System, apparatus, and method for recommending myopia progression inhibition treatment method through vision prediction

Abstract

A method for recommending a myopia progression inhibition treatment method, according to an embodiment of the present invention, may comprise the steps of: obtaining age information of a subject, vision measurement values of the subject, and corneal state measurement values of the subject; obtaining, on the basis of a first learning model, a plurality of vision prediction values corresponding to a plurality of future time points by using the age information of the subject and the vision measurement values of the subject; obtaining, on the basis of a second learning model, a plurality of corneal state prediction values corresponding to the plurality of future time points by using the age information of the subject and the corneal state measurement values of the subject; obtaining a recommended myopia progression inhibition treatment method to be applied to the subject; and obtaining, on the basis of a third learning model, a recommended treatment time point for the recommended myopia progression inhibition treatment method among the plurality of future time points by using the recommended myopia progression inhibition treatment method, the plurality of vision prediction values, and the plurality of corneal state prediction values.

Description

System, device, and method for recommending treatment methods for suppressing myopia progression through visual acuity prediction

[0001] The present invention relates to a system, device, and method for recommending a treatment method for suppressing myopia progression through vision prediction.

[0002] The eyes are a very important element of our human body, and as industry develops, eye health becomes an increasingly important factor in improving the quality and value of life and leading a happy life.

[0003] Vision is significantly affected by age and environment. Factors affecting vision may differ between growing children and adolescents or adults experiencing growth retardation. By developing technologies to predict and address vision changes across different age groups, vision problems can be detected early and appropriate vision protection measures can be provided.

[0004] The present invention aims to provide a system, device and method for predicting future vision of a subject.

[0005] The present invention aims to provide a system, device and method for recommending an appropriate myopia progression suppression treatment method and treatment timing by predicting the future vision of a subject.

[0006] A method for recommending a myopia progression suppression treatment method using a learning model performed by a processor of a device according to an embodiment of the present invention may include: obtaining, through the processor, age information of a subject, a visual acuity measurement value of the subject, and a corneal condition measurement value of the subject; obtaining, through the processor, a plurality of visual acuity prediction values ​​corresponding to a plurality of future time points based on a first learning model using the age information of the subject and the visual acuity measurement value of the subject; obtaining, through the processor, a plurality of corneal condition prediction values ​​corresponding to the plurality of future time points based on a second learning model using the age information of the subject and the corneal condition measurement value of the subject; obtaining, through the processor, a recommended myopia progression suppression treatment method to be applied to the subject from among a plurality of preset myopia progression suppression treatment methods; and obtaining, through the processor, a recommended treatment time point for the recommended myopia progression suppression treatment method from among the plurality of future time points based on a third learning model using the recommended myopia progression suppression treatment method, the plurality of visual acuity prediction values, and the plurality of corneal condition prediction values.

[0007] In one embodiment, the operation of obtaining a recommended myopia progression suppression treatment method to be applied to the subject from among the plurality of preset myopia progression suppression treatment methods may include an operation of obtaining, through the processor, a specific time point for determining the recommended myopia progression suppression treatment method from among the plurality of future time points based on the plurality of visual acuity prediction values, an operation of obtaining, through the processor, a visual acuity prediction value corresponding to the specific time point from among the plurality of visual acuity prediction values ​​and a corneal condition prediction value corresponding to the specific time point from among the plurality of corneal condition prediction values, and an operation of determining the recommended myopia progression suppression treatment method based on the visual acuity prediction value corresponding to the specific time point and the corneal condition prediction value corresponding to the specific time point.

[0008] In one embodiment, the plurality of myopia progression suppression treatment methods may include at least one of DreamLens, atropine treatment, or myopia suppression spectacle treatment.

[0009] In one embodiment, the method for recommending a treatment method for suppressing myopia progression according to one embodiment of the present invention may further include an operation of outputting the plurality of visual acuity prediction values ​​and the plurality of corneal condition prediction values ​​in the form of a graph through a display, and an operation of displaying the recommended treatment time point on the graph.

[0010] A device for recommending a treatment method for suppressing myopia progression according to one embodiment may include at least one processor, a memory storing a first learning model, a second learning model, and a third learning model.

[0011] In one embodiment, the processor may be configured to obtain age information of a subject, a visual acuity measurement value of the subject, and a corneal condition measurement value of the subject, obtain a plurality of visual acuity prediction values ​​corresponding to a plurality of time points in the future based on the first learning model using the age information of the subject and the visual acuity measurement value of the subject, obtain a plurality of corneal condition prediction values ​​corresponding to the plurality of time points in the future based on the second learning model using the age information of the subject and the corneal condition measurement value of the subject, obtain a recommended myopia progression suppression treatment method to be applied to the subject among a plurality of preset myopia progression suppression treatment methods, and obtain a recommended treatment time point for the recommended myopia progression suppression treatment method among the plurality of time points in the future based on a third learning model using the recommended myopia progression suppression treatment method, the plurality of visual acuity prediction values, and the plurality of corneal condition prediction values.

[0012] According to the system, device and method of the present invention, an appropriate myopia progression suppression treatment method can be recommended in advance by predicting the visual acuity of a subject.

