Detection of slight cognitive impairment

Abstract

A means for distinguishing subjects with slight cognitive impairment in the context of neuropsychological assessment includes a set of cognitive tests. A first set of tests to which a temporal constraint or other cognitive demand parameter is applied is administered. A second set of tests is administered without temporal constraints or other cognitive demand parameters being administered. Based on comparing or correlating the scores between the two sets of tests, the slight cognitive impairment may be detected based on a criterion that a subject with the slight cognitive impairment has a greater difference in the two sets of scores than a normal subject.

Description

Technical Field

[0001] The present invention relates to the field of neuropsychological assessment. Background Art

[0002] Patients with subtle cognitive impairment, such as due to mild traumatic brain injury (mTBI) or multiple sclerosis (MS), often perform well on standard neuropsychological assessments, such as the Philips ISC (IntelliSpace Cognition) test battery. The main reason for this is that standard outcome measures for cognitive testing are not sensitive enough to detect subtle cognitive impairment. This is a problem because patients with subtle cognitive impairment may experience considerable difficulty in their daily lives due to their subtle cognitive impairment, but would be considered healthy based on the results of their neuropsychological assessments. Summary of the invention

[0003] The invention is defined by the claims.

[0004] According to an example according to one aspect of the present invention, there is provided a system comprising:

[0005] Input / output; and

[0006] One or more processors adapted to execute a method comprising:

[0007] controlling the testing device via control signals communicated through the input / output to administer a set of cognitive tests to the subject, wherein the set of cognitive tests comprises:

[0008] a plurality of first tests, wherein each of the first tests is a test that imposes a time constraint related to a completion time of the test or imposes another cognitive demand constraint, and

[0009] a plurality of second tests, wherein each of the second tests is a test without imposing the time constraint or without imposing the another cognitive demand constraint;

[0010] generating a first composite score based on a combination of test scores obtained for the subject from the plurality of first tests;

[0011] generating a second composite score based on a combination of test scores obtained for the subject from the plurality of second tests;

[0012] calculating a characteristic value based on the first comprehensive score and the second comprehensive score;

[0013] detecting the presence of mild cognitive impairment based on the characteristic value; and

[0014] An output indicative of the detection is generated at the input / output.

[0015] The general concept involves detecting mild cognitive impairment in a cognitive test battery by using a composite score for cognitive tests that impose specific cognitive demand constraints and cognitive tests that do not impose cognitive demand constraints (e.g., timed cognitive tests and untimed cognitive tests).

[0016] Regarding the time constraint option, studies have shown that patients with mild cognitive impairment have more difficulty performing time-related cognitive tests. This is likely due to the additional cognitive demands imposed by time-related tests, making the test more difficult. For example, see the following paper: Barrow, IM et al. (2003). Can within-category namingidentify subtle cognitive deficits in the mild traumatic brain-injured patient? The Journal of Trauma, 54 (5), 888-895. Also, for example, see the following paper: Raskin, SA, et al. (1998). Neuropsychological assessment of individuals with mild traumatic brain injury. The Clinical Neuropsychologist, 12 (1), 21-30.

[0017] Thus, by administering a first and second set of tests (e.g., timed and untimed tests), and calculating a characteristic value that depends on the relative scores obtained for these two categories, a more sensitive detection of mild cognitive impairment is achieved. In particular, it is expected that the difference between the typical scores obtained for timed tests and the typical scores obtained for untimed tests will be greater for those individuals with mild cognitive impairment.

[0018] In addition to time constraints, the same principles apply to any other cognitive demand constraints that are added to one test and not another. Other examples of cognitive demand constraints / parameters can include, for example: the presence of ambient noise, the imposition of multitasking requirements, adjustments to the visibility of test stimuli (e.g., brightness, clarity of stimuli, contrast of stimuli), the imposition of tactile constraints (e.g., chair movement, pen difficult to hold). It should be noted that in this disclosure, the terms "cognitive demand constraint" and "cognitive demand parameter" are synonymous. Each relates to a parameter or property or aspect or constraint of a test that has the effect of imposing additional cognitive demands on the subject performing the test compared to in the absence of that parameter / property / aspect / constraint.

[0019] Time constraints or other cognitive demand constraints present cognitive demands beyond those of the test itself.

[0020] In some embodiments, the scores for different tests may be normalized scores so that the scores from different tests are comparable to each other.

[0021] In some embodiments, the time constraint includes instructions for the subject to complete the task as quickly as possible and / or includes a time limit for completing the task.

[0022] In some embodiments, the characteristic value comprises a ratio between the first composite score and the second composite score, or vice versa.

[0023] As mentioned above, the differences between scores can be expected to be greater for people with mild cognitive impairment. Therefore, the ratio is a simple way to express the difference between the composite scores.

