Predictive analysis method for disease progress monitoring and management and device for performing same

Abstract

The present invention relates to a disease prediction and disease analysis method for disease management, and a device for performing the method. The disease prediction and disease analysis method for disease management may comprise the steps in which a disease management device: receives user data; and generates user disease management data on the basis of the user data.

Description

Methods for predictive analysis for disease progression monitoring and management and devices for performing such methods

[0001] The present invention relates to a predictive analysis method for disease progression monitoring and management, and a device for performing such a method. More specifically, the present invention relates to a predictive analysis method for disease progression monitoring and management, and a device for performing such a method, for monitoring the progression of a user's disease and managing the user's disease.

[0002] The development of various smart technologies has enabled the recording of data on individuals' daily activities, enabling them to manage their lives more efficiently. Among these, health-related data logging is gaining attention due to the growing interest in health. Many users are already generating and utilizing various health-related data, such as exercise, diet, and sleep, through their smartphones and wearable devices. This shift is a shift from the past, when health-related data was solely generated and managed by medical institutions, to users themselves, through their own devices like smartphones and wearables.

[0003] Health-related data logging is often accomplished through wearable devices. Wearable devices are devices worn or attached to the user's body. Thanks to advancements in technologies like the Internet of Things, wearable devices are increasingly being used to collect health-related data. Wearable devices can collect information about the user's physical changes and the environment surrounding them, and based on this data, they can provide necessary health advice.

[0004] A user's health-related data may include user biomarkers, and research is underway on methods to provide more adaptive medical prescriptions to users based on their health-related data.

[0005] Related technology includes Korean registered patent No. 10-2425479.

[0006] The purpose of the present invention is to solve all of the above-described problems.

[0007] In addition, the present invention aims to manage a user's disease by performing disease prediction and disease monitoring through a disease prediction model and disease monitoring model based on artificial intelligence.

[0008] In addition, the present invention aims to perform the most accurate disease prediction and disease monitoring by training various artificial intelligence models for disease prediction and disease monitoring, and replacing the artificial intelligence models for disease prediction and disease monitoring through performance comparison of the various artificial intelligence models.

[0009] A representative configuration of the present invention to achieve the above purpose is as follows.

[0010] According to one embodiment of the present invention, a disease prediction and disease analysis method for disease management may include a step in which a disease management device receives user data and a step in which the disease management device generates user disease management data based on the user data.

[0011] Meanwhile, the disease management data may include disease prediction data for the user or disease monitoring data for the user, and the disease prediction data may be generated based on a disease prediction artificial intelligence model, and the disease monitoring data may be generated based on a disease monitoring artificial intelligence model.

[0012] In addition, the user data is preprocessed into user data (disease prediction) and inputted into the disease prediction artificial intelligence model, the user data is preprocessed into user data (disease monitoring) and inputted into the disease monitoring artificial intelligence model, and the user data (disease prediction) and the user data (disease monitoring) may be time series data.

[0013] According to another embodiment of the present invention, a disease management device that performs disease prediction and disease analysis for disease management may be implemented to receive user data and generate user disease management data based on the user data.

[0014] Meanwhile, the disease management data may include disease prediction data for the user or disease monitoring data for the user, and the disease prediction data may be generated based on a disease prediction artificial intelligence model, and the disease monitoring data may be generated based on a disease monitoring artificial intelligence model.

[0015] In addition, the user data is preprocessed into user data (disease prediction) and inputted into the disease prediction artificial intelligence model, the user data is preprocessed into user data (disease monitoring) and inputted into the disease monitoring artificial intelligence model, and the user data (disease prediction) and the user data (disease monitoring) may be time series data.

[0016] According to the present invention, a user's disease can be managed by performing disease prediction and disease monitoring through a disease prediction model and a disease monitoring model based on artificial intelligence.

[0017] In addition, according to the present invention, various artificial intelligence models are trained for disease prediction and disease monitoring, and the most accurate disease prediction and disease monitoring can be performed by replacing the artificial intelligence models for disease prediction and disease monitoring through performance comparison of various artificial intelligence models.

[0018] Figure 1 is a conceptual diagram illustrating a disease management system for disease prediction and disease analysis according to an embodiment of the present invention.

[0019] Figure 2 is a conceptual diagram illustrating the operation of a disease management device according to an embodiment of the present invention.

