ray drive, solid state drive, flash memory or other types of non-volatile data storage. Processor 628 may execute instructions included on secondary storage device 624 to perform processing for the functions and methods described herein.

[0147] In some embodiments, system 100 stores information in a remote storage device, such as cloud storage, accessible across a network, such as network 604 or another network. In some embodiments, system 100 stores information distributed across multiple storage devices, such as memory 608 and secondary storage device 624 (i.e., each of the multiple storage devices stores a portion of the information and collectively the multiple storage devices store all of the information). Accordingly, storing data on a storage device as used herein and in the claims, means storing that data in a local storage device, storing that data in a remote storage device, or storing that data distributed across multiple storage devices, each of which can be local or remote.

[0148] Input device 632 can include any device for entering information into system 100. For example, input device 632 can be a keyboard, keypad, cursor-device, touchscreen, camera, or microphone. Input device 632 can also include input ports and wireless radios (e.g., Bluetooth®, or 802.11x) for making wired and wireless connections to external devices.

[0149] Display device 620 can include any type of device for presenting visual information. For example, display device 620 can be a computer monitor, a flat-screen display, a projector or a display panel.

[0150] Output device 616 can include any type of device for presenting a hard copy of information, such as a printer for example. Output device 616 can also include other types of output devices such as speakers, for example. In at least one embodiment, output device 616 includes one or more of output ports and wireless radios (e.g., Bluetooth®, or 802.11x) for making wired and wireless connections to external devices.

[0151] Communication device 636 can have any design suitable to receive analog and / or digital inputs from, and to provide analog and / or digital outputs. In some embodiments, communication device 636 may include separate modules for analog and digital signals.

[0152] Processor 628 may be any device that can execute applications, computer readable instructions or programs. The applications, computer readable instructions or programs can be stored in memory 608 or in secondary storage device 624, or can be received from remote storage accessible through network 604, for example. Processor 628 may be a high-performance general processor, a standard processor (e.g., an Intel® processor or an AMD® processor), specialized hardware (e.g., GPUs), or multiple processing devices that collectively perform the functions provided by processor 628.

[0153] Processor 628 may determine a user cognition score by inputting measured user data points into a stored mode. Processor 628 may also assess cognition of a user by comparing the determined user cognition score with one or more threshold values.

[0154] FIG. 6 illustrates one example hardware schematic of system 100. In alternative embodiments, system 100 contains fewer, additional or different components. In addition, although aspects of an implementation of system 100 are described as being stored in memory, one skilled in the art will appreciate that these aspects can also be stored on or read from other types of computer program products or computer-readable media, such as secondary storage devices, including hard disks, floppy disks, CDs, or DVDs; a carrier wave from the Internet or other network; or other forms of RAM or ROM. For example, system 100 may include a non- transitory computer readable medium storing computer-readable instructions that when executed by processor 628, configure processor 628 to perform method(s) described herein.

[0155] The systems and processes described herein can further comprise determining one or more demographic characteristics of the user, for example age, education or gender.

[0156] As mentioned herein, the systems and methods can be used to screen users for further intervention. For example, the methods can be used to identify prioritization for imaging, monitoring, further assessment or treatment.

[0157] Accordingly, also provided in another aspect is a mild cognitive impairment or an early dementia assessment tool for a user, comprising having a candidate perform a process described herein and identifying the user for medical intervention according to their user cognition score. In some embodiments, the medical intervention is a scan, test or a treatment. For example, a scan (e.g., a positron emission tomography (PET) scan) or a blood / cerebrospinal fluid (CSF) biomarker test (e.g., for amyloid beta, tau) may be performed based on the cognition assessment. In some embodiments treatments may be provided based on the cognition assessment and / or the results of the scan / test. (eg. Scan and / or test). The treatments can include, for example, a cholinesterase inhibitor (e.g. galantamine, rivastigmine, donepezil), aducanumab or lecanemab. The process or tool may comprise selecting for, or may comprise, the medical intervention when the user score is below (and / or equal to) or above (and / or equal to) to a threshold value or falls within one or more threshold values, for example that corresponds to a predefined cutoff, for example MOCA score of 10-26, including for example the shoulders 10 and 26.

