Determination assistance system, determination assistance method, and computer program

Abstract

This determination assistance system comprises: a storage device that stores a trained model obtained by performing learning processing by using a plurality of writing information items indicating information on writing when subjects write by using a pen-shaped object, and a plurality of correct information items each indicating types of mental disorders of the subjects; a determination unit that acquires a writing information item indicating information on writing when a target person performs writing by using the pen-shaped object, and determines the type of mental disorder of the target person by using the writing information item and the trained model; and an output unit that outputs the determination result of the determination unit.

Description

Judgment support system, judgment support method, and computer program

[0001] The present invention relates to a judgment support system, a judgment support method, and a computer program. This application claims priority based on Japanese Patent Application No. 2023-076257, filed on May 2, 2023, the contents of which are incorporated herein by reference.

[0002] Neurodevelopmental disorders (hereinafter referred to as "developmental disorders") are a group of diseases that occur during the developmental period, and it is important to provide consistent support according to the developmental stage from an early stage, and early detection is extremely necessary. In response to this demand, a method has been devised to quantify the severity of attention deficit hyperactivity disorder (ADHD) in children using brain function measurement methods (see, for example, Patent Document 1).

[0003] Patent No. 6128651

[0004] There are several types of developmental disorders. One of them is the aforementioned ADHD, and another type is autism spectrum disorder (ASD). For example, ADHD and ASD have completely different core symptoms and intervention methods, so it is important to correctly distinguish between them. However, these are easily subjectively confused as the same developmental disorder, making it difficult to correctly distinguish between them. This problem is not only common to developmental disorders, but also to psychiatric disorders in general. In other words, in addition to the aforementioned developmental disorders, psychiatric disorders also include depression and bipolar disorder, making it difficult to classify these types.

[0005] The present invention has been made in view of the above circumstances, and provides a technique that enables the type of mental illness to be more accurately determined.

[0006] One aspect of the present invention is a judgment support system that includes a storage device that stores a trained model obtained by performing a learning process using multiple pieces of handwriting information indicating information about handwriting when a subject writes using a pen-like object and correct answer information indicating the type of mental illness of the subject; a judgment unit that acquires handwriting information indicating information about handwriting when a subject writes using a pen-like object and judges the type of mental illness of the subject using the handwriting information and the trained model; and an output unit that outputs the judgment result of the judgment unit.

[0007] One aspect of the present invention is the above-mentioned judgment support system, wherein the handwriting information is information regarding the handwriting when each of the subjects wrote a figure using a pen-like object, and the figure is a handwritten figure constructed by repeatedly connecting multiple predetermined unit figures.

[0008] One aspect of the present invention is the judgment support system, wherein the writing is performed along the written figure that is shown in advance.

[0009] One aspect of the present invention is the judgment support system, wherein the writing is performed while predicting a written figure based on the unit figure shown in advance.

[0010] One aspect of the present invention is the above-mentioned judgment support system, wherein the correct answer information includes information indicating whether or not the subject is an ADHD patient and information indicating whether or not the subject is an ASD patient.

[0011] One aspect of the present invention is the above-mentioned judgment support system, wherein the learning process is performed further using brain activity information indicating the brain activity of the subject while the subject is using the pen-like object, and the judgment unit further acquires brain activity information indicating the brain activity of the subject while the subject is writing with the pen-like object, and uses the writing information, the brain activity information, and the trained model to estimate whether the subject is a healthy person or a mental illness patient.

[0012] One aspect of the present invention is the above-mentioned judgment support system, wherein the brain activity information is information indicating brain activity of the frontal lobe and parietal lobe of the subject and the object, respectively.

[0013] One aspect of the present invention is the above-described judgment support system, wherein the brain activity information is information indicating an oxygen amount.

[0014] One aspect of the present invention is the above-mentioned judgment support system, wherein the handwriting information includes at least one of the time for which a trajectory is created, the pressure used when creating the trajectory, and the inclination of the pen-like object when creating the trajectory.

[0015] One aspect of the present invention is an estimation support method comprising: a determination support device having a storage device that stores a trained model obtained by performing a learning process using multiple pieces of handwriting information indicating information about handwriting when a subject writes using a pen-like object and correct answer information indicating the type of mental illness of the subject; a determination step in which the device acquires handwriting information indicating information about handwriting when a subject writes using a pen-like object, and determines the type of mental illness of the subject using the handwriting information and the trained model; and an output step in which the determination result of the determination step is output.

[0016] One aspect of the present invention is a computer program for causing a computer to function as an estimation support system, which includes: a storage device that stores a trained model obtained by performing a learning process using multiple pieces of handwriting information indicating information about handwriting when a subject writes using a pen-like object and correct answer information indicating the type of mental illness of the subject; a judgment unit that acquires handwriting information indicating information about handwriting when a subject writes using a pen-like object and determines the type of mental illness of the subject using the handwriting information and the trained model; and an output unit that outputs the judgment result of the judgment unit.

[0017] According to the present invention, it is possible to more accurately determine the type of mental illness in a captured image.