[0020] Figure 3 is a conceptual diagram illustrating the operation of a disease management device according to an embodiment of the present invention.

[0021] Figure 4 is a conceptual diagram illustrating the operation of a disease management device according to an embodiment of the present invention.

[0022] FIG. 5 is a conceptual diagram illustrating a method for preprocessing user data for disease management and disease monitoring according to an embodiment of the present invention.

[0023] Figure 6 is a conceptual diagram illustrating a method for determining a disease prediction time series unit according to an embodiment of the present invention.

[0024] Figure 7 is a conceptual diagram illustrating a method for determining a disease monitoring time series unit according to an embodiment of the present invention.

[0025] Figure 8 is a conceptual diagram illustrating an artificial intelligence model creation platform for creating an artificial intelligence model according to an embodiment of the present invention.

[0026] The following detailed description of the present invention refers to the accompanying drawings, which illustrate specific embodiments in which the present invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the present invention. It should be understood that the various embodiments of the present invention, while different from each other, are not necessarily mutually exclusive. For example, specific shapes, structures, and characteristics described herein may be modified and implemented from one embodiment to another without departing from the spirit and scope of the present invention. Furthermore, it should be understood that the positions or arrangements of individual components within each embodiment may also be modified without departing from the spirit and scope of the present invention. Accordingly, the following detailed description is not to be taken in a limiting sense, and the scope of the present invention is to be construed to encompass the scope of the claims and all equivalents thereof. Like reference numerals in the drawings represent the same or similar elements throughout the several aspects.

[0027] Hereinafter, various preferred embodiments of the present invention will be described in detail with reference to the attached drawings so that a person having ordinary skill in the art to which the present invention pertains can easily practice the present invention.

[0028]

[0029] Figure 1 is a conceptual diagram illustrating a disease management system for disease prediction and disease analysis according to an embodiment of the present invention.

[0030] In Fig. 1, a disease management system for predicting and analyzing a user's disease based on user data is disclosed.

[0031] Referring to FIG. 1, the disease management system may include a user device (100), a disease management device (120), and an information security device (140).

[0032] The user device (100) can be implemented to generate user data for a prescription for the user and transmit it to the disease management device (120), and receive disease management data adaptively determined according to the user.

[0033] User data may include various data used for disease management for the user. For example, user data may include biomarker data acquired through a user device (100) (e.g., a smartphone, a wearable device), input data separately entered by the user, and data regarding the user's personal information (gender, age, etc.).

[0034] Disease management data may include disease prediction data for the user determined by the disease management device (120), disease monitoring data for the user, etc. The disease management device (120) may transmit the disease management data through the user device (100).

[0035] A disease management device (120) may be implemented to determine user disease management data based on user data. The disease management device (120) may generate disease prediction data, disease monitoring data, etc. for the user through data collection, data processing, and data analysis of the collected user data. The disease management data may be generated based on the disease prediction data, disease monitoring data, etc. for the user.

[0036] The disease management device (120) can generate disease prediction data, disease monitoring data, etc. based on a disease prediction artificial intelligence model and a disease monitoring artificial intelligence model.

[0037] An information security device (140) can be implemented to secure information generated from a user device (100) and a disease management device (120).

[0038]

[0039] Figure 2 is a conceptual diagram illustrating the operation of a disease management device according to an embodiment of the present invention.

[0040] FIG. 2 discloses a method for processing user data in a disease management device to generate user disease management data. In particular, a disease prediction artificial intelligence model for generating disease prediction data is specifically disclosed.

[0041] Referring to Figure 2, the disease management device can receive user data and predict a disease based on the user data, generating disease prediction data. Furthermore, the disease management device can generate disease monitoring data for monitoring the predicted or confirmed disease.

[0042] The disease management device can predict a user's disease based on a disease prediction artificial intelligence model (200). The disease prediction artificial intelligence model (200) can be generated based on learning about user data with a disease.

[0043] The disease prediction AI model (200) can be trained to predict multiple diseases or to predict individual diseases. For example, a single disease prediction AI model for predicting insomnia, eating disorders, dementia, etc., or individual disease prediction AI models (200) for predicting each of insomnia, eating disorders, and dementia, may exist.

[0044] A disease prediction artificial intelligence model (200) can be created based on learning about user data with a disease.

[0045] For example, a disease prediction artificial intelligence model (200) can learn user data necessary for diagnosing a specific disease based on user data of each of multiple users with a specific disease. The disease prediction artificial intelligence model (200) can extract user data patterns associated with a specific disease to predict the disease.

