KR20220103898A - Method and apparatus for predicting amyloid positive for cognitive function normal group - Google Patents

Abstract

An embodiment of the present invention provides a method for predicting an amyloid positive status for a cognitive function normal group of a population. The method comprises the steps of: acquiring amyloid PET information and neuropsychological test data of a cognitive function normal group; extracting an important cognitive domain that distinguishes amyloid positive and negative statuses from among a plurality of cognitive domains by using the amyloid PET information and the neuropsychological test data; extracting specific subtest items that are relatively sensitive to the difference between the amyloid positive and negative statuses among the subtest items related to the extracted important cognitive domain; and deriving a comprehensive score model using the extracted specific subtest items as factors. Therefore, the method can early predict an amyloid positive for the cognitive function normal group by using a neuropsychological test.

Description

Apparatus and method for predicting amyloid positivity performed on subjects with normal cognitive function

Embodiments of the present invention relate to an apparatus and method for predicting amyloid positivity performed in a group with normal cognitive function.

With the recent advances in scientific technology and imaging techniques, computed tomography (CT), magnetic resonance imaging (MRI), positron imaging (positron) imaging techniques for diagnosing and predicting brain diseases emission tomography (PET), etc. have been developed. Among them, the amyloid PET test, which can confirm the accumulation of amyloid beta, is known to be effective in diagnosing degenerative brain diseases such as Alzheimer's disease and dementia. Amyloid PET scan is performed by injecting a special contrast agent that responds only to amyloid into the body to determine whether abnormal form of amyloid, which is produced due to abnormalities in protein metabolism, is deposited in the brain. to determine whether it is positive or negative.

Amyloid beta accumulation is known to affect cognitive function, but early detection is difficult because this difference is subtle in preclinical Alzheimer's disease. On the other hand, it is difficult to perform many tests for amyloid PET due to concerns about high cost and radioactive material tracer. Therefore, there is a need for research in which clinicians can identify preclinical Alzheimer's disease at an early stage.

Embodiments of the present invention are intended to provide an apparatus and method for early prediction of amyloid positivity in a group with normal cognitive function using a neuropsychological test.

In an embodiment of the present invention, in a method for predicting amyloid positivity performed for a group with normal cognitive function among a population, the steps of obtaining amyloid PET information and neuropsychological test data of the group with normal cognitive function, the amyloid PET extracting an important cognitive domain that distinguishes amyloid positive and negative from among a plurality of cognitive domains using information and the neuropsychological test data, relative to the difference between amyloid positive and negative among subtest items related to the extracted important cognitive domain A method of predicting amyloid positivity performed on a cognitive function normal group, including extracting sensitive specific subtest items and deriving a comprehensive score model using the extracted specific subtest items as a factor to provide.

In an embodiment of the present invention, the extracting of the important cognitive region may include extracting the important cognitive region using factor analysis.

In an embodiment of the present invention, the extracting of the important cognitive region may include extracting the important cognitive region using a multiple-indicators multiple-causes model (MIMIC model).

In an embodiment of the present invention, the important cognitive domain may be a memory cognitive domain and a frontal executive function cognitive domain.

In an embodiment of the present invention, the extracting of the specific subtest item may include extracting the specific subtest item using a multivariate analysis of variance (MANOVA).

In one embodiment of the present invention, the step of deriving the comprehensive score model includes verifying validity using factor analysis and a multiple-indicators multiple-causes model (MIMIC model) in the comprehensive score model. may include the step of

In an embodiment of the present invention, the comprehensive score model may be derived using a standard score (z-score) of the specific subtest items.

In an embodiment of the present invention, in the deriving of the comprehensive score model, weight information to be applied to the specific subtest items may be calculated using Principal Components Analysis (PCA).

An embodiment of the present invention provides a computer program stored in a medium to execute any one of the methods described above using a computer.

An embodiment of the present invention provides an apparatus for predicting amyloid positivity performed for a group with normal cognitive function among a population. A cognitive domain extraction unit for extracting an important cognitive domain that distinguishes between positive and negative amyloid, a subtest extraction unit for extracting specific subtest items that are relatively sensitive to the difference between positive and negative amyloid among the subtest items related to the extracted important cognitive domain; Provided is an apparatus for predicting amyloid positivity performed on a normal cognitive function group including a comprehensive score model generator for deriving a comprehensive score model using the extracted specific subtest items as factors.

