Information processing apparatus, information processing method, program, and storage medium

Abstract

According to the present invention, the probability that a patient's mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD) symptoms will advance is predicted by inputting patient information corresponding to at least three variables based on information selected from among first information regarding orientation, second information regarding memory, third information regarding either memory of holidays, family gatherings, appointments, or medicine taking schedule in IADL, or the actual activities of dining, shopping or movement in IADL, and fourth information regarding biomarker positivity or negativity into a prediction model (132) trained using training data in which the at least three variables are associated with the presence or absence of advancement of symptoms of MCI or mild AD. Attribute information of the patient information includes at least one among a first feature quantity obtained by adding together fellow items of information with which an evaluation value representing the degree of MCI or mild AD symptoms shows a positive correlation, and a second feature quantity obtained by dividing fellow items of information with which the size of the evaluation value representing the degree of the symptoms shows a negative correlation.

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, an information processing method, a program, and a storage medium.

Background Art

[0002] Conventionally, various techniques for predicting the degree of dementia symptoms have been proposed. For example, Patent Document 1 discloses that by analyzing free conversations made by a patient, it is possible to predict the severity of dementia without performing a Mini Mental State Examination (MMSE) used for dementia screening tests and severity evaluations.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] By the way, in recent years, in order to enhance the treatment effect for dementia patients, in addition to predicting dementia diseases, it has been required to predict diseases for patients with mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD) who are at risk of dementia. However, patients with mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD) sometimes have milder symptoms compared to dementia patients, and it has been difficult to accurately predict their diseases.

[0005] The present invention has been made in view of such circumstances, and an object thereof is to provide an information processing apparatus, an information processing method, a program, and a storage medium that can accurately predict the probability of progression of symptoms of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD).

Means for Solving the Problems

[0006] The present disclosure is based on at least three variables selected from information including first information related to estimation knowledge, second information related to memory, third information related to memory of holidays, family gatherings, reservations, or medication schedules in IADL, or actual tasks of meals, shopping, or movement in IADL, and fourth information related to the positivity or negativity of biomarkers, and the presence or absence of symptom progression of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD). For a prediction model trained using learning data in which the above are associated, information of a patient corresponding to each of the three variables is input to predict the probability that the patient's symptoms of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD) will progress. The at least three variables include at least one of information related to estimation knowledge related to time among the first information and information related to memory of holidays, family gatherings, reservations, or medication schedules in IADL among the third information, information related to delayed recall among the second information, and information related to the positivity or negativity of amyloid-beta (Aβ) among the fourth information. For at least four pieces of information selected from the first information, second information, third information, and fourth information, a first feature amount obtained by integrating information showing a positive correlation between the magnitudes of evaluation values indicating the degree of symptoms of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD), and at least one of a second feature amount obtained by dividing information showing a negative correlation between the magnitudes of evaluation values indicating the degree of symptoms of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD) are included. An information processing apparatus is provided.

[0007] The at least three variables may include at least one of the first feature amount and the second feature amount for at least four pieces of information including information related to memory of holidays, family gatherings, reservations, or medication schedules in IADL among the third information, information related to delayed recall among the second information, and information related to the positivity or negativity of Aβ among the fourth information.

[0008] At least three variables may include at least one of the first feature amount and the second feature amount for at least four pieces of information including information regarding an estimate of time among the first information, information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL among the third information, information regarding delayed playback among the second information, and information regarding the positive or negative of Aβ among the fourth information.

[0009] At least three variables may include at least one of the first feature amount and the second feature amount for four or five pieces of information.

[0010] At least three variables may include at least one of the first feature amount and the second feature amount for four pieces of information including information regarding an estimate of time among the first information, information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL among the third information, information regarding delayed playback among the second information, and information regarding the positive or negative of Aβ among the fourth information.

[0011] At least three variables may include at least one of the first feature amount and the second feature amount for five pieces of information including information regarding an estimate of time among the first information, information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL among the third information, information regarding delayed playback among the second information, information regarding the positive or negative of Aβ among the fourth information, and fifth information selected from the first information, the second information, the third information, and the fourth information.

[0012] At least three variables may include at least one of the first feature amount and the second feature amount for at least four pieces of information selected from the first information, the second information, the third information, and the fourth information, including at least one of the information regarding an estimate of time among the first information and the information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL among the third information, information regarding delayed playback among the second information, and information regarding the positive or negative of Aβ among the fourth information.

[0013] The present disclosure relates to a method for providing information, which includes: a step of obtaining patient information; at least three variables based on information selected from first information regarding estimation knowledge, second information regarding memory, third information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL, or actual operations of meals, shopping, or movement in IADL, and fourth information regarding the positivity or negativity of biomarkers; a step of inputting patient information corresponding to each of the three variables into a prediction model learned using learning data in which the presence or absence of symptom progression of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD) is associated therewith, to predict the probability that the patient's symptoms of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD) will progress; and a step of outputting a prediction result regarding the probability that the patient's symptoms of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD) will progress. The at least three variables include at least one of information regarding estimation knowledge related to time among the first information and information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL among the third information, information regarding delayed reproduction among the second information, and information regarding the positivity or negativity of Aβ among the fourth information. Regarding at least four pieces of information selected from the first information, second information, third information, and fourth information, a first feature amount obtained by integrating information showing a positive correlation in the magnitude of an evaluation value indicating the degree of symptoms of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD), and at least one of a second feature amount obtained by dividing information showing a negative correlation in the magnitude of an evaluation value indicating the degree of symptoms of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD).

[0014] The present disclosure is based on a prediction model learned using learning data in which a computer associates at least three variables selected from the process of acquiring patient information, first information regarding orientation, second information regarding memory, third information regarding the memory of holidays, family gatherings, reservations, or medication schedules in IADL, or the actual tasks of eating, shopping, or moving in IADL, and fourth information regarding the positivity or negativity of biomarkers, with the presence or absence of symptom progression of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD). For the prediction model, patient information corresponding to each of the three variables is input, and a process of predicting the probability that the patient's symptoms of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD) will progress, and a process of outputting a prediction result regarding the probability that the patient's symptoms of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD) will progress are executed. The at least three variables include at least one of the information regarding orientation in time among the first information and the information regarding the memory of holidays, family gatherings, reservations, or medication schedules in IADL among the third information, the information regarding delayed recall among the second information, and the information regarding the positivity or negativity of Aβ among the fourth information. Regarding at least four pieces of information selected from the first information, second information, third information, and fourth information, a first feature amount obtained by integrating information showing a positive correlation among information showing the degree of symptoms of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD), and at least one of a second feature amount obtained by dividing information showing a negative correlation among information showing the magnitude of the evaluation value indicating the degree of symptoms of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD) are included. A program is provided.

[0015] The present disclosure provides a computer-readable non-transitory storage medium storing the program having the above configuration.

Advantages of the Invention

[0016] According to the present invention, the probability of progression of symptoms of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD) can be accurately predicted.

Brief Description of the Drawings

[0017]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Figure 18

Figure 19

Figure 20

Figure 21

Figure 22

Figure 23

Figure 24

Figure 25

Figure 26

Figure 27

Figure 28

Figure 29

Figure 30

Figure 31

Figure 32

MODE FOR CARRYING OUT THE INVENTION

[0018] Hereinafter, an embodiment of an information processing apparatus will be described with reference to the drawings. Note that the present disclosure is not limited to the embodiments described below.

[0019] As shown in FIG. 1, the information processing apparatus 100 is connected to a terminal device 10 via a communication network NW, for example. The communication network NW is constituted by, for example, a communication device, a wireless communication network, or the like.

[0020] The terminal device 10 is a device for a doctor to input patient information, and is constituted by, for example, a computer terminal device or a portable information terminal device.

[0021] The information processing apparatus 100 includes, for example, a communication unit 110, a control unit 120, and a storage unit 130. The control unit 120 is realized, for example, by a hardware processor such as a CPU (Central Processing Unit) executing a program (software). Also, some or all of these components may be realized by hardware (including circuitry) such as LSI (Large Scale Integration), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array), GPU (Graphics Processing Unit), or may be realized by cooperation of software and hardware. The program may be stored in advance in the storage unit 130 of the information processing apparatus 100, or may be stored in a removable computer-readable recording medium such as a DVD or a CD-ROM, and installed in the storage unit 130 of the information processing apparatus 100 by mounting the computer-readable recording medium on a drive device.

[0022] The communication device 110 includes a communication interface such as a NIC (Network Interface Card). The communication device 110 communicates with the terminal device 10 using, for example, a cellular network or a Wi-Fi (registered trademark) network.

[0023] The control unit 120 includes, for example, an acquisition unit 121, a prediction unit 122, and an output unit 123.

[0024] The acquisition unit 121 acquires patient information transmitted from the terminal device 10 through the communication network NW. Here, the patient information is information used when predicting the probability that a patient will develop symptoms of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD). Details of the patient information will be described later.

[0025] The prediction unit 122 inputs the patient information acquired by the acquisition unit 121 into the prediction model 132 and predicts the probability that a patient will develop symptoms of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD).

[0026] The output unit 123 outputs information regarding the probability that a patient will develop symptoms of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD), predicted by the prediction unit 122, to the terminal device 10 through the communication device 110. The output unit 123 may output, for example, in response to a request from the patient, information regarding the probability that a patient will develop symptoms of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD), predicted by the prediction unit 122, to a terminal device possessed by a medical professional such as a doctor or the patient.

[0027] FIG. 2 is a diagram showing an example of the learning phase of the prediction model 132.