[0013] According to the system, device and method of the present invention, it is possible to recommend a treatment time point early according to the predicted future vision of the subject.

[0014] Figure 1 illustrates a future vision prediction system according to one embodiment of the present invention.

[0015] FIG. 2 is a block diagram showing a schematic configuration of a prediction device according to one embodiment of the present invention.

[0016] FIG. 3 is a block diagram showing the configuration of a prediction device according to one embodiment of the present invention.

[0017] FIG. 4 is a schematic flowchart of a learning system for predicting future vision according to one embodiment of the present invention.

[0018] FIG. 5A illustrates a vision prediction module and its operation according to one embodiment.

[0019] FIG. 5b illustrates a corneal condition prediction module and its operation according to one embodiment.

[0020] FIG. 5c illustrates a recommendation module for a treatment method for suppressing myopia progression and its operation according to one embodiment.

[0021] FIG. 5d illustrates a treatment outcome prediction module and its operation according to one embodiment.

[0022] FIG. 5e illustrates a treatment point recommendation module and its operation according to one embodiment.

[0023] Fig. 6 is a flowchart of a future vision prediction method according to one embodiment.

[0024] Fig. 7 is a flowchart of a corneal condition prediction method according to one embodiment.

[0025] Figure 8 is a flowchart of a method for recommending a treatment method for inhibiting myopia progression according to one embodiment.

[0026] Figure 9 is a schematic flowchart of a method for recommending a treatment method for inhibiting myopia progression according to one embodiment of the present invention.

[0027] Figure 10 is a schematic flowchart of a method for recommending a treatment method for inhibiting myopia progression according to one embodiment of the present invention.

[0028] Hereinafter, various embodiments of the present invention will be described with reference to the accompanying drawings. It should be understood that the present invention is not limited to specific embodiments, but rather encompasses various modifications, equivalents, and / or alternatives of the embodiments of the present invention. In connection with the description of the drawings, similar reference numerals may be used for similar components.

[0029] In this document, the expressions “has”, “may have”, “includes”, or “may include” indicate the presence of a feature (e.g., a number, function, operation, or component such as a part), but do not exclude the presence of additional features.

[0030] In this document, the expressions "A or B," "at least one of A and / or B," or "one or more of A and / or B" can include all possible combinations of the listed items. For example, "A or B," "at least one of A and B," or "at least one of A or B" can all refer to cases where (1) at least one A is included, (2) at least one B is included, or (3) at least one A and at least one B are included.

[0031] The terms "first," "second," "first," or "second" used herein may describe various components, regardless of order and / or importance, and are used only to distinguish one component from another, without limiting the components. For example, without departing from the scope of the rights set forth in this document, the first component may be renamed the second component, and similarly, the second component may be renamed the first component.

[0032] The expression "configured to" as used herein can be used interchangeably with, for example, "suitable for", "having the capacity to", "designed to", "adapted to", "made to", or "capable of". The term "configured to" does not necessarily mean "specifically designed to".

[0033] In this document, the words "command", "instruction", "control information", "message", "information", "data", "packet", "data packet", "intent" and / or "signal" transmitted and received between the first electronic device(s) and the second electronic device(s) may include or refer to human-perceivable ideas or specific electrical expressions (e.g., digital codes / analog physical quantities) regardless of their expressions. It will be apparent to those skilled in the art to which the invention disclosed in this document pertains that the exemplary expressions listed above may be interpreted in various ways depending on the context in which they are used. In this document, "is greater than B" not only simply means "is greater than B" but also includes the meaning of "is equal to or greater than B."

[0034] The terms used in this document are used only to describe specific embodiments and may not be intended to limit the scope of other embodiments. The singular expression may include the plural expression unless the context clearly indicates otherwise. Terms used herein, including technical or scientific terms, may have the same meaning as commonly understood by those of ordinary skill in the art described in this document. Terms defined in general dictionaries among the terms used in this document may be interpreted as having the same or similar meaning in the context of the relevant technology, and shall not be interpreted in an idealized or overly formal sense unless explicitly defined in this document. In some cases, even if a term is defined in this document, it cannot be interpreted to exclude the embodiments of this document.

[0035]

[0036] Figure 1 illustrates a future vision prediction system according to one embodiment of the present invention.

[0037] Referring to FIG. 1, the future vision prediction system may include an inspection device (10) and a prediction device (30). However, this is merely an example, and according to another embodiment of the present disclosure, the prediction device (30) may include the inspection device (10) as an internal or external component. In this case, the future vision prediction system may refer to the prediction device (30). Furthermore, the inspection device (10) and / or the prediction device (30) may refer to a plurality of devices.

[0038] In one embodiment, the prediction device (30) can receive visual acuity information from an inspection device (10) connected via a network. However, as described above, the inspection device (10) can be included in the prediction device (30). In this case, the prediction device (30) can also measure visual acuity.

[0039] Additionally, the prediction device (30) can receive corneal condition information from the inspection device (10) connected via a network. However, as described above, the inspection device (10) can be included in the prediction device (30). In this case, the corneal condition can also be measured by the prediction device (30).