In an embodiment of the present invention, the cognitive domain extractor may extract the important cognitive domain using factor analysis.

In an embodiment of the present invention, the cognitive region extractor may extract the important cognitive region using a multiple-indicators multiple-causes model (MIMIC model).

In an embodiment of the present invention, the important cognitive domain may be a memory cognitive domain and a frontal executive function cognitive domain.

In an embodiment of the present invention, the subtest extractor may extract the specific subtest item using a multivariate analysis of variance (MANOVA).

In an embodiment of the present invention, the comprehensive score model generator may verify validity by using factor analysis and a multiple-indicators multiple-causes model (MIMIC model) in the comprehensive score model. .

In an embodiment of the present invention, the comprehensive score model may be derived using a standard score (z-score) of the specific subtest items.

In an embodiment of the present invention, the comprehensive score model generator may calculate weight information to be applied to the specific subtest items by using Principal Components Analysis (PCA).

Other aspects, features and advantages other than those described above will become apparent from the following drawings, claims, and detailed description of the invention.

The apparatus and method for predicting amyloid positivity performed on a group with normal cognitive function according to embodiments of the present invention may predict amyloid positivity of a test subject using the above-described comprehensive score model. Through this, the device and method for predicting amyloid positivity performed on the cognitively normal group predicts amyloid positivity only through a neuropsychological test without taking a separate brain image. has the advantage of being In addition, the apparatus and method for predicting amyloid positivity performed on the normal cognitive function group can contribute to reducing the screening failure rate in many clinical studies targeting the amyloid positive group.

1 is a diagram schematically illustrating an amyloid-positive prediction system performed for a group with normal cognitive function according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating the amyloid positivity prediction apparatus of FIG. 1 .
3 is a flowchart sequentially illustrating a method for predicting amyloid positivity performed on a group of normal cognitive function according to an embodiment of the present invention.
4 is a diagram for explaining a step of deriving a comprehensive score model.
5 to 8 are diagrams for explaining step by step a method for predicting amyloid positivity performed for a group with normal cognitive function.

Since the present invention can apply various transformations and can have various embodiments, specific embodiments are illustrated in the drawings and described in detail in the detailed description. Effects and features of the present invention, and a method for achieving them, will become apparent with reference to the embodiments described below in detail in conjunction with the drawings. However, the present invention is not limited to the embodiments disclosed below and may be implemented in various forms.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings, and when described with reference to the drawings, the same or corresponding components are given the same reference numerals, and the overlapping description thereof will be omitted. .

In the following embodiments, terms such as first, second, etc. are used for the purpose of distinguishing one component from another, not in a limiting sense.

In the following examples, the singular expression includes the plural expression unless the context clearly dictates otherwise.

In the following embodiments, terms such as include or have means that the features or components described in the specification are present, and the possibility that one or more other features or components may be added is not excluded in advance.

In the following embodiments, when it is said that a part such as a film, region, or component is on or on another part, not only when it is directly on the other part, but also another film, region, component, etc. is interposed therebetween. Including cases where there is

In the drawings, the size of the components may be exaggerated or reduced for convenience of description. For example, since the size and thickness of each component shown in the drawings are arbitrarily indicated for convenience of description, the present invention is not necessarily limited to the illustrated bar.

In cases where certain embodiments are otherwise practicable, a specific process sequence may be performed different from the described sequence. For example, two processes described in succession may be performed substantially simultaneously, or may be performed in an order opposite to the order described.

In the following embodiments, when a film, region, or component is connected, other films, regions, and components are interposed between the films, regions, and components as well as when the films, regions, and components are directly connected. It also includes cases where it is indirectly connected. For example, in the present specification, when it is said that a film, a region, a component, etc. are electrically connected, not only the case where the film, a region, a component, etc. are directly electrically connected, but also other films, regions, and components are interposed therebetween. Indirect electrical connection is also included.

FIG. 1 is a diagram schematically showing an amyloid positivity prediction system performed for a group with normal cognitive function according to an embodiment of the present invention, and FIG. 2 is a block diagram illustrating the amyloid positivity prediction apparatus 100 of FIG. 1 .

