Method for measuring cognitive ability using game application, diagnosing cognitive impairment, and recommending customized cognitive training solution based thereon, and system therefor

Abstract

The present invention relates to a method for measuring and evaluating cognitive ability using a game application, diagnosing cognitive impairment according to the result, and recommending a customized cognitive training solution on the basis of the result thereof, and a system for executing same. An embodiment of the present invention includes: a data processing step in which a server computer receives a task program execution result of an examinee from a terminal device, thereby calculating a cognitive ability index of the examinee, and calculates a cognitive ability estimation score of the examinee from the calculated cognitive ability index; a data analysis step in which the server computer estimates the cognitive ability level of the examinee step by step in response to the calculated cognitive ability estimation score; and a solution recommendation step of providing a cognitive training solution to the terminal device in accordance with the estimated cognitive ability level of the examinee and the cognitive impairment status.

Description

A method for measuring cognitive abilities and diagnosing cognitive impairments using game applications, and recommending customized cognitive training solutions accordingly, and a system therefor.

[0001] The present invention relates to a method for measuring and evaluating cognitive ability using a game application, diagnosing cognitive impairment based on the results, and recommending a customized cognitive training solution based on the results, and to a system for executing the same.

[0002]

[0003] Cognitive abilities are a series of processes by which a person receives information from the outside world and responds to it with thoughts and actions. Examples of cognitive abilities include memory, attention, judgment, and language skills.

[0004] Cognitive impairment is a decline in cognitive abilities and can be caused by a variety of factors, including aging and brain disease. Examples of cognitive impairment include memory loss, attention deficits, impaired judgment, and language impairment.

[0005] Recently, there has been a growing demand for assessing cognitive abilities and diagnosing cognitive impairment to prevent future mental illness. Mild cognitive impairment, in particular, is a condition characterized by cognitive decline compared to age-matched individuals. It is a pre-dementia cognitive impairment that places individuals at high risk for developing Alzheimer's disease, necessitating prompt diagnosis.

[0006] Attention tests such as the Wechsler Intelligence Scale, the Continuous Performance Test (CPT), and the Comprehensive Attention Test (CAT), which are used to measure cognitive ability, are expensive, require extensive testing and analysis time, and are often conducted in person, making them difficult to access. Furthermore, prolonged testing can reduce the test taker's concentration, preventing the test results from fully reflecting the test taker's condition.

[0007] Furthermore, the arbitrary nature of the diagnostic methods for cognitive impairments presents a challenge with the validity of diagnostic results. For example, attention deficit hyperactivity disorder (ADHD) is classified by statistical analysis of CPT results. However, subjective assessments can be included depending on the reporter, resulting in inconsistent results. In particular, sensitivity for ADHD measured from CPT results ranges from 9% to 88%, and specificity from 23% to 100%, making diagnostic results difficult to trust.

[0008] Accordingly, there is a growing demand for methods for measuring cognitive ability and diagnosing cognitive impairment that are easy for both examiners and test subjects to use and whose results are reliable.

[0009]

[0010] The purpose of the present invention is to solve the above problems, and to provide a method for measuring and evaluating cognitive ability using a game application, diagnosing cognitive impairment based on the results, and providing a customized cognitive training solution, and a system for executing the same.

[0011]

[0012] In order to achieve the above object, one embodiment of the present invention includes a data processing step in which a server computer receives a result of a task program performed by a testee from a terminal device, calculates a cognitive ability index of the testee, and calculates an estimated cognitive ability score of the testee from the calculated cognitive ability index; a data interpretation step in which the server computer estimates the level of cognitive ability of the testee step by step in response to the calculated estimated cognitive ability score; and a solution recommendation step in which a cognitive training solution is provided to the terminal device in response to the estimated level of cognitive ability and cognitive impairment of the testee.

[0013] In one embodiment, in the data processing step, the server computer calculates one or more cognitive ability indicators among omission errors, false alarm errors, correct reaction time, standard deviation of correct reaction time, sensitivity, response criterion, and digit range for each task program performed by the test subject.

[0014] In one embodiment, in the data processing step, the server computer calculates a cognitive ability estimate score as the sum of the standard scores of the cognitive ability indices calculated by age and gender, or the sum of the product of the weights of the standard scores of the cognitive ability indices calculated by age and gender.

[0015] In one embodiment, before the data processing step, the server computer further includes a task program execution step in which a plurality of task programs are provided to a terminal device, and the examinee executes the task programs on the terminal device.

[0016] In one embodiment, in the task program execution step, the task program provided by the server computer to the terminal device is at least one of: a first task program, which is a game application that measures the degree of visual reaction to a target; a second task program, which is a game application that measures the degree of auditory reaction to a target; a third task program, which is a game application that sequentially inputs a plurality of numbers displayed on the terminal device; and a fourth task program, which is a game application that sequentially inputs a plurality of numbers displayed on the terminal device.

[0017] In one embodiment, before the data processing step, the server computer provides questionnaire data to a terminal device, and the subject or guardian further includes a questionnaire response step in which the subject or guardian inputs answers to questionnaire items on the terminal device.

[0018] As an example, in the data processing step, the server computer receives the test subject's questionnaire response results from the terminal device and calculates a cognitive ability index corresponding to each questionnaire question.

[0019] In one embodiment, after the data interpretation step, if the cognitive ability level of the examinee is at the “low” level, the server computer further includes an abnormality checking step in which the state of the examinee’s cognitive impairment is estimated step by step.

[0020] In one embodiment, after the data interpretation step, the server computer further includes a report display step in which the estimated cognitive ability level and cognitive impairment status of the test subject are processed into a report and provided to a terminal device.

[0021] Another embodiment of the present invention includes a server computer having a data processing module that receives the results of a task program performed by a subject from a terminal device, calculates a cognitive ability index of the subject, and calculates an estimated cognitive ability score of the subject from the calculated cognitive ability index; and a data interpretation module that estimates the level of cognitive ability of the subject step by step in response to the calculated estimated cognitive ability score.