[0040] The examination device (10) can measure the visual acuity of the subject and generate visual acuity information. The visual acuity information may include a visual acuity measurement value. The visual acuity information may include, for example, at least one of corneal curvature, ocular refractive power, corneal curvature, pupil size, corneal size, or astigmatism axis as factors affecting visual acuity. Alternatively, the visual acuity information may include information such as the degree of myopia, hyperopia, or astigmatism. The visual acuity information or visual acuity measurement value may be a value expressed in diopters.

[0041] An example of the inspection device (10) may be an auto-refractometer-keratometer (ARK). In this case, the inspection device (10) may be a device used for refraction testing. A refraction test is a test performed when there is a refractive error, accommodation error, or visual acuity abnormality in the eye when looking at a distance or near.

[0042] The examination device (10) can measure the corneal condition of the subject and generate corneal condition information. The corneal condition information can include, for example, at least one of corneal thickness, corneal curvature, or corneal topography. The examination device (10) can include, for example, a device such as a corneal endothelial cell measurement device, an optical coherence tomography (OCT), or a Pantacam. However, the present invention is not limited thereto, and the examination device (10) can be a device that measures corneal thickness, corneal curvature, or corneal topography.

[0043] The prediction device (30) can predict the future vision of the subject by considering the current vision information of the subject and the age information of the subject. The prediction device (30) can predict the future vision according to the age or year of the subject. According to the vision prediction, the information generated can be expressed as a vision prediction value. For example, the vision prediction value can include a prediction value of at least one of corneal curvature, ocular refractive power, corneal curvature, pupil size, corneal size, or astigmatism axis. Alternatively, the vision prediction value can include information such as the degree of myopia, the degree of hyperopia, and the degree of astigmatism. The vision prediction value can also be a value expressed in diopter units.

[0044] The prediction device (30) can predict the future corneal condition based on the current corneal condition information of the subject and the age information of the subject. The prediction device (30) can predict the future corneal condition according to the age or year of the subject. The information generated according to the corneal condition prediction can be expressed as a corneal condition prediction value or corneal condition prediction information. The corneal condition prediction value can include, for example, at least one of corneal thickness, corneal curvature, or corneal topography.

[0045] The prediction device (30) can generate a vision management schedule according to the growth process based on the predicted future vision. The prediction device (30) can recommend a myopia progression suppression treatment method suitable for the subject based on the predicted future vision. The prediction device (30) can also recommend a myopia progression suppression treatment method suitable for the subject based on the future corneal condition. To this end, the prediction device (30) can determine a time point for recommending a suitable myopia progression suppression treatment method. This time point can be expressed as a first time point. Furthermore, the prediction device (30) can also determine a time point for applying the recommended myopia progression suppression treatment method (hereinafter, referred to as a recommended myopia progression suppression treatment method). This time point can be expressed as a recommended treatment time point or a second time point. The vision management schedule can include a recommended myopia progression suppression treatment method and a recommended treatment time point.

[0046] The operation of the prediction device (30) is described in more detail through the drawings below.

[0047] A network refers to a connection structure that enables information exchange between individual nodes, such as terminals and servers, and may include wireless and wired communications. Wireless communications may utilize, for example, at least one of the following cellular communication protocols: LTE, LTE-A, CDMA, WCDMA, UMTS, Wibro, or GSM.

[0048] In addition, the wireless communication may include, for example, short-range communication. The short-range communication may include, for example, at least one of Wi-Fi, Bluetooth, near field communication (NFC), or global positioning system (GPS). The wired communication may include, for example, at least one of universal serial bus (USB), high definition multimedia interface (HDMI), recommended standard 232 (RS-232), or plain old telephone service (POTS). The network (40) may include a telecommunications network, for example, at least one of a computer network (e.g., LAN or WAN), the Internet, or a telephone network.

[0049] Hereinafter, the operation of the prediction device (30) will be specifically described. In addition, the future vision prediction method is described together as a method performed by the prediction device (30) and another device. Each step of the future vision prediction method may be performed by another device, such as the inspection device (10). As another example, some steps of each step of the future vision prediction method may be performed by the prediction device (30), and the remaining steps may be performed by the inspection device (10).

[0050] For example, the prediction device (30) only performs the function of receiving user input as a part of a future vision prediction method, transmitting the received user input to the inspection device (10), and displaying information transmitted from the inspection device (10) on the screen in response to the user input, and the remaining steps of the future vision prediction method may be performed in the inspection device (10).

[0051] In addition, the method for recommending a treatment method for suppressing myopia progression is described together as a method performed by the prediction device (30) and another device. Each step of the method for recommending a treatment method for suppressing myopia progression may be performed by the prediction device (30), as another device. As another example, some steps of each step of the method for recommending a treatment method for suppressing myopia progression may be performed by the prediction device (30), and the remaining steps may be performed by the examination device (10) or a separate device (or server).

[0052] Hereinafter, for convenience of explanation, an example in which a method for predicting future vision and a method for recommending a treatment method for suppressing myopia progression are performed in a prediction device (30) will be mainly described. The method for recommending a treatment method for suppressing myopia progression may also be used as a concept encompassing a method for recommending a treatment timing below.

[0053]

[0054] Figure 2 is a block diagram showing the configuration of a device according to one embodiment of the present invention.