[0018] 1 is a schematic block diagram showing the system configuration of a judgment support system 100 of the present invention. FIG. 1 is a schematic block diagram showing a specific example of the functional configuration of a terminal device 10. FIG. 2 is a diagram showing a specific example of an input device used in the input unit 12. FIG. 3 is a diagram showing a specific example of written information. FIG. 4 is a schematic block diagram showing a specific example of the functional configuration of a learning device 20. FIG. 5 is a flowchart showing a specific example of the processing of the learning device 20. FIG. 6 is a schematic block diagram showing a specific example of the functional configuration of a judgment support device 30. FIG. 7 is a flowchart showing a specific example of the processing of the judgment support device 30. FIG. 8 is a diagram showing a specific example of a unit figure of a figure written by a target person. FIG. 9 is a diagram showing a specific example of a written figure. FIG. 10 is a diagram showing another specific example of a unit figure. FIG. 11 is a diagram showing another specific example of a written figure. FIG. 12 is a diagram showing another specific example of a screen of an input device used in the input unit 12. FIG. 13 is a diagram showing another specific example of a screen of an input device used in the input unit 12. FIG. 14 is a diagram showing another specific example of a screen of an input device used in the input unit 12. FIG. 15 is a diagram showing another specific example of a screen of an input device used in the input unit 12. FIG. 16 is a diagram showing another specific example of a screen of an input device used in the input unit 12. 1 is a diagram showing the fixation time after an error in the PL line task. FIG. 2 is a diagram showing the z-score of the oxygenated hemoglobin value for each brain region in the Zigzag line task. FIG. 3 is a diagram showing the z-score of the oxygenated hemoglobin value for each brain region in the PL line task. FIG. 4 is a diagram showing the measurement results of PFC activity in the predict condition of the PL line task. FIG. 5 is a diagram showing the time-dependent change in left PFC activity in the predict condition of the PL line task. FIG. 6 is a diagram showing an outline of an example of the hardware configuration of an information processing device 90 applied to the present embodiment. FIG. 7 is a diagram showing a modified example of the judgment support device 30. FIG. 8 is a diagram showing a modified example of the judgment support system 100.

[0019] FIG. 1 is a schematic block diagram showing the system configuration of a judgment support system 100 according to the present invention. The judgment support system 100 is used to determine the type of mental illness of a person to be judged (hereinafter referred to as the "target person") based on information (hereinafter referred to as "writing information") related to the person's handwriting. More specifically, the judgment support system 100 may be used to determine the type of developmental disorder of the target person. The judgment support system 100 assists the assessor in making such a judgment. The judgment support system 100 may also make such a judgment itself. The handwriting information may be information obtained when the target person writes characters or information obtained when the target person writes shapes. Hereinafter, a person who performs operations to make such a judgment is referred to as a "user." The handwriting information of the target person may be information acquired when the target person previously performed a handwriting action, or may be information newly acquired when making a judgment. The following description will mainly focus on a configuration in which new handwriting information is acquired by the terminal device 10 when making a judgment.

[0020] The judgment support system 100 includes a terminal device 10, a learning device 20, and a judgment support device 30. The terminal device 10 and the judgment support device 30 are communicatively connected via a network 70. The learning device 20 and the judgment support device 30 may also be communicatively connected via the network 70. The network 70 may be a network using wireless communication or a network using wired communication. The network 70 may be configured using, for example, the Internet or a local area network (LAN). The network 70 may also be configured by combining multiple networks.

[0021] 2 is a schematic block diagram showing a specific example of the functional configuration of the terminal device 10. The terminal device 10 is configured using information devices such as a smartphone, tablet, personal computer, dedicated device, etc. The terminal device 10 includes a communication unit 11, an input unit 12, an output unit 13, a storage unit 14, and a control unit 15.

[0022] The communication unit 11 is a communication device. The communication unit 11 may be configured as, for example, a network interface. The communication unit 11 communicates data with other devices via the network 70 in accordance with the control of the control unit 15. The communication unit 11 may be a device that performs wireless communication or a device that performs wired communication.

[0023] The input unit 12 is configured using an input device that allows input while performing a writing action using a pen-type input tool 121, such as a pen tablet or a touch panel. The input unit 12 is operated by a user when inputting the user's instructions to the terminal device 10. The input unit 12 is also operated by a user when acquiring the user's handwritten information. The input unit 12 may be an interface for connecting an input device such as a pen tablet or a touch panel to the terminal device 10. In this case, the input unit 12 inputs an input signal generated in the input device in response to the user's input to the terminal device 10.

[0024] FIG. 3 is a diagram showing a specific example of an input device used in the input unit 12. In FIG. 3, a touch panel is used as a specific example of an input device used in the input unit 12. The touch panel may display a model image 81 and a frame 82 indicating the frame of an input area. In this display, the user prompts the target person to use a pen-type input device 121 to write (draw) the same line as the image 81 inside the frame 82. While the target person is drawing a line inside the frame 82 using the pen-type input device 121, the input unit 12 and the pen-type input device 121 acquire handwritten information of the target person.

[0025] 4 is a diagram showing a specific example of handwritten information. The input unit 12 and the pen-type input device 121 may repeatedly acquire the input position (x-y coordinates), pen pressure (pen pressure p), pen horizontal tilt (pen direction θ), pen vertical tilt (pen altitude φ), and input elapsed time (elapsed time t) at a predetermined cycle (e.g., 10 times / second, 20 times / second, etc.), and acquire this time-series information as handwritten information. The input position indicates the position where the tip of the pen-type input device 121 touches the touch panel. The input position may be represented by a coordinate system on the touch panel. The coordinate system on the touch panel may be, for example, a planar coordinate system with the lower left corner of the touch panel as the origin, the x-axis extending to the right, and the y-axis extending upward.