[0028] In the example shown in FIG. 2, for each of a plurality of subjects, among the cohort data (ADNI) described later, the attribute information of the subject is used as the first data group, and the diagnostic information regarding mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD) of the subject is used as the second data group, and the prediction model 132 is learned using the data extracted by being associated therewith. In the present embodiment, as will be described later, as an example of the attribute information of the subject, information regarding orientation is used as the first information, information regarding memory is used as the second information, information regarding the memory of holidays, family gatherings, reservations, or medication schedules in IADL, or information regarding the actual operations of meals, shopping, or movement in IADL is used as the third information, and information regarding the positive or negative of biomarkers is used as the fourth information. When at least one of the information regarding the orientation regarding time among the first information and the information regarding the memory of holidays, family gatherings, reservations, or medication schedules in IADL among the third information, the information regarding delayed recall among the second information, and the information regarding the positive or negative of Aβ among the fourth information, for at least four pieces of information selected from the first information, the second information, the third information, and the fourth information, the first feature amount obtained by integrating information showing a positive correlation in the magnitudes of the evaluation values indicating the degree of symptoms of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD), and preferably includes at least one of the second feature amounts obtained by dividing information showing a negative correlation in the magnitudes of the evaluation values indicating the degree of symptoms of AD).

[0029] FIG. 3 is a diagram showing an example of the evaluation phase of the prediction model 132.

[0030] In the example shown in FIG. 3, the evaluation of the prediction model 132 learned as described above is being performed using the evaluation data 131. In the present embodiment, the evaluation data 131 uses three databases, namely, ADNI (Alzheimer’s Disease Neuroimaging Initiative), J-ADNI (Japanese Alzheimer’s Disease Neuroimaging Initiative), and MissionAD (clinical phase III trial data of elenbecestat), and the evaluation of the prediction model 132 is performed individually for each database. ADNI is a database based on cohort data collected from multiple clinical periods to conduct clinical trials of dementia disease-modifying drugs in the United States. J-ADNI is a database based on cohort data collected from multiple clinical periods to conduct clinical trials of dementia disease-modifying drugs in Japan. MissionAD is a database based on trial data independently collected by the applicant to conduct clinical trials of dementia disease-modifying drugs. Since the set of subjects is different for each database, the evaluation of the prediction model 132 using each of these databases is meaningful in determining the range of patients to which the prediction model 132 is applicable.

[0031] FIG. 4 is a diagram for explaining an example of an evaluation index of the prediction model 132.

[0032] In the example shown in FIG. 4, examples of evaluation metrics of the prediction model 132 include accuracy, sensitivity, specificity, and AUC (Area Under the ROC Curve). Accuracy is an index indicating the overall correct answer rate regardless of positive or negative. Sensitivity is an index indicating the ratio (true positive rate) of correctly predicting positive data as positive. Specificity is an index indicating the ratio (true negative rate) of correctly predicting negative data as negative. AUC is an index calculated taking into account both sensitivity and specificity. Generally, in evaluating the prediction model 132 as a whole, evaluation based on AUC is preferred. In one embodiment, in addition to AUC, a mode of adding sensitivity is included. In another embodiment, a mode of adding sensitivity and specificity is included. In yet another embodiment, a mode of adding accuracy, sensitivity, and specificity is included. For each index, 0.7, 0.67, or 0.6 or more can be mentioned as the criterion for judging the conformity / non - conformity of the prediction result.

[0033] In the example shown in FIG. 5, for the prediction model 132 learned as described above, patient information acquired from the terminal device 10 is input, and the probability that the patient's symptoms of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD) will progress is predicted. In the present embodiment, as will be described later, as an example of the attribute information of the patient information, it is preferable to include at least one of the above - described first feature amount and second feature amount.

[0034] As shown in FIG. 6, the information processing device 100 first acquires patient data from the terminal device 10 (step S10).

[0035] Next, the information processing device 100 extracts information for diagnosis prediction from the patient data acquired in the previous step S10 (step S20).

[0036] Next, the information processing apparatus 100 inputs the information used for the diagnosis prediction extracted in the previous step S20 into the prediction model 132, and predicts the probability that the patient's symptoms of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD) will progress (step S30).

[0037] Next, the information processing apparatus 100 outputs the prediction result regarding the probability that the patient's symptoms of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD) will progress in the previous step S30 to the terminal device 10 (step S40), and ends the flowchart shown in FIG. 6.

[0038] In this embodiment, the patient information is, for example, information obtained by a doctor conducting an interview with the patient. Examples of interview methods include, for example, MMSE (Mini-Mental State Examination), FAQ (Functional activities questionnaire), and ADAS (Alzheimer’s Disease Assessment Scale) (refer to the Dementia Disease Treatment Guidelines 2017 (https: / / www.neurology-jp.org / guidelinem / nintisyo_2017.html), Japanese Journal of Geriatrics 2011;48:431-438 (https: / / jpn-geriat-soc.or.jp / publications / other / pdf / review_geriatrics_48_5_431.pdf)).

[0039] FIG. 7 is a graph showing an example of the time change in the degree of progression of symptoms of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD) predicted by the prediction model 132. In the example shown in this figure, the prediction of the onset of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD) (prediction of symptom progression) at a future time point is performed over time using the prediction model 132. In this case, based on the time-series data of the cohort data (ADNI) from the past to the current time point, for example, prediction models 132 for predicting the onset of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD) at each future time point such as six months later, one year later, two years later, five years later, ten years later, etc. are generated respectively. Then, by inputting the cohort data (ADNI) at the current time point to these multiple prediction models 132, it becomes possible to continuously plot the degree of progression of the symptoms of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD). And by referring to the graph shown in this example, it is also possible to compare and predict the time change in the degree of progression of symptoms and the effect of medication treatment between the cases where patients with mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD) receive medication treatment and those who do not.

[0040] As shown in FIG. 8, the MMSE is a type of neuropsychological test performed when dementia is suspected. The MMSE diagnoses dementia by scoring each of a plurality of diagnostic items and summing up those scores, and the lower the sum of the scores, the more the symptoms are progressing. The diagnostic items of the MMSE include, for example, orientation to time, orientation to place, repetition of object names, attention, recall of object names (delayed recall), naming of object names, repetition of sentences, three-step oral commands, reading comprehension, writing, and figure copying.

[0041] As shown in Fig. 9, the FAQ is a method for objectively evaluating the life management ability of dementia patients. The FAQ diagnoses dementia by scoring each of a plurality of diagnostic items and summing up those scores. The higher the sum of the scores, the lower the life management ability. The plurality of diagnostic items are, for example, for evaluating diet, memory, household management, organization, shopping, games, preparation of drinks, grasp of recent events, grasp of content from TV, and ability related to movement. <Question Items> · Remembering reservations, family gatherings, holidays, and taking medications (in this specification, memory evaluated by the FAQ, or simply called FAQ memory) · Preparing a balanced diet (in this specification, diet evaluated by the FAQ, or simply called FAQ diet) · Going out to a distant place, driving a car, taking a bus: Movement (in this specification, movement evaluated by the FAQ, or simply called FAQ movement) · Shopping alone: Shopping (in this specification, shopping evaluated by the FAQ, or simply called FAQ shopping) · Household management such as bank transfers · Organizing tax records, etc. · Games that require skills · Preparation of drinks · Grasp of recent events · Paying attention to and understanding the content of TV, etc. <Score> 0: Can be done without difficulty 1: With difficulty but can be done independently 2: Assistance required 3: Full assistance

[0042] As shown in FIG. 10, ADAS is a test that is continuously performed multiple times and evaluates changes in cognitive functions based on score changes. ADAS scores each of a plurality of diagnostic items, and the higher the scores, the more the symptoms are progressing. The plurality of diagnostic items are for evaluating the ability to reproduce words, oral language ability, auditory comprehension of language, anomia in spontaneous speech, comprehension of oral commands, naming of fingers and objects, constructive behavior, ideomotor, orientation, word recognition, and the ability to reproduce test instructions.

[0043] As shown in FIG. 11, in the present embodiment, the patient information includes, for example, information related to orientation, information related to memory, information related to IADL (Instrumental Activities of Daily Living) (see (https: / / www.mhlw.go.jp / www1 / topics / kenko21_11 / s1.html)), and information related to the positivity or negativity of amyloid β.

[0044] FIG. 12 is a diagram for explaining an example of the attribute information of the data used for evaluating the prediction model 132, and shows the branching from the upper concept to the lower concept from the left to the right of the page. As shown in FIG. 11, the information related to orientation is information related to the ability to comprehensively judge the date, current time, location, surrounding situation, understanding of people, etc., and understand the situation where oneself is currently located, and includes, for example, information related to time orientation, information related to location orientation, and information related to person orientation. The information related to time orientation is, for example, information indicating the score obtained from the patient for the items related to time orientation in MMSE or ADAS. The information related to location orientation is, for example, information indicating the score obtained from the patient for the items related to location orientation in MMSE.

[0045] Information regarding memory refers to information related to a patient's ability to retain short-term or long-term memory, and includes, for example, information regarding delayed recall and information regarding long-term memory related to language. Information regarding delayed recall refers to information related to the ability to recall something learned after a certain period of time. Information regarding delayed recall is, for example, information indicating the score obtained from the patient for items related to delayed recall in MMSE or ADAS. Information regarding delayed recall includes question items for repeating the names of objects. Information regarding long-term memory related to language refers to information related to the ability to remember things related to language over a long period of time, and includes, for example, information related to the ability of the subject to repeat the same words when the examiner conveys three words at one-second intervals (recall of the names of objects), information related to the ability to say the correct name of what has been seen while looking at an object prepared by the examiner (naming of objects), and information related to the ability to accurately remember the content conveyed by the examiner (delayed recall). Information regarding long-term memory related to language is, for example, information indicating the score obtained from the patient for items such as naming of objects in MMSE.