First, the network environment of FIG. 1 shows an example including the amyloid positivity prediction apparatus 100 , the network 200 , the brain imaging apparatus 300 , and the user terminal 400 . In this case, the amyloid-positive prediction system of FIG. 1 may predict amyloid-positive or negative for a normal group with normal cognitive function among the population. Here, the cognitive function normal group may refer to a group in the normal range of cognitive function, not a patient group having cognitive dysfunction. Cognitive dysfunction may include problems with concentration, decreased speech function, decreased temporal and spatial abilities, decreased memory, decreased frontal executive function, and decreased other cognitive functions. The patient group with cognitive dysfunction may be a group whose disease has been confirmed using brain imaging techniques such as positron tomography and magnetic resonance imaging. However, it is important to detect cognitive dysfunction at an early stage even in the case of a group within the normal range of cognitive function, and the amyloid positivity prediction device according to the embodiments of the present invention uses only the neuropsychological test results, not the brain imaging technique described above. The technical idea is to predict amyloid positive or negative for the group.

1 and 2 , the amyloid positivity prediction apparatus 100 may include a user input/output interface 110 , a communication unit 120 , a processor 130 , and a memory 140 .

The user input/output interface 110 may be a means for an interface with an input/output device. For example, the input device may include a device such as a keyboard or mouse, and the output device may include a device such as a display for displaying a communication session of an application. As another example, the input/output interface 110 may be a means for an interface with a device in which functions for input and output are integrated into one, such as a touch screen. As a more specific example, the processor 130 processes a command of a computer program loaded in the memory 140 , and a service screen or content configured using data provided by the user terminal 400 is transmitted through the input/output interface 110 . can be displayed on the display.

The communication unit 120 is configured to transmit/receive data to and from devices such as a server and other electronic devices. The communication unit 120 may include a wireless network or a wired network, and may have a plurality of transmission/reception channels and a mixture of wired and wireless networks. The communication unit 120 may connect with the amyloid positivity prediction apparatus 100 in a manner according to a request of the amyloid positivity prediction apparatus 100 or a user input.

The processor 130 may include one or more processors as a configuration for controlling the overall amyloid positivity prediction apparatus 100 . The processor 130 may be configured to process instructions of a computer program by performing basic arithmetic, logic, and input/output operations. The command may be provided to the processor 130 by the memory 140 or the communication unit 120 . For example, the processor 130 may be configured to execute a received instruction according to a program code stored in a recording device such as the memory 140 . The processor 130 may include a cognitive region extraction unit 131 , a subtest extraction unit 132 , and a comprehensive score model generation unit 133 .

The memory 140 is a computer-readable recording medium and may include a random access memory (RAM), a read only memory (ROM), and a permanent mass storage device such as a disk drive. Also, an operating system and at least one program code may be stored in the memory 140 . These software components may be loaded from a computer-readable recording medium separate from the memory 140 using a drive mechanism. The separate computer-readable recording medium may include a computer-readable recording medium such as a floppy drive, a disk, a tape, a DVD/CD-ROM drive, and a memory card. In another embodiment, the software components may be loaded into the memory 140 through the communication unit 120 instead of a computer-readable recording medium. For example, at least one program is a program (eg, the above-described application) installed by files provided through the network 200 by a file distribution system (eg, the above-described server) for distributing installation files of developers or applications. ) may be loaded into the memory 140 based on the

The communication method of the amyloid positivity prediction system is not limited, and the communication method using a communication network (eg, mobile communication network, wired Internet, wireless Internet, broadcasting network) that the network 200 may include as well as a communication method using a short distance between devices Wireless communication may also be included. For example, the network 200 may include a personal area network (PAN), a local area network (LAN), a capus area network (CAN), a metropolitan area network (MAN), a wide area network (WAN), and a metropolitan area network (MAN). ), a wide area network (WAN), a broadband network (BBN), and any one or more of networks such as the Internet. In addition, the network 200 may include any one or more of a network topology including a bus network, a star network, a ring network, a mesh network, a star-bus network, a tree or a hierarchical network, etc. not limited

The brain imaging device 300 may take a brain image of the user. For example, the brain imaging device 300 may be an MRI imaging device or a positron emission tomography (PET) device. The brain imaging device 300 may provide the brain image captured by the user to the amyloid positivity prediction device 100 through a wired/wireless communication method.

The user terminal 400 may be a fixed terminal implemented as a computer device or a mobile terminal. Examples of the user terminal 400 include a smart phone, a mobile phone, a navigation system, a computer, a notebook computer, a digital broadcasting terminal, a personal digital assistant (PDA), a portable multimedia player (PMP), a tablet PC, and the like. The user terminal 400 may provide a result value for the neuropsychological test by directly communicating with the amyloid positivity prediction apparatus 100 through the network 200 by having a user input/output interface.