[0022] In another embodiment, the present invention further includes a result display module that processes the estimated cognitive ability level and cognitive impairment status of the test subject into a report and provides a cognitive training solution to a terminal device in response to the cognitive ability level and cognitive impairment status.

[0023]

[0024] The present invention allows a subject to measure and evaluate their cognitive abilities and diagnose their cognitive impairments remotely, without spatial or temporal constraints, using a computing device. Furthermore, the system calculates the subject's cognitive abilities and cognitive impairment status, eliminating the examiner's subjective judgment and reducing testing costs and the time required for result analysis. Accordingly, the system can be useful in communities with limited access to healthcare for the early detection and treatment of various cognitive impairments that can result from cognitive decline, such as mild cognitive impairment, thereby reducing social costs.

[0025] Since the present invention requires the examinee to perform a task program consisting of a game application, it is possible to minimize the examinee's feelings of rejection and burden when performing the test, loss of concentration, and distortion of test result data due to involuntary participation.

[0026] In the data interpretation module of the present invention, data is accumulated each time a test subject performs a test, thereby continuously improving reliability in estimating the level of cognitive ability and cognitive impairment status.

[0027]

[0028] FIG. 1 is a schematic diagram illustrating a cognitive ability measurement and cognitive disorder diagnosis system using a game application according to one embodiment of the present invention.

[0029] FIG. 2 is a diagram schematically showing a configuration included in a server computer in one embodiment of the present invention.

[0030] FIG. 3 is a diagram showing an example of questionnaire data displayed on a terminal device in one embodiment of the present invention.

[0031] FIG. 4 is a drawing showing an example of a task program displayed on a terminal device in one embodiment of the present invention.

[0032] FIG. 5 is a diagram illustrating a method for performing a task program in one embodiment of the present invention.

[0033] FIG. 6 is a diagram illustrating a method for constructing a machine learning model of a cognitive impairment estimation unit in one embodiment of the present invention.

[0034] FIG. 7 is a diagram illustrating an ensemble machine learning model of a cognitive impairment estimation unit in one embodiment of the present invention.

[0035] FIGS. 8A to 8H are diagrams showing examples of reports processed by a report display unit in one embodiment of the present invention.

[0036] FIG. 9 is a diagram illustrating an example of a cognitive training solution provided by a solution recommendation unit in one embodiment of the present invention.

[0037] FIG. 10 is a diagram schematically illustrating a method for measuring cognitive ability and diagnosing cognitive impairment using a game application in one embodiment of the present invention.

[0038] FIG. 11 is a diagram showing the configuration of a computer device in one embodiment of the present invention.

[0039]

[0040] The following merely illustrates the principles of the present invention. Therefore, those skilled in the art will be able to implement the principles of the present invention and invent various devices within the scope and spirit of the present invention, even if not explicitly described or illustrated herein. Furthermore, all conditional terms and embodiments listed herein are expressly intended, in principle, to facilitate understanding of the present invention, and should be understood as being in no way limiting to the specifically enumerated embodiments and conditions.

[0041] Furthermore, it should be understood that all detailed descriptions of the principles, aspects, and embodiments of the present invention, as well as specific embodiments, are intended to encompass structural and functional equivalents thereof. Furthermore, it should be understood that such equivalents encompass not only currently known equivalents but also equivalents developed in the future, i.e., all devices invented to perform the same function, regardless of structure.

[0042] Thus, for example, the block diagrams herein should be understood as representing conceptual views of exemplary circuits embodying the principles of the present invention. Similarly, all flowcharts, state transition diagrams, pseudocode, and the like, which may be substantially represented on a computer-readable medium, should be understood as representing various processes performed by a computer or processor, regardless of whether a computer or processor is explicitly depicted.

[0043] The functions of various components depicted in the drawings, including functional blocks represented by processors or similar concepts, may be provided using dedicated hardware as well as hardware capable of executing software in conjunction with appropriate software. When provided by a processor, the functions may be provided by a single dedicated processor, a single shared processor, or multiple individual processors, some of which may be shared.

[0044] Furthermore, any explicit use of terms such as processor, controller, or similar concepts should not be construed to exclusively refer to hardware capable of executing software, but should be understood to implicitly include, without limitation, digital signal processor (DSP) hardware, read-only memory (ROM), random access memory (RAM), and non-volatile memory for storing software. Other commonly used hardware may also be included.

[0045] In the claims of this specification, a component expressed as a means for performing a function described in the detailed description is intended to include any method for performing the function, including, for example, a combination of circuit elements performing the function, or any form of software including firmware / microcode, combined with appropriate circuitry for executing said software to perform the function. The invention defined by these claims should be understood to be equivalent to any means found in this specification for providing the functions provided by the various enumerated means, as long as they are combined and combined in the manner required by the claims.

[0046] The above-described purposes, features, and advantages will become more apparent through the following detailed description, taken in conjunction with the accompanying drawings. Accordingly, those skilled in the art will be able to readily implement the technical concepts of the present invention. Furthermore, in describing the present invention, detailed descriptions of known technologies related to the present invention will be omitted if they are deemed to unnecessarily obscure the gist of the invention.

[0047] Hereinafter, a preferred embodiment of the present invention will be described in detail with reference to the attached drawings.

[0048]

[0049] In one embodiment of the present invention, the "subject" refers to a person whose cognitive ability is to be measured and assessed and whose cognitive impairment is to be diagnosed. For example, the subject may be a child, an elderly person, or someone seeking to be diagnosed with mild cognitive impairment, Alzheimer's disease, or another mental illness.

[0050] A "guardian" of a subject is a person who protects, raises, or educates the subject, or has a duty to do so, or a person who actually protects or supervises the subject due to a work, employment, or other relationship. For example, a guardian may be the subject's parent, guardian, family member, or teacher.