[0024] For example, in some embodiments, mild cognitive impairment is detected when the ratio between a first composite score (e.g., a timed test) and a second composite score (e.g., an untimed test) falls outside a predefined range (e.g., falls below a predefined threshold).

[0025] Since the first test score will generally always be lower than the second test score for both healthy and unhealthy individuals, this can be reflected by determining the ratio between the first composite score (e.g., time-constrained) and the second composite score (e.g., non-time-constrained) and seeing if this is below a predefined threshold. The greater the difference between the scores, the smaller the ratio becomes.

[0026] In some embodiments, the characteristic value comprises a difference between the second composite score and the first composite score.

[0027] In some embodiments, the one or more second tests include one or more of the following: a clock drawing test, a digit span test, a Rey auditory verbal learning test, a Rey Osterrieth composite figure test.

[0028] In some embodiments, the one or more first tests include one or more of: a line connection test, a controlled oral word association test, a categorization fluency test, a star deletion test, a symbol-digit modality.

[0029] In some embodiments, at least a subset of the set of cognitive tests can be configured to either impose or not impose time constraints or other cognitive demand constraints when administering the tests.

[0030] In some embodiments, the method includes administering the same cognitive test with a time constraint or other cognitive demand constraint imposed to form a first test among one or more first tests, and administering the same cognitive test without a time constraint or other cognitive demand constraint imposed to form a second cognitive test among one or more second cognitive tests.

[0031] For example, the same test is administered with and without time pressure to increase or decrease cognitive demand, respectively. By administering the same test with and without time constraints or other cognitive demand constraints, this means that any differences between the scores obtained by an individual for the two are more likely to be due to time constraints or other cognitive demand constraints. In some embodiments, corrections may additionally be performed on the scores of the second administered version of the test to correct for learning effects.

[0032] In some embodiments, a flow may be followed where, by default, a first test is administered first, and where, only in response to a score on the first test being outside the normal range, then the set of second tests is administered. Thus, this applies an initial filter to identify subjects who are more likely to be potential patients with mild cognitive impairment. For example, in some embodiments, a flow may be followed where, by default, a timed test is administered first, and where, only in response to a score on the timed test being outside the normal range, then a set of untimed tests is administered.

[0033] Thus, in some embodiments, at least a subset of a set of cognitive tests can be configured to either impose or not impose a time constraint or other cognitive demand constraint when administering the test; and wherein the method comprises: first administering the cognitive test with the time constraint or other cognitive demand constraint to form one of the one or more first tests; determining a score for the test; and determining whether the score is within a predefined normal range. In some embodiments, in response to the score being outside the predefined normal range (e.g., below a threshold), the method further comprises: administering the same cognitive test without imposing the time constraint or other cognitive demand constraint to form one of the one or more second tests.

[0034] In some embodiments, testing may be performed with additional layers of imposed cognitive demands (eg, the presence of ambient noise) and the imposition of multi-tasking requirements.

[0035] Thus, in some embodiments, at least a subset of the set of cognitive tests can be configured to impose one or more additional cognitive demand parameters / constraints.

[0036] In some embodiments, the method further comprises administering at least a subset of the set of cognitive tests again with the addition of additional one or more cognitive demand parameters / constraints.

[0037] In some embodiments, the method comprises administering at least a subset of the set of cognitive tests at least two additional times, each time adding a different number of additional cognitive demand parameters / constraints;

[0038] In some embodiments, the method includes calculating the characteristic value separately for the score of each administration of the set of tests.

[0039] In some embodiments, the method includes determining a relationship between the characteristic value and the number of cognitive demand parameters / constraints added. In some embodiments, detecting the presence of mild cognitive impairment is based at least in part on the relationship.

[0040] In some embodiments, one or more additional cognitive demand parameters / constraints include one or more of the following: the presence of ambient noise, the imposition of multitasking requirements, the adjustment of the visibility of the test stimuli (e.g., brightness, clarity of the stimuli, contrast of the stimuli), the imposition of tactile constraints (e.g., chair movement, pen difficult to hold).

[0041] In some embodiments, the scores of the tests can be calibrated or normalized according to the background noise level in the environment. This ensures that the scores are comparable to each other in terms of the level of cognitive demand imposed by the background noise in each.

[0042] Thus, in some embodiments, the method further comprises: sensing ambient noise intensity during administration of the set of cognitive tests. In some embodiments, the method comprises calibrating or compensating the derived score for the set of tests to control for the sensed ambient noise. Additionally or alternatively, in some embodiments, the method comprises generating a suggestion item for delivery to an operator indicating the presence and intensity of detected ambient noise.

[0043] For example, a camera (and application of machine vision algorithms to estimate noise) and / or a microphone may be used to detect the ambient noise level or intensity.

[0044] In some embodiments, the system further comprises a memory storing a database comprising control instructions for administering each test in the set of cognitive tests.