[0158] The process or tool can be performed within a set time period, for example within 60 days of the of the medical intervention. In some embodiments, the process, system or tool is performed is self administered, for example in a home or long term care setting.

[0159] In some embodiments, the process, system or tool is performed in a clinical setting.

[0160] The systems and methods can also be used to select individuals for a clinical trial. Another aspect provides a method for selecting participants for a dementia treatment or assessment clinical trial, the process comprising having a candidate user perform a process described herein, and selecting the user to be or not be a participant according to their user cognition score. EXAMPLES Example Study 1

[0161] An example study was conducted based on the disclosed systems and processes. Participants completed the digital MoCA test and a test referred to as the XpressO test based on the disclosed systems and processes. The administration of the XpressO test included participants completing the series of user tasks described herein. The memory tasks of the XpressO test correspond to the first user task, the third user task, the fourth user task, the sixth user task, the seventh user task and the ninth user task described herein. The logical tasks of the XpressO test correspond to the second user task, the fifth user task and the eighth user task described herein. The XpressO test score corresponds to the user cognition score described herein. The displayed elements are also referred to as objects in the example study. Participants in the example study

[0162] The study had a randomized cross-over active comparator design. The study sample consisted of 118 participants that were randomized into two groups: (I) completing the digital MoCA first (n= 58), and (II) completing the XpressO test first (n= 60). Of the 118 participants, 18 did not complete the study due to impaired comprehension and inability to complete the disclosed user tasks independently. Twelve more participants did not meet eligibility criteria or had technology interferences (e.g., Wi-Fi interruptions, software freezing) and therefore excluded from analysis. A total of 88 participants were included in the primary analysis. Demographic characteristics are described in Table 1. To enter the study, participants had to meet the followingeligibility criteria. Inclusion criteria: age ≥50 years; years of formal education ≥6; fluency in English or French; all sex and gender inclusive; Exclusion criteria: completion of MoCA test during the most recent 3 months; years of formal education <6; age <50 years; past MoCA score <11 / 30. Ethics approval was received, and all participants provided informed consent for the study procedures and research aims, fully described by the study staff. Formal registration of the clinical trial was completed; ClinicalTrials.gov Identifier: NCT05879562. Table 1 Demographic characteristics of participants Overall Sample size 88 Age (mean (SD)) 70.34 (7.23) Sex = M (%) 38 (43.2%) Years of education after kindergarten (mean (SD)) 13.62 (3.07) Language (%) English 36 (40.9%) French 45 (51.1%) Other 7 (8.0%) Language of test = French (%) 31 (35.2%) Technology hours per week (mean (SD)) 17.86 (13.20) Procedures of the example study

[0163] The study had a crossover design. The order of administration of the two tests were randomized to ensure that half of the participants received the digital MoCA first, and the other half received the XpressO test first. The randomization sequence was determined prior to startingthe study by an outside source. After completion of both tests, participants were compensated for their time and travel. Digital MoCA test

[0164] The digital MoCA test was administered and scored by MoCA certified raters. The digital MoCA test is the same as the paper version of the classic MoCA test, but it is administered on a tablet device. In this validated test, the rater scores the participant as they do a series of cognitive tasks on multiple cognitive domains, including: executive / visuospatial, naming, memory, attention, language, abstraction, delayed recall, and orientation. XpressO test

[0165] The XpressO was completed on a tablet device independently by the participant with no disruptions. The test consisted of a first series of user tasks and two additional series of user tasks resulting in a total of 9 user tasks. The first user task required the participant to place 5 objects into boxes in an order that they were instructed to remember; the second user task required the participant to identify a pattern and enter other objects into boxes according to that pattern; and the third user task required the participant to identify the objects from the first user task, and enter them into boxes in the same order entered in the first user task. The three user tasks are repeated in two additional variations for a total of 9 tasks. The screen of the tablet was recorded to troubleshoot any errors that occurred during the test. Participants who required assistance or asked questions regarding the test content were excluded from the analysis. Outcome and predictors

[0166] The continuous total MoCA score was dichotomized into a binary variable, defined as (1) if the MoCA score is smaller or equal to 24 and (0) otherwise. The potential predictors were XpressO sub-test results including average memory task scores, average logical task scores, total task time, average task time of memory tasks, average task time of logical tasks, total number of drags (each user interaction where the participant moved an object into an answer box during a user task), average drags for the memory tasks, and average drags for the logical tasks. Statistical Analysis

[0167] Demographic characteristics were described using means, standard deviations, frequencies, and percentages (Table 1). The associations between XpressO sub-test results andbinary MoCA scores was described and evaluated pairwise, using t-tests for continuous variables and Chi squared-tests for categorical variables. Standardized mean differences (SMDs) for all pairwise comparisons were calculated.