[0055] As illustrated in FIG. 2, a device (150) according to one embodiment of the present invention (e.g., the inspection device (10) or the prediction device (30) of FIG. 1) may include a bus (210), a display (220), a communication circuit (230), a database (240), a memory (250), an input / output (I / O) interface (260), and a processor (270). In other embodiments, the device (150) may omit at least one of the above components or may additionally include other components.

[0056] For reference, the components (210, 220, 230, 240, 250, 260, 270) of the device (150) illustrated in FIG. 2 are merely exemplary components for explaining a health care method according to an embodiment of the present invention. That is, it is clear that the device (150) according to an embodiment of the present invention may additionally include other components in addition to the illustrated components.

[0057] The bus (210) can electrically connect the components (220 to 270) to each other. The bus (210) can include circuitry for communication (e.g., control messages and / or data) between the components (220 to 270).

[0058] The display (220) can display text, images, videos, icons, or symbols that constitute various contents. The display (220) can include a touch screen and can receive touch, gesture, proximity, or hovering input using an electronic pen or a part of the subject's body.

[0059] For example, the display (220) may include a liquid crystal display (LCD), a light emitting diode (LED) display, an organic light emitting diode (OLED) display, a microelectromechanical systems (MEMS) display, or an electronic paper display. The display (220) may be implemented as included in the device (150), or may be implemented separately from the device (150) but operatively connected to the device (150).

[0060] The communication circuit (230) can establish a communication channel between the device (150) and external devices. The communication circuit (230) can access a network (280) via wireless or wired communication to communicate with the external devices. In one embodiment, the communication circuit (230) may include a circuit for forming a wide area network connection or peer-to-peer connection, such as a Wi-Fi, Bluetooth, and / or cellular communication circuit.

[0061] The database (240) may be implemented on the memory (250) or on a separate storage medium. The database (240) may store all of the contents and details of data transmitted and received with an external device. The data stored in the database (240) may be regularly updated according to a predetermined cycle.

[0062] According to an embodiment of the present invention, information related to parameters and objects may be stored in the database (240). Specifically, the database (240) may store associations between information related to parameters and objects.

[0063] According to one embodiment, the database (240) may store learning models according to various embodiments of the present invention. For example, the database (240) may store learning models for extracting objects and / or information associated with objects from images (e.g., the learning models of FIGS. 5A to 5E).

[0064] According to various embodiments, the data stored in the database (240) may be sensitive information about the subject and may be distributed and stored on a blockchain network to enhance security regarding the use of such information. When the database (240) is distributed and stored on a blockchain network, the history of transmission, modification, deletion, and addition of information contained in the database (240) can be more securely managed on the blockchain network.

[0065] The memory (250) may include volatile and / or non-volatile memory. The memory (250) may store instructions or data related to at least one other component of the device (150). For example, the memory (250) may store instructions that, when executed, cause the processor (270) to perform various operations described herein. For example, the instructions may be included in a package file of an application program.

[0066] The I / O interface (260) can perform a role of transmitting commands or data input from a user or another external device to other components of the device (150). The I / O interface (260) can be implemented in hardware or software, and can be used as a concept encompassing a user interface (UI) and a terminal for communication with other external devices.

[0067] The processor (270) may include at least one of a central processing unit (CPU), an application processor (AP), or a communication processor (CP). The processor (270) is electrically connected to the memory (250), the display (220), and the communication circuit (230) via the bus (210), and during operation, may execute operations or data processing related to control and / or communication of other components according to commands, programs, or software stored in the memory (250). Therefore, the execution of the commands, application programs, or software may be understood as the operation of the processor (270).

[0068] The network (280) may include at least one of a telecommunications network, a computer network, the Internet, or a telephone network. A wireless communication protocol for accessing the network (280) may use, for example, at least one of LTE (Long-Term Evolution), LTE-A (LTE Advanced), CDMA (Code Division Multiple Access), WCDMA (Wideband CDMA), UMTS (Universal Mobile Telecommunications System), WiBro (Wireless Broadband), GSM (Global System for Mobile communications), or 5G standard communication protocols. However, this is merely exemplary, and various wired and wireless communication technologies applicable in the relevant technical field may be utilized depending on the embodiment to which the present invention is applied.

[0069] According to one embodiment, a method for recommending a myopia progression suppression treatment method using a learning model performed by a processor (270) according to various embodiments of the present invention may include an operation of obtaining, through the processor (270), age information of a subject, a visual acuity measurement value of the subject, and a corneal condition measurement value of the subject, an operation of obtaining, based on a first learning model using the age information of the subject and the visual acuity measurement value of the subject, a plurality of visual acuity prediction values ​​corresponding to a plurality of future time points, an operation of obtaining, based on a second learning model using the age information of the subject and the corneal condition measurement value of the subject, a plurality of corneal condition prediction values ​​corresponding to the plurality of future time points, an operation of obtaining a recommended myopia progression suppression treatment method to be applied to the subject from among a plurality of preset myopia progression suppression treatment methods, and an operation of obtaining a recommended treatment time point for the recommended myopia progression suppression treatment method from among the plurality of future time points based on a third learning model using the recommended myopia progression suppression treatment method, the plurality of visual acuity prediction values, and the plurality of corneal condition prediction values.