[0051] "Tester" refers to an institution or person who uses the present invention to test a subject to measure and assess the subject's cognitive abilities and diagnose cognitive impairment. For example, the tester may be a medical institution or its staff.

[0052] FIG. 1 is a schematic diagram illustrating a cognitive ability measurement and cognitive disorder diagnosis system using a game application according to one embodiment of the present invention.

[0053] A cognitive ability measurement and cognitive disorder diagnosis system (hereinafter, “system”) using a game application according to one embodiment of the present invention may each include a terminal device (100) and a server computer (200).

[0054] The terminal device (100) may be a computing device used by the subject or guardian. The terminal device (100) may receive questionnaire data and a task program from the server computer (200) and display or execute the same.

[0055] The examinee and their guardian can input answers to each question included in the survey data on the terminal device (100). Furthermore, the examinee can select actions or reactions or input answers in response to a task program running on the user terminal device (100). The terminal device (100) can transmit the answers to the survey questions input by the examinee or guardian and the results of the task program execution to the server computer (200).

[0056] The terminal device (100) can display the level of cognitive ability of the subject measured and evaluated by the server computer (200) and the diagnosed cognitive impairment status of the subject, and the subject and guardian can check the displayed contents.

[0057] The terminal device (100) may be a portable mobile device such as a smart phone, tablet computer, laptop computer, PDA, smart watch, video game console, or a desktop computer, nettop computer, workstation, set-top box, etc., and may use the service of the present invention through interaction with the server computer (200).

[0058] The server computer (200) may be a computing device that provides questionnaire data and a task program to a terminal device (100), measures and evaluates cognitive ability in response to answers to questionnaire items entered by the subject and guardian and the performance results of the task program, and diagnoses cognitive impairment.

[0059] The server computer (200) may be a single computing device or a collection of multiple computing devices connected to each other via a computer network. The server computer (200) may be composed of, for example, multiple rack-mount servers, blade servers, etc., and may be connected to a network device such as a router.

[0060] The terminal device (100) and the server computer (200) may be connected via a computer network. The computer network may be, for example, the Internet, or one or more of a personal area network (PAN), a local area network (LAN), a campus area network (CAN), a metropolitan area network (MAN), a wide area network (WAN), a radio access network (RAN), and an internet area network (IAN), which are subsets of the Internet. Each component may transmit or receive data using a data communication protocol such as TCP / IP.

[0061] The configuration of a computing device operating as a terminal device (100) and a server computer (200) is described in detail in Fig. 11.

[0062] FIG. 2 is a diagram schematically showing a configuration included in a server computer in one embodiment of the present invention.

[0063] The server computer (200) may include a questionnaire display module (210), a task display module (220), a data reception module (230), a data processing module (240), a data interpretation module (250), and a result display module (260). Each module may be a computing device or multiple computing devices connected to a computer network, or application software running on a computing device.

[0064] The questionnaire display module (210) can provide questionnaire data to the terminal device (100). The questionnaire data is used to measure and evaluate the cognitive abilities of the subject and diagnose cognitive impairment, and may include multiple questionnaire questions related to measuring the subject's attention, hyperactivity, impulsivity, etc.

[0065] Survey data may be binary data processed into a web page in HTML (hypertext markup language), JSON (javascript object notation), XML (extensible markup language), YAML (YAML ain't markup language), or another data format.

[0066] FIG. 3 is a diagram showing an example of questionnaire data displayed on a terminal device in one embodiment of the present invention.

[0067] Survey data may be expressed in the form of multimedia, such as text, static images, video, or sound, containing multiple questions and corresponding answer choices. The terminal device (100) may render the survey questions and selectable answer choices on a display device included in the terminal device (100) in response to the survey data. The subject or guardian may input appropriate answers to the survey questions on the terminal device (100).

[0068] If the examinee is a child or has mental limitations due to illness, disability, old age, or other reasons, a guardian may input answers to multiple questionnaire items on the terminal device (100) on behalf of the examinee. Alternatively, if the examinee is an adult, the examinee may input answers to multiple questionnaire items directly on the terminal device (100). The terminal device (100) may transmit the answers input by the examinee or guardian to the server computer (200).

[0069] The task presentation module (220) can provide multiple task programs to the terminal device (100). The task programs may be game applications designed to measure and evaluate the cognitive abilities of the test subject. For example, the task programs may be designed to measure and evaluate factors related to the test subject's attention.

[0070] The task program can be executed on a terminal device (100), and may be composed of, for example, a binary file that can be executed on the same platform or operating system as the terminal device (100), or a web page that implements an HTML5 game that can be executed on a web browser.

[0071] The task program may display a tutorial explaining the content and operation of each task program in a storytelling format. Furthermore, the task program may be configured to display practice items for the examinee to perform the task for practice purposes, followed by the main items for the purpose of measuring and assessing cognitive abilities.

[0072] FIG. 4 is a drawing showing an example of a task program displayed on a terminal device in one embodiment of the present invention.

[0073] The first task program illustrated in (a) may be a game application that measures the degree to which a subject reacts to visually presented targets. For example, a shape may be displayed as a target, and the subject may select a shape with the same shape or form as the displayed shape. The subject may respond to the visually presented target by selecting the location of the target and may not select objects that are visually presented but are not targets (non-targets).

[0074] The terminal device (100) executing the first task program can measure the number of selected and unselected targets, and the number of selected and unselected non-targets, and store the results in a memory device.

[0075] The second task program illustrated in (b) may be a game application that measures the extent to which a subject responds to an auditory target. For example, a sound may be played as a target, and the subject may select a sound identical or similar to the played sound. The subject may respond and select a sound when the auditory target appears, and may not select a sound when an auditory target appears that is not the target (a non-target).