[0168] A predictive model was built based on logistic regression. Composite proportion predictors based on XpressO sub-test results were calculated. For the memory task, these predictors included the proportion of correct objects among the placed objects and the proportion of correct objects and positions among the placed objects. For the logical task, the predictors included the proportion of 100% correct objects among the placed objects and the proportion of correct color among the placed objects. Two more participants with zero placed objects were subsequently excluded from the model-building process, reducing the sample size to 86. To assess the performance of the selected predictive model on unseen data, the original data were split into a training set (70%) and a testing set (30%). The area under the Receiver Operating Characteristic (ROC) curve, i.e., AUC value, was used to evaluate the predictive performance of all candidate logistic models. The final predictive model was then built on the entire dataset. Definition of total XpressO score

[0169] The minimum total task time was restricted to 100 seconds, the maximum number of average drags per memory task was restricted to 6, and the maximum number of average drags per logical task was restricted to 10. With these restrictions, the outcomes of the logistic regression, i.e., the predicted probability of a participant having a total MoCA score smaller than or equal to 24, were scaled into a range from 0 to 100. The scaled outcomes were used as participants’ total XpressO scores. Two cut-off points and an indecisive zone for the XpressO test

[0170] Two cut-off points were considered for the predicted probabilities of the final logistic regression, aiming to achieve either high sensitivity or high specificity. The aim of the cut-off points was to two zones with either sensitivity above 90% or specificity above 90% and a third indecisive zone. Results Demographic characteristics

[0171] Table 1 describes the demographic characteristics of participants in the example study (n=88). The mean age was 70.34 years old with a standard deviation of 7.23 years. More than half of the participants were female (females = 62%; males = 38%). Language, technology usage, and MoCA scores are also listed. Descriptive analysis results

[0172] Table 2 describes participant XpressO sub-test results among high MoCA scores and low MoCA scores. P-values lower than 0.05 are considered statistically significant, and SMD higher than 0.5 are considered to be medium to high effect sizes. Most of the XpressO sub-test results, including average number of same objects and same object and position in memory tasks, average number of 100% correct objects and correct colors in logical tasks, and the task times, were statistically significant with SMDs in the medium to high range. These results indicate a strong association between XpressO performance and the binary MoCA score. Table 2. XpressO test results and demographic characteristics of participants by binary MoCA score MoCA<= 24 MoCA>= 25 P values SMD Sample size 46 42 Memory Tasks: Average number of 4.69 (0.75) 4.83 (0.50) 0.317 0.217 objects placed (mean (SD)) Memory Tasks: Average number of same 4.23 (1.01) 4.71 (0.52) 0.008 0.591 objects (mean (SD)) Memory Tasks: Average number of same 3.56 (1.35) 4.33 (0.72) 0.001 0.709 objects and position (mean (SD)) Logical Tasks: Average number of objects 6.91 (1.36) 6.81 (1.97) 0.789 0.057 placed (mean (SD)) Logical Tasks: Average number of 100% 3.79 (2.14) 5.56 (2.17) <0.001 0.820 correct answers (mean (SD)) Logical Tasks: Average number of correct 5.21 (1.73) 6.19 (1.95) 0.014 0.532 colors (mean (SD)) Total task time in seconds (mean (SD)) 463.30 377.93 0.014 0.542 (197.04) (103.60)Average task time of memory tasks in 57.63 (24.29) 49.32 0.060 0.411 seconds (mean (SD)) (15.17) Average task time of logical tasks in 39.17 (21.52) 27.34 (8.66) 0.001 0.721 seconds (mean (SD)) Total drags (mean (SD)) 5.52 (0.48) 5.73 (0.50) 0.050 0.424 Average drags of memory tasks (mean 6.13 (0.65) 6.30 (0.83) 0.302 0.220 (SD)) Average drags of logical tasks (mean 4.91 (0.79) 5.17 (0.71) 0.118 0.337 (SD)) Age (mean (SD)) 70.37 (6.50) 70.31 (8.03) 0.969 0.008 Sex = M (%) 21 (45.7) 17 (40.5) 0.784 0.105 Years of education after kindergarten 12.83 (2.67) 14.50 (3.26) 0.010 0.562 (mean (SD)) Language (%) 0.018 0.647 English 15 (32.6) 21 (50.0) French 24 (52.2) 21 (50.0) Other 7 (15.2) 0 (0.0) Language of test = French (%) 20 (43.5) 11 (26.2) 0.141 0.369 Technology hours per week (mean (SD)) 19.14 (14.92) 16.52 0.362 0.198 (11.15)