[0045] In some embodiments, the system further comprises a testing device for administering a digital neuropsychological assessment to the subject.

[0046] The present invention can also be implemented in the form of a method.

[0047] Therefore, an embodiment of the present invention also includes a method, the method comprising:

[0048] controlling the testing device to administer a battery of cognitive tests to the subject, wherein the battery of cognitive tests comprises:

[0049] a plurality of first tests, wherein each of the first tests is a test that imposes a time constraint related to a completion time of the test or imposes another cognitive demand constraint, and

[0050] a plurality of second tests, wherein each of the second tests is a test without imposing the time constraint or without imposing the another cognitive demand constraint;

[0051] generating a first composite score based on a combination of test scores obtained for the subject from the plurality of first tests;

[0052] generating a second composite score based on a combination of test scores obtained for the subject from the plurality of second tests;

[0053] calculating a characteristic value based on the first comprehensive score and the second comprehensive score;

[0054] detecting the presence of mild cognitive impairment based on the characteristic value; and

[0055] An output is generated indicative of the detection.

[0056] The present invention may also be implemented in the form of software. Therefore, embodiments of the present invention also include a computer program product, which includes a code module, which is configured to cause the processor to perform a method according to any embodiment or example described in the present disclosure when running on a processor. It should also be noted that the features between different aspects of the present invention (system, method, computer program product) are intended to be fully compatible, so that features or options recorded in the context of one aspect can be equally applied to any other aspect.

[0057] These and other aspects of the invention will be apparent from and elucidated with reference to the embodiment(s) described hereinafter. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] For a better understanding of the invention, and in order to more clearly show how the invention may be carried into effect, reference will now be made, by way of example only, to the accompanying drawings, in which:

[0059] Figure 1 The steps of an example method according to one or more embodiments of the present invention are outlined;

[0060] Figure 2Components of example processing devices and systems are schematically outlined in accordance with one or more embodiments of the present invention;

[0061] Figure 3 showing a graph illustrating comparative performance scores of healthy subjects and subjects with mild cognitive impairment for timed and untimed tests; and

[0062] Figure 4 Shown is a graph illustrating the ratio between the composite scores of untimed and timed cognitive tests as a function of the amount of cognitive demand imposed for healthy subjects and subjects with mild cognitive impairment. DETAILED DESCRIPTION

[0063] The present invention will be described with reference to the accompanying drawings.

[0064] It should be understood that the detailed description and specific examples, although indicating exemplary embodiments of the apparatus, system and method, are intended only for illustrative purposes and are not intended to limit the scope of the invention. These and other features, aspects and advantages of the apparatus, system and method of the present invention will be better understood from the following description, the appended claims and the accompanying drawings. It should be understood that the drawings are merely schematic and are not drawn to scale. It should also be understood that the same reference numerals are used throughout the drawings to indicate the same or similar parts.

[0065] The present invention provides a means for distinguishing subjects with mild cognitive impairment in the context of a neuropsychological assessment comprising a set of cognitive tests. A first set of tests is administered that imposes a time constraint or other cognitive demand constraint / parameter. A second set of tests is administered that does not impose a time constraint or other cognitive demand constraint / parameter. Based on comparing or correlating the scores between the two sets of tests, mild cognitive impairment can be detected based on the criterion that subjects with mild cognitive impairment have a greater difference in the two sets of scores than normal subjects.

[0066] Figure 1 The steps of an example method according to one or more embodiments are summarized in block diagram form.Before further explanation in the form of an example embodiment, the steps will be generally recorded.

[0067] The method 10 includes controlling a test device to administer a set of cognitive tests to a subject. The administered set of cognitive tests includes: a plurality of first tests 12, wherein each of the first tests is a test that imposes a time constraint related to the completion time of the test or imposes another cognitive demand constraint; and a plurality of second tests 14, wherein each of the second tests is a test that does not impose the time constraint or does not impose the another cognitive demand constraint.

[0068] The method also includes generating 16 a first composite score based on a combination of test scores obtained for the subject from a plurality of first tests. The method also includes generating 18 a second composite score based on a combination of test scores obtained for the subject from a plurality of second tests. The method also includes calculating 22 a characteristic value based on the first composite score and the second composite score (e.g., a difference between the scores or a ratio between the scores). The method also includes detecting 24 the presence of mild cognitive impairment based on the characteristic value. The method also includes generating 26 an output indicative of the detection. For example, the output may be a data output for transfer to another device, such as a memory, another computing device, or a user interface device.

[0069] As mentioned above, the method may also be embodied in software. Therefore, another aspect of the invention is a computer program product comprising code modules configured to, when run on a processor, cause the processor to perform a method according to any embodiment outlined in this document or according to any claim of this application.

[0070] As mentioned above, the method may also be embodied in the form of hardware, for example in the form of a system configured to perform the method according to any example or embodiment described in this document or according to any claim of this application.