[0046] Information regarding IADL refers to information about daily life activities that involve judgment ability. For example, it is information for numerically evaluating abilities related to telephone use, meal preparation, laundry, medication management, shopping, housework, transportation, and property management. Generally, after a decline in the evaluation value regarding IADL is observed, a decline in the evaluation value regarding ADL (Activities of Daily Living, which are indicators of dementia such as eating, dressing, excretion, and bathing) is seen. Therefore, information regarding IADL is meaningful information for early detection of dementia symptoms. Information regarding IADL is classified based on whether it is an activity of daily life involving multiple elements, a relatively simple activity of daily life, or an activity that varies according to regional culture, personal preferences, or circumstances. Activities of daily life involving multiple elements are activities far from ADL. For example, they are classified into activities related to the ability to remember schedules in IADL, such as activities related to holidays, family gatherings, reservations, and medication management, and execution-related tasks in IADL, such as meal preparation, movement, and shopping. Information regarding the ability to remember schedules in IADL is information indicating the scores obtained from patients regarding items such as holidays, family gatherings, reservations, and medication management in, for example, an FAQ. Information regarding execution-related tasks in IADL is information indicating the scores obtained from patients regarding items such as meal preparation and movement in, for example, an FAQ. Relatively simple activities of daily life are activities close to ADL and are related to the ability regarding telephone use, housework, laundry, and housework. Information regarding relatively simple activities of daily life in IADL is information indicating the scores obtained from patients regarding, for example, telephone use, housework, laundry, etc. Also, activities that vary according to regional culture, personal preferences, or circumstances correspond to abilities related to, for example, property management and games that require skills. Information regarding activities that vary according to regional culture, personal preferences, or circumstances in IADL is information indicating the scores obtained from patients regarding, for example, property management and games that require skills through neuropsychological tests (including an FAQ, etc.).

[0047] A biomarker refers to an item or substance in the body that serves as an indicator of the presence or absence of a certain disease, changes in the disease state, or the effectiveness of treatment. What is used as a biomarker mainly consists of biological data such as blood pressure, heart rate, electrocardiogram, and substances such as proteins measured in the blood. Information regarding the positive or negative of a biomarker may be information regarding evaluation and determination obtained from amyloid-β, as well as information regarding evaluation and determination obtained from Tau, p-Tau, ApoE4, etc. Tau is a protein that accumulates in the brain in various neurodegenerative diseases including Alzheimer's disease, leading to nerve cell death and causing dementia. p-Tau means phosphorylated tau protein, which is an abnormal structure that appears in the brains of Alzheimer's disease patients, and the accumulation amount thereof correlates with the severity of dementia. ApoE4 is the ε4 (ApoE-ε4) of the apolipoprotein E (ApoE) gene subtype, and has been attracting attention as a genetic factor highly associated with AD. Information regarding the positive or negative of a biomarker is information indicating whether a biomarker, which is a factor highly correlated with the onset of dementia, has accumulated in a predetermined amount in the patient's brain, and is, for example, information obtained through imaging diagnosis or blood diagnosis (including CSF examination, etc.). When the biomarker is positive, it suggests that the disease state of dementia is progressing compared to the case where the biomarker is negative.

[0048] Next, the operation of the information processing apparatus 100 of the present embodiment will be described with reference to FIG. 13 based on the evaluation index of the prediction model 132. In the example shown in FIG. 13, a prediction model 132 having five pieces of information including information regarding orientation in time evaluated by MMSE, information regarding delayed recall evaluated by MMSE, information regarding memory of object naming evaluated by MMSE, information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ, and information regarding Aβ positive or negative as variables is cited as a comparative example.

[0049] Also, in this example, two prediction models 132 including, as variables, the above-described first feature amount and second feature amount are exemplified based on five pieces of information composed of information regarding time estimation evaluated by MMSE, information regarding delayed recall evaluated by MMSE, information regarding memory of object naming evaluated by MMSE, information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ, and information regarding Aβ positive / negative.

[0050] When generating a feature amount using the information regarding delayed recall evaluated by MMSE and the information regarding language memory evaluated by MMSE, since there is a positive correlation between the magnitudes of the evaluation values indicating the degree of symptoms of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD), a first feature amount obtained by integrating the information regarding delayed recall evaluated by MMSE and the information regarding language memory evaluated by MMSE is used as a variable.

[0051] Also, MMSE means that the more advanced the symptoms are, the lower the total score is, and FAQ means that the lower the life management ability is, the higher the total score is. That is, MMSE and FAQ show a negative correlation between the magnitudes of the evaluation values indicating the degree of symptoms of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD). Therefore, when generating a feature amount using the information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ and the information regarding time estimation evaluated by MMSE, as in the prediction model 132 of the above-described example, for example, a second feature amount obtained by dividing the information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ by the information regarding time estimation evaluated by MMSE is used as a variable.

[0052] As an example of the evaluation metrics for the prediction model 132, accuracy, sensitivity, specificity, and AUC (Area Under the ROC Curve) are listed. For these four evaluation metrics, the evaluation values using the evaluation data of ADNI, J-ADNI, and MissionAD have been calculated. In the example shown in FIG. 12, since the prediction model 132 of the example is improved in all four evaluation metrics compared to the prediction model 132 of the comparative example, it can be said that the performance is excellent.

[0053] Next, an example of the prediction model 132 of the present embodiment will be described with reference to the drawings. As described above, as an example of the evaluation metrics for the prediction model 132, accuracy, sensitivity, specificity, and AUC (Area Under the ROC Curve) are listed. The usage method of the evaluation metrics for the prediction model 132 is not particularly limited. However, in the following, in the present embodiment, as an example, in the evaluation of the prediction model 132 using ADNI, J-ADNI, and MissionAD, the prediction model 132 that satisfies the conditions of "sensitivity ≥ 0.7", "specificity ≥ 0.6", and "AUC ≥ 0.7" is taken as an example. Here, the examples of the present disclosure described below are one aspect and are not limited to the examples described below.

[0054] (Implementation Conditions) For the construction and evaluation of the prediction model, first, among the ADNI data that associates various information with the presence or absence of symptom progression, 80% of the data is used as learning data to construct a model for predicting the presence or absence of symptom progression. Further, the remaining 20% of the ADNI data, J-ADNI, and MissionAD data are used as evaluation data, and the presence or absence of symptom progression based on the prediction model is compared with the actual presence or absence of symptom progression to calculate various evaluation metrics.

[0055] (Example) The data used for evaluating the prediction model 132 of the embodiment is data among the learning data that was not used for constructing the prediction model 132, and includes at least three variables based on information selected from the first information regarding rough estimates, the second information regarding memory, the third information regarding the memory of holidays, family gatherings, reservations, or medication schedules in IADL, or the actual tasks of meals, shopping, or movement in IADL, and the fourth information regarding the positive or negative of biomarkers. The at least three variables include at least one of the information regarding rough estimates of time among the first information and the information regarding the memory of holidays, family gatherings, reservations, or medication schedules in IADL among the third information, the information regarding delayed reproduction among the second information, and the information regarding the positive or negative of amyloid-β among the fourth information. For at least four pieces of information selected from the first information, the second information, the third information, and the fourth information, a first feature amount obtained by integrating information showing a positive correlation among evaluation values indicating the degree of symptoms of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD), and at least one of a second feature amount obtained by dividing information showing a negative correlation among evaluation values indicating the degree of symptoms of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD). The at least three variables may calculate the first feature amount and the second feature amount by integrating or dividing a plurality of information for at least four pieces of information other than the first information, the second information, the third information, and the fourth information.