[0076] The terminal device (100) executing the second task program can measure the number of selected and unselected items in response to a target, and the number of selected and unselected items in response to a non-target, and store the measured values ​​in a memory device.

[0077] The third task program illustrated in (c) may be a game application that sequentially inputs a plurality of numbers displayed on the terminal device (100). The examinee may memorize the plurality of numbers displayed on the terminal device (100) for a certain period of time, and then sequentially input the numbers on the terminal device (100) after a certain period of time has elapsed. For example, if “2, 4, 3, 7” is displayed on the terminal device (100), the examinee may sequentially input “2, 4, 3, 7” on the terminal device (100).

[0078] The terminal device (100) executing the third task program can measure whether the order of numbers entered by the examinee matches the order of numbers displayed on the terminal device (100), and store the result in the memory device. In addition, the terminal device (100) can measure the time taken by the examinee to complete the input of numbers, and store the result in the memory device.

[0079] The fourth task program illustrated in (d) may be a game application that inputs a plurality of numbers displayed on the terminal device (100) in reverse order. The examinee may memorize the plurality of numbers displayed on the terminal device (100) for a certain period of time, and then, after a certain period of time, input the numbers in the reverse order from the order displayed on the terminal device (100). For example, if “2, 4, 3, 7” is displayed on the terminal device (100), the examinee may input “7, 3, 4, 2” on the terminal device (100).

[0080] The terminal device (100) executing the 4th task program can measure whether the order of numbers entered by the examinee matches the reverse order of numbers displayed on the terminal device (100), and store the result in the memory device. In addition, the terminal device (100) can measure the time taken by the examinee to complete the input of numbers, and store the result in the memory device.

[0081] The terminal device (100) can transmit the results of the subject's task program execution stored in the memory device to the server computer (200).

[0082] FIG. 5 is a diagram illustrating a method for performing a task program in one embodiment of the present invention.

[0083] First, the terminal device (100) can display a tutorial for the task program. The examinee can view the tutorial and learn how to perform the task program. (T1010)

[0084] Then, the terminal device (100) can display practice items so that the examinee can perform the task program for practice purposes. (T1020)

[0085] If the examinee correctly answers all the practice questions or the number of practice trials performed is greater than or equal to the standard number of practice trials, the examinee can proceed to the next step. Otherwise, the terminal device (100) may display the practice questions again. (T1030) The standard number of practice trials may be, for example, three.

[0086] Then, the terminal device (100) can display this question so that the cognitive ability of the test subject can be measured and evaluated. (T1040)

[0087] The examinee can sequentially execute steps T1010 to T1040 for each of the first to fourth task programs.

[0088] After the examinee has completed the execution of all task programs, the terminal device (100) can transmit the results of the examinee's task program execution to the server computer (200).

[0089] The data receiving module (230) can receive answers entered by the examinee or guardian in response to the questionnaire questions and the results of the examinee's task program performance, and store them in a memory device.

[0090] The data receiving module (230) can store the information of the examinee, the answers entered by the examinee or guardian in response to the questionnaire items, and the results of the examinee's task program performance in tables included in the database.

[0091] The table that stores the information of the examinee can store information that identifies the examinee (e.g., a string of numbers and letters) and the examinee's personal information (e.g., name, age, gender, phone number, etc.) for each examinee.

[0092] The table that stores the survey question response results can store, for each survey question response result, information identifying the survey question response result, identification information of the examinee who submitted the response result, answers entered for each survey question, the time the response result was submitted, etc.

[0093] The table that stores the results of the task program execution can store information identifying the results of the task program execution, identification information of the examinee who submitted the results, the results of each task program, the time at which the results were submitted, etc. for each result of the task program execution.

[0094] The data processing module (240) can calculate cognitive ability indices corresponding to each questionnaire question from the questionnaire response results. Furthermore, the data processing module (240) can calculate the cognitive ability indices of the test subject from the task program performance results. The data processing module (240) can generate the calculated cognitive ability indices as primary processed data.

[0095] The data processing module (240) can calculate one or more of the following cognitive ability indicators: omission errors, false alarm errors, correct reaction time, standard deviation of correct reaction time, sensitivity, response criterion, and numerical range. The data processing module (240) can calculate cognitive ability indicators for each task program performed by the test subject.

[0096] Omission errors are an indicator of the degree of inattention of the examinee, indicating that the examinee does not respond to a target stimulus. The data processing module (240) can calculate omission errors by dividing the number of targets to which the examinee did not respond by the total number of targets.

[0097] For example, the data processing module (240) may calculate the omission error by dividing the number of targets to which the examinee did not respond in the first or second task program by the number of targets in the first or second task program, respectively. Alternatively, the data processing module (240) may calculate the omission error by dividing the number of targets to which the examinee did not respond in both the first and second task programs by the sum of the numbers of targets in the first and second task programs.

[0098] Commission error is an indicator of a subject's impulsivity and disinhibition, indicating that the subject reacts to non-target stimuli. The data processing module (240) can calculate the commission error by dividing the number of non-target stimuli to which the subject responded by the total number of non-target stimuli.

[0099] For example, the data processing module (240) may calculate the false alarm error by dividing the number of non-targets to which the examinee responded in the first or second task program by the number of non-targets in the first or second task program, respectively. Alternatively, the data processing module (240) may calculate the false alarm error by dividing the number of non-targets to which the examinee responded in both the first and second task programs by the sum of the numbers of non-targets in the first and second task programs.

[0100] Response time (RT) is an indicator of the delay time when a subject accurately responds to a target stimulus. The data processing module (240) can calculate the RT from the sum or average of the times it takes for a subject to respond to a target stimulus and then input it.

[0101] For example, the data processing module (240) may calculate the sum or average of the time it takes for the examinee to react to the target and enter the input in the first and second task programs as the correct reaction time. Alternatively, the data processing module (240) may calculate the sum or average of the time it takes for the examinee to enter the input when the number entered is correct in the third and fourth task programs as the correct reaction time.