[0071] To further aid understanding, Figure 2 A schematic representation of an example system 30 configured to perform methods according to one or more embodiments of the invention is presented.

[0072] The illustrated system includes a processing unit 32 including an input / output 34 and one or more processors 36 .

[0073] The one or more processors are suitable for executing the steps according to what has been recorded above or the method according to any embodiment described in this document.

[0074] More specifically, in some embodiments, the one or more processors 36 are adapted to perform a method comprising: controlling the test device 42 via a control signal transmitted through the input / output unit 34 to administer a set of cognitive tests to the subject. The set of cognitive tests comprises: a plurality of first tests, wherein each of the first tests is a test that imposes a time constraint related to the completion time of the test or imposes another cognitive demand constraint; and a plurality of second tests, wherein each of the second tests is a test that does not impose the time constraint or does not impose the other cognitive demand constraint. The method performed by the one or more processors 36 also includes: generating a first composite score based on a combination of test scores obtained from the plurality of first tests for the subject; generating a second composite score based on a combination of test scores obtained from the plurality of second tests for the subject; calculating a characteristic value based on the first composite score and the second composite score; detecting the presence of mild cognitive impairment based on the characteristic value; and generating an output indicating the detection at the input / output unit 34.

[0075] One aspect of the present invention is a system that includes only the processing unit 32 (or expressed in another way, only the input / output 34 and one or more processors 36).

[0076] Optionally, the system 30 may also include a memory 38 storing a database including control instructions for administering each test in a set of cognitive tests.

[0077] Optionally, the system may include a testing device 42 for administering a set of cognitive tests to a subject. For example, this may be a computer-based testing device, i.e., comprising a computing device. It may be a dedicated computing console or terminal. It may include a mobile computing device, such as a tablet computer, a smart phone, or a laptop computer. It may include a user interface. The user interface may include one or more sensory output devices for generating user-perceivable stimuli. The user interface may include a user input device. This may include one or more pointer devices, such as an electronic pen or pencil and / or a touch screen, and / or a gesture capture device, such as a handheld unit in which an inertial measurement unit is integrated or a camera / sensor-based gesture capture device.

[0078] The principles behind embodiments of the present invention will now be further explained.

[0079] It is expected that healthy persons, persons with mild cognitive impairment, e.g. due to mild traumatic brain injury (mTBI) or multiple sclerosis (MS), and persons with significant cognitive impairment (e.g. dementia, mild or severe TBI) will present different profiles with respect to the two (i.e. timed and untimed) composite scores.

[0080] This is shown in the expected results Figure 3Each line represents a composite performance score (y-axis) composed of a different number of tests (x-axis). Each composite score can be formed, for example, by the average of a set of scores.

[0081] Line 52 corresponds to healthy subjects for untimed tests (no time constraints were imposed). Line 54 corresponds to healthy subjects for timed tests (time constraints were imposed). Line 56 corresponds to subjects with mild cognitive impairment for untimed tests. Line 58 corresponds to subjects with mild cognitive impairment for timed tests. Line 60 corresponds to subjects with significant (i.e., non-mild) cognitive impairment for untimed tests. Line 62 corresponds to subjects with significant cognitive impairment for timed tests. For all categories of objects, performance on timed cognitive tests was slightly worse than on untimed cognitive tests. Although performance on untimed tests may be high and comparable for healthy and mildly impaired people, the difference between timed and untimed tests should be greater for people with mild cognitive impairment than for healthy people and people with significant cognitive impairment.

[0082] By way of example only, the Philips ISC (IntelliSpace Cognition) platform includes the following cognitive tests that do not impose time constraints. Thus, in some examples, the plurality of second tests may include any two or more of the following:

[0083] Clock drawing test

[0084] Digit Span Test

[0085] Rey Auditory Verbal Learning Test

[0086] Rey-Oestrich composite graph test

[0087] For further details on these tests, refer to the following books: Lezak, MD, Howieson, DB, Bigler, ED, &

[0088] Tranel, D. (2012). Neuropsychological assessment (5th ed.). New York, US: Oxford University Press.

[0089] By further development of this example, the Philips ISC (IntelliSpace Cognition) platform includes the following cognitive tests that impose time constraints. Thus, in some examples, the plurality of first tests may include any two or more of the following:

[0090] Connection test

[0091] Controlled Oral Word Association Test

[0092] Categorization Fluency Test

[0093] (Star deletion test)

[0094] Symbolic Number Mode

[0095] For further details on these tests, refer to the following books: Lezak, MD, Howieson, DB, Bigler, ED, &

[0096] Tranel, D. (2012). Neuropsychological assessment (5th ed.). New York, US: Oxford University Press.