[0173] Table 3 describes participant XpressO sub-test results and their MoCA Memory Index Score (MIS) and MoCA Executive Index Score (EIS). These results indicate a strong association between XpressO logical task scores and MoCA EIS, and between XpressO memory task scores and MoCA MIS. Table 3. P-value of testing the associations between MoCA Memory Index Score and XpressO memory task scores, the association between MoCA Executive Index Score and XpressO logical task scores, and the association between XpressO and MIS and demographic variables. Years of Age MoCA Executive education after Memory Index kindergarten Index Score ScoreMemory Tasks: Average number 0.032 <0.001 0.126 - of objects placed Memory Tasks: Average number 0.006 <0.001 <0.001 - of same objects Memory Tasks: Average number 0.008 0.009 <0.001 - of same objects and position Logical Tasks: Average number 0.642 0.049 - 0.525 of objects placed Logical Tasks: Average number 0.095 0.007 - 0.003 of 100% correct answers Logical Tasks: Average number 0.135 0.041 - 0.059 of correct colors Total task time in seconds 0.319 0.004 - - Average task time of memory 0.525 0.003 - - tasks in seconds Average task time of logical 0.110 0.047 - - tasks in seconds Total drags 0.632 0.008 - - Diagnosis of predictive model

[0174] The predictors included in the logistic regression are: total task time (seconds), average task time of the memory tasks (seconds), average task time of logical tasks (seconds); total number of successes entering an object into a box; additionally, for the memory tasks: the average number of objects placed, average number of correct objects, and average number of both correct object and position; for the logical tasks: the average number of correct objects (by type), the average number of correct objects (by color), average number of correct objects on all criteria (type, color and size). The XpressO memory task scores were highly associated with the MoCA Memory Index Score (MIS) (p-values<.001); the XpressO logical tasks scores were highly associated with the MoCA Executive Index Score (p-values<.03); the total XpressO scores were highly associated with the total MoCA scores (p-values<.007). Two cut-off points and an indecisive zone

[0175] Reference is now made to FIGS.7 to 9. FIG.7 shows the ROC curve and AUC values for the predictive logistic model based on the 86 participants. FIG. 8 shows the sensitivity and specificity across the total XpressO scores. FIG.9 shows histogram of MoCA scores among low, medium, and high XpressO scores. As seen in FIG. 7, sensitivity increases with high XpressOscore, and specificity increases with low XpressO score. The cut point of 72 for the scaled total XpressO score corresponds to a predicted logistic probability of 0.30, while a score of 42 corresponds to a probability of 0.59. At the cut point of 72, sensitivity was 91.3%, indicating that 8.7% of true low MoCA participants were predicted to have a score greater or equal to 25. At the cut point of 42, specificity was 90%, implying that 10% of participants with true high MoCA were classified into a low MoCA score less than or equal to 24. The two low probabilities, 8.7% and 10%, are considered improbable for a specific population. Therefore, two cut points can be used and XpressO scores between 43 and 71 constitute a gray zone that is indecisive. Discussion

[0176] The AUC was 0.828 on the training set and 0.827 on the testing set, implying good predictive performance and consistency of the logistic regression model across both the training and testing datasets. The results demonstrate that certain cut-off scores on the XpressO are highly associated with a specific range of scores on the digital classic MoCA test. This allows for the prediction of the range of the MoCA score based on the participant’s XpressO score.