[0026] The pen pressure may indicate the pressure that the pen-type input device 121 applies to the touch panel at the position where the tip of the pen-type input device 121 touches the touch panel. The pen horizontal tilt indicates the angle at which the pen-type input device 121 is tilted in a horizontal plane. The pen horizontal tilt may indicate, for example, the angle formed between the center line of the projection image and a predetermined axis when the pen-type input device 121 is projected onto the plane of the touch panel. The side horizontal tilt may be, for example, the angle formed between the center line and the y-axis. This angle may be expressed as an angle proceeding clockwise from the y-axis.

[0027] The pen vertical tilt indicates the angle formed between the center line of the pen-type input device 121 and the center line of the image of the pen-type input device 121 projected onto the plane of the touch panel. The input elapsed time indicates the time elapsed since the start of input using the pen-type input device 121.

[0028] The above-described information is merely a specific example of handwritten information. Information different from the above-described information may be acquired as handwritten information. The acquired handwritten information is output to the control unit 15. The control unit 15 transmits the handwritten information to the judgment support device 30 via the network 70 using the communication unit 11.

[0029] The output unit 13 outputs information in a form that can be recognized by the user. The output unit 13 may be, for example, an image display device such as a liquid crystal display or an organic electroluminescence (EL) display. The output unit 13 may be an interface for connecting an image display device to the terminal device 10. In this case, the output unit 13 generates a video signal for displaying image data and outputs the video signal to the image display device connected to the output unit 10. The output unit 13 may be a device for outputting audio, such as a speaker. The output unit 13 may be an interface for connecting an audio output device, such as a speaker or headphones, to the terminal device 10. In this case, the output unit 13 generates an audio signal for reproducing audio data and outputs the audio signal to the audio output device connected to the output unit 10. The output unit 13 may also be configured as a touch panel integrated with the input unit 12. In the embodiment shown in FIG. 3, the output unit 13 is configured as a touch panel. In this case, the output unit 13 may also be provided in the terminal device 10 as a device (e.g., a speaker) in a form different from a touch panel.

[0030] The storage unit 14 is configured using a storage device such as a magnetic hard disk drive or a semiconductor storage device. The storage unit 14 stores data used by the control unit 15. The storage unit 14 stores data required when the control unit 15 performs processing.

[0031] The control unit 15 is configured using a processor such as a CPU (Central Processing Unit) and a memory (main storage device). The control unit 15 functions when the processor executes a program. Note that all or part of the functions of the control unit 15 may be realized using hardware such as an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), or an FPGA (Field Programmable Gate Array). The program may be recorded on a computer-readable recording medium. Examples of computer-readable recording media include portable media such as a flexible disk, a magneto-optical disk, a ROM, a CD-ROM, and a semiconductor storage device (e.g., an SSD: Solid State Drive), as well as storage devices such as a hard disk or semiconductor storage device built into a computer system. The program may be transmitted via a telecommunications line.

[0032] The control unit 15 may execute, for example, an application installed on its own device (the terminal device 10). A specific example of such an application is an application provided to the terminal device 10 as a dedicated application for the judgment support system 100. Another specific example of such an application is a web browser application. Such an application may be pre-installed on the terminal device 10 or may be downloaded each time a judgment process is executed. For example, when implemented as a web browser application, the terminal device 10 may download and execute the application from a device specified by a specific web server (for example, the web server itself or another server) in response to the terminal device 10 connecting to the web server. The control unit 15 operates according to the program of the application being executed.

[0033] The control unit 15 controls the terminal device 10 in response to user operations and information received from the judgment support device 30. For example, the control unit 15 transmits information input by the target person or the user operating the input unit 12 to the judgment support device 30 using the communication unit 11. For example, the control unit 15 acquires handwritten information when the target person writes on the input unit 12 (e.g., a touch panel) using the pen-type input instrument 121 and transmits the acquired handwritten information to the judgment support device 30. For example, when information transmitted from the judgment support device 30 is received by the communication unit 11 via the network 70, the control unit 15 generates screen data based on the received information and displays the screen data on the output unit 13. Such screen data includes images and text transmitted from the judgment support device 30. For example, when information transmitted from the judgment support device 30 is received by the communication unit 11 via the network 70, the control unit 15 generates voice data based on the received information and outputs the voice data from the output unit 13.

[0034] 5 is a schematic block diagram showing a specific example of the functional configuration of learning device 20. Learning device 20 is configured using an information processing device such as a personal computer or a server device. Learning device 20 includes a communication unit 21, a storage unit 22, and a control unit 23.

[0035] The communication unit 21 is a communication device. The communication unit 21 may be configured as, for example, a network interface. The communication unit 21 communicates data with other devices via the network 70 in accordance with the control of the control unit 23. The communication unit 21 may be a device that performs wireless communication or a device that performs wired communication.

[0036] The storage unit 22 is configured using a storage device such as a magnetic hard disk drive or a semiconductor storage device. The storage unit 22 stores data used by the control unit 23. The storage unit 22 may function as, for example, a teacher data storage unit 221, a preprocessed teacher data storage unit 222, and a trained model storage unit 223.