[0097] As already indicated, a first composite score is generated from a combination of test scores obtained for the subject from a plurality of first tests, and a second composite score is generated from a combination of test scores obtained for the subject from a plurality of second tests. These composite scores may, for example, each be formed as an average of the scores for a set of untimed tests and a set of timed tests, respectively. A weighted average may also be used in some examples.

[0098] The method also includes calculating a characteristic value based on the first comprehensive score and the second comprehensive score. This can be a value indicating the relationship between the first score and the second score. It can be a value related to the degree of difference between the two scores.

[0099] A simple example of a characteristic value is the ratio between a first comprehensive score and a second comprehensive score, or vice versa.

[0100] Thus, in some embodiments, based on the automatically calculated first and second composite scores, a ratio or difference score may be calculated for each patient. The ratio or difference score provides a characteristic value.

[0101] By way of example, in some embodiments, based on the automatically calculated TIMED and UNTIMED composite scores, a ratio or difference score can be calculated for each patient. The ratio or difference score provides a characteristic value.

[0102] For example, a lower ratio of the first / second (e.g., TIMED / UNTIMED) composite score can be expected for patients with mild cognitive impairment than for normal or healthy patients (where " / " here means "divided by"). A higher ratio of the second / first (UNTIMED / TIMED) composite score can be expected for patients without mild cognitive impairment.

[0103] If the ratio score (e.g., TIMED / UNTIMED) is below a certain threshold for patients scoring within the norms for the individual cognitive tests, then the patient is more likely to have mild cognitive impairment. By way of illustration, Table 1 below shows a graphical representation of the composite scores for healthy people and people with mild cognitive impairment, and also graphically shows the TIMED:UNTIMED composite score ratio. Note that this is not based on real data.

[0104] Healthy individuals People with mild cognitive impairment Overall scoreTIMED 92 86 Overall score: UNTIMED 98 95 Ratio(TIMED:UNTIMED) 0.94 0.91

[0105] Table 1

[0106] By calculating the TIMED and UNTIMED composite scores and the TIMED / UNTIMED ratio or difference score, mild cognitive impairment can be better detected even when patients with mild cognitive impairment perform within the norms of individual cognitive tests.

[0107] For example, if for a healthy person, the composite score for the untimed test is 95, and for the timed test, the composite score is 90, this will produce a TIMED:UNTIMED ratio score of 90 / 95=0.95. If for a person with mild cognitive impairment, the score for the untimed test is 93, and for the timed test, the score is 82, this will result in a TIMED:UNTIMED ratio score of 82 / 93=0.88, which is less than the TIMED:UNTIMED ratio score of a healthy person because there is a large difference between the two composite scores. Therefore, in some embodiments, mild cognitive impairment can be detected when the ratio between the first (TIMED) composite score and the second (UNTIMED) composite score is lower than a predefined threshold. Similarly, the same principle applies in reverse, so that mild cognitive impairment can be detected when the ratio between the second (UNTIMED) composite score and the first (TIMED) composite score is higher than a predefined threshold.

[0108] Optionally, each of the test scores that form the first composite score and each of the test scores that form the second composite score can be normalized or weighted so that the results of one test are comparable to another. This can be done based on historical test data for healthy populations and populations with pathology, from which a "normative" score or normative range for the test data can be established, which represents a threshold or range, and a score outside of which may indicate an abnormality. The scoring system for each test can then be calibrated so that, for example, all tests are run on a standardized score range (e.g., 1-100), and where there is a standardization of the normative score over that range for each test. In this way, the score for one test is comparable to the score for another test in terms of its relationship to the "norm."

[0109] However, this is optional in the context of the present invention, since in practice the characteristic value is based on the relationship between two composite scores, and thus it is based on the relative values ​​of two sets of tests (e.g., timed and untimed). Therefore, absolute score values ​​may not be necessary.

[0110] In certain embodiments, it is proposed to carry out cognitive testing with and without time pressure to increase or reduce cognitive demand respectively.Even tests that are usually not timed (e.g., the Rey Auditory Verbal Learning Test) can also be carried out in a timed manner, and similarly, tests that are usually timed (e.g., the line connection test) can also be carried out in an untimed manner.Adding time pressure to untimed cognitive tests increases the cognitive demand of the test, and therefore may make it more likely to detect slight cognitive impairment.Removing time pressure from a timed test reduces the cognitive demand of the test, and may make it easier for the patient to perform the test.In addition, the method has the effect of providing a purer measure of the influence of timing on performance, because except for the presence or absence of time constraints, the characteristics of the two tests will be all the same.

[0111] It should be noted that for each version of the test - with or without time constraints - a separate normative score can be pre-established to allow for normalization with other test scores in the group.

[0112] Besides the time constraint, the same principle can be applied to any other cognitive demand constraint: the same test can be applied with or without the constraint to form one of the first and second tests, respectively.