[0046] Hereinafter, a disease prediction method is disclosed assuming a disease prediction artificial intelligence model (200) that performs prediction for a specific disease A.

[0047] First, the disease prediction artificial intelligence model (200) can be trained by extracting default user data related to disease A. The default user data may be user data determined based on existing medical knowledge about disease A. The disease prediction artificial intelligence model (200) can be initially generated based on the default user data.

[0048] Thereafter, in the present invention, a plurality of candidate user data can be generated based on various combinations of user data, and a plurality of candidate disease prediction artificial intelligence models (250) can be generated based on each of the plurality of candidate user data.

[0049] If a specific candidate disease prediction artificial intelligence model (250) among multiple candidate disease prediction artificial intelligence models (250) has higher performance and higher reliability than the disease prediction artificial intelligence model (200), the disease prediction artificial intelligence model (200) is replaced with the specific candidate disease prediction artificial intelligence model (250), the specific candidate disease prediction artificial intelligence model (250) operates as the disease prediction artificial intelligence model (200), and candidate user data corresponding to the candidate disease prediction artificial intelligence model (250) can be set as user data.

[0050] For convenience of explanation, a disease prediction artificial intelligence model (200) that performs a separate prediction for disease A is assumed, but a disease prediction artificial intelligence model (200) that performs prediction for multiple diseases is also possible, and such an embodiment may also be included in the scope of the present invention.

[0051] The disease prediction artificial intelligence model (200) determined in the above manner can generate user disease prediction data based on user data.

[0052]

[0053] Figure 3 is a conceptual diagram illustrating the operation of a disease management device according to an embodiment of the present invention.

[0054] FIG. 3 discloses a method for processing user data in a disease management device to generate user disease management data. Specifically, a disease monitoring AI model is disclosed, which is linked to a disease prediction AI model and monitors user diseases predicted by the linked disease prediction AI model and already confirmed user diseases.

[0055] Referring to FIG. 3, the disease monitoring artificial intelligence model (300) can generate disease monitoring data that monitors the user's disease based on user data (disease monitoring).

[0056] User data (disease monitoring) preprocessed with a disease monitoring artificial intelligence model (300) may be input. The user data (disease monitoring) may be determined differently for each disease by considering the user's disease prediction data and / or the user's disease data.

[0057] The disease monitoring artificial intelligence model (300) can generate disease monitoring data by analyzing user data (disease monitoring) input over time in a time series manner to monitor changes in the user's disease.

[0058] Extracting user data for time-series analysis (disease monitoring) can be determined by considering the amount and characteristics of user data (disease monitoring) for each disease. For example, the degree of change in disease progression may vary over time. While some diseases exhibit rapid recovery, others may take a long time to show any change in progression. Therefore, considering the progression of disease progression, the faster the progression, the shorter the period of analysis and monitoring of user data (disease monitoring).

[0059] In addition, in terms of the amount and characteristics of user data (disease monitoring), the amount of user data (disease monitoring) is relatively large, and the frequency of inputting relatively reliable user data (e.g., actual examination results at a hospital, precise measurement results based on wearable devices) is relatively high, so more accurate analysis is possible, and therefore the monitoring cycle by analyzing user data (disease monitoring) can be relatively shortened.

[0060] The disease monitoring artificial intelligence model (300) can learn changes in the diseases of multiple users by extracting user data (disease monitoring) for each of multiple users with the same disease. For example, if users 1 to N are diagnosed with disease A, the user data (disease monitoring) 1 to user data (disease monitoring) N of each of users 1 to N can be linked to a disease prediction artificial intelligence model and / or an offline hospital's diagnosis results to learn user data (disease monitoring) about changes until the point where the user's disease disappears.

[0061] That is, the disease monitoring artificial intelligence model (300) can learn user data (disease monitoring) on ​​the process of users recovering from a specific disease, monitor the process of users recovering from the disease, and provide the monitoring results as user disease monitoring data.

[0062]

[0063] Figure 4 is a conceptual diagram illustrating the operation of a disease management device according to an embodiment of the present invention.