[0037] The teacher data storage unit 221 stores teacher data used in the learning process executed by the learning device 20. The teacher data stored in the teacher data storage unit 221 includes handwritten information obtained as a result of past writing by multiple people, and label information for each piece of handwritten information regarding the person who wrote the handwritten information. The label information includes information regarding the type of mental illness of that person. In the following explanation, developmental disorders will be used as a specific example of mental illness. If the teacher data includes handwritten information of a person who does not suffer from a developmental disorder, a value indicating that the person does not suffer from a developmental disorder is assigned to the label of that handwritten information. Types of developmental disorders include, for example, ADHD and ASD.

[0038] The preprocessed teacher data storage unit 222 stores preprocessed teacher data. The preprocessed teacher data stores information obtained by the preprocessing control unit 232 performing preprocessing on handwriting information. The preprocessing may be, for example, a process of acquiring handwriting feature information. In this case, the preprocessed teacher data includes handwriting feature information and label information corresponding to the handwriting information used to acquire each piece of handwriting feature information.

[0039] The writing feature information is information relating to the feature quantities of a writing action. Specific examples of writing feature information are listed below. Height: The difference between the maximum y-coordinate and the minimum y-coordinate Velocity: The length of the written line / The time required to write the line PIAL: The minimum acceleration when writing the line GAMW: The average value of the vertical pen tilt GAML: The average value of the horizontal pen tilt GASDW: The standard deviation of the vertical pen tilt GASDL: The standard deviation of the horizontal pen tilt Average writing pressure: The average value of the writing pressure SD writing pressure: The standard deviation of the writing pressure PSMax: The maximum increase in the writing pressure within a predetermined time PSMin: The maximum decrease in the writing pressure within a predetermined time Writing feature information other than those described above may also be acquired. Only a portion of the writing feature information described above may be used as preprocessed training data.

[0040] The trained model storage unit 223 stores trained models obtained by a learning process using the teacher data stored in the teacher data storage unit 221 and the preprocessed teacher data stored in the preprocessed teacher data storage unit 222.

[0041] The control unit 23 is configured using a processor such as a CPU and a memory. The control unit 23 functions as an information control unit 231, a preprocessing control unit 232, and a learning control unit 233 by the processor executing a program. Note that all or part of the functions of the control unit 23 may be realized using hardware such as an ASIC, a PLD, or an FPGA. The above program may be recorded on a computer-readable recording medium. Examples of computer-readable recording media include portable media such as a flexible disk, a magneto-optical disk, a ROM, a CD-ROM, and a semiconductor storage device (e.g., an SSD), as well as storage devices such as a hard disk or semiconductor storage device built into a computer system. The above program may be transmitted via a telecommunications line.

[0042] The information control unit 231 controls the input and output of information. For example, the information control unit 231 acquires teacher data from another device (an information processing device or a storage medium) and records it in the teacher data storage unit 221. For example, the information control unit 231 transmits the trained model stored in the trained model storage unit 223 to another device (for example, the judgment support device 30).

[0043] The preprocessing control unit 232 generates preprocessed training data by performing a predetermined preprocessing on the training data. The preprocessing control unit 232 may generate preprocessed training data by, for example, performing a predetermined calculation based on the handwriting information to acquire handwriting feature information. Specifically, the preprocessing control unit 232 may perform the following process, for example: First, the preprocessing control unit 232 reproduces the shape of the written line by connecting input positions in the handwriting information in order, starting from the first input position in the time series. The "height" value is obtained by calculating the difference between the maximum and minimum y-coordinates of the input coordinates used in this reproduction. The "velocity" value is obtained by calculating the length of the reproduced line and dividing it by the time difference between the first and last handwriting information in the time series used in the reproduction. The "PIAL" value is obtained by calculating the acceleration at each input position based on the velocity value at each input position. The other average values ​​and standard deviations are obtained by calculating statistical values ​​of each value of the handwriting information.

[0044] The learning control unit 233 performs a learning process using the preprocessed teacher data stored in the preprocessed teacher data storage unit 222. Specific examples of such learning processes include supervised learning for classification, such as support vector machines, random forests, and neural networks. The learning control unit 233 generates a trained model for outputting the type of developmental disorder of a person based on input handwriting feature information, for example, by performing supervised learning. The learning control unit 233 records the generated trained model in the trained model storage unit 223. The trained model obtained by the learning control unit 233 may be transmitted to the assessment support device 30 and recorded in the trained model storage unit 321 of the assessment support device 30. Such a trained model can obtain, as an output, a value indicating the type of developmental disorder of the person when given handwriting feature information as input.

[0045] 6 is a flowchart showing a specific example of processing by the learning device 20. First, the information control unit 231 acquires training data (step S101). The training data may be input by a user, acquired via communication from another information device, or acquired from a recording medium connected to the learning device 20, for example. The preprocessing control unit 232 performs predetermined preprocessing on the training data (step S102). The learning control unit 233 performs a learning process using the preprocessed training data and records a trained model in the trained model storage unit 223 (step S103).

[0046] 7 is a schematic block diagram showing a specific example of the functional configuration of the judgment support device 30. The judgment support device 30 is configured using an information processing device such as a personal computer or a server device. The judgment support device 30 includes a communication unit 31, a storage unit 32, and a control unit 33.

[0047] The communication unit 31 is a communication device. The communication unit 31 may be configured as, for example, a network interface. The communication unit 31 communicates data with other devices via the network 70 in accordance with the control of the control unit 33. The communication unit 31 may be a device that performs wireless communication or a device that performs wired communication.