[0102] The standard deviation of response time (SRT) is an indicator of the consistency of a test subject's responses. The data processing module (240) can calculate the SRT from multiple SRTs obtained for each test subject for each task program.

[0103] Sensitivity (d') is an indicator of the degree to which a test subject can distinguish between target and non-target stimuli. The data processing module (240) calculates the number of targets to which the test subject responded divided by the total number of targets, and a standard score (z-score) from a normal distribution for each omission error, and then calculates the difference between the calculated standard scores as sensitivity.

[0104] The response criterion (β) is an indicator of the subject's impulsivity. The data processing module (240) can calculate the ratio between the number of targets to which the subject responded divided by the total number of targets and the omission error as the response criterion.

[0105] Digital span is an indicator of the working memory capacity of the test subject. The data processing module (240) can calculate the digital span from the number of digits the test subject remembers.

[0106] For example, the data processing module (240) can calculate the number of correct numbers or the number of consecutive correct numbers among the numbers entered by the examinee in the third or fourth task program and set the number width.

[0107] The data processing module (240) can generate secondary processed data from cognitive ability indices calculated from questionnaire questions or cognitive ability indices calculated from task program performance results, or can generate secondary processed data by combining multiple cognitive ability indices. For example, the secondary processed data generated by the data processing module (240) can include estimated scores of cognitive abilities such as attention, impulse control (inhibition), working memory, and processing speed.

[0108] The data processing module (240) can calculate cognitive ability indices by distinguishing the results of questionnaire responses and task program performance according to the age and gender of the test subject. The data processing module (240) can calculate a standard score (z-score) of the cognitive ability indices calculated according to age and gender, and then calculate the sum of the standard scores or the sum of the weights multiplied by each standard score to assign an estimated cognitive ability score.

[0109] The data interpretation module (250) can estimate the cognitive ability level of the test subject by stage. Furthermore, the data interpretation module (250) can estimate the cognitive impairment status of the test subject by stage or calculate it as a numerical value (e.g., percentage, etc.).

[0110] The data interpretation module (250) may include a cognitive ability estimation unit (251) and a cognitive impairment estimation unit (252), respectively. Each unit may be a computing device or a plurality of computing devices connected to a computer network, or application software running on a computing device.

[0111] The cognitive ability estimation unit (251) can estimate the level of cognitive ability of the test subject by level. For example, the cognitive ability estimation unit (251) can classify the level of cognitive ability into three levels: “low,” “average,” and “high,” corresponding to the cognitive ability estimation scores for attention, impulse control (inhibition), working memory, and processing speed.

[0112] The cognitive ability estimation unit (251) can estimate the level of cognitive ability by comparing it with the cognitive ability estimation scores of other test subjects by age. For example, the cognitive ability estimation unit (251) calculates a standard score corresponding to attention based on the cognitive ability estimation score of the test subject, then calculates the percentile of the test subject by comparing it with the standard scores of other test subjects of the same age, and determines which section among the “low,” “average,” and “high” sections the calculated percentile belongs to, thereby estimating the level of cognitive ability for attention of the test subject.

[0113] The cognitive ability estimation unit (251) may include a machine learning model. The cognitive ability estimation unit (251) may estimate the level of cognitive ability by inputting one or more of the cognitive ability indices or cognitive ability estimation scores calculated by the data processing module (240) into the machine learning model.

[0114] Machine learning models can use clustering, an unsupervised learning method, to classify the test subject's estimated cognitive ability scores into clusters corresponding to their cognitive ability levels. Clustering methods can include, for example, K-means clustering, K-medians clustering, mean shift clustering, Gaussian mixture models (GMM), and density-based spatial clustering of applications with noise (DBSCAN).

[0115] A machine learning model can be trained using cognitive ability estimation scores and corresponding tagged or labeled cognitive ability levels as training data. For example, models such as support vector machines, logistic regression, extreme gradient boosting (XGBoost), light gradient boosting models (LightGBM), k-nearest neighbors, random forests, linear discriminant analysis (LDA), and quadratic discriminant analysis (QDA) can be trained by inputting training data containing multiple pairs of cognitive ability estimation scores and cognitive ability levels, thereby updating the parameters of the machine learning model.

[0116] The cognitive impairment estimation unit (252) can estimate the likelihood or stage of a subject's mental illness related to cognitive impairment. The likelihood of the subject's mental illness or the stage of the cognitive impairment can be categorized into three stages: "good," "suspicious," and "cautionary," for example.

[0117] The cognitive impairment estimation unit (252) may include a machine learning model. The machine learning model may be, for example, one of deep neural networks (DNNs), such as SAINT, TabNet, VIME, SubTab, SCARF, Contrastive Mixup, and TabTransformer. Alternatively, the machine learning model may be one of logistic regression, random forest, support vector machine, decision tree, gradient boosting, and XGBoost.

[0118] FIG. 6 is a diagram illustrating a method for constructing a machine learning model of a cognitive impairment estimation unit in one embodiment of the present invention.

[0119] The cognitive impairment estimation unit (252) can select features that constitute a machine learning model. (W1010)

[0120] Feature selection methods include filtering, which uses statistical analysis to select features with high correlation coefficients, or wrapping, which trains a machine learning model using a subset of features and then selects features that yield high evaluation indices. In wrapping, the evaluation indices can be, for example, Akaike information criteria (AIC), Bayes information criteria (BIC), or accuracy.

[0121] The cognitive impairment estimation unit (252) can sample or augment training data. (W1020)

[0122] Training data measured in the real world and used to train a machine learning model may not be balanced due to differences in the composition ratios of majority and minority classes. If a machine learning model that performs classification is trained using such training data, the machine learning model may overfit to the majority category, rendering the classification results for the minority category unreliable. Therefore, the cognitive impairment estimation unit (252) may implement a method of sampling or augmenting the training data to prevent overfitting of the machine learning model.