[0064] In FIG. 4, a disease management device discloses a method for processing user data based on a disease prediction artificial intelligence model and a disease monitoring artificial intelligence model to generate disease prediction data, disease monitoring data, etc. for the user. For convenience of explanation, it is assumed that the disease prediction artificial intelligence model of the disease management device performs predictions for multiple diseases. However, it is also possible for each of the multiple disease prediction artificial intelligence models to predict a separate disease, and such embodiments are also included within the scope of the present invention.

[0065] Referring to Figure 4, when user data is input, the user data may be first preprocessed and divided into user data (disease prediction) for disease prediction. For example, the user data may be preprocessed into user data 1 (disease prediction) to user data n (disease prediction) for prediction of diseases 1 to n.

[0066] In an embodiment of the present invention, screening is performed primarily based on user data, so that predictions can be made only for diseases likely to occur to the user, or only user data (disease predictions) for diseases likely to occur to the user with a threshold probability or higher can be preprocessed and generated.

[0067] User data (disease prediction) can be collected at different time series (or cycles) depending on the disease, enabling disease prediction for the user. For example, user data (disease prediction) for disease A and user data (disease prediction) for disease B are accumulated as data at different cycles and time series, and predictions for the user's diseases A and B can be made using a disease prediction artificial intelligence model (400).

[0068] Additionally, user data can be preprocessed and generated as user data (disease monitoring) to be input into a disease monitoring artificial intelligence model (420).

[0069] User data (disease monitoring) can adaptively change based on disease monitoring results. For example, initially, default data for disease monitoring can be generated as user data (disease monitoring).

[0070] Afterwards, based on the user disease monitoring data, data that does not require additional monitoring and data that requires additional monitoring can be determined, and the user data (disease monitoring) can be adaptively changed based on these determinations.

[0071] In the present invention, if a specific disease is predicted to have a threshold probability or higher through a disease prediction artificial intelligence model (400), user data (disease monitoring) is generated, and disease monitoring can be performed based on a disease monitoring artificial intelligence model (420).

[0072] In addition, for diseases already confirmed through online / offline hospitals, user data (diagnosis monitoring) can be generated directly without going through a separate disease prediction artificial intelligence model (400), and disease monitoring can be performed based on a disease monitoring artificial intelligence model (420).

[0073] When monitoring is performed using a disease monitoring artificial intelligence model (420) based on a disease predicted by a disease prediction artificial intelligence model (400), additional prediction procedures can be performed on the predicted disease. If the probability of a specific disease predicted and monitored based on the disease prediction artificial intelligence model (400) falls below a threshold probability, the specific disease may be excluded from monitoring.

[0074] In the above-described embodiment of the present invention, it is assumed that both disease prediction and disease monitoring are performed in the disease management device. However, it is also possible to perform only disease prediction based on the disease prediction artificial intelligence model (400) or only disease monitoring based on the disease monitoring artificial intelligence model (420), and such embodiments may also be included in the scope of the present invention.

[0075]

[0076] FIG. 5 is a conceptual diagram illustrating a method for preprocessing user data for disease management and disease monitoring according to an embodiment of the present invention.

[0077] In FIG. 5, a method for preprocessing user data for disease management and disease monitoring is disclosed.

[0078] Referring to FIG. 5, user data (500) is separated by disease, and the user data (500) separated by disease is data in a time series, forming time series unit data, which can be used for disease monitoring and disease management.

[0079] When users A, B, and C exist, user data A, user data B, and user data C of users A, B, and C can be collected as time series data. User data (500) can be collected at different cycles considering the possibility of obtaining data for each user, and the types of user data (500) that can be obtained can also be different.

[0080] User data (500) may be divided into sub-user data (disease n) by disease, taking into account the relevance to the disease. For example, if user A has disease 1 and disease 2, user data A may be divided into sub-user data A (disease 1) and sub-user data A (disease 2). If user B has disease 2 and disease 3, user data B may be divided into sub-user data B (disease 2) and sub-user data B (disease 3).

[0081] The lower user data (disease n) (510) can be divided into a disease prediction time series unit (520) for disease prediction and a disease monitoring time series unit (530) for disease monitoring.

[0082] The disease prediction time series unit (520) and the disease monitoring time series unit (530) can be adaptively determined by considering the characteristics of user data (amount of user data, collection cycle of user data, reliability of user data, etc.), disease characteristics (disease treatment speed, whether it is a chronic disease, whether offline treatment linkage is necessary, etc.), disease prediction results, disease monitoring feedback results, etc.