[0177] Task times (total duration in seconds) of the XpressO were evaluated, and due to the skewed nature of the histogram the average task time or a standard deviation (SD) could not be applied. Therefore, the distribution is described according to the percentiles of the study population: those with scores in the lower 30% of the range were defined as “slow task times” (XpressO task time ≤318 seconds), the middle 40% was defined as “medium task times” (XpressO task time between 319 – 472 seconds), and the upper 30% was defined as the “high task times” (XpressO task time ≥473 seconds).

[0178] The sensitivity and specificity were defined by the ROC Curve for logistic regression, shown in FIG. 8. Sensitivity refers to detecting cognitive impairment, defined by MoCA scores ≤24 / 30; specificity refers to detection of intact cognition, defined by MoCA scores ≥25 / 30.

[0179] The AUC for logistic regression showed sensitivity of 91.3% for XpressO cut-off score ≤41; this suggests high accuracy for detecting the population with true cognitive impairment. According to this, XpressO scores ≤41 are likely to receive a total score ≤24 / 30 on the classic digital MoCA. Although this does not allow for a specific degree of cognitive impairment, the high sensitivity does identify the population at risk that requires further cognitive evaluation.

[0180] The AUC for logistic regression showed specificity of 90.5% for XpressO cut-off scores ≥72; this cutoff presents high accuracy in detecting the population with no objective cognitive impairment. This XpressO cutoff score may identify the population with intact cognition who are likely to score ≥25 / 30 on the MoCA test. Recognizing this population at low risk for cognitive decline may allow reassurance of the “worried well”, who may have subjective concerns of their cognitive function with no objective cognitive impairment. In addition to providing reassurance, this may shorten waiting times for specialty clinics by using the XpressO as a pre- screening tool. Table 4. MoCA score distribution among low, medium, and high XpressO scores Low XpressO (≤ 41) Medium XpressO (42-71) High XpressO (≥72) Sample size 37 (43.0%) 23 (26.7%) 26 (30.2%) MoCA (%) score Median 21 25 27 Mean 20.7 25.0 26.1 Min to Max [12, 28] [22, 27] [17, 29] 1stto 3rd[18, 24] [24, 26.5] [26, 28] quantiles

[0181] Table 4 shows MoCA score distribution among low, medium and high XpressO scores. XpressO scores between 42-71 are indecisive, likely to have MoCA scores in the range 24 / 30-26 / 30, making it difficult to distinguish intact versus impaired cognition based on the test alone. To summarize, XpressO total scores ≤41 are expected to receive a MoCA score ≤24 / 30 with sensitivity of 91.3%; XpressO total scores ≥72 are expected to receive a MoCA score ≥25 / 30 with specificity of 90.5%. Example Study 2

[0182] This study demonstrated that adding demographic characteristics of age and education to the set of predictors improved the discrimination power of the XpressO test. Method

[0183] A least absolute shrinkage and selection operator (LASSO) regression was applied to the dataset from the Example study 1 to identify additional predictors for the MoCA scoreamong the variables measured by the XpressO test. Variables that measure similar or overlapping concepts were eliminated, resulting in an optimized set of predictors that added age and education to the original set of predictors. The discrimination power of the original and modified (i.e. factoring age and education) scoring models was then evaluated using a cross-validation setup, where the dataset (n=86) was split at random into 80% training vs.20% validation subsets, and the Area under the Curve (AUC) was calculated. Sensitivity and specificity were calculated for a cutoff determined by an odds ratio of 1:1, and mean and standard deviation were calculated over 1000 repetitions. Results

[0184] The XpressO scoring model showed an average AUC of 0.797 (SD=0.104) for discriminating participants that would score above the MoCA threshold (i.e., >=25) from participants that would score below. Adding age and education to the set of predictors, the modified scoring model resulted in an improved AUC of 0.825 (SD=0.098) and a sensitivity of 77.6% at a specificity of 74.1%, so that it maintains a Negative Predictive Value (NPV) of 90% or more for prevalence of up to 25%. Example Study 3

[0185] In another example, the dependencies of raw MoCA and / or XpressO scores to certain demographic characteristics, such as age and / or education, may removed by converting such MoCA and / or XpressO scores to z-scores. The correlation between adjusted MoCA and XpressO scores, rather than between raw MoCA and XpressO scores, may allow for a better prediction of whether the user would score below the cut-off point. Example Study 4

[0186] Another example study was conducted based on the disclosed systems and processes.