[0123] Methods to prevent overfitting at the data level include oversampling, which creates new data points in the minority category, undersampling, which removes data points in the majority category, and composite sampling, which combines oversampling and undersampling. Oversampling includes, for example, SMOTE (synthetic minority oversampling technique), SMOTE-NC (SMOTE for nominal and continuous features), and ADASYN (adaptive synthetic sampling). Undersampling includes, for example, Tomek's links, CNN (condensed nearest neighbor), and OSS (one-sided selection). Composite sampling includes, for example, SMOTE-ENN (SMOTE with edited nearest neighbors), and SMOTE-Tomek (SMOTE with TomekLinks).

[0124] The cognitive impairment estimation unit (252) can prevent overfitting of the machine learning model by performing sampling for each of the categories indicating whether or not there is a disease, the category indicating age, and the category indicating gender.

[0125] Methods to prevent overfitting at the algorithm level include cost-sensitive learning, which sets higher weights on the costs of minority categories, and two-stage training, which trains the machine learning model end-to-end and then retrains only the classifier while fixing only the feature selection part.

[0126] The cognitive impairment estimation unit (252) can prevent overfitting of a machine learning model by using data augmentation. For example, a conditional tabular generative adversarial network (CTGAN) can be used for data augmentation.

[0127] The cognitive impairment estimation unit (252) can learn and verify a machine learning model. (W1030)

[0128] The cognitive impairment estimation unit (252) can use either K-fold cross validation, which divides training data into K folds to perform learning and validation, or LOOCV (leave one out cross validation), which includes only one data per fold, to verify the machine learning model.

[0129] The cognitive impairment estimation unit (252) can evaluate a machine learning model. (W1040)

[0130] The cognitive impairment estimation unit (252) can, during the evaluation phase, perform hyperparameter optimization and model calibration, which adjusts the classification probability predicted by the machine learning model to be closer to the actual classification probability. Hyperparameter optimization can utilize, for example, grid search, random search, or Bayesian optimization. Model calibration can utilize, for example, Platt's scaling.

[0131] The cognitive impairment estimation unit (252) can select an evaluated machine learning model. (W1050)

[0132] FIG. 7 is a diagram illustrating an ensemble machine learning model of a cognitive impairment estimation unit in one embodiment of the present invention.

[0133] The cognitive impairment estimation unit (252) may include multiple (N) machine learning models that classify the cognitive impairment status of the subject by age, gender, and other characteristics. Furthermore, the cognitive impairment estimation unit (252) may construct a machine learning model using an ensemble method that combines multiple machine learning models, and use this to classify the cognitive impairment status.

[0134] For example, the cognitive impairment estimation unit (252) can perform voting on the predicted probability values ​​for each cognitive impairment state output by each machine learning model. The voting can be performed using either a hard voting method that selects an output value determined by multiple machine learning models (classification models) among the output values ​​of each machine learning model, or a soft voting method that selects an average value of the output values ​​of the machine learning models.

[0135] The result display module (260) can process the measured and evaluated cognitive ability level of the test subject and the diagnosed cognitive impairment status of the test subject into a report and provide it to the terminal device (100). In addition, the result display module (260) can recommend a cognitive training solution corresponding to the cognitive ability level and cognitive impairment status of the test subject.

[0136] The result display module (260) may include a report display unit (261) and a solution recommendation unit (262).

[0137] The report display unit (261) can process the cognitive ability index and cognitive ability estimation score calculated by the data processing module (240) and the cognitive ability level and cognitive impairment status estimated by the data interpretation module (250) into a report and provide it to the terminal device (100).

[0138] FIGS. 8A to 8H are diagrams showing examples of reports processed by a report display unit in one embodiment of the present invention.

[0139] The report display unit (261) can process a report that visualizes and displays the average value of the task program performance results of the subject and the task program performance results of subjects of the same age group as the subject, and provides an explanation of the task programs that the subject performed well and the task programs that the subject did not perform well compared to subjects of the same age group.

[0140] As shown in Fig. 8a, the report display unit (261) can display the representative score of the task program performed by the examinee and the average score for the same age group in the report. The representative score of the task program may be the average value of the scores obtained by performing all task programs.

[0141] And the report display unit (261) can display the scores obtained for each task program performed and the average score for the same age group in the report. For example, the scores obtained by the examinee and the average score for the same age group can be displayed together for the first task program, “Find the right shape,” the second task program, “Find the right sound,” the third task program, “Remember numbers in order,” and the fourth task program, “Remember numbers backwards.”

[0142] The report display unit (261) can display in the report, for a task program in which the testee's score is higher than the first reference score, a description of the cognitive ability measured by the task program and the level of cognitive ability of the testee. In addition, the report display unit (261) can display in the report, for a task program in which the testee's score is lower than the second reference score, a description of the cognitive ability measured by the task program and the level of cognitive ability of the testee.

[0143] The report display unit (261) can display cognitive ability indicators according to the results of the task program execution in the report.

[0144] As shown in Fig. 8b, the report display unit (261) can display the numerical values ​​and degrees of omission errors, false alarm errors, mean values ​​of correct reaction times, and standard deviations of correct reaction times, respectively, for the first task program, “Find the Right Shape,” and the second task program, “Find the Right Sound,” in the report. The degrees of cognitive ability indicators can be expressed as “insufficient,” “good,” or “excellent,” corresponding to the numerical values.

[0145] And as in Fig. 8c, the report display unit (261) can display the numerical value and degree of the number width in the report, respectively, for the third task program, “Remember numbers in order”, and the fourth task program, “Remember numbers backwards”.

[0146] The report display unit (261) can display information describing the cognitive ability level of the test subject in the report. For example, the data processing module (240) can display the cognitive ability level of the test subject and information describing the cognitive ability level for each of the following areas: attention, impulse control (inhibition), working memory, and processing speed.