In the neuropsychological examination, examination information of a subject may be obtained through a questionnaire method, and the user terminal 400 may include a processor to derive a result value for the obtained examination information. Alternatively, the user terminal may provide the test information to the amyloid positivity prediction apparatus 100 through wired/wireless communication, and the amyloid positivity prediction apparatus 100 may derive a result value using the test information. As an embodiment, the neuropsychological examination may be performed by Seoul Neuropsychological Screening Battery-II (SNSB-II). The Seoul Neuropsychological Test is a comprehensive neuropsychological test book developed for the purpose of evaluating dementia and mild cognitive impairment. It consists of various subtests on the overall cognitive function.

Hereinafter, a method for predicting amyloid positivity performed on a group with normal cognitive function among the population will be described with reference to the drawings.

3 is a flowchart sequentially illustrating a method for predicting amyloid positivity performed on a group with normal cognitive function according to an embodiment of the present invention, and FIG. 4 is a diagram for explaining the step of deriving a comprehensive score model. 5 to 8 are diagrams for explaining step by step a method for predicting amyloid positivity performed for a group with normal cognitive function.

Referring back to FIG. 2 and FIGS. 3 to 8 , the method for predicting amyloid positivity performed for a group with normal cognitive function according to an embodiment of the present invention is first performed by the communication unit 120 in a group with normal cognitive function. Amyloid PET information and neuropsychological test data can be obtained (S100). Here, the communication unit 120 may communicate with the brain imaging device 300 and the user terminal 400 through the network 200 . 2 illustrates a case of communicating with one brain imaging device 300 and a user terminal 400, the present invention is not limited thereto, and a plurality of brain imaging devices 300 or a plurality of user terminals 400 and It is possible to obtain the above information by communicating. The above-described information may be directly obtained using the brain imaging device 300 and the user terminal 400, or may be stored and used in a database (not shown).

Next, the amyloid positivity prediction method uses the amyloid PET information and neuropsychological test data of the normal cognitive function group by the cognitive domain extraction unit 131 to determine an important cognitive domain that distinguishes positive and negative amyloid among a plurality of cognitive domains. can be extracted (S200). As shown in FIG. 5 , the human cognitive domain may be divided into an attention cognitive domain, a spatiotemporal function cognitive domain, a language ability cognitive domain, a memory cognitive domain, and a frontal executive function cognitive domain. Each cognitive domain may be associated with one or more subtest items among subtest items of a neuropsychological test.

On the other hand, the cognitive domain extractor 131 may extract the important cognitive domain after separating the measurement error in the subtest items using factor analysis. In particular, the cognitive region extractor 131 may extract an important cognitive region using a multiple-indicators multiple-causes model (MIMIC model). The multi-indicator multi-causal model is a type of Structural Equation Model (SEM), in which the latent variable is a model made by the observed variable, a reflection index type, and a formative index type that grasps the influence of the observed variables on the latent variable. is a coexistence model. In other words, the multi-index multi-causal model is a type of structural equation model that combines regression analysis and factor analysis, and can isolate measurement errors in subtest items through the latent mean analysis method. Through the above analysis, the memory cognitive domain and the prefrontal executive function cognitive domain can be extracted as important cognitive domains.

Next, the subtest extractor 132 may extract specific subtest items that are relatively sensitive to the difference between positive and negative amyloid among the extracted subtest items related to the important cognitive region (S300). The subtest items constituting the neuropsychological test data may be associated with one or more cognitive domains according to their characteristics. In other words, the cognitive domain may be associated with one or more subtest items, and the subtest extraction unit 132 may extract specific subtest items that are relatively sensitive to the difference between positive and negative amyloid among the subtest items related to the important cognitive domain. have.

Specifically, the subtest extractor 132 may extract the specific subtest item using a multivariate analysis of variance (MANOVA). Multivariate ANOVA is an analysis method for comparing differences between groups when there are two or more dependent variables, and the subtest extraction unit 132 may extract a subtest item that is relatively sensitive to a significant difference as a specific subtest item. As an embodiment, the subtest extraction unit 132 is a verbal memory test SVLT delayed (V1) and an image memory test RCFT delayed (V2) among the subtest items related to the memory recognition area and the prefrontal executive function recognition area through multivariate ANOVA. ), Stroop test, STROOP CR (V3), controlled word association test, COWAT animal (V4), and simplified mental state test, MMSE (V5), can be extracted as specific subtest items.