[0113] Thus, following this concept, in some embodiments, at least a subset of the set of cognitive tests may be configurable to either impose or not impose a time constraint or other cognitive demand constraint when administering the test; and wherein the method comprises administering the same cognitive test with a time constraint or other cognitive demand constraint imposed to form one of one or more first tests, and administering the same cognitive test without a time constraint or other cognitive demand constraint imposed to form one of one or more second cognitive tests.

[0114] Additionally or alternatively, in some embodiments, performance on a first test can be used to personalize a set of tests administered as part of a neuropsychological assessment and guide the selection of subsequent cognitive tests to be administered. For example, if a patient with suspected mild cognitive impairment performs well on a first test (e.g., a timed cognitive test) with a cognitive demand constraint (i.e., within specification), subsequent tests can be applied with the same cognitive demand constraint (e.g., timing) applied (even if the normal version of the test does not have any time constraints) in order to increase cognitive demand. Conversely, if a patient with suspected mild cognitive impairment performs poorly on a first test with a cognitive demand constraint for the current cognitive test (i.e., outside the specification), subsequent tests can be applied without applying a cognitive demand constraint, such as untimed (even if their original versions were timed), in order to reduce cognitive demand.

[0115] In other words, it is proposed in some embodiments that at least a subset of the set of cognitive tests can be configured to either impose or not impose a time constraint or other cognitive demand constraint when administering the test, and wherein the method comprises the following:

[0116] first administering a cognitive test having a time constraint or other cognitive demand constraint to form a first test of the one or more first tests;

[0117] determining a score for said test;

[0118] determining whether the score is within a predefined normal range (e.g., above a minimum threshold), and

[0119] In response to the score being outside of the predefined normal range, administering the same cognitive test without imposing the time constraint or other cognitive demand constraint to form a second test of the one or more second tests.

[0120] In addition to or as an alternative to any of the above, in some embodiments, one or more additional cognitive demands may be added to one or more cognitive tests to increase their difficulty (i.e., two or more cognitive demands may be applied instead of just one cognitive demand). As already discussed, time pressure is a way to make a test more cognitively demanding. In addition to time pressure, other factors that increase the cognitive demands of a test include, among others, ambient noise or multitasking. In this regard, for example, reference is made to the paper: Reynolds, McClelland & Furnham (2014). An investigation of cognitive test performance across conditions of silence, background noise and music as a function of neuroticism. Anxiety, Stress & Coping, 27, 410-421.

[0121] Adding several cognitive demands has a cumulative effect on test performance. Patients with mild cognitive impairment are less likely to cope with this added difficulty compared to healthy people. Therefore, performance on cognitive tests may be more informative when considering how many different cognitive demands a test contains, for example by calculating ratios and ratio trends and potentially comparing these to healthy groups.

[0122] Based on this consideration, it is proposed that in some embodiments, at least a subset of a set of cognitive tests can be configured to apply one or more additional cognitive demand parameters, and wherein the method further includes: administering at least a subset of the set of cognitive tests again with the addition of one or more additional cognitive demand parameters.

[0123] In order to achieve a comparative indicator between patients that takes into account the differential performance of adding different amounts of cumulative cognitive demands (according to the concepts presented above), in some embodiments, the following may be implemented. The method may include:

[0124] administering at least a subset of the battery of cognitive tests at least two additional times, each time adding a different number of additional cognitive demand parameters;

[0125] calculating the characteristic value separately for the score of each application of the set of tests;

[0126] determining a relationship between the characteristic value and the number of cognitive demand parameters added; and

[0127] Optionally, the presence of mild cognitive impairment is detected based at least in part on the relationship.

[0128] As mentioned, and by way of example, the one or more additional cognitive demand parameters may include one or more of: the presence of ambient noise and the imposition of multitasking requirements.

[0129] To illustrate this concept, Table 2 below presents a set of illustrative comparative data (not based on real data).

[0130]

[0131] Table 2

[0132] This illustrates the expectation that normalized performance decreases with additional cognitive demands for both healthy people and people with mild cognitive impairment. However, it can be seen that for individuals with mild cognitive impairment, normalized performance decreases much more significantly. As a result, the difference (difference) between the scores for the second and first set of tests increases more dramatically with the number of cognitive demands for people with mild cognitive impairment compared to healthy people. Similarly, the ratio between the combined scores for the second:first test (e.g., untimed:timed test) also increases more dramatically with the number of cognitive demands added for people with mild cognitive impairment compared to the healthy group. This is in Figure 4 , where line 72 corresponds to subjects with mild cognitive impairment and line 74 corresponds to healthy subjects. The x-axis corresponds to the number of cognitive demands and the y-axis corresponds to the ratio of the composite scores of the untimed:timed tests.