[0070] In one embodiment, the operation of obtaining a recommended myopia progression suppression treatment method to be applied to the subject from among the plurality of preset myopia progression suppression treatment methods may include, through the processor (270), an operation of obtaining a specific time point for determining the recommended myopia progression suppression treatment method from among the plurality of future time points based on the plurality of visual acuity prediction values, an operation of obtaining a visual acuity prediction value corresponding to the specific time point from among the plurality of visual acuity prediction values ​​and a corneal state prediction value corresponding to the specific time point from among the plurality of corneal state prediction values, and an operation of determining the recommended myopia progression suppression treatment method based on the visual acuity prediction value corresponding to the specific time point and the corneal state prediction value corresponding to the specific time point.

[0071] In one embodiment, the plurality of myopia progression suppression treatment methods may include at least one of DreamLens, atropine treatment, or myopia suppression spectacle treatment.

[0072] In one embodiment, the method for recommending a treatment method for suppressing myopia progression according to one embodiment of the present invention may further include an operation of outputting the plurality of visual acuity prediction values ​​and the plurality of corneal condition prediction values ​​in the form of a graph through a display via the processor (270), and an operation of displaying the recommended treatment time point on the graph.

[0073] A device for recommending a treatment method for suppressing myopia progression according to one embodiment may include at least one processor (270), a memory storing a first learning model, a second learning model, and a third learning model.

[0074] In one embodiment, the processor (270) may be configured to obtain age information of a subject, a visual acuity measurement value of the subject, and a corneal condition measurement value of the subject, obtain a plurality of visual acuity prediction values ​​corresponding to a plurality of time points in the future based on the first learning model using the age information of the subject and the visual acuity measurement value of the subject, obtain a plurality of corneal condition prediction values ​​corresponding to the plurality of time points in the future based on the second learning model using the age information of the subject and the corneal condition measurement value of the subject, obtain a recommended myopia progression suppression treatment method to be applied to the subject among a plurality of preset myopia progression suppression treatment methods, and obtain a recommended treatment time point for the recommended myopia progression suppression treatment method among the plurality of time points in the future based on a third learning model using the recommended myopia progression suppression treatment method, the plurality of visual acuity prediction values, and the plurality of corneal condition prediction values.

[0075]

[0076] FIG. 3 is a block diagram showing the configuration of a prediction device according to one embodiment of the present invention.

[0077] Referring to FIG. 3, the prediction device (30) may include at least some of an input unit (31), a vision prediction unit (32), a corneal condition prediction unit (33), a myopia progression suppression treatment method recommendation unit (34), a treatment timing recommendation unit (35), or a display unit (36).

[0078] For example, referring to FIG. 3, the input unit (31) can receive information about the subject through a user interface. The input unit (31) can receive age information about the subject through the user interface. When the subject's age information (e.g., date of birth) is entered, the age can be automatically calculated by calculating it with the current (today's) date. The subject's age is not applied in units of months, and the full age can be applied in units of years, but is not limited thereto.

[0079] The input unit (31) can receive personal information (e.g., date of birth, name) of the subject through a user interface. The input unit (31) can receive information on visual acuity influencing factors through a user interface. Information on visual acuity influencing factors may include genetic factors, biological factors, environmental factors, and therapeutic factors.

[0080] The input unit (31) can receive the subject's visual acuity information through a user interface. In this case, the visual acuity information may include at least one of the subject's corneal curvature, ocular refractive power, corneal curvature, pupil size, corneal size, or astigmatism axis. Alternatively, the visual acuity information may include myopia, astigmatism, and emmetropia information.

[0081] The input unit (31) can receive corneal condition information of the subject through a user interface. In this case, the corneal condition information may include at least one of the corneal thickness, corneal curvature, or corneal topography of the subject.

[0082] When entering the subject's vision information or corneal condition information, the subject or administrator may enter information separately for the subject's right and left eyes.

[0083] For example, the user interface may be a touch interface or a hardware (e.g., button) interface included in the vision measurement device. In addition, the user interface may be a device or an interface thereof that is linked to the prediction device (30) via a network, for example, a smartphone, a smart pad, a tablet PC, a wearable device, etc., and all kinds of wireless communication devices such as a PCS (Personal Communication System), a GSM (Global System for Mobile communication), a PDC (Personal Digital Cellular), a PHS (Personal Handyphone System), a PDA (Personal Digital Assistant), an IMT (International Mobile Telecommunication)-2000, a CDMA (Code Division Multiple Access)-2000, a W-CDMA (W-Code Division Multiple Access), a Wibro (Wireless Broadband Internet) terminal, and a desktop computer, a smart TV, or a software or hardware interface thereof.

[0084] A receiving unit (not shown) can receive vision information from an inspection device (10). The receiving unit can receive vision information from an inspection device (10) connected via a network.

[0085] Referring to FIG. 3, the vision prediction unit (32) can predict the future vision of the subject. The vision prediction unit (32) can predict the vision of the subject at a specific point in the future. The vision predicted by the vision prediction unit (32) can be referred to as a vision prediction value.