[0147] As shown in FIGS. 8d to 8g, the report display unit (261) can display in the report the definition and effect of cognitive ability by attention, inhibition, working memory, and processing speed, related cognitive ability, the degree and status of the cognitive ability evaluation of the subject, and training content to increase the corresponding cognitive ability.

[0148] The report display unit (261) can display a summary of the subject's cognitive ability level and cognitive impairment status in the report.

[0149] As in FIG. 8h, the report display unit (261) can display in the report the date on which the test subject performed the test, the age of the test subject, the level of cognitive ability, and an explanation thereof.

[0150] The solution recommendation unit (262) can recommend a cognitive training solution that will help improve the cognitive ability of the subject and treat cognitive impairment in response to the cognitive ability level and cognitive impairment state estimated by the data interpretation module (250).

[0151] For example, if the test subject's false alarm error value is particularly low, while other cognitive abilities are close to the average value for the same age group, the solution recommendation unit (262) may recommend a program that performs the "Go / No-go" task, which is part of inhibitory control training. Furthermore, if the test subject performs poorly on the fourth task program, which requires inputting displayed numbers in reverse, resulting in a low digit span index, the solution recommendation unit (262) may recommend a program that performs the "Spatial N-back" task.

[0152] FIG. 9 is a diagram illustrating an example of a cognitive training solution provided by a solution recommendation unit in one embodiment of the present invention.

[0153] In case the subject's attention, inhibition, processing speed, etc. are judged to be reduced as in (a), the solution recommendation unit (262) may recommend a “Carrot Runner” program that performs a “Go / No-go” task or provide it to the terminal device (100).

[0154] In case it is determined that attention, cognitive control ability, etc. are reduced as in (b), the solution recommendation unit (262) may recommend a “color shooter” program that performs the “Simon” task or provide it to the terminal device (100).

[0155] In case attention, working memory, etc. are determined to be reduced as in (c), the solution recommendation unit (262) may recommend a “Jumping Rabbit” program that performs a “Spatial N-back” task or provide it to the terminal device (100).

[0156] FIG. 10 is a diagram schematically illustrating a method for measuring cognitive ability and diagnosing cognitive impairment using a game application in one embodiment of the present invention.

[0157] According to one embodiment of the present invention, each step included in the method for measuring cognitive ability and diagnosing cognitive impairment using a game application may be selectively executed. Furthermore, the order in which each step, which is not data dependent, is executed is not fixed, and may be executed simultaneously or in a different order.

[0158] In the survey response step (S1010), the survey display module (210) provides survey data to the terminal device (100), and the subject or guardian can input answers corresponding to the survey questions on the terminal device (100). The terminal device (100) can transmit the answers entered by the subject or guardian to the server computer (200).

[0159] In the task program execution step (S1020), the task presentation module (220) provides multiple task programs to the terminal device (100), and the examinee can perform the task programs on the terminal device (100). The terminal device (100) can transmit the results of the examinee's task program execution to the server computer (200).

[0160] In the data processing step (S1030), the data processing module (240) can calculate a cognitive ability index corresponding to each questionnaire item from the questionnaire response results. Furthermore, the data processing module (240) can calculate the cognitive ability index of the test subject from the task program execution results.

[0161] The data processing module (240) can generate secondary processed data from cognitive ability indices calculated from questionnaire items or cognitive ability indices calculated from task program performance results, or can generate secondary processed data by combining multiple cognitive ability indices. The secondary processed data can be estimated scores of cognitive abilities such as attention, impulse control (inhibition), working memory, and processing speed.

[0162] In the data interpretation step (S1040), the data interpretation module (250) can estimate the level of cognitive ability of the test subject step by step from the calculated cognitive ability estimation score.

[0163] In the abnormality detection step (S1050), the data interpretation module (250) can determine whether the subject's cognitive ability level is abnormal. If the subject's cognitive ability level exceeds or falls below a standardized value or level, or falls at the "low" level, the data interpretation module (250) can estimate the subject's cognitive impairment level by level or calculate it numerically.

[0164] In the data synthesis step (S1060), the data interpretation module (250) can synthesize and process the estimated cognitive ability level and cognitive impairment status of the test subject.

[0165] In the report display step (S1070), the result display module (260) can process the estimated cognitive ability level and cognitive impairment status of the test subject into a report and provide it to the terminal device (100).

[0166] In the solution recommendation step (S1080), the result display module (260) can provide a cognitive training solution to the terminal device in response to the estimated cognitive ability level and cognitive impairment status of the test subject.

[0167] FIG. 11 is a diagram showing the configuration of a computer device in one embodiment of the present invention.

[0168] The computing device (10) includes a processor (11), a memory device (12), an input / output device (13), and a system board (14).

[0169] The processor (11) executes an operation to read, change, or generate data used in one embodiment of the present invention. In addition, the processor (11) interprets and processes computer-readable instructions that execute a method of one embodiment of the present invention. The processor (11) may be a microprocessor including a control device that generates a control signal for interpreting and executing instructions, an arithmetic and logic operation device that executes arithmetic and logic operation instructions, a register that stores a plurality of instructions and the locations of the next instruction to be executed, input / output data, a cache memory that temporarily stores data exchanged between the processor (11) and a memory device (12), and a system bus that is a passage through which data moves within the processor (11).

[0170] The memory device (12) stores data processed or input / output within the computing device (10). In addition, the memory device (12) stores computer-readable instructions that execute a method according to an embodiment of the present invention. The memory device (12) may include a main memory device and an auxiliary memory device. The main memory device may include a random access memory device or a flash memory device. The auxiliary memory device may include one or more of a hard disk drive, a solid state drive (SSD), a flash memory device, an optical disc drive, and a magnetic tape.