[0187] A real-world evidence (RWE) study was conducted using XpressO test results from 3321 participants who performed the XpressO test (as detailed in Example Study 1) available on the MoCA Cognition website. The age of the participants is shown in FIG.10A and the number of years of education in Fig.10B. FIG.11 shows the distribution of XpressO scores.

[0188] The accuracy of the model in this RWE dataset was assessed by comparing the classification of participants scoring low on the XpressO test (42 or less) with the prevalence of dementia in the US population, as shown in Table 5 below. As can be seen there is a near perfect correlation at age bins 60-64, 65-69, and 70-74, and what would appear to be a slightly enriched population with cognitive impairment for 75-84. Table 5. Regression based model applied to the RWE dataset as a function of age compared to US prevalence for dementia.

[0189] The data from the 3321 participants was further used to train an unsupervised Gaussian mixed model which identified two distributions: a cognitively normal distribution andcognitively impaired distribution. A model based on these two distributions was created and used to classify data collected in the MoCA clinic where the paper MoCA score was known, as shown in FIG.12. As can be seen, the unsupervised Gaussian mixed model performed similarly to the XpressO regression-based model. Example Study 5

[0190] Another example study was conducted based on the disclosed systems and processes.

[0191] A real-world evidence (RWE) study was conducted using XpressO test results from 3168 participants who performed the XpressO test (as detailed in Example Study 1). As can be seen in FIGS.13A-B, the difficulty level for the memory tasks (FIG.13A) and the logical tasks (FIG.13B) increases as the user progresses through the XpressO test.

[0192] While the above description provides examples of the embodiments, it will be appreciated that some features and / or functions of the described embodiments are susceptible to modification without departing from the spirit and principles of operation of the described embodiments. Accordingly, what has been described above has been intended to be illustrative of the invention and non-limiting and it will be understood by persons skilled in the art that other variants and modifications may be made without departing from the scope of the invention as defined in the claims appended hereto. The scope of the claims should not be limited by the preferred embodiments and examples, but should be given the broadest interpretation consistent with the description as a whole.

Claims

WE CLAIM:

1. A medical process comprising: administering a first series of user tasks to a user by: displaying a first group of elements on a display and prompting the user to perform a first user task of selecting a first sub-group of elements from the first group and arranging the first sub-group in a first sequence; displaying a second group of elements on the display and prompting the user to perform a second user task of arranging one or more elements of the second group based on a predefined sequence, the second user task providing a time interval between the first user task and a third user task; and displaying a third group of elements on the display, the third group of elements including the first sub-group, and prompting the user to perform the third user task of selecting and arranging elements from the third group to reproduce the first sequence; and measuring user data points for one or more task performance parameters, the task performance parameters including: task times associated with completing each of the first user task, the second user task and the third user task; a total task time associated with completing the first series of user tasks; a number of user interactions associated with completing each of the first user task, the second user task and the third user task; a total number of user interactions associated with completing the first series of user tasks; a number of elements selected in the third user task; a number of matching elements between the first sub-group and elements selected in the third user task;a number of elements correctly arranged to reproduce the first sequence in the third user task; and a number of elements correctly arranged to match the predefined sequence in the second user task.

2. The medical process of claim 1 further comprising: determining a user cognition score based on the measured user data points; and assessing cognition of the user by comparing the user cognition score with one or more threshold values.

3. The medical process of claim 2, wherein determining the user cognition score is based on an algorithm having the one or more task performance parameters and / or one or more user demographic characteristics, for example age or education, number of times the user underwent the medical process, and / or period of time since the user last underwent the medical process, as predictor variables and a total Montreal Cognitive Assessment (MoCA) score as response variable.

4. The medical process of claim 3, wherein the algorithm is based on a regression model, for example a logistic regression model or a lasso regression model.

5. The medical process of claim 3, wherein the algorithm is based on an unsupervised Machine Learning Model e.g. a Gaussian Mixture Model, cluster analysis, manifold learning.