[0048] The storage unit 32 is configured using a storage device such as a magnetic hard disk drive or a semiconductor storage device. The storage unit 32 stores data used by the control unit 33. The storage unit 32 may function as a trained model storage unit 321, for example.

[0049] The trained model storage unit 321 stores information about trained models generated in advance by a training process. Such training process may be performed by, for example, another device (e.g., the training device 20) or by the device itself (the judgment support device 30).

[0050] The control unit 33 is configured using a processor such as a CPU and a memory. The control unit 33 functions as an information control unit 331, a preprocessing control unit 332, and a determination unit 333 by the processor executing a program. Note that all or part of the functions of the control unit 33 may be realized using hardware such as an ASIC, a PLD, or an FPGA. The above program may be recorded on a computer-readable recording medium. Examples of computer-readable recording media include portable media such as a flexible disk, a magneto-optical disk, a ROM, a CD-ROM, and a semiconductor storage device (e.g., an SSD), as well as storage devices such as a hard disk or semiconductor storage device built into a computer system. The above program may be transmitted via a telecommunications line.

[0051] The information control unit 331 acquires handwritten information of the target person from another device such as the terminal device 10 .

[0052] The information control unit 331 transmits information indicating the determination result obtained by the determination unit 333 to another device such as the terminal device 10. Such exchange of information between the information control unit 331 and another device may be performed by communication using the communication unit 31, for example.

[0053] The preprocessing control unit 332 acquires handwriting feature information by performing predetermined preprocessing on the handwriting information of the target person acquired by the information control unit 331. The preprocessing performed by the preprocessing control unit 332 is similar to the preprocessing performed when generating a trained model used by the determination unit 333. In other words, the processing performed by the preprocessing control unit 332 on the handwriting information of the target person is the same as the processing performed by the preprocessing control unit 232 on the handwriting information of the target person. The preprocessing control unit 332 acquires handwriting feature information by performing such preprocessing.

[0054] The determination unit 333 performs a determination process using the learned model stored in the learned model storage unit 321 and the handwriting feature information. The determination process determines the type of mental illness of the target person. In this embodiment, the determination unit 333 determines the type of developmental disorder of the target person. The determination unit 333 outputs a determination result regarding at least the type of developmental disorder of the target person.

[0055] 8 is a flowchart showing a specific example of processing by the judgment support device 30. First, the information control unit 331 acquires handwriting information of the target person from the terminal device 10 (step S201). The preprocessing control unit 332 acquires handwriting feature information by performing preprocessing on the handwriting information of the target person (step S202). The judgment unit 333 performs judgment processing using at least the handwriting feature information (step S203). The judgment unit 333 transmits information indicating the judgment result to the terminal device 10 (step S204).

[0056] The assessment support system 100 configured in this manner can more accurately determine the type of developmental disorder of a target person by using the handwriting information of the target person. Specifically, the assessment support system 100 executes a learning process using multiple pieces of handwriting feature information generated using the handwriting information of multiple people, and obtains a trained model. The assessment support system 100 then acquires handwriting information of a new person to be assessed, and executes preprocessing based on the acquired information to acquire handwriting feature information. The handwriting feature information has a correlation with the type of mental disorder (e.g., developmental disorder).

[0057] For example, individuals with ASD often have fully automated motor planning and superior perceptual processing of details. Therefore, it is believed that characteristics appear in the handwriting feature information in accordance with these characteristics, resulting in a higher correlation. For example, individuals with ADHD tend to have difficulty sustaining attention. Therefore, it is believed that characteristics such as unstable writing pressure due to an inability to sustain attention appear in the handwriting feature information in accordance with these characteristics, resulting in a higher correlation. Therefore, by using handwriting feature information to determine the type of mental disorder (e.g., developmental disorder), it is possible to more accurately determine the type of mental disorder (e.g., developmental disorder). For the above reasons, ASD can be more accurately determined by using a feature related to the speed of movement (e.g., velocity). For example, ADHD can be more accurately determined by using a feature related to changes in writing pressure (e.g., SD writing pressure, PSMax, PSMin, etc.). In determining the type, the severity of each disease may also be determined. That is, instead of simply determining the type of disease as 1 or 0, a numerical value representing the degree (severity) of the subject's illness may be obtained for each type of mental illness.

[0058] FIG. 9 is a diagram showing a specific example of a unit figure of a figure (hereinafter referred to as a "written figure") written by a target person. The written figure may be constructed by repeatedly connecting a plurality of unit figures, each of which is made up of one specific figure, for example. The unit figure shown in FIG. 9 is a figure showing the shape of a mountain formed by two straight lines. FIG. 10 is a diagram showing a specific example of a written figure. The written figure shown in FIG. 10 is constructed by connecting a plurality of unit figures shown in FIG. 9. In the following description, the unit figure shown in FIG. 9 and the written figure shown in FIG. 10 are referred to as zigzag lines.

[0059] FIG. 11 is a diagram showing another specific example of a unit figure. The unit figure shown in FIG. 11 is composed of two types of specific figures. Specifically, the unit figure shown in FIG. 11 is composed of a combination of a platform-like figure composed of three straight lines and a mountain-shaped figure composed of two straight lines. FIG. 12 is a diagram showing another specific example of a written figure. The written figure shown in FIG. 12 is composed by connecting multiple unit figures shown in FIG. 11. In this way, the written figure may be composed by connecting multiple unit figures (e.g., the unit figure shown in FIG. 11) composed of multiple types (e.g., two types) of specific figures. The unit figure shown in FIG. 11 and the written figure shown in FIG. 12 are called PL (Periodic Line) lines.