[0056] FIG. 14 and FIG. 15 are diagrams showing an example of data used for evaluating the prediction model 132 of the embodiment. FIG. 14 shows an example of evaluation values using the evaluation data of ADNI, J-ADNI, and MissionAD for the accuracy rate and sensitivity, which are examples of evaluation indicators of the prediction model 132. FIG. 15 shows an example of evaluation values using the evaluation data of ADNI, J-ADNI, and MissionAD for the specificity and AUC, which are examples of evaluation indicators of the prediction model 132. In the examples shown in FIGS. 14 and 15, in the data used for evaluating the prediction model 132, for example, at least three variables include a first variable that is information obtained by squaring information regarding time estimation in the first information, a second variable that includes, as a first feature amount, a feature amount obtained by integrating information regarding time estimation in the first information and information regarding delayed reproduction in the second information, and a third variable that includes, as a first feature amount, a feature amount obtained by integrating information regarding holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ in the third information and information regarding the positive or negative of amyloid β in the fourth information. Further, at least three variables include, for example, a first variable that is information obtained by squaring information regarding time estimation in the first information, a second variable that includes, as a first feature amount, a feature amount obtained by integrating information regarding delayed reproduction in the second information and information regarding the name of an item in the second information, and a third variable that includes, as a first feature amount, a feature amount obtained by integrating information regarding holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ in the third information and information regarding the positive or negative of amyloid β in the fourth information. Further, at least three variables include, for example, a first variable that is information obtained by squaring information regarding time estimation in the first information, a second variable that includes, as a first feature amount, a feature amount obtained by integrating information regarding holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ in the third information and information regarding the positive or negative of amyloid β in the fourth information, and a third variable that includes, as a second feature amount, a feature amount obtained by dividing the information regarding delayed reproduction in the second information by the information regarding the positive or negative of amyloid β in the fourth information.Further, at least three variables are constituted by, for example, a first variable which is information obtained by squaring information regarding delayed playback among the second information, a second variable which is information obtained by squaring information regarding the positive or negative of amyloid β among the fourth information, and a third variable which includes, as a first feature amount, a feature amount obtained by integrating information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information and information regarding shopping in IADL evaluated by FAQ among the third information. Further, at least three variables are constituted by, for example, a first variable which is information obtained by squaring information regarding delayed playback among the second information, a second variable which includes, as a second feature amount, a feature amount obtained by dividing information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information by information regarding estimation of time among the first information, and a third variable which includes, as a first feature amount, a feature amount obtained by integrating information regarding meals in IADL evaluated by FAQ among the third information and information regarding the positive or negative of amyloid β among the fourth information. Further, at least three variables are constituted by, for example, a first variable which is information obtained by squaring information regarding delayed playback among the second information, a second variable which includes, as a second feature amount, a feature amount obtained by dividing information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information by information regarding estimation of time among the first information, and a third variable which includes, as a first feature amount, a feature amount obtained by integrating information regarding shopping evaluated by FAQ among the third information and information regarding the positive or negative of amyloid β among the fourth information. Further, at least three variables are constituted by, for example, a first variable which is information obtained by squaring information regarding delayed playback among the second information, a second variable which includes, as a second feature amount, a feature amount obtained by dividing information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information by information regarding delayed playback among the second information, and a third variable which includes, as a second feature amount, a feature amount obtained by dividing information regarding estimation of time among the first information by information regarding the positive or negative of amyloid β among the fourth information.Further, at least three variables are constituted by, for example, a first variable which is information obtained by squaring information regarding delayed playback among the second information, a second variable which includes, as a second feature amount, a feature amount obtained by dividing information regarding meals in IADL evaluated by FAQ among the third information by information regarding time estimation among the first information, and a third variable which includes, as a first feature amount, a feature amount obtained by integrating information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information and information regarding the positive or negative of amyloid β among the fourth information. Further, at least three variables are constituted by, for example, a first variable which is information obtained by squaring information regarding delayed playback among the second information, a second variable which includes, as a second feature amount, a feature amount obtained by dividing information regarding meals in IADL evaluated by FAQ among the third information by information regarding time estimation among the first information, and a third variable which includes, as a first feature amount, a feature amount obtained by integrating information regarding movement in IADL evaluated by FAQ among the third information and information regarding the positive or negative of amyloid β among the fourth information. In any of the evaluations of the prediction model 132 using ADNI, J-ADNI, and MissionAD in the above-described example, the evaluation value of sensitivity is "0.7" or more, the evaluation value of specificity is "0.6" or more, and the evaluation value of AUC is "0.7" or more.

[0057] Figures 16 and 17 are diagrams showing an example of data used for evaluating the prediction model 132 of the embodiment. Figure 16 shows an example of evaluation values using the respective evaluation data of ADNI, J-ADNI, and MissionAD for the accuracy rate and sensitivity, which are examples of evaluation indices of the prediction model 132. Figure 17 shows an example of evaluation values using the respective evaluation data of ADNI, J-ADNI, and MissionAD for the specificity and AUC, which are examples of evaluation indices of the prediction model 132. In the examples shown in Figures 16 and 17, in the data used for evaluating the prediction model 132, for example, at least three variables include a first variable which is information obtained by squaring information related to delayed reproduction among the second information, a second variable including a feature amount obtained by integrating information related to holidays, family gatherings, reservations, or memory of medication schedules in IADL evaluated by FAQ among the third information and information related to shopping in IADL evaluated by FAQ among the third information as the first feature amount, and a third variable including a feature amount obtained by dividing information related to location recognition among the first information by information related to the positive or negative of amyloid β among the fourth information as the second feature amount. Also, at least three variables are composed of, for example, a first variable which is information obtained by squaring information related to delayed reproduction among the second information, a second variable including a feature amount obtained by integrating information related to holidays, family gatherings, reservations, or memory of medication schedules in IADL evaluated by FAQ among the third information and information related to shopping in IADL evaluated by FAQ among the third information as the first feature amount, and a third variable including a feature amount obtained by dividing information related to the name of an item among the second information by information related to the positive or negative of amyloid β among the fourth information as the second feature amount. Also, at least three variables are composed of, for example, a first variable which is information obtained by squaring information related to delayed reproduction among the second information, a second variable including a feature amount obtained by integrating information related to holidays, family gatherings, reservations, or memory of medication schedules in IADL evaluated by FAQ among the third information and information related to shopping in IADL evaluated by FAQ among the third information as the first feature amount, and a third variable which is information related to the positive or negative of amyloid β among the fourth information.Further, at least three variables are composed of a first variable which is information obtained by squaring information regarding delayed reproduction among the second information, a second variable which includes, as a first feature amount, a feature amount obtained by integrating information regarding time estimation among the first information and information regarding article names among the second information, and a third variable which includes, as a first feature amount, a feature amount obtained by integrating information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information and information regarding the positivity or negativity of amyloid β among the fourth information. Further, at least three variables are, for example, composed of a first variable which is information obtained by squaring information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information, a second variable which includes, as a first feature amount, a feature amount obtained by integrating information regarding time estimation among the first information and information regarding delayed reproduction among the second information, and a third variable which includes, as a first feature amount, a feature amount obtained by integrating information regarding meals in IADL evaluated by FAQ among the third information and information regarding the positivity or negativity of amyloid β among the fourth information. Further, at least three variables are, for example, composed of a first variable which is information obtained by squaring information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information, a second variable which includes, as a first feature amount, a feature amount obtained by integrating information regarding time estimation among the first information and information regarding delayed reproduction among the second information, and a third variable which includes, as a first feature amount, a feature amount obtained by integrating information regarding movement in IADL evaluated by FAQ among the third information and information regarding the positivity or negativity of amyloid β among the fourth information. Further, at least three variables are composed of a first variable which is information obtained by squaring information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information, a second variable which includes, as a first feature amount, a feature amount obtained by integrating information regarding time estimation among the first information and information regarding delayed reproduction among the second information, and a third variable which includes, as a first feature amount, a feature amount obtained by integrating information regarding shopping in IADL evaluated by FAQ among the third information and information regarding the positivity or negativity of amyloid β among the fourth information.Further, at least three variables are constituted by, for example, a first variable which is information obtained by squaring information regarding movement in IADL evaluated by FAQ among the third information, a second variable which includes, as a second feature amount, a feature amount obtained by dividing information regarding meals in IADL evaluated by FAQ among the third information by information regarding time estimation among the first information, and a third variable which includes, as a second feature amount, a feature amount obtained by dividing information regarding delayed playback among the second information by information regarding the positive or negative of amyloid β among the fourth information. Further, at least three variables are constituted by, for example, a first variable which is information obtained by squaring information regarding movement in IADL evaluated by FAQ among the third information, a second variable which includes, as a first feature amount, a feature amount obtained by integrating information regarding delayed playback and information regarding article naming among the second information, and a third variable which includes, as a first feature amount, a feature amount obtained by integrating information regarding the memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information and information regarding the positive or negative of amyloid β among the fourth information. In the above-described examples, in any evaluation of the prediction model 132 using ADNI, J-ADNI, and MissionAD, the evaluation value of sensitivity is "0.7" or more, the evaluation value of specificity is "0.6" or more, and the evaluation value of AUC is "0.7" or more.