[0133] Thus, if this ratio is used as a characteristic value, for example, it can be seen that the relationship between the characteristic value (y-axis) and the number of added cognitive demand parameters (x-axis) is different for subjects with mild cognitive impairment compared to healthy subjects.

[0134] Of course, the imposition of additional cognitive demand parameters can itself be done as an optional feature, regardless of Figure 4 As shown in Figure 4 It is evident that the application of the additional cognitive demand parameter resulted in a greater difference between the second:first score ratios of the mildly cognitively impaired subjects and the healthy subjects. Thus, the sensitivity of the detection of mild cognitive impairment was improved by the application of the additional cognitive demand.

[0135] In some embodiments, the presence and intensity of ambient noise during the performance of the cognitive test(s) is determined so that the ambient noise can be better controlled. This is particularly important in situations where ambient noise is added as an additional cognitive demand.

[0136] Thus, by way of example, this may include: sensing ambient noise intensity during administration of a set of cognitive tests, and then calibrating or compensating the derived scores of the set of tests to control for the sensed ambient noise and / or generating an advisory item for delivery to an operator indicating the presence and intensity of the detected ambient noise.

[0137] Therefore, in this set of embodiments, a baseline ambient noise level is determined. This allows a comparative level of test difficulty to be determined. It also allows the addition of additional ambient noise as additional cognitive demand in a standardized manner, i.e., such that the added ambient noise imposes a standardized additional level of difficulty.

[0138] The level of ambient noise may be measured using one or more microphones or even a camera in some examples, and image data therefrom may be processed using a machine vision algorithm suitable for inferring the noise level from the image data.

[0139] More generally, an environmental observation system including one or more cameras and / or microphones may be used to obtain an indication of the background. This information may then be used to advise or instruct the test administrator to adjust or change the background.

[0140] In some embodiments, the user interface can be controlled to display suggestion items that suggest excluding recorded data points in impaired environmental situations, such as high background noise levels, improper seating of the subject, improper position and / or movement of an input device (e.g., a tablet computer) on which the cognitive test is conducted; or the presence of other distracting factors.

[0141] In some embodiments, a real-time reliability score can be calculated for each cognitive test result based on the collected environmental background data. Based on the score, one or more suggestion items can be generated and presented on the user interface, which suggest one or more response actions: such as stopping the test or redoing the test. In some embodiments, depending on the reliability score falling below a predefined threshold, the score can be deducted from the calculation of the comprehensive score.

[0142] In some embodiments, with respect to the background recording system, event-based recording may be implemented. Here, to ensure the privacy of the subject, the background data may only be recorded within a set time window, for example, a set time interval starting before a cognitive test group and ending a set time interval thereafter. The background data may be automatically deleted after it has been used to calculate the reliability score.

[0143] The embodiments of the present invention described above employ one or more processors. One or more processors may be located in a single containing device, structure or unit, or may be distributed between a plurality of different devices, structures or units. Therefore, a reference to a processing device adapted or configured to perform a particular step or task may correspond to a step or task performed either individually or in combination by any one or more of a plurality of processing components. Those skilled in the art will understand how such a distributed processing device may be implemented. One or more processors may be implemented in a variety of ways with software and / or hardware to perform the various functions required. The processor typically employs one or more microprocessors that can be programmed using software (e.g., microcode) to perform the desired functions. The processor may be implemented as a combination of dedicated hardware for performing some functions and one or more programmed microprocessors and associated circuits for performing other functions.

[0144] Examples of circuits that may be employed in various embodiments of the present disclosure include, but are not limited to, conventional microprocessors, application specific integrated circuits (ASICs), and field programmable gate arrays (FPGAs).

[0145] In various embodiments, the processor may be associated with one or more storage media, such as volatile and non-volatile computer memory, such as RAM, PROM, EPROM, and EEPROM. The storage media may be encoded with one or more programs that, when executed on one or more processors and / or controllers, perform the desired functions. The various storage media may be fixed within the processor or controller, or may be transportable so that one or more programs stored thereon can be loaded into the processor.

[0146] By studying the drawings, the disclosure and the appended claims, those skilled in the art can understand and implement variations to the disclosed embodiments when practicing the claimed invention. In the claims, the word "comprising" does not exclude other elements or steps, and the word "a" or "an" does not exclude a plurality.

[0147] A single processor or other unit may fulfill the functions of several items recited in the claims.

[0148] The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.

[0149] The computer program may be stored / distributed on suitable media, such as optical storage media or solid-state media provided together with or as part of other hardware, but the computer program may also be distributed in other forms, such as via the Internet or other wired or wireless telecommunication systems.

[0150] If the term "suitable for" is used in the claims or the specification, it should be noted that the term "suitable for" is intended to be equivalent to the term "configured to".

[0151] Any reference signs in the claims should not be construed as limiting the scope.