6. The medical process of claim 3, wherein the response variable is a binary variable defined as: 1 if the total MoCA score is smaller or equal to a predefined cutoff score; and 0 if the total MoCA score is greater than the predefined cutoff score.

7. The medical process of claim 6, wherein the predefined cutoff score is 23, 24, or 25.

8. The medical process of claim 6 or claim 7, wherein the user cognition score is a scaled probability output value of the regression model corresponding to the measured user data points being inputs to the regression model.

9. The medical process of any one of claims 6 to 8, wherein the one or more threshold values includes a first threshold value and a second threshold value, and assessing cognition of the user comprises: assessing cognition of the user to correspond to total MoCA score smaller or equal to the predefined cutoff score if the user cognition score is below the first threshold value; and assessing cognition of the user to correspond to total MoCA score greater than the predefined cutoff score if the user cognition score is above the second threshold value.

10. The medical process of any one of claims 1 to 9, wherein the predefined sequence is a logical sequence based on one or more of type, color and size of the second group of elements.

11. The medical process of any one of claims 1 to10, wherein the user interactions include click and drag interactions of the user with displayed elements.

12. The medical process of any one of claims 1 to 11, wherein the medical process is self- administered by the user.

13. The medical process of any one of claims 1 to 12, wherein the first series of user tasks is administered using a personal computer, a tablet device or a smartphone that comprises the display.

14. The medical process of any one of claims 1 to 13, further comprising administering one or more additional series of user tasks, each additional series of user tasks comprising three user tasks correspond to the first user task, the second user task and the third user task.

15. The medical process of claim 14, wherein the additional series of user tasks comprises: a second series of user tasks including a fourth user task corresponding to the first user task, a fifth user task corresponding to the second user task, and a sixth user task corresponding to the third user task; and a third series of user tasks including a seventh user task corresponding to the first user task, an eighth user task corresponding to the second user task, and a ninth user task corresponding to the third user task.

16. The medical process of claim 15, wherein:the fifth user task corresponds to a higher task difficulty level compared with the second user task; the eighth user task corresponds to a higher task difficulty level compared with the fifth user task; the sixth user task corresponds to a higher task difficulty level compared with the third user task; and the ninth user task corresponds to a higher task difficulty level compared with the sixth user task.

17. The medical process of claim 15 or claim 16, wherein the task performance parameters further comprise: an average task time associated with completing the third user task, the sixth user task, and the ninth user task; an average task time associated with completing the second user task, the fifth user task, and the eighth user task; an average number of user interactions associated with completing the third user task, the sixth user task, and the ninth user task; an average number of user interactions associated with completing the second user task, the fifth user task, and the eighth user task; an average number of elements selected in the third user task, the sixth user task, and the ninth user task; an average number of matching elements selected in the third user task, the sixth user task, and the ninth user task; an average number of elements correctly arranged in the third user task, the sixth user task, and the ninth user task; and an average number of elements correctly arranged in the second user task, the fifth user task, and the eighth user task.

18. The medical process of claim 17, wherein the task performance parameters further comprise: an average task time associated with completing the first user task, the third user task, the fourth user task, the sixth user task, the seventh user task and the ninth user task; and an average number of user interactions associated with completing the first user task, the third user task, the fourth user task, the sixth user task, the seventh user task and the ninth user task.

19. The medical process of any one of claims 1 to 18, wherein the user is aged 50 years or older.

20. The medical process of any one of claims 2 to 19 further comprising, assessing cognition of the user by comparing the user cognition score with one or more historical user cognition scores determined based on previously administered user tasks.

21. A cognition and / or early dementia assessment tool for a user, comprising performance of the medical process of any one of claims 2 to 20 for the user and identifying the user for medical intervention according to their user cognition score.

22. A method for selecting participants for a clinical trial, for example a dementia treatment or assessment clinical trial, the method comprising performance of the medical process of any one of claims 2 to 20 for a user, and selecting the user to be or not be a participant according to their user cognition score.

23. A system comprising a memory storing program instructions and a processor that is coupled to the memory to read and execute the program instructions that configure the processor to perform a medical process, wherein the medical process is defined according to any one of claims 1 to 18.

24. A non-transitory computer readable medium storing thereon program instructions that are executable by a processor for performing a medical process, wherein the medical process is defined according to any one of claims 1 to 20.

Images