[0083]

[0084] Figure 6 is a conceptual diagram illustrating a method for determining a disease prediction time series unit according to an embodiment of the present invention.

[0085] In FIG. 6, a method for determining a disease prediction time series unit is disclosed.

[0086] Referring to FIG. 6, in order to determine a disease prediction time series unit, the minimum data unit for generating disease prediction results may be determined as a reference disease prediction time series unit (600). The reference disease prediction time series unit (600) may be defined in consideration of disease characteristics. Additionally, the reference disease prediction time series unit (600) may be defined to have a disease prediction probability greater than a threshold probability.

[0087] The characteristics of the reference disease prediction time series unit (600) can be defined based on the sub-user data generation interval, the sub-user data type, and the sub-user data quantity. For example, the reference disease prediction time series unit (600) for predicting migraine can be defined based on the migraine-related sub-user data generation interval, the migraine-related sub-user data type, and the migraine-related sub-user data quantity defined for migraine prediction.

[0088] The reference disease prediction time series unit (600) can be adjusted in consideration of the disease prediction result. In an embodiment of the present invention, the characteristics of the reference disease prediction time series unit (600) can be changed in consideration of the disease prediction result of the disease prediction artificial intelligence model. For example, even if the amount of lower-level user data is relatively reduced or the lower-level user data generation interval is reduced due to an increase in the performance of the disease prediction artificial intelligence model, if a prediction above the critical probability is possible, the amount of lower-level user data to be included in the reference disease prediction time series unit (600) can be changed. That is, the characteristics of the reference disease prediction time series unit (600) can be newly set based on feedback on the disease prediction result of the disease prediction artificial intelligence model.

[0089] The reference disease prediction time series unit (600) may be adjusted in consideration of the characteristics of the user data and determined as the user disease prediction time series unit (620). As the reliability of the user data increases relatively, the amount of lower-level user data of the reference disease prediction time series unit (600) may be set relatively small and the lower-level user data generation interval may be set relatively short, thereby defining the user disease prediction time series unit (620). In addition, as the cycle in which the user data is input becomes relatively short, the lower-level user data generation interval may be set relatively short, thereby defining the user disease prediction time series unit.

[0090]

[0091] Figure 7 is a conceptual diagram illustrating a method for determining a disease monitoring time series unit according to an embodiment of the present invention.

[0092] In FIG. 7, a method for determining a disease monitoring time series unit is disclosed.

[0093] Referring to FIG. 7, to determine a disease monitoring time series unit, the minimum data unit for generating disease monitoring results can be determined as a reference disease monitoring time series unit (700). The reference disease monitoring time series unit (700) can be defined in consideration of disease characteristics. In addition, the reference disease monitoring time series unit (700) can be defined to have disease monitoring performance with an accuracy greater than a critical probability.

[0094] The characteristics of the reference disease monitoring time series unit (700) can be defined based on the sub-user data generation interval, the sub-user data type, and the sub-user data quantity. For example, the reference disease monitoring time series unit (700) for predicting migraine can be defined based on the migraine-related sub-user data generation interval, the migraine-related sub-user data type, and the migraine-related sub-user data quantity defined for migraine prediction.

[0095] The reference disease monitoring time series unit (700) can be adjusted in consideration of the disease monitoring results. In an embodiment of the present invention, the characteristics of the reference disease monitoring time series unit (700) can be changed in consideration of the disease monitoring results of the disease monitoring artificial intelligence model. For example, even if the amount of sub-user data is relatively reduced or the sub-user data generation interval is reduced due to an increase in the performance of the disease monitoring artificial intelligence model, if a prediction above the critical probability is possible, the amount of sub-user data to be included in the reference disease monitoring time series unit (700) can be changed. In other words, the characteristics of the reference disease monitoring time series unit (700) can be newly set based on feedback on the disease monitoring results of the disease monitoring artificial intelligence model.

[0096] The reference disease monitoring time series unit (700) may be adjusted in consideration of the characteristics of the user data and determined as the user disease monitoring time series unit (720). As the reliability of the user data increases relatively, the amount of lower-level user data of the reference disease monitoring time series unit (700) may be set relatively small and the lower-level user data generation interval may be set relatively short, thereby defining the user disease monitoring time series unit (720). In addition, as the cycle in which user data is input becomes relatively short, the lower-level user data generation interval may be set relatively short, thereby defining the user disease monitoring time series unit (720).