[0058] Figs. 18 and 19 are diagrams showing an example of data used for evaluating the prediction model 132 of the embodiment. Fig. 18 shows an example of evaluation values using the evaluation data of ADNI, J-ADNI, and MissionAD for the accuracy rate and sensitivity, which are examples of evaluation indices of the prediction model 132. Fig. 19 shows an example of evaluation values using the evaluation data of ADNI, J-ADNI, and MissionAD for the specificity and AUC, which are examples of evaluation indices of the prediction model 132. In the examples shown in Figs. 18 and 19, in the data used for evaluating the prediction model 132, for example, at least three variables include, for example, a first variable which is information obtained by squaring the information regarding the positive / negative of amyloid β among the fourth information, a second variable including, as a second feature amount, a feature amount obtained by dividing the information regarding the memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information by the information regarding the sense of time among the first information, and a third variable including, as a second feature amount, a feature amount obtained by dividing the information regarding the memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information by the information regarding delayed reproduction among the second information. Further, at least three variables include, for example, a first variable which is information obtained by squaring the information regarding the positive / negative of amyloid β among the fourth information, a second variable including, as a second feature amount, a feature amount obtained by dividing the information regarding the memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information by the information regarding the sense of time among the first information, and a third variable including, as a first feature amount, a feature amount obtained by integrating the information regarding delayed reproduction and the information regarding the names of articles among the second information.Also, at least three variables are constituted by, for example, a first variable which is information obtained by squaring information regarding the positive or negative of amyloid β among the fourth information, a second variable including, as a first feature amount, a feature amount obtained by integrating information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information and information regarding shopping in IADL evaluated by FAQ among the third information, and a third variable including, as a first feature amount, a feature amount obtained by integrating information regarding delayed reproduction among the second information and information regarding article names among the second information. Also, at least three variables are constituted by, for example, a first variable which is information obtained by squaring information regarding the positive or negative of amyloid β among the fourth information, a second variable including, as a first feature amount, a feature amount obtained by integrating information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information and information regarding shopping in IADL evaluated by FAQ among the third information, and a third variable which is information regarding delayed reproduction among the second information. Also, at least three variables are constituted by, for example, a first variable including, as a second feature amount, a feature amount obtained by dividing information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information by information regarding time estimation among the first information, a second variable including, as a second feature amount, a feature amount obtained by dividing information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information by information regarding delayed reproduction among the second information, and a third variable including, as a first feature amount, a feature amount obtained by integrating information regarding shopping in IADL evaluated by FAQ among the third information and information regarding the positive or negative of amyloid β among the fourth information.Further, at least three variables are composed of, for example, a first variable including, as a second feature amount, a feature amount obtained by dividing information regarding a holiday, a family gathering, a reservation, or a medication schedule in IADL evaluated by FAQ in the third information by information regarding a sense of time in the first information; a second variable including, as a second feature amount, a feature amount obtained by dividing information regarding a holiday, a family gathering, a reservation, or a medication schedule in IADL evaluated by FAQ in the third information by information regarding delayed playback in the second information; and a third variable including, as a second feature amount, a feature amount obtained by dividing information regarding an article name in the second information by information regarding the positive / negative of amyloid β in the fourth information. Further, at least three variables are composed of, for example, a first variable including, as a second feature amount, a feature amount obtained by dividing information regarding a holiday, a family gathering, a reservation, or a medication schedule in IADL evaluated by FAQ in the third information by information regarding a sense of time in the first information; a second variable including, as a first feature amount, a feature amount obtained by integrating information regarding delayed playback and information regarding an article name in the second information; and a third variable including, as a second feature amount, a feature amount obtained by dividing information regarding a sense of time in the first information by information regarding the positive / negative of amyloid β in the fourth information. Further, at least three variables are composed of, for example, a first variable including, as a second feature amount, a feature amount obtained by dividing information regarding a holiday, a family gathering, a reservation, or a medication schedule in IADL evaluated by FAQ in the third information by information regarding a sense of time in the first information; a second variable including, as a first feature amount, a feature amount obtained by integrating information regarding delayed playback and information regarding an article name in the second information; and a third variable including, as a second feature amount, a feature amount obtained by dividing information regarding an article name in the second information by information regarding the positive / negative of amyloid β in the fourth information.Further, at least three variables include, for example, a first variable including, as a second feature amount, a feature amount obtained by dividing information related to the memory of holidays, family gatherings, reservations, or medication schedules in IADLs evaluated by FAQ among the third information by information related to time estimation among the first information; a second variable including, as a first feature amount, a feature amount obtained by integrating information related to location estimation among the first information and information related to delayed playback among the second information; and a third variable including, as a first feature amount, a feature amount obtained by integrating information related to shopping in IADLs evaluated by FAQ among the third information and information related to the positive / negative of amyloid β among the fourth information. In the above-described example, in any evaluation of the prediction model 132 using ADNI, J-ADNI, and MissionAD, the evaluation value of sensitivity is "0.7" or more, the evaluation value of specificity is "0.6" or more, and the evaluation value of AUC is "0.7" or more.

[0059] Figures 20 and 21 are diagrams showing an example of data used for the evaluation of the prediction model 132 of the embodiment. Figure 20 shows an example of evaluation values using the evaluation data of ADNI, J-ADNI, and MissionAD for the accuracy rate and sensitivity, which are examples of evaluation indicators of the prediction model 132. Figure 21 shows an example of evaluation values using the evaluation data of ADNI, J-ADNI, and MissionAD for the specificity and AUC, which are examples of evaluation indicators of the prediction model 132. In the examples shown in Figures 20 and 21, in the data used for the evaluation of the prediction model 132, for example, at least three variables include a first variable including, as a second feature amount, a feature amount obtained by dividing information on holidays, family gatherings, reservations, or memory of medication schedules in IADL evaluated by FAQ in the third information by information on time estimation in the first information; a second variable including, as a first feature amount, a feature amount obtained by integrating information on delayed reproduction and information on article names in the second information; and a third variable including, as a first feature amount, a feature amount obtained by integrating information on meals in IADL evaluated by FAQ in the third information and information on the positive or negative of amyloid β in the fourth information. Also, at least three variables include, for example, a first variable including, as a second feature amount, a feature amount obtained by dividing information on holidays, family gatherings, reservations, or memory of medication schedules in IADL evaluated by FAQ in the third information by information on time estimation in the first information; a second variable including, as a first feature amount, a feature amount obtained by integrating information on delayed reproduction and information on article names in the second information; and a third variable including, as a first feature amount, a feature amount obtained by integrating information on shopping in IADL evaluated by FAQ in the third information and information on the positive or negative of amyloid β in the fourth information.Further, at least three variables are composed of, for example, a first variable including, as a second feature amount, a feature amount obtained by dividing information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among third information by information regarding time estimation among first information; a second variable including, as a first feature amount, a feature amount obtained by integrating information regarding delayed reproduction and information regarding article names among second information; and a third variable which is information regarding the positive or negative of amyloid β among fourth information. Further, at least three variables are composed of, for example, a first variable including, as a second feature amount, a feature amount obtained by dividing information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among third information by information regarding time estimation among first information; a second variable including, as a first feature amount, a feature amount obtained by integrating information regarding delayed reproduction and information regarding article names among second information; and a third variable including, as a second feature amount, a feature amount obtained by dividing information regarding location estimation among first information by information regarding the positive or negative of amyloid β among fourth information. Further, at least three variables are composed of, for example, a first variable including, as a second feature amount, a feature amount obtained by dividing information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among third information by information regarding time estimation among first information; a second variable including, as a first feature amount, a feature amount obtained by integrating information regarding meals in IADL evaluated by FAQ among third information and information regarding the positive or negative of amyloid β among fourth information; and a third variable which is information regarding delayed reproduction among second information.Further, at least three variables are composed of, for example, a first variable including, as a second feature amount, a feature amount obtained by dividing information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information by information regarding time estimation among the first information; a second variable including, as a first feature amount, a feature amount obtained by integrating information regarding shopping in IADL evaluated by FAQ among the third information and information regarding the positive / negative of amyloid β among the fourth information; and a third variable including, as a second feature amount, a feature amount obtained by dividing information regarding delayed reproduction among the second information by information regarding the positive / negative of amyloid β among the fourth information. Further, at least three variables are composed of, for example, a first variable including, as a second feature amount, a feature amount obtained by dividing information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information by information regarding time estimation among the first information; a second variable including, as a first feature amount, a feature amount obtained by integrating information regarding shopping in IADL evaluated by FAQ among the third information and information regarding the positive / negative of amyloid β among the fourth information; and a third variable which is information regarding delayed reproduction among the second information. In any of the evaluations of the prediction model 132 using ADNI, J-ADNI, and MissionAD in the above-described example, the evaluation value of sensitivity is 0.7 or more, the evaluation value of specificity is 0.6 or more, and the evaluation value of AUC is 0.7 or more.

[0060] Figures 22 and 23 are diagrams showing an example of data used for evaluating the prediction model 132 of the embodiment. FIG. 22 shows an example of evaluation values using the evaluation data of each of ADNI, J-ADNI, and MissionAD for the accuracy rate and sensitivity, which are examples of evaluation indices of the prediction model 132. FIG. 23 shows an example of evaluation values using the evaluation data of each of ADNI, J-ADNI, and MissionAD for the specificity and AUC, which are examples of evaluation indices of the prediction model 132. In the examples shown in FIGS. 22 and 23, in the data used for evaluating the prediction model 132, for example, at least three variables include a first variable including, as a first feature amount, a feature amount obtained by integrating information regarding the estimation of time among the first information and information regarding delayed reproduction among the second information; a second variable including, as a first feature amount, a feature amount obtained by integrating information regarding the memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information and information regarding the positive or negative of amyloid β among the fourth information; and a third variable including, as a first feature amount, a feature amount obtained by integrating information regarding meals in IADL evaluated by FAQ among the third information and information regarding the positive or negative of amyloid β among the fourth information. Also, at least three variables are composed of, for example, a first variable including, as a second feature amount, a feature amount obtained by dividing information regarding the memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information by information regarding the estimation of location among the first information; a second variable including, as a first feature amount, a feature amount obtained by integrating information regarding the estimation of location among the first information and information regarding delayed reproduction among the second information; and a third variable including, as a second feature amount, a feature amount obtained by dividing information regarding the estimation of time among the first information by information regarding the positive or negative of amyloid β among the fourth information.Further, at least three variables are constituted by, for example, a first variable including, as a second feature amount, a feature amount obtained by dividing information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ in the third information by information regarding location awareness in the first information; a second variable including, as a second feature amount, a feature amount obtained by integrating information regarding delayed reproduction and information regarding article names in the second information; and a third variable including, as a second feature amount, a feature amount obtained by dividing information regarding time awareness in the first information by information regarding amyloid-β positivity or negativity in the fourth information. Further, at least three variables are constituted by, for example, a first variable including, as a second feature amount, a feature amount obtained by dividing information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ in the third information by information regarding delayed reproduction in the second information; a second variable including, as a second feature amount, a feature amount obtained by dividing information regarding meals in IADL evaluated by FAQ in the third information by information regarding delayed reproduction in the second information; and a third variable including, as a second feature amount, a feature amount obtained by dividing information regarding time awareness in the first information by information regarding amyloid-β positivity or negativity in the fourth information. Further, at least three variables are constituted by, for example, a first variable including, as a second feature amount, a feature amount obtained by dividing information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ in the third information by information regarding delayed reproduction in the second information; a second variable including, as a first feature amount, a feature amount obtained by integrating information regarding delayed reproduction and information regarding article names in the second information; and a third variable including, as a second feature amount, a feature amount obtained by dividing information regarding time awareness in the first information by information regarding amyloid-β positivity or negativity in the fourth information.Also, at least three variables are composed of, for example, a first variable including, as a second feature amount, a feature amount obtained by dividing information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ in the third information by information regarding delayed reproduction in the second information; a second variable including, as a second feature amount, a feature amount obtained by dividing information regarding time estimation in the first information by information regarding the positive or negative of amyloid β in the fourth information; and a third variable which is information regarding delayed reproduction in the second information. Also, at least three variables are composed of, for example, a first variable including, as a second feature amount, a feature amount obtained by dividing information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ in the third information by information regarding article names in the second information; a second variable including, as a first feature amount, a feature amount obtained by integrating information regarding time estimation in the first information and information regarding delayed reproduction in the second information; and a third variable including, as a second feature amount, a feature amount obtained by integrating information regarding meals in IADL evaluated by FAQ in the third information and information regarding the positive or negative of amyloid β in the fourth information. Also, at least three variables are composed of, for example, a first variable including, as a second feature amount, a feature amount obtained by dividing information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ in the third information by information regarding article names in the second information; a second variable including, as a first feature amount, a feature amount obtained by integrating information regarding time estimation in the first information and information regarding delayed reproduction in the second information; and a third variable including, as a first feature amount, a feature amount obtained by integrating information regarding movement in IADL evaluated by FAQ in the third information and information regarding the positive or negative of amyloid β in the fourth information.Further, at least three variables include, for example, a first variable including, as a second feature amount, a feature amount obtained by dividing information regarding a holiday, a family gathering, a reservation, or a medication schedule in IADL evaluated by FAQ among the third information by information regarding an article name among the second information; a second variable including, as a first feature amount, a feature amount obtained by integrating information regarding a time estimate among the first information and information regarding delayed playback among the second information; and a third variable including, as a first feature amount, a feature amount obtained by integrating information regarding shopping in IADL evaluated by FAQ among the third information and information regarding the positivity or negativity of amyloid β among the fourth information. In the above-described example, in any evaluation of the prediction model 132 using ADNI, J-ADNI, and MissionAD, the evaluation value of sensitivity is 0.7 or more, the evaluation value of specificity is 0.6 or more, and the evaluation value of AUC is 0.7 or more.