Claims

1. A system comprising: Input / output; as well as One or more processors adapted to execute a method comprising: controlling the testing device via control signals communicated through the input / output to administer a set of cognitive tests to the subject, wherein the set of cognitive tests comprises: a plurality of first tests, wherein each of the first tests is a test that imposes a time constraint related to a completion time of the test or imposes another cognitive demand constraint, and a plurality of second tests, wherein each of the second tests is a test without imposing the time constraint or without imposing the another cognitive demand constraint; generating a first composite score based on a combination of test scores obtained for the subject from the plurality of first tests; generating a second composite score based on a combination of test scores obtained for the subject from the plurality of second tests; calculating a characteristic value based on the first comprehensive score and the second comprehensive score; detecting the presence of mild cognitive impairment based on the characteristic value; and An output indicative of the detection is generated at the input / output.

2. The system according to claim 1, wherein: Each of the first tests is a test that imposes a time constraint related to the completion time of the test, and wherein the time constraint includes an instruction for the subject to complete the task as quickly as possible and / or includes a time limit for completing the task.

3. The system according to claim 1 or 2, wherein: The characteristic value comprises a ratio between the first comprehensive score and the second comprehensive score, or vice versa.

4. The system according to claim 3, wherein: Mild cognitive impairment is detected in case the ratio between the first composite score and the second composite score falls outside a predefined range, such as falling below a predefined threshold.

5. The system according to any one of claims 1 to 4, wherein: The one or more second tests include one or more of the following: a clock drawing test, a digit span test, a Rey Auditory Verbal Learning Test, a Rey-Oestrich Composite Figure Test.

6. The system according to any one of claims 1 to 5, wherein: Each of the first tests is a test that imposes a time constraint related to the completion time of the test, and wherein the one or more first tests include one or more of the following: a line connection test, a controlled oral word association test, a categorization fluency test, a star deletion test, and a symbol-digit modality.

7. The system according to any one of claims 1 to 6, wherein: At least a subset of the set of cognitive tests can be configured to either impose or not impose time constraints or other cognitive demand constraints when administering the tests; and The method includes: administering the same cognitive test under a time constraint to form a first test among the one or more first tests, and administering the same cognitive test without imposing the time constraint or other cognitive demand constraints to form a second cognitive test among the one or more second cognitive tests.

8. The system according to any one of claims 1 to 7, in, At least a subset of the set of cognitive tests can be configured to either impose or not impose a time constraint when administering the tests; and Wherein, the method comprises: first administering a cognitive test having a time constraint or other cognitive demand constraint to form a first test of the one or more first tests, determining a score for said test, determining whether the score is within a predefined normal range, and In response to the score being outside of the predefined normal range, administering the same cognitive test without imposing the time constraint or other cognitive demand constraint to form a second one of the second tests.

9. The system according to any one of claims 1 to 8, in, At least a subset of the set of cognitive tests can be configured to impose one or more additional cognitive demand constraints; and Wherein, the method further comprises: At least a subset of the set of cognitive tests is administered again with the addition of additional one or more of the cognitive demand constraints.

10. The system of claim 9, wherein: The method comprises administering at least a subset of the set of cognitive tests at least two additional times, each time adding a different number of the additional cognitive demand constraints; calculating the characteristic value separately for the score of each application of the set of tests; determining a relationship between the characteristic value and the number of cognitive requirement constraints added; and Wherein detecting the presence of mild cognitive impairment is based at least in part on the relationship.

11. The system according to claim 9 or 10, wherein: The one or more additional cognitive demand constraints include one or more of: the presence of ambient noise and the imposition of multitasking requirements.

12. The system according to any one of claims 1 to 11, wherein: The method further comprises: sensing ambient noise intensity during administration of the set of cognitive tests; and calibrating or compensating the derived scores for the set of tests to control for sensed ambient noise; and / or An advisory item indicative of the presence and intensity of the detected ambient noise is generated for delivery to an operator.

13. The system of any one of claims 1-12, further comprising a testing device for administering the battery of cognitive tests to the subject.

14. A computer-implemented method comprising: controlling the testing device to administer a battery of cognitive tests to the subject, wherein the battery of cognitive tests comprises: a plurality of first tests, wherein each of the first tests is a test that imposes a time constraint related to a completion time of the test or imposes another cognitive demand constraint, and a plurality of second tests, wherein each of the second tests is a test without imposing the time constraint or without imposing the another cognitive demand constraint; generating a first composite score based on a combination of test scores obtained for the subject from the plurality of first tests; generating a second composite score based on a combination of test scores obtained for the subject from the plurality of second tests; calculating a characteristic value based on the first comprehensive score and the second comprehensive score; detecting the presence of mild cognitive impairment based on the characteristic value; and An output is generated indicative of the detection.

15. A computer program product comprising code means, the code means being configured to, when executed on a processor, cause the processor to perform the method according to claim 14.

Images