[0097]

[0098] Figure 8 is a conceptual diagram illustrating an artificial intelligence model creation platform for creating an artificial intelligence model according to an embodiment of the present invention.

[0099] In Fig. 8, a method for generating an artificial intelligence model, such as a disease prediction artificial intelligence model and a disease monitoring artificial intelligence model, by a user (e.g., a developer) is disclosed.

[0100] Referring to FIG. 8, the artificial intelligence model creation platform may include a database (810), an artificial intelligence model provision unit (820), and a developer workspace (830).

[0101] The database (810) may include training data for training an artificial intelligence model. For example, the database (810) may include user data for training artificial intelligence models, such as disease prediction artificial intelligence models and disease monitoring artificial intelligence models.

[0102] The artificial intelligence model provision unit (820) may be implemented to provide disease prediction artificial intelligence models and disease monitoring artificial intelligence models that are currently used for disease prediction and disease monitoring. The artificial intelligence model provision unit (820) may provide disease prediction artificial intelligence models and disease monitoring artificial intelligence models so that developers can utilize them for updating and additional learning of the artificial intelligence models.

[0103] Although it is expressed as an artificial intelligence model providing unit (820), various modules for disease prediction and disease analysis other than artificial intelligence models can be provided by the artificial intelligence model providing unit (820).

[0104] The developer workspace (830) can be implemented to develop new AI models based on database-based learning data and existing AI models. The developer workspace (830) can be implemented to generate candidate AI models to replace AI models in new disease management devices, or to enable AI learning to create AI models for predicting new diseases.

[0105] According to an embodiment of the present invention, when a keyword for a disease to be developed is input in the developer workspace (830), learning data related to the input disease data is recommended, and information on a target artificial intelligence engine currently being used as an artificial intelligence engine related to the input disease data may be provided.

[0106]

[0107] The embodiments of the present invention described above may be implemented in the form of program commands that can be executed through various computer components and recorded on a computer-readable recording medium. The computer-readable recording medium may include program commands, data files, data structures, etc., either singly or in combination. The program commands recorded on the computer-readable recording medium may be specially designed and configured for the present invention or may be known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and hardware devices specifically configured to store and execute program commands, such as ROMs, RAMs, and flash memories. Examples of program commands include not only machine language codes generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter, etc. Hardware devices may be changed into one or more software modules to perform processing according to the present invention, and vice versa.

[0108] Although the present invention has been described above with specific details such as specific components and limited examples and drawings, these are provided only to help a more general understanding of the present invention, and the present invention is not limited to the above examples, and those with ordinary knowledge in the technical field to which the present invention pertains can make various modifications and changes based on this description.

[0109] Therefore, the idea of ​​the present invention should not be limited to the embodiments described above, and not only the scope of the patent claims described below but also all scopes equivalent to or equivalently modified from the scope of the patent claims are considered to fall within the scope of the idea of ​​the present invention.

Claims

1. Disease prediction and disease analysis methods for disease management, Step of the disease management device receiving user data; and A method characterized in that the disease management device comprises a step of generating user disease management data based on the user data.

2. In paragraph 1, The above disease management data includes disease prediction data for the user or disease monitoring data for the user, The above disease prediction data is generated based on a disease prediction artificial intelligence model, A method characterized in that the above disease monitoring data is generated based on a disease monitoring artificial intelligence model.

3. In paragraph 2, The above user data is preprocessed into user data (disease prediction) and input into the disease prediction artificial intelligence model. The above user data is preprocessed as user data (disease monitoring) and input into the disease monitoring artificial intelligence model. A method characterized in that the above user data (disease prediction) and the above user data (disease monitoring) are time series data.

4. A disease management device that performs disease prediction and disease analysis for disease management, Receive user data, A disease management device characterized in that it is implemented to generate user disease management data based on the above user data.

5. In paragraph 4, The above disease management data includes disease prediction data for the user or disease monitoring data for the user, The above disease prediction data is generated based on a disease prediction artificial intelligence model, A disease management device characterized in that the above disease monitoring data is generated based on a disease monitoring artificial intelligence model.

6. In paragraph 5, The above user data is preprocessed into user data (disease prediction) and input into the disease prediction artificial intelligence model. The above user data is preprocessed as user data (disease monitoring) and input into the disease monitoring artificial intelligence model. A disease management device, characterized in that the user data (disease prediction) and the user data (disease monitoring) are time series data.

Images