[0060] The Zigzag line and the PL line are merely specific examples of the unit figure and the written figure, and figures of other shapes may be used as the unit figure and the written figure. For example, although the unit figures shown in Figures 9 and 11 are all composed of straight lines, the unit figure may be composed of curved lines in part or in whole. Furthermore, as in the written figure shown in Figure 12, the last unit figure may be composed of only a part of the unit figure (for example, a figure like a stand).

[0061] FIG. 13 is a diagram showing another specific example of a screen of an input device used in the input unit 12. In the example of FIG. 3 , the written figure itself is displayed as a model image (hereinafter referred to as a "model image") 81. However, as shown in FIG. 13 , a unit figure may be displayed as the model image 81. In the example of FIG. 3 , the target person looks at the written figure displayed as the model image 81 and writes the written figure within a frame 82. In the example of FIG. 13 , the target person looks at the unit figure displayed as the model image 81 and predicts a written figure in which the unit figure is repeated, and writes the written figure within the frame 82. Furthermore, in the example of FIG. 3 , the target person may write the written figure within the frame 82 along the written figure displayed as the model image 81. In the example of FIG. 13 , the target person may write the written figure within the frame 82 while predicting a written figure in which the unit figure is repeated, based on the unit figure displayed as the model image 81.

[0062] Fig. 14 is a diagram showing another specific example of a screen of an input device used in the input unit 12. In the example of Fig. 14, a model image 81 is displayed within a frame 82. In the example of Fig. 14, what is displayed as the model image 82 is the handwritten figure itself. In the example of Fig. 14, the target person writes the handwritten figure within the frame 82 along the lines of the model image 81.

[0063] Fig. 15 is a diagram showing another specific example of a screen of an input device used in the input unit 12. In the example of Fig. 15, a model image 81 is displayed within a frame 82. In the example of Fig. 15, what is displayed as the model image 81 is a unit figure. In the example of Fig. 15, the target person writes the first unit figure along the line of the unit figure displayed as the model image 81, and then predicts a written figure in which the unit figure is repeated and writes a written figure following the model image 81.

[0064] Fig. 16 is a diagram showing another specific example of a screen of an input device used in the input unit 12. In the example of Fig. 16, a plurality of handwritten images are displayed as a model image 81 within a frame 82. In the example of Fig. 16, the target person writes a plurality of handwritten figures along the lines of the handwritten figure displayed as the model image 81. The mode in which the handwritten figures are displayed as the model image 81 as in Fig. 16 is called a trace condition.

[0065] Fig. 17 is a diagram showing another specific example of a screen of an input device used in the input unit 12. In the example of Fig. 17, a plurality of unit images are displayed as a model image 81 within a frame 82. In the example of Fig. 17, the target person writes the first unit figure along the line of the unit figure displayed as the model image 81, and then predicts a written figure in which the unit figure is repeated and writes a written figure following the model image 81. The target person writes a plurality of written figures by repeating such writing multiple times. The manner in which the unit figures are displayed as the model image 81 as in Fig. 17 is called a predict condition.

[0066] Fig. 18 is a diagram showing another specific example of a screen of an input device used in the input unit 12. In the example of Fig. 18, the handwritten image in Fig. 16 is composed of a different image (an image composed of multiple types of specific figures). That is, while Zigzag lines are used in the example of Fig. 16, PL lines are used in the example of Fig. 18. The example of Fig. 18 is the same as the example of Fig. 16 except for the handwritten figures.

[0067] Fig. 19 is a diagram showing another specific example of a screen of an input device used in the input unit 12. In the example of Fig. 19, the handwritten image in Fig. 17 is composed of a different image (an image composed of multiple types of specific figures). That is, while Zigzag lines were used in the example of Fig. 17, PL lines are used in the example of Fig. 19. The example of Fig. 19 is the same as the example of Fig. 17 except for the handwritten figures.

[0068] Below, we show the results obtained when a clinical group (a group of individuals with developmental disorders) and a typically developing group (a group of individuals without developmental disorders) wrote handwritten figures. The person writing (hereinafter referred to as the "writer") performed either a Zigzag line task or a PL line task. In the Zigzag line task, participants wrote a Zigzag line in 30 seconds under the trace condition, followed by a 20-second break, and in the predict condition, they wrote a Zigzag line in 30 seconds, followed by a 20-second break, repeating this action three times. In the PL line task, participants wrote a PL line in 30 seconds under the trace condition, followed by a 20-second break, and in the predict condition, they wrote a PL line in 30 seconds, followed by a 20-second break, repeating this action three times.

[0069] The scribe wears a device for measuring brain activity. A specific example of such a device for measuring brain activity is a device that measures brain activity non-invasively from the scalp using near-infrared light. More specifically, brain activity may be measured using indicators associated with increases and decreases in hemoglobin or oxygen exchange information. Such measurement results are used as brain activity information. The brain activity information may be obtained as information on either or both of the frontal lobe and the parietal lobe, for example. More specifically, information on the prefrontal cortex (PFC) may be obtained. Even more specifically, information on the left PFC may be obtained.