[0061] Figs. 24 and 25 are diagrams showing an example of data used for evaluating the prediction model 132 of the embodiment. Fig. 24 shows an example of evaluation values using the evaluation data of ADNI, J-ADNI, and MissionAD for the accuracy rate and sensitivity, which are examples of evaluation indicators of the prediction model 132. Fig. 25 shows an example of evaluation values using the evaluation data of ADNI, J-ADNI, and MissionAD for the specificity and AUC, which are examples of evaluation indicators of the prediction model 132. In the examples shown in Figs. 24 and 25, in the data used for evaluating the prediction model 132, for example, at least three variables include a first variable including, as a second feature amount, a feature amount obtained by dividing information regarding memory of meals in IADL evaluated by FAQ in the third information by information regarding time estimation in the first information; a second variable including, as a second feature amount, a feature amount obtained by dividing information regarding movement in IADL evaluated by FAQ in the third information by information regarding article name calling in the second information; and a third variable including, as a second feature amount, a feature amount obtained by dividing information regarding delayed reproduction in the second information by information regarding the positive or negative of amyloid β in the fourth information. Further, at least three variables include, for example, a first variable including, as a second feature amount, a feature amount obtained by dividing information regarding meals in IADL evaluated by FAQ in the third information by information regarding time estimation in the first information; a second variable including, as a first feature amount, a feature amount obtained by integrating information regarding location estimation in the first information and information regarding delayed reproduction in the second information; and a third variable including, as a first feature amount, a feature amount obtained by integrating information regarding movement in IADL evaluated by FAQ in the third information and information regarding the positive or negative of amyloid β in the fourth information.Further, at least three variables are constituted by, for example, a first variable including, as a second feature amount, a feature amount obtained by dividing information regarding eating in IADL evaluated by FAQ in the third information by information regarding time estimation in the first information; a second variable including, as a first feature amount, a feature amount obtained by integrating information regarding delayed playback and information regarding article names in the second information; and a third variable including, as a first feature amount, a feature amount obtained by integrating information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ in the third information and information regarding the positivity or negativity of amyloid-β in the fourth information. Further, at least three variables are constituted by, for example, a first variable including, as a second feature amount, a feature amount obtained by dividing information regarding eating in IADL evaluated by FAQ in the third information by information regarding time estimation in the first information; a second variable including, as a first feature amount, a feature amount obtained by integrating information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ in the third information and information regarding the positivity or negativity of amyloid-β in the fourth information; and a third variable which is information regarding delayed playback in the second information. Further, at least three variables are constituted by, for example, a first variable including, as a second feature amount, a feature amount obtained by dividing information regarding eating in IADL evaluated by FAQ in the third information by information regarding time estimation in the first information; a second variable including, as a first feature amount, a feature amount obtained by integrating information regarding movement in IADL evaluated by FAQ in the third information and information regarding the positivity or negativity of amyloid-β in the fourth information; and a third variable which is information regarding delayed playback in the second information. Further, at least three variables are constituted by, for example, a first variable including, as a second feature amount, a feature amount obtained by dividing information regarding eating in IADL evaluated by FAQ in the third information by information regarding time estimation in the first information; a second variable including, as a second feature amount, a feature amount obtained by dividing information regarding delayed playback in the second information by information regarding the positivity or negativity of amyloid-β in the fourth information; and a third variable which is information regarding movement in IADL evaluated by FAQ in the third information.Further, at least three variables are composed of, for example, a first variable including, as a second feature amount, a feature amount obtained by dividing information regarding meals in IADL evaluated by FAQ in the third information by information regarding the sense of location in the first information; a second variable including, as a first feature amount, a feature amount obtained by integrating information regarding delayed playback and information regarding article names in the second information; and a third variable including, as a first feature amount, a feature amount obtained by integrating information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ in the third information and information regarding the positive / negative of amyloid-β in the fourth information. Further, at least three variables are composed of, for example, a first variable including, as a second feature amount, a feature amount obtained by dividing information regarding meals in IADL evaluated by FAQ in the third information by information regarding delayed playback in the second information; a second variable including, as a first feature amount, a feature amount obtained by integrating information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ in the third information and information regarding the positive / negative of amyloid-β in the fourth information; and a third variable including, as a first feature amount, a feature amount obtained by integrating information regarding shopping in IADL evaluated by FAQ in the third information and information regarding the positive / negative of amyloid-β in the fourth information. Further, at least three variables are composed of, for example, a first variable including, as a first feature amount, a feature amount obtained by integrating information regarding the sense of time in the first information and information regarding delayed playback in the second information; a second variable including, as a first feature amount, a feature amount obtained by integrating information regarding movement in IADL evaluated by FAQ in the third information and information regarding the positive / negative of amyloid-β in the fourth information; and a third variable which is information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ in the third information.Further, at least three variables include, for example, a first variable including, as a second feature amount, a feature amount obtained by dividing information on meals in IADL evaluated by FAQ in the third information by information on the article name in the second information; a second variable including, as a first feature amount, a feature amount obtained by integrating information on time estimation in the first information and information on delayed reproduction in the second information; and a third variable including, as a first feature amount, a feature amount obtained by integrating information on memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ in the third information and information on the positive / negative of amyloid β in the fourth information. In the above-described example, in any evaluation of the prediction model 132 using ADNI, J-ADNI, and MissionAD, the evaluation value of sensitivity is 0.7 or more, the evaluation value of specificity is 0.6 or more, and the evaluation value of AUC is 0.7 or more.