[0086] According to one embodiment, the vision prediction unit (32) can predict the vision of the subject at each of a plurality of future specific points in time. The vision prediction unit (32) can obtain a vision prediction value of the subject at each of a plurality of future specific points in time using at least the acquired vision information. In other words, it can obtain a plurality of vision prediction values ​​of the subject at a plurality of future points in time.

[0087] According to one embodiment, the vision prediction unit (33) can obtain a vision prediction value of the subject based on a learning model (e.g., the vision prediction model (511) of FIG. 5A) that uses at least the acquired vision measurement value as input data. The vision prediction unit (33) can include a vision prediction module (e.g., the vision prediction module (510)).

[0088] According to one embodiment, the vision prediction unit (33) can predict the vision value of the subject at multiple specific points in the future in units of age or years. For example, if the prediction device (30) is set to predict the vision up to the age of 100 in the future and the current age of the subject is 10, the plurality of specific points in the future can predict the vision of the subject at 90 points corresponding to the ages of 11 to 100. In this case, the output vision values ​​can also correspond to 90 points. The current vision measurement value is the current level of vision at the time of measurement, and the future vision prediction value is the level of vision at a specific point in the future.

[0089] A change prediction unit (not shown) can predict the rate of change of the current visual acuity measurement value and the future visual acuity prediction value based on visual acuity information. The change prediction unit (not shown) can predict the rate of change based on the current visual acuity measurement value, the future visual acuity prediction value, and the difference between the second time point and the first time point. The first time point may be a time point relatively earlier than the second time point. For example, if the first time point is the user's current age (e.g., 8 years old), the second time point may be a time point that is older than the current age (e.g., 9 to 20 years old).

[0090] The corneal condition prediction unit (33) can predict the future corneal condition of the subject. The corneal condition prediction unit (33) can predict the corneal condition of the subject at multiple specific future points in time. Each of the multiple specific future points in time can correspond to the multiple specific future points in time of the corneal condition prediction unit (33).

[0091] The corneal condition prediction unit (33) can obtain a corneal condition prediction value of the subject at each of a plurality of future specific points in time. According to one embodiment, the corneal condition prediction unit (33) can obtain a corneal condition prediction value of the subject at each of a plurality of future specific points in time using at least the obtained current corneal condition information. The corneal condition prediction unit (33) can obtain a corneal condition prediction value of the subject based on a learning model (e.g., the corneal condition prediction model (521) of FIG. 5b) that uses the obtained corneal condition information as input data. A plurality of corneal condition prediction values ​​at a plurality of future points in time can be obtained.

[0092] According to one embodiment, the corneal condition prediction unit (34) can predict the corneal condition of the subject at multiple specific points in the future in units of age or years. For example, if the prediction device (30) is set to predict the corneal condition up to the age of 100 in the future and the subject's current age is 10, the corneal condition values ​​of the subject at 90 points in the future corresponding to the ages of 11 to 100 can be predicted as the multiple specific points in the future.

[0093] The myopia progression suppression treatment method management unit (not shown) can determine whether the subject requires the myopia progression suppression treatment method based on at least one of the future visual acuity prediction value or the future corneal condition prediction value.

[0094] For example, a myopia progression suppression treatment method management unit (not shown) can determine whether the future visual acuity prediction value satisfies a predetermined standard. If the future visual acuity prediction value satisfies the predetermined standard, the myopia progression suppression treatment method management unit (not shown) can determine that the procedure is necessary, and if the future visual acuity prediction value does not satisfy the predetermined standard, the procedure is not necessary.

[0095] The myopia progression suppression treatment method recommendation unit (34) can recommend a myopia progression suppression treatment method based on the visual acuity prediction value at multiple future points in time and the corneal condition prediction value at multiple future points in time. Alternatively, the myopia progression suppression treatment method recommendation unit (34) can recommend a myopia progression suppression treatment method type based on the visual acuity prediction value at a specific point in time and the corneal condition prediction value at a specific point in time. The myopia progression suppression treatment method recommendation unit (34) can recommend a myopia progression suppression treatment method type suitable for the subject based on a learning model (e.g., the myopia progression suppression treatment method recommendation model (531) of FIG. 5c).

[0096] The treatment time recommendation unit (35) can recommend a suitable treatment time point for applying the recommended myopia progression suppression treatment method to the subject based on the visual acuity prediction value at multiple future time points, the corneal condition prediction value at multiple future time points, and the recommended myopia progression suppression treatment method (or myopia progression suppression treatment method type) obtained from the myopia progression suppression treatment method recommendation unit (34).

[0097] The display unit (36) can display the current visual acuity measurement value and the future visual acuity prediction value through a display device. The display unit (36) can be, for example, a display device such as a user interface. In addition, the display device can be a display device included inside or outside the prediction device (30) or the inspection device (10). The prediction device (30) can output the visual acuity prediction values ​​of the subject at multiple specific points in the future in the form of a graph through the display unit (36). The prediction device (30) can output the corneal condition of the subject at multiple specific points in the future in the form of a graph through the display unit (36). The user can directly check the change in the visual acuity value or the change in the corneal condition according to the future growth process of the subject through the graph. The graph can include, for example, an age axis and a visual acuity axis, and can indicate the visual acuity prediction value according to age.