[0070] Figure 20 shows the number of errors in the PL line task. An error was defined as an angle of 80 degrees or more in the valley portion. The vertical axis shows the average number of errors. In both the trace and predict conditions, the clinical group had a higher number of errors.

[0071] Figure 21 shows the fixation time after an error in the PL line task. Fixation time refers to the time it takes from when an error occurs until the next line is drawn. The vertical axis shows the average length of fixation time. In both the trace and predict conditions, fixation time was longer in the clinical group.

[0072] Figure 22 shows the z-scores of oxygenated hemoglobin values ​​for each brain region in the Zigzag line task. The horizontal axis indicates the brain region for each condition, and the vertical axis indicates the z-scores of oxygenated hemoglobin values. In the trace condition, the right PFC tended to have higher values ​​than the left PFC. In the trace and predict conditions, differences were observed in the central PFC between the clinical group and the typically developing group (non-clinical group). Specifically, the clinical group had higher z-scores of oxygenated hemoglobin values.

[0073] Figure 23 shows the z-scores of oxygenated hemoglobin values ​​for each brain region in the PL line task. The horizontal axis indicates the brain region for each condition, and the vertical axis indicates the z-scores of oxygenated hemoglobin values. Under the trace condition, the right PFC tended to have higher values ​​than the left PFC. In the clinical group, brain activity tended to be lower under the predict condition compared to the trace condition. In the typically developing group (non-clinical group), PFC activity tended to be higher under the predict condition compared to the trace condition.

[0074] Figure 24 shows the results of measuring PFC activity in the predict condition of the PL line task. The vertical axis represents blood flow in the prefrontal cortex. In the typically developing group, there was no significant difference in activity between the right, central, and left frontal lobes, but in the clinical group, the left PFC was significantly lower than the right PFC. The left PFC also tended to be lower than the central PFC.

[0075] FIG. 25 shows the change over time in left PFC activity during the predict condition of the PL line task. The vertical axis represents the blood flow rate of the left PFC (z-score of oxygenated hemoglobin). The horizontal axis represents the elapsed time (seconds) from the start of drawing the PL line, which is set to 0. As shown, the clinical group showed a smaller increase in left PFC activity than the typically developing group. Furthermore, while the typically developing group showed an increase in left PFC activity immediately after the start of the task, the clinical group showed almost no increase in left PFC activity until 15 seconds had elapsed. Note that instead of the oxygenated hemoglobin described above, other values ​​related to hemoglobin may be used. For example, deoxygenated hemoglobin may be used, or the sum of the values ​​related to oxygenated hemoglobin and deoxygenated hemoglobin may be used.

[0076] It is also possible to identify a target person based on the differences between the clinical group and the typically developing group as shown in Figures 21 to 25. In this embodiment, it is also possible to identify a target person by writing a cursive figure instead of a character. Therefore, even if the target person is, for example, a person who cannot understand or write characters (e.g., a preschool child or an infant), it is possible to appropriately identify the target person.

[0077] FIG. 26 is a diagram illustrating an outline of an example hardware configuration of an information processing device 90 applied to this embodiment. The information processing device 90 includes a processor 91, a main storage device 92, a communication interface 93, an auxiliary storage device 94, an input / output interface 95, and an internal bus 96. The processor 91, the main storage device 92, the communication interface 93, the auxiliary storage device 94, and the input / output interface 95 are communicably connected to each other via the internal bus 96. The information processing device 90 may be applied to, for example, the learning device 20 and the judgment support device 30. In this case, for example, the communication units 21 and 31 may be configured using the communication interface 93. For example, the memory units 22 and 32 may be configured using the auxiliary storage device 94. Furthermore, the control units 23 and 33 may be configured using the processor 91 and the main storage device 92.

[0078] (Modification) In the present embodiment, the terminal device 10 and the judgment support device 30 are configured as separate devices, but they may also be configured as an integrated device. Fig. 27 is a diagram showing a modification of the judgment support device 30 configured in this manner. The judgment support device 30 shown in Fig. 27 includes an input unit 34 and an output unit 35. The input unit 34 and the output unit 35 of the judgment support device 30 shown in Fig. 27 function in the same manner as the input unit 12 and the output unit 13 of the terminal device 10, respectively. The control unit 33 operates in response to an operation on the input unit 34, performs a judgment process using the input handwritten information, and outputs the information using the output unit 35.

[0079] In this embodiment, the learning device 20 and the judgment support device 30 are configured as separate devices, but they may also be configured as an integrated device. FIG. 28 is a diagram showing a modified example of the judgment support device 30 configured in this manner. The storage unit 32 of the judgment support device 30 shown in FIG. 28 also functions as a teacher data storage unit 322 and a preprocessed teacher data storage unit 323. The control unit 33 of the judgment support device 30 shown in FIG. 28 also functions as a preprocessing control unit 332 and a learning control unit 334. The teacher data storage unit 322 and the preprocessed teacher data storage unit 323 function similarly to the teacher data storage unit 221 and the preprocessed teacher data storage unit 222 of the learning device 20, respectively. The preprocessing control unit 332 performs preprocessing not only for the judgment support device 30 (preprocessing for the handwritten information of the target person) but also for the learning device 20 (preprocessing for the handwritten information of the teacher data). The learning control unit 334 functions similarly to the learning control unit 233 of the learning device 20.