[0062] Figures 26 and 27 are diagrams showing an example of data used for the evaluation of the prediction model 132 of the embodiment. FIG. 26 shows an example of evaluation values using the evaluation data of each of ADNI, J-ADNI, and MissionAD for the accuracy rate and sensitivity, which are examples of evaluation indices of the prediction model 132. FIG. 27 shows an example of evaluation values using the evaluation data of each of ADNI, J-ADNI, and MissionAD for the specificity and AUC, which are examples of evaluation indices of the prediction model 132. In the examples shown in FIGS. 26 and 27, in the data used for the evaluation of the prediction model 132, for example, at least three variables include a first variable including, as a first feature amount, a feature amount obtained by integrating information on holidays, family gatherings, reservations, or memory of medication schedules in IADL evaluated by FAQ among the third information and information on meals in IADL evaluated by FAQ among the third information, a second variable including, as a first feature amount, a feature amount obtained by integrating information on time estimation among the first information and information on delayed playback among the second information, and a third variable including, as a first feature amount, a feature amount obtained by integrating information on meals in IADL evaluated by FAQ among the third information and information on the positive / negative of amyloid-β among the fourth information. Further, at least three variables include, for example, a first variable including, as a first feature amount, a feature amount obtained by integrating information on holidays, family gatherings, reservations, or memory of medication schedules in IADL evaluated by FAQ among the third information and information on meals in IADL evaluated by FAQ among the third information, a second variable including, as a first feature amount, a feature amount obtained by integrating information on location estimation among the first information and information on delayed playback among the second information, and a third variable including, as a second feature amount, a feature amount obtained by dividing the information on time estimation among the first information by the information on the positive / negative of amyloid-β among the fourth information.Also, at least three variables are constituted by, for example, a first variable including, as a first feature amount, a feature amount obtained by integrating information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information and information regarding shopping in IADL evaluated by FAQ among the third information, a second variable including, as a first feature amount, a feature amount obtained by integrating information regarding delayed reproduction among the second information and information regarding article name designations among the second information, and a third variable including, as a second feature amount, a feature amount obtained by dividing information regarding location estimation among the first information by information regarding amyloid-β positivity / negativity among the fourth information. Also, at least three variables are constituted by, for example, a first variable including, as a first feature amount, a feature amount obtained by integrating information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information and information regarding shopping in IADL evaluated by FAQ among the third information, a second variable including, as a first feature amount, a feature amount obtained by integrating information regarding delayed reproduction among the second information and information regarding article name designations among the second information, and a third variable including, as a second feature amount, a feature amount obtained by dividing information regarding article name designations among the second information by information regarding amyloid-β positivity / negativity among the fourth information. Also, at least three variables are constituted by, for example, a first variable including, as a first feature amount, a feature amount obtained by integrating information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information and information regarding shopping in IADL evaluated by FAQ among the third information, a second variable including, as a first feature amount, a feature amount obtained by integrating information regarding delayed reproduction among the second information and information regarding article name designations among the second information, and a third variable which is information regarding amyloid-β positivity / negativity among the fourth information.Further, at least three variables are composed of, for example, a first variable including, as a first feature amount, a feature amount obtained by integrating information on holidays, family gatherings, reservations, or medication schedules in IADLs evaluated by FAQ among the third information and information on shopping in IADLs evaluated by FAQ among the third information, a second variable including, as a second feature amount, a feature amount obtained by dividing information on location awareness among the first information by information on amyloid-β positivity or negativity among the fourth information, and a third variable which is information on delayed playback among the second information. Further, at least three variables are composed of, for example, a first variable including, as a first feature amount, a feature amount obtained by integrating information on holidays, family gatherings, reservations, or medication schedules in IADLs evaluated by FAQ among the third information and information on shopping in IADLs evaluated by FAQ among the third information, a second variable including, as a second feature amount, a feature amount obtained by dividing information on article names among the second information by information on amyloid-β positivity or negativity among the fourth information, and a third variable which is information on delayed playback among the second information. Further, at least three variables are composed of, for example, a first variable including, as a first feature amount, a feature amount obtained by integrating information on holidays, family gatherings, reservations, or medication schedules in IADLs evaluated by FAQ among the third information and information on shopping in IADLs evaluated by FAQ among the third information, a second variable which is information on delayed playback among the second information, and a third variable which is information on amyloid-β positivity or negativity among the fourth information. Further, at least three variables are composed of, for example, a first variable including, as a first feature amount, a feature amount obtained by integrating information on meals in IADLs evaluated by FAQ among the third information and information on shopping in IADLs evaluated by FAQ among the third information, a second variable including, as a first feature amount, a feature amount obtained by integrating information on time awareness among the first information and information on delayed playback among the second information, and a third variable including, as a first feature amount, a feature amount obtained by integrating information on holidays, family gatherings, reservations, or medication schedules in IADLs evaluated by FAQ among the third information and information on amyloid-β positivity or negativity among the fourth information.Furthermore, at least three variables include a first variable including, as a first feature amount, a feature amount obtained by integrating information on mobility in IADL evaluated by FAQ among the third information and information on shopping in IADL evaluated by FAQ among the third information; a second variable including, as a first feature amount, a feature amount obtained by integrating information on memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information and information on the positivity or negativity of amyloid β among the fourth information; and a third variable including, as a second feature amount, a feature amount obtained by dividing information on delayed playback among the second information by information on the positivity or negativity of amyloid β among the fourth information. In the above-described example, in any evaluation of the prediction model 132 using ADNI, J-ADNI, and MissionAD, the evaluation value of sensitivity is 0.7 or more, the evaluation value of specificity is 0.6 or more, and the evaluation value of AUC is 0.7 or more.

[0063] Figs. 28 and 29 are diagrams showing an example of data used for evaluating the prediction model 132 of the embodiment. Fig. 28 shows an example of evaluation values using the evaluation data of ADNI, J-ADNI, and MissionAD for the accuracy rate and sensitivity, which are examples of evaluation indicators of the prediction model 132. Fig. 29 shows an example of evaluation values using the evaluation data of ADNI, J-ADNI, and MissionAD for the specificity and AUC, which are examples of evaluation indicators of the prediction model 132. In the examples shown in Figs. 28 and 29, in the data used for evaluating the prediction model 132, for example, at least three variables include a first variable including, as a first feature amount, a feature amount obtained by integrating information related to the sense of time among the first information and information related to the sense of location among the first information, a second variable including, as a first feature amount, a feature amount obtained by integrating information related to delayed reproduction among the second information and information related to the name of an article among the second information, and a third variable including, as a first feature amount, a feature amount obtained by integrating information related to the memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information and information related to the positive or negative of amyloid β among the fourth information. Further, at least three variables are composed of, for example, a first variable including, as a first feature amount, a feature amount obtained by integrating information related to the sense of time among the first information and information related to delayed reproduction among the second information, a second variable including, as a first feature amount, a feature amount obtained by integrating information related to the sense of time among the first information and information related to the name of an article among the second information, and a third variable including, as a first feature amount, a feature amount obtained by integrating information related to the memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information and information related to the positive or negative of amyloid β among the fourth information.Also, at least three variables are composed of, for example, a first variable including, as a first feature amount, a feature amount obtained by integrating information regarding delayed playback among the second information and information regarding article names among the second information; a second variable including, as a first feature amount, a feature amount obtained by integrating information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information and information regarding the positive or negative of amyloid-β among the fourth information; and a third variable which is information regarding movement in IADL evaluated by FAQ among the third information. Also, at least three variables are composed of, for example, a first variable including, as a first feature amount, a feature amount obtained by integrating information regarding time estimation among the first information and information regarding delayed playback among the second information; a second variable including, as a first feature amount, a feature amount obtained by integrating information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information and information regarding the positive or negative of amyloid-β among the fourth information; and a third variable including, as a first feature amount, a feature amount obtained by integrating information regarding shopping in IADL evaluated by FAQ among the third information and information regarding the positive or negative of amyloid-β among the fourth information. Also, at least three variables are composed of, for example, a first variable including, as a first feature amount, a feature amount obtained by integrating information regarding time estimation among the first information and information regarding delayed playback among the second information; a second variable including, as a first feature amount, a feature amount obtained by integrating information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information and information regarding the positive or negative of amyloid-β among the fourth information; and a third variable which is information regarding time estimation among the first information.Further, at least three variables are composed of, for example, a first variable including, as a first feature amount, a feature amount obtained by integrating information regarding the estimation of time among the first information and information regarding delayed reproduction among the second information; a second variable including, as a first feature amount, a feature amount obtained by integrating information regarding meals in IADL evaluated by FAQ among the third information and information regarding the positivity or negativity of amyloid-β among the fourth information; and a third variable which is information regarding the memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information. Further, at least three variables are composed of, for example, a first variable including, as a second feature amount, a feature amount obtained by dividing information regarding the memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information by information regarding the estimation of time among the first information; a second variable including, as a second feature amount, a feature amount obtained by dividing information regarding the memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information by information regarding delayed reproduction among the second information; and a third variable including, as a second feature amount, a feature amount obtained by dividing information regarding the estimation of time among the first information by information regarding the positivity or negativity of amyloid-β among the fourth information. Further, at least three variables are composed of, for example, a first variable including, as a first feature amount, a feature amount obtained by integrating information regarding the estimation of time among the first information and information regarding delayed reproduction among the second information; a second variable including, as a first feature amount, a feature amount obtained by integrating information regarding shopping in IADL evaluated by FAQ among the third information and information regarding the positivity or negativity of amyloid-β among the fourth information; and a third variable which is information regarding the memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information.Furthermore, at least three variables are composed of a first variable including, as a first feature amount, a feature amount obtained by integrating information regarding time estimation in the first information and information regarding article names in the second information, a second variable including, as a first feature amount, a feature amount obtained by integrating information regarding delayed reproduction in the second information and information regarding article names in the second information, and a third variable including, as a first feature amount, a feature amount obtained by integrating information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ in the third information and information regarding the positive or negative of amyloid β in the fourth information. Also, in any of the evaluations of the prediction model 132 using ADNI, J-ADNI, and MissionAD in the above-described example, the evaluation value of sensitivity is 0.7 or more, the evaluation value of specificity is 0.6 or more, and the evaluation value of AUC is 0.7 or more.