Next, the comprehensive score model generator 133 may derive a Preclinical Amyloid Sensitive Composite (PASC) using the extracted specific subtest items as factors (S400). As an embodiment, the overall score model may be derived using a standard score (z-score) of specific subtest items. The comprehensive score model may be constructed in such a way that the standard scores of the specific subtest items are summed.

Then, as shown in FIGS. 4 and 7 , the comprehensive score model generator 133 can verify validity using factor analysis and a multiple-indicators multiple-causes model (MIMIC model). There is (S410). Thereafter, as shown in FIGS. 4 and 8 , the comprehensive score model generator 133 may calculate weight information to be applied to the specific subtest items by using Principal Components Analysis (PCA) (S420). . Here, the comprehensive score model generation unit 133 may extract specific information of specific subtest items. The specific information may be a weight imposed on specific subtest items. The comprehensive score model generation unit 133 may calculate weight information for each specific subtest item using the specific information, and then use this to generate a comprehensive score model (PASC) as shown in Equation 1 below.

[Equation 1]

PASC=0.7*V1+0.61*V2+0.67*V3+0.55*V4+0.58*V5

The apparatus and method for predicting amyloid positivity performed on a group with normal cognitive function according to embodiments of the present invention may predict amyloid positivity of a test subject using the above-described comprehensive score model. Through this, the device and method for predicting amyloid positivity performed on the cognitively normal group predicts amyloid positivity only through a neuropsychological test without taking a separate brain image. has the advantage of being In addition, the apparatus and method for predicting amyloid positivity performed on the normal cognitive function group can contribute to reducing the screening failure rate in many clinical studies targeting the amyloid positive group.

The embodiment according to the present invention described above may be implemented in the form of a computer program that can be executed through various components on a computer, and such a computer program may be recorded in a computer-readable medium. In this case, the medium may be to store a program executable by a computer. Examples of the medium include a hard disk, a magnetic medium such as a floppy disk and a magnetic tape, an optical recording medium such as CD-ROM and DVD, a magneto-optical medium such as a floppy disk, and those configured to store program instructions, including ROM, RAM, flash memory, and the like.

Meanwhile, the computer program may be specially designed and configured for the present invention, or may be known and used by those skilled in the computer software field. Examples of the computer program may include not only machine code generated by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like.

The specific implementations described in the present invention are only examples, and do not limit the scope of the present invention in any way. For brevity of the specification, descriptions of conventional electronic components, control systems, software, and other functional aspects of the systems may be omitted. In addition, the connections or connecting members of the lines between the components shown in the drawings exemplify functional connections and/or physical or circuit connections, and in an actual device, various functional connections, physical connections that are replaceable or additional may be referred to as connections, or circuit connections. In addition, unless there is a specific reference such as “essential” or “importantly”, it may not be a necessary component for the application of the present invention.

Therefore, the spirit of the present invention should not be limited to the above-described embodiments, and the scope of the spirit of the present invention is not limited to the scope of the scope of the present invention. will be said to belong to

100: amyloid positivity prediction device
110: input/output interface
120: communication department
130: processor
131: cognitive region extraction unit
132: subtest extraction unit
133: generator
140: memory
200: network
300: brain imaging device
400: user terminal
?

Claims (17)