[0171] The input / output device (13) inputs data into the computing device (10) and outputs data to the outside. In addition, the input / output device (13) inputs a computer-readable command that executes a method according to an embodiment of the present invention. The input / output device may include an external input / output terminal and a driver device that processes the external input / output terminal. For example, the external input / output terminal may include one or more of a serial port, a parallel port, a small computer system interface (SCSI), a universal serial bus (USB), IEEE 1394, an external serial advanced technology attachment (e-SATA), and Thunderbolt. In addition, the input / output device may include a network interface controller, and the network interface controller may be connected to a local area network (LAN) based on Ethernet in a wired manner, or to a wireless local area network (WLAN) based on Wi-Fi in a wireless manner.

[0172] The system board (14) connects between the processor (11), the memory device (12), and the input / output device (13), and provides a path for data processed by the computing device (10). The system board (14) may include an address bus, a command bus, a data bus, a chipset device that controls the bus, and a power system that supplies power to the components of the computer device.

[0173]

[0174] The method according to the present invention described above can be produced as a program to be executed on a computer and stored in a computer-readable recording medium. Examples of the computer-readable recording medium include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

[0175] Computer-readable recording media can be distributed across network-connected computer systems, allowing computer-readable code to be stored and executed in a distributed manner. Furthermore, functional programs, codes, and code segments for implementing the above method can be readily inferred by programmers skilled in the art to which the present invention pertains.

[0176] In addition, although the preferred embodiments of the present invention have been illustrated and described above, the present invention is not limited to the specific embodiments described above, and various modifications can be made by a person having ordinary skill in the art to which the invention pertains without departing from the gist of the present invention claimed in the claims, and such modifications should not be understood individually from the technical idea or prospect of the present invention.

Claims

1. A data processing step in which a server computer receives the test subject's task program performance results from a terminal device, calculates the test subject's cognitive ability index, and calculates the test subject's cognitive ability estimate score from the calculated cognitive ability index; A data interpretation step in which the server computer estimates the level of cognitive ability of the examinee step by step in response to the calculated cognitive ability estimation score; and A solution recommendation step for providing a cognitive training solution to a terminal device in response to the estimated cognitive ability level and cognitive impairment status of the test subject; A method for measuring cognitive ability and diagnosing cognitive impairment using game applications and recommending customized cognitive training solutions accordingly.

2. In claim 1, In the above data processing step, The server computer calculates one or more cognitive ability indicators among omission errors, false alarm errors, correct reaction time, standard deviation of correct reaction time, sensitivity, response criterion, and digit span for each task program performed by the examinee. A method for measuring cognitive ability and diagnosing cognitive impairment using game applications and recommending customized cognitive training solutions accordingly.

3. In claim 1, In the above data processing step, The server computer calculates the cognitive ability estimate score as the sum of the standard scores of the cognitive ability indicators calculated by age and gender, or the sum of the product of the weights of the standard scores of the cognitive ability indicators calculated by age and gender. A method for measuring cognitive ability and diagnosing cognitive impairment using game applications and recommending customized cognitive training solutions accordingly.

4. In claim 1, Before the above data processing step, A task program execution step in which a server computer provides multiple task programs to a terminal device and the examinee performs the task program on the terminal device; A method for measuring cognitive ability and diagnosing cognitive impairment using game applications and recommending customized cognitive training solutions accordingly.

5. In claim 4, In the above task program execution stage, The task program provided by the server computer to the terminal device is The first task program is a game application that measures the degree to which a person reacts visually to a target; The second task program is a game application that measures the degree to which the subject responds to auditory targets; The third task program is a game application that sequentially inputs multiple numbers displayed on the terminal device; and The fourth task program is a game application that inputs multiple numbers displayed on the terminal device in reverse order; one or more of A method for measuring cognitive ability and diagnosing cognitive impairment using game applications and recommending customized cognitive training solutions accordingly.

6. In claim 1, Before the above data processing step, A server computer provides survey data to a terminal device, and a survey response step in which the subject or guardian inputs answers to the survey questions on the terminal device is further included. A method for measuring cognitive ability and diagnosing cognitive impairment using game applications and recommending customized cognitive training solutions accordingly.

7. In claim 6, In the above data processing step, The server computer receives the test subject's questionnaire response results from the terminal device and calculates the cognitive ability index corresponding to each questionnaire question. A method for measuring cognitive ability and diagnosing cognitive impairment using game applications and recommending customized cognitive training solutions accordingly.

8. In claim 1, After the above data interpretation step, If the cognitive ability level of the examinee is at the “low” level, the server computer further includes a step of checking whether there is an abnormality in estimating the cognitive impairment status of the examinee by level; A method for measuring cognitive ability and diagnosing cognitive impairment using game applications and recommending customized cognitive training solutions accordingly.

9. In claim 1, After the above data interpretation step, A server computer further includes a step of processing a report on the estimated cognitive ability level and cognitive impairment status of the test subject and providing the report to a terminal device; A method for measuring cognitive ability and diagnosing cognitive impairment using game applications and recommending customized cognitive training solutions accordingly.

10. A data processing module that receives the test subject's task program performance results from a terminal device, calculates the test subject's cognitive ability index, and calculates the test subject's cognitive ability estimate score from the calculated cognitive ability index; and A server computer including a data interpretation module that estimates the level of cognitive ability of the examinee step by step in response to the calculated cognitive ability estimation score; A system for measuring cognitive abilities and diagnosing cognitive impairments using game applications and recommending customized cognitive training solutions accordingly.

11. In claim 10, A result display module that processes the estimated cognitive ability level and cognitive impairment status of the test subject into a report and provides a cognitive training solution to a terminal device in response to the cognitive ability level and cognitive impairment status; further comprising: A system for measuring cognitive abilities and diagnosing cognitive impairments using game applications and recommending customized cognitive training solutions accordingly.

Images