[0064] FIG. 30 and FIG. 31 are diagrams showing an example of data used for the evaluation of the prediction model 132 of the embodiment. FIG. 30 shows an example of evaluation values using the evaluation data of each of ADNI, J-ADNI, and MissionAD for the accuracy rate and sensitivity, which are examples of evaluation indices of the prediction model 132. FIG. 31 shows an example of evaluation values using the evaluation data of each of ADNI, J-ADNI, and MissionAD for the specificity and AUC, which are examples of evaluation indices of the prediction model 132. In the examples shown in FIGS. 30 and 31, in the data used for the evaluation of the prediction model 132, for example, at least three variables include a first variable including, as a first feature amount, a feature amount obtained by integrating information regarding the estimation of time among the first information and information regarding the article name among the second information, a second variable including, as a first feature amount, a feature amount obtained by integrating information regarding the memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information and information regarding the positive / negative of amyloid β among the fourth information, and a third variable including, as a second feature amount, a feature amount obtained by dividing the information regarding delayed reproduction among the second information by the information regarding the positive / negative of amyloid β among the fourth information. Further, at least three variables include, for example, a first variable including, as a first feature amount, a feature amount obtained by integrating information regarding the estimation of time among the first information and information regarding the article name among the second information, a second variable including, as a first feature amount, a feature amount obtained by integrating information regarding the memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information and information regarding the positive / negative of amyloid β among the fourth information, and a third variable which is the information regarding delayed reproduction among the second information.Also, at least three variables are composed of a first variable including, as a first feature amount, a feature amount obtained by integrating information regarding location estimation among the first information and information regarding delayed reproduction among the second information; a second variable including, as a first feature amount, a feature amount obtained by integrating information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information and information regarding the positive or negative of amyloid β among the fourth information; and a third variable including, as a second feature amount, a feature amount obtained by dividing information regarding time estimation among the first information by information regarding the positive or negative of amyloid β among the fourth information. Also, at least three variables are composed of, for example, a first variable including, as a first feature amount, a feature amount obtained by integrating information regarding delayed reproduction among the second information and information regarding article naming among the second information; a second variable including, as a first feature amount, a feature amount obtained by integrating information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information and information regarding the positive or negative of amyloid β among the fourth information; and a third variable which is information regarding time estimation among the first information. Also, at least three variables are composed of, for example, a first variable including, as a first feature amount, a feature amount obtained by dividing information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information by information regarding time estimation among the first information; a second variable including, as a second feature amount, a feature amount obtained by dividing information regarding memory of holidays, family gatherings, reservations, or medication schedules in IADL evaluated by FAQ among the third information by information regarding delayed reproduction among the second information; and a third variable which is information regarding the positive or negative of amyloid β among the fourth information.Further, at least three variables are composed of, for example, a first variable including, as a first feature amount, a feature amount obtained by integrating information regarding a holiday, a family gathering, a reservation, or a medication schedule in IADL evaluated by FAQ among the third information and information regarding the positive or negative of amyloid β among the fourth information; a second variable including, as a first feature amount, a feature amount obtained by dividing information regarding delayed reproduction among the second information by information regarding the positive or negative of amyloid β among the fourth information; and a third variable which is information regarding time estimation among the first information. In the above-described example, in any evaluation of the prediction model 132 using ADNI, J-ADNI, and MissionAD, the evaluation value of sensitivity is 0.7 or more, the evaluation value of specificity is 0.6 or more, and the evaluation value of AUC is 0.7 or more.

[0065] According to the information processing apparatus 100 described above, as learning data used for learning the prediction model 132, by selecting data that can obtain a high evaluation as an evaluation based on a plurality of evaluation data 131 such as ADNI, J-ADNI, and MissionAD, which are not easily affected by differences in culture, habits, and preferences due to covering a wide area, high prediction accuracy can be achieved regardless of race, culture, habits, etc. Further, as learning data used for learning the prediction model 132, by selecting data that can be relatively easily obtained by a questionnaire for patients, the examination (questionnaire) time, the physical load of the examination (biological sample collection), and the number of hospital visits can be shortened and reduced, and the processing load on the patient and the apparatus can be reduced.

[0066] 〔Hardware Configuration〕 FIG. 31 is a diagram showing an example of the hardware configuration of the information processing apparatus 100 according to the present embodiment. As shown in the figure, the information processing apparatus 100 includes a communication controller 100-1, a CPU 100-2, a RAM (Random Access Memory) 100-3 used as a working memory, a ROM (Read Only Memory) 100-4 that stores a boot program and the like, a storage device 100-5 such as a flash memory or an HDD (Hard Disk Drive), a drive device 100-6, etc., which are interconnected by an internal bus or a dedicated communication line. The communication controller 100-1 communicates with components other than the information processing apparatus 100. The storage device 100-5 stores a program 100-5a executed by the CPU 100-2. This program is expanded in the RAM 100-3 by a DMA (Direct Memory Access) controller (not shown) and executed by the CPU 100-2. As a result, the acquisition unit 121, the prediction unit 122, and the output unit 123 are realized.

[0067] Note that the embodiments described above are for facilitating the understanding of the present invention and are not for limiting the interpretation of the present invention. The present invention can be changed / improved without departing from its gist, and equivalents thereof are also included in the present invention. That is, as long as those appropriately designed and changed by those skilled in the art for each embodiment have the features of the present invention, they are included in the scope of the present invention. Also, each embodiment is an example, and it goes without saying that partial substitution or combination of the configurations shown in different embodiments is possible, and these are also included in the scope of the present invention as long as they include the features of the present invention.

Description of Reference Numerals

[0068] 10... Terminal device, 100... Information processing apparatus, 110... Communication device, 120... Control unit, 121... Acquisition unit, 122... Prediction unit, 123... Output unit, 130... Storage unit, 131... Evaluation data, 132... Prediction model, NW... Communication network.

Claims

1. First information regarding orientation, Second information regarding memory, Third information regarding the memory of holidays, family gatherings, reservations, or medication schedules in IADL, or the actual tasks of meals, shopping, or mobility in IADL, At least three variables based on information selected from the above, and the presence or absence of symptom progression of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD), and using learning data in which the above are associated, for a prediction model learned using the learning data, inputting patient information corresponding to each of the three variables, and a prediction unit that predicts the probability that the patient's symptoms of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD) will progress, an information processing apparatus comprising: The at least three variables are: At least one of the information regarding orientation related to time among the first information and the information regarding the memory of holidays, family gatherings, reservations, or medication schedules in IADL among the third information, The information regarding delayed reproduction among the second information, Regarding at least four pieces of information selected from the first information, the second information, the third information, and the fourth information, including the information regarding the positivity or negativity of amyloid-β among the fourth information, A first feature amount obtained by integrating information showing a positive correlation among information showing the degree of symptoms of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD), and An information processing apparatus including at least one of a second feature amount obtained by dividing information showing a negative correlation among information showing the magnitude of the degree of symptoms of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD). Information processing apparatus.

2. The at least three variables are: The information regarding the memory of holidays, family gatherings, reservations, or medication schedules in IADL among the third information, The information regarding delayed reproduction among the second information, The fourth information Including at least one of the first feature amount and the second feature amount for at least four pieces of information including The information processing apparatus according to Claim 1.

3. The at least three variables are: The information regarding orientation related to time among the first information, The information regarding the memory of holidays, family gatherings, reservations, or medication schedules in IADL among the third information, The information regarding delayed reproduction among the second information, The fourth information For at least four pieces of information, including at least one of the first feature amount and the second feature amount The information processing apparatus according to claim 1.

4. The at least three variables include at least one of the first feature amount and the second feature amount for four or five pieces of information. The information processing apparatus according to claim 3.

5. The at least three variables are Information regarding an estimate of time among the first information, Information regarding the memory of holidays, family gatherings, reservations, or medication schedules in IADL among the third information, Information regarding delayed playback among the second information, The fourth information For four pieces of information including, for at least one of the first feature amount and the second feature amount. The information processing apparatus according to claim 3.

6. The at least three variables are Information regarding an estimate of time among the first information, Information regarding the memory of holidays, family gatherings, reservations, or medication schedules in IADL among the third information, Information regarding delayed playback among the second information, The fourth information, For five pieces of information including the first information, the second information, the third information, the fourth information, and a fifth information selected from the first information, the second information, the third information, and the fourth information, including at least one of the first feature amount and the second feature amount. The information processing apparatus according to claim 1.

7. A computer A step of acquiring patient information, Using a prediction model learned using learning data in which at least three variables based on information selected from first information regarding an estimate, second information regarding memory, third information regarding the memory of holidays, family gatherings, reservations, or medication schedules in IADL, or the actual operations of meals, shopping, or movement in IADL, and fourth information regarding the positivity or negativity of biomarkers are associated with the presence or absence of symptom progression of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD), inputting the patient's information corresponding to each of the three variables, and predicting the probability that the patient has symptoms of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD) progressing, A step of outputting a prediction result regarding the probability that the patient has symptoms of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD) progressing, An information processing method for executing The at least three variables are At least one of the information regarding the estimate of time among the first information and the information regarding the memory of holidays, family gatherings, reservations, or medication schedules in IADL among the third information, and the information regarding delayed playback among the second information, the information regarding the positive or negative of amyloid β among the fourth information For at least four pieces of information selected from the first information, the second information, the third information, and the fourth information, which includes the above, a first feature amount obtained by integrating information that shows a positive correlation among information showing the degree of symptoms of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD), and including at least one of the second feature amounts obtained by dividing information that shows a negative correlation between the magnitudes of the evaluation values showing the degree of symptoms of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD), An information processing method.

8. On a computer, A process of acquiring patient information, Using the learned prediction model learned using learning data in which at least three variables based on information selected from the first information regarding estimate, the second information regarding memory, the third information regarding the memory of holidays, family gatherings, reservations, or medication schedules in IADL, or the actual operations of meals, shopping, or movement in IADL, and the fourth information regarding the positive or negative of biomarkers, and the presence or absence of symptom progression of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD) are associated, input the patient information corresponding to each of the three variables, and predict the probability that the patient has symptoms of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD) progressing, Execute a process of outputting a prediction result regarding the probability that the patient has symptoms of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD) progressing, The at least three variables are At least one of the information regarding the estimate of time among the first information and the information regarding the memory of holidays, family gatherings, reservations, or medication schedules in IADL among the third information, and the information regarding delayed playback among the second information, the information regarding the positive or negative of amyloid β among the fourth information For at least four pieces of information selected from the first information, the second information, the third information, and the fourth information including, a first feature amount obtained by integrating pieces of information that show a positive correlation with an evaluation value indicating the degree of symptoms of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD), and A program including at least one of a second feature amount obtained by dividing pieces of information that show a negative correlation with the magnitude of an evaluation value indicating the degree of symptoms of mild cognitive impairment (MCI) or mild Alzheimer's disease (mild AD). Program.

9. A computer-readable non-transitory storage medium storing the program according to Claim 8.

Images