In the method of predicting amyloid positivity of a device for predicting amyloid positivity,
Selecting a cognitive function normal group except for the group having cognitive dysfunction among the population;
acquiring amyloid PET information and neuropsychological test data for the cognitive function normal group;
extracting an important cognitive domain that distinguishes positive and negative amyloid from among a plurality of cognitive domains in the neuropsychological test data based on the amyloid PET information targeting the cognitive function normal group;
extracting specific subtest items sensitive to the difference between positive and negative amyloid from among the subtest items corresponding to the extracted important cognitive domain based on the amyloid PET information targeting the cognitive function normal group;
determining the extracted specific subtest items as factors;
Based on the factors, deriving a first overall score model for predicting amyloid positivity for the cognitive function normal group; A method for predicting amyloid positivity performed on a cognitive function normal group, comprising a. The method of claim 1,
The step of extracting the important cognitive region is a method of predicting amyloid positivity performed for a group with normal cognitive function in which the important cognitive region is extracted using factor analysis. 3. The method of claim 2,
In the step of extracting the important cognitive region, extracting the important cognitive region using a multiple-indicator multiple-case model (MIMIC model), amyloid positivity performed for a normal cognitive function group How to predict. The method of claim 1,
The plurality of cognitive domains includes an attention cognitive domain, a spatiotemporal function cognitive domain, a language ability cognitive domain, a memory cognitive domain, and a frontal executive function cognitive domain,
The important cognitive domain is a memory cognitive domain and a frontal executive function cognitive domain, a method for predicting amyloid positivity performed for a group with normal cognitive function. The method of claim 1,
The step of extracting the specific subtest item includes extracting the specific subtest item using a multivariate analysis of variance (MANOVA). A method of predicting amyloid positivity performed on a cognitive function normal group. The method of claim 1,
A method for predicting amyloid positivity performed on a cognitive function normal group, further comprising the step of deriving a second overall score model using the first overall score model and the standard score (z-score) of the factors. The method of claim 1,
The step of deriving the first overall score model is,
Amyloid performed on a group with normal cognitive function, including: verifying validity using factor analysis and a multiple-indicator multiple-case model (MIMIC model) in the first comprehensive score model How to predict positivity. The method of claim 1,
calculating weight information to be applied to the specific subtest items using Principal Components Analysis (PCA);
The method of predicting amyloid positivity performed for a group with normal cognitive function, further comprising the step of deriving a second overall score model by using the first overall score model, the factors, and the weight information. A computer program stored in a medium for executing the method of any one of claims 1 to 8 using a computer. In the device for predicting amyloid positivity,
Excluding the group with cognitive dysfunction among the population, selecting the cognitive function normal group, acquiring amyloid PET information and neuropsychological test data targeting the cognitive function normal group, and targeting the cognitive function normal group a cognitive domain extracting unit for extracting an important cognitive domain for discriminating amyloid positive and negative from among a plurality of cognitive domains in the neuropsychological test data, based on the amyloid PET information;
a subtest extraction unit for extracting specific subtest items sensitive to a difference between positive and negative amyloid from among the subtest items corresponding to the extracted important cognitive domain based on the amyloid PET information targeting the cognitive function normal group; and
The cognitive function normal group is determined by determining the extracted specific subtest items as a factor, and based on the factor, a first comprehensive score model for predicting amyloid positivity targeting the cognitive function normal group is derived A device for predicting amyloid positivity performed on a group with normal cognitive function, including a comprehensive score model generation unit that is performed with 11. The method of claim 10,
The cognitive region extraction unit
A device for predicting amyloid positivity performed on a group with normal cognitive function, extracting the important cognitive domain using factor analysis using principal component analysis. 12. The method of claim 11,
The cognitive region extraction unit,
A multi-indicator multiple-case model (MIMIC model) to extract the important cognitive region, a device for predicting amyloid positivity performed on a cognitive function normal group. 11. The method of claim 10,
The plurality of cognitive domains includes an attention cognitive domain, a spatiotemporal function cognitive domain, a language ability cognitive domain, a memory cognitive domain, and a frontal executive function cognitive domain, and the important cognitive domain is a memory cognitive domain and a frontal executive function cognitive domain. A device for predicting amyloid positivity performed in a functional group. 11. The method of claim 10,
The subtest extraction unit,
A device for predicting amyloid positivity performed on a group with normal cognitive function, extracting the specific subtest items using multivariate analysis of variance (MANOVA). 11. The method of claim 10,
The comprehensive score model generation unit,
A device for predicting amyloid positivity performed on a cognitive function normal group, deriving a second overall score model using the first overall score model and the standard score (z-score) of the factors. 11. The method of claim 10,
The comprehensive score model generation unit,
A device for predicting amyloid positivity performed on a cognitive function normal group to verify validity using factor analysis and a multiple-indicator multiple-case model (MIMIC model) in the comprehensive score model. 11. The method of claim 10,
The comprehensive score model generation unit,
Cognitive function normal, which calculates weight information to be applied to the specific subtest items using PCA (Principal Components Analysis), and derives a second comprehensive score model using the first comprehensive score model, the factors, and the weight information A device for predicting amyloid positivity performed in a group.

Images