[0080] The learning device 20 may be implemented using a plurality of information processing devices. For example, the learning device 20 may be implemented using a device such as a cloud. For example, in the learning device 20, the memory unit 22 and the control unit 23 may be implemented in different information processing devices. For example, the memory unit 22 of the learning device 20 may be distributed and implemented across a plurality of information processing devices. The judgment support device 30 may be implemented using a plurality of information processing devices. For example, the judgment support device 30 may be implemented using a device such as a cloud. For example, in the judgment support device 30, the memory unit 32 and the control unit 33 may be implemented in different information processing devices. For example, the memory unit 32 of the judgment support device 30 may be distributed and implemented across a plurality of information processing devices.

[0081] FIG. 29 is a diagram showing a modified example of the judgment support system 100. As shown in FIG. 29, a brain function measuring device 19 may be further used in the judgment support system 100. The brain function measuring device 19 measures information about the brain function of the target person and transmits the information about the brain function to the judgment support device 30. The information about brain function may be, for example, information about blood flow in the head of the target person. In this case, the information about brain function may be used as input in generating a trained model. A specific example of the information about brain function is, for example, information indicating the activity of a part of the brain. Specific examples of parts of the brain include the frontal lobe, parietal lobe, and basal ganglia. Other parts may also be used as parts of the brain. The information about brain function may be, for example, information about oxygen content.

[0082] Although an embodiment of the present invention has been described above in detail with reference to the drawings, the specific configuration is not limited to this embodiment, and includes designs within the scope of the gist of the present invention.

[0083] The present invention can be applied to a system for determining the type of mental illness.

[0084] REFERENCE SIGNS LIST 100... Judgment support system, 10... Terminal device, 11... Communication unit, 12... Input unit, 13... Output unit, 14... Memory unit, 15... Control unit, 20... Learning device, 21... Communication unit, 22... Memory unit, 221... Teacher data memory unit, 222... Preprocessed teacher data memory unit, 223... Trained model memory unit, 23... Control unit, 231... Information control unit, 232... Preprocessing control unit, 233... Learning control unit, 30... Judgment support device, 31... Communication unit, 32... Memory unit, 321... Trained model memory unit, 33... Control unit, 331... Information control unit, 332... Preprocessing control unit, 333... Judgment unit

Claims

1. A storage device that stores a trained model obtained by performing a learning process using a plurality of pieces of handwriting information indicating information about handwriting when each subject wrote using a pen-like object and correct answer information indicating the type of mental illness of the subject; and a determination unit that acquires handwriting information indicating information related to handwriting when a subject writes using a pen-like object, and determines a type of mental illness of the subject using the handwriting information and the trained model; an output unit that outputs the determination result of the determination unit, the handwriting information is information about handwriting when each of the subjects writes a figure using a pen-like object, the figure is a handwritten figure formed by repeatedly connecting a plurality of predetermined unit figures, The judgment support system is configured such that the writing is performed while predicting the written figure based on the unit figure that is previously shown.

2. (delete)

3. The judgment support system according to claim 1 , wherein the writing is performed along the written figure that is previously indicated.

4. (delete)

5. The judgment support system according to claim 1 , wherein the correct answer information includes information indicating whether the person is an ADHD patient or not, and information indicating whether the person is an ASD patient or not.

6. the learning process is performed further using brain activity information indicating brain activity of the subject while the subject is using the pen-like object; The judgment support system of claim 1, wherein the judgment unit further acquires brain activity information indicating the brain activity of the subject while the subject is writing with the pen-like object, and uses the writing information, the brain activity information, and the trained model to estimate whether the subject is a healthy person or a mental illness patient.

7. The judgment support system according to claim 6 , wherein the brain activity information is information indicating brain activity of the frontal lobe and parietal lobe of the subject and the object, respectively.

8. The judgment support system according to claim 7 , wherein the brain activity information is information indicating an oxygen amount.

9. The judgment support system according to claim 1 , wherein the handwriting information includes at least one of a time period during which the writing was made, a pressure applied to the writing, and an inclination of the pen-like object when the writing was made.

10. A judgment support device including a storage device that stores a trained model obtained by performing a learning process using a plurality of pieces of handwriting information indicating information about handwriting when each subject writes using a pen-like object and correct answer information indicating the type of mental illness of the subject, a determination step of acquiring handwriting information indicating information about handwriting when a subject writes using a pen-like object, and determining a type of mental illness of the subject using the handwriting information and the trained model; an output step of outputting a determination result in the determination step, the handwriting information is information about handwriting when each of the subjects writes a figure using a pen-like object, the figure is a handwritten figure formed by repeatedly connecting a plurality of predetermined unit figures, The method for assisting judgment is such that the writing is performed while predicting the written figure based on the unit figure shown in advance.

11. A storage device that stores a trained model obtained by performing a learning process using a plurality of pieces of handwriting information indicating information about handwriting when each subject wrote using a pen-like object and correct answer information indicating the type of mental illness of the subject; and a determination unit that acquires handwriting information indicating information related to handwriting when a subject writes using a pen-like object, and determines a type of mental illness of the subject using the handwriting information and the trained model; an output unit that outputs the determination result of the determination unit, the handwriting information is information about handwriting when each of the subjects writes a figure using a pen-like object, the figure is a handwritten figure formed by repeatedly connecting a plurality of predetermined unit figures, A computer program for causing a computer to function as a judgment support system in which the writing is performed while predicting the written figure based on the unit figure that is previously shown.