[0098]

[0099] FIG. 4 is a schematic flowchart of a learning system for predicting future vision according to one embodiment of the present invention.

[0100] Referring to FIG. 4, the system for recommending a treatment method for suppressing myopia progression according to one embodiment may further include a learning device (50). The learning device (50) may learn or generate a learning model related to vision prediction and myopia progression suppression treatment method recommendation based on learning data. The learning device (50) and the prediction device (10) may be separate devices, as illustrated in FIG. 4, or may be implemented as a single device.

[0101] The learning model related to predicting vision and recommending a treatment method to suppress myopia progression can be learned and / or implemented as an artificial intelligence model or algorithm. For example, the learning model related to predicting vision and recommending a treatment method to suppress myopia progression can be learned through various machine learning or deep learning models or algorithms such as a classification algorithm, a regression algorithm, supervised learning, unsupervised learning, reinforcement learning, a support vector machine, a decision tree, a random forest, LASSO, AdaBoost, XGBoost, an artificial neural network, etc. The learning model learned through the learning step can be stored in the prediction device (30). In the learning device (50), a plurality of learning models can be stored in the prediction device (30).

[0102] Parameters constituting a learning model can be acquired through learning in a learning device (50). The parameters can be changed through learning in the learning device (50), and the output results of the learning model can vary depending on the parameters. The parameters associated with the learning model can be stored in the prediction device (30). In the following, a plurality of learning models may be learning models each having different parameters.

[0103] The prediction device (30) can acquire input data and provide output data based on a learning model. The input data can include subject-related data. For example, it can include examination data of the subject. The prediction device (30) can output future vision prediction results, future corneal condition prediction results, myopia progression suppression treatment method recommendation results, and recommended treatment timing based on a learning model that inputs examination data.

[0104] At least some of the multiple learning models may be trained on the same learning device. For example, the vision prediction model and corneal condition prediction model of FIGS. 5A and 5B may be run on the same prediction device. Alternatively, at least some of the multiple learning models may be run on different prediction devices.

[0105] The multiple learning models may include a vision prediction model (511), a corneal condition prediction model (521), a myopia progression suppression treatment method recommendation model (531), a treatment outcome prediction model (541), or a treatment timing recommendation model (551) as illustrated in FIGS. 5a to 5d.

[0106]

[0107] FIG. 5A illustrates a vision prediction module and its operation according to one embodiment.

[0108] According to one embodiment, the vision prediction module (510) may be implemented by a processor (e.g., processor (270) of FIG. 2) of a prediction device (e.g., prediction device (30) of FIG. 1) or an inspection device (e.g., inspection device (10) of FIG. 1).

[0109] According to one embodiment, the vision prediction module (510) can predict the future vision of a subject based on input data. The future vision of the subject can be predicted based on a vision prediction model (511) using the input data of the vision prediction module (510). The output data of the vision prediction module (510) can include a vision prediction value. Hereinafter, for convenience of explanation, the input data of the vision prediction module (510) will be referred to as first input data, and the output data will be referred to as first output data.

[0110] According to one embodiment, the vision prediction module (510) may include a vision prediction model (511). The vision prediction model (511) may be a learning model trained to output a vision prediction value according to the age or year of the subject based on first input data.

[0111] The vision prediction model (511) may be learned based on information about multiple past subjects and age-specific vision information for each of the multiple past subjects. The information about the multiple past subjects may include age information for the multiple past subjects. The age-specific vision information for the multiple past subjects may include age-specific vision measurement values ​​for each of the multiple past subjects.

[0112] According to one embodiment, the vision prediction model (511) may be pre-trained on a different device or pre-trained on the same device based on the first input data before being deployed on the prediction device or the inspection device.

[0113] The first input data may include the subject's current age information at the time of the vision measurement and the subject's vision measurement value at the time of the vision measurement.

[0114] The first input data may further include examination data at the time of measurement. The examination data may include examination data obtained from an ocular measurement device for the subject. Furthermore, the examination data may include various types of parameters as multiple examination data. For example, the examination data may include at least one of the following data: the subject's Spherical Equivalent (SE), Mean Keratometry (Km), pupil size, Intraocular Pressure (IOP), White-to-White (WHW), and Central Corneal Thickness (CCT).

[0115] In one embodiment, the examination data may include questionnaire data. Specifically, it may include data such as the subject's gender. The examination data may include the subject's medical records. For example, the examination data may include data on the prescription of glasses worn in the past.

[0116] The examination data may include measurement data about the cornea. For example, it may include corneal shape, corneal symmetry, corneal thickness measurement data, corneal structural tomography data, corneal topography data, corneal refraction, and corneal endothelial cell examination data.

[0117] The examination data may include measurement data regarding distances within the eye, etc. Specifically, it may include pupil size, eye length, and the distance of the space where the lens will be inserted.

[0118] The examination data may include data on ocular diseases and / or underlying conditions. For example, it may include data on the presence or absence of retinal diseases, such as glaucoma and retinal degeneration, cataracts, and diseases of the posterior surface of the iris.

[0119] In addition, input data can include various types of data. For example, it can include test data such as eye-related genes and blood tests.

[0120] The first output data may include a predicted visual acuity value of the subject at a time point after the time point of the visual acuity measurement. The first output data may include a predicted visual acuity value of the subject at multiple time points in the future. That is, the first output data may include a predicted visual acuity value according to the subject's age. The first output data may include a predicted visual acuity value according to the subject's age after the time point of the visual acuity measurement.

[0121]

[0122] FIG. 5b illustrates a corneal condition prediction module and its operation according to one embodiment.

[0123] According to one embodiment, the corneal condition prediction module (520) may be implemented by a processor (e.g., processor (270) of FIG. 2) of a prediction device (e.g., prediction device (30) of FIG. 1) or an inspection device (e.g., inspection device (10) of FIG. 1).

[0124] The corneal condition prediction module (520) can predict the future corneal condition of the subject based on input data. When the corneal condition prediction module (520) obtains input data, it can predict the future corneal condition of the subject based on a corneal condition prediction model (521) using the input data. The output data of the corneal condition prediction module (520) may include a corneal condition prediction value. Hereinafter, for convenience of explanation, the input data of the corneal condition prediction module (520) is referred to as second input data, and the output data is referred to as second output data.

[0125] According to one embodiment, the corneal condition prediction module (520) may include a corneal condition prediction model (521). The corneal condition prediction model (521) may be a learning model trained to output a corneal condition prediction value according to the age or year of the subject based on second input data.

[0126] The corneal condition prediction model (521) may be learned based on information of a plurality of past subjects and corneal condition information by age of each of the plurality of past subjects. The information of the plurality of past subjects may include age information of the plurality of subjects. The corneal condition information by age of each of the plurality of past subjects may include corneal condition measurement values ​​by age of each of the plurality of subjects. For example, it may include at least one of corneal thickness, corneal curvature, or corneal topography by age of each of the plurality of subjects.

[0127] In one embodiment, the corneal condition prediction model (521) may be pre-trained on a different device or pre-trained on the same device based on the second input data before being deployed on the prediction device or the inspection device.

[0128] The second input data may include the subject's current age information at the time of corneal condition measurement and the corneal condition measurement value of the subject at the time of corneal condition measurement. The corneal condition measurement time may be substantially the same time as the visual acuity measurement time. The corneal condition measurement value may include at least one of corneal thickness, corneal curvature, or corneal topography.

[0129] The second input data may further include examination data at the time of measurement. The examination data may include examination data obtained from an ocular measurement device for the subject. Furthermore, the examination data may include various types of parameters as multiple examination data. For example, the examination data may include at least one of the following data: the subject's Spherical Equivalent (SE), Mean Keratometry (Km), pupil size, Intraocular Pressure (IOP), White-to-White (WHW), and Central Corneal Thickness (CCT).

[0130] In one embodiment, the examination data may include questionnaire data. Specifically, it may include data such as the subject's gender. The examination data may include the subject's medical records. For example, the examination data may include data on the prescription of glasses worn in the past.

[0131] The examination data may include measurement data about the cornea. For example, it may include corneal shape, corneal symmetry, corneal structural tomography data, corneal topography data, corneal refraction, and corneal endothelial cell examination data.

[0132] The examination data may include measurement data regarding distances within the eye, etc. Specifically, it may include pupil size, eye length, and the distance of the space where the lens will be inserted.

[0133] The examination data may include data on ocular diseases and / or underlying conditions. For example, it may include data on the presence or absence of retinal diseases, such as glaucoma and retinal degeneration, cataracts, and diseases of the posterior surface of the iris.

[0134] The second output data may include a corneal condition prediction value of the subject at a time point after the corneal condition measurement time point. The second output data may include a corneal condition prediction value of the subject at multiple time points in the future. That is, the second output data may include a corneal condition prediction value according to the age of the subject. The second output data may include a corneal condition prediction value according to the age of the subject at a time point after the corneal condition measurement time point. The corneal condition prediction value may include at least one of corneal thickness, corneal curvature, corneal thickness, or corneal topography.

[0135] In Fig. 5b, a learning model for predicting the corneal condition at multiple future points in time is described, but the corneal condition prediction model may also be set to predict the corneal condition at any one specific point in time.

[0136]

[0137] FIG. 5c illustrates a recommendation module for a treatment method for suppressing myopia progression and its operation according to one embodiment.

[0138] According to one embodiment, the myopia progression suppression treatment method recommendation module (530) may be implemented by a processor (e.g., processor (270) of FIG. 2) of a prediction device (e.g., prediction device (30) of FIG. 1) or an inspection device (e.g., inspection device (10) of FIG. 1).

[0139] According to one embodiment, the myopia progression suppression treatment method recommendation module (530) may recommend a treatment type suitable for a subject based on input data. The myopia progression suppression treatment method recommendation module (530) may recommend a myopia progression suppression treatment method type suitable for application to a subject based on a myopia progression suppression treatment method recommendation model (531) using the input data. The output data of the myopia progression suppression treatment method recommendation model (531) may include myopia progression suppression treatment method recommendation information. Hereinafter, for convenience of explanation, the input data of the myopia progression suppression treatment method recommendation module (530) is referred to as third input data, and the output data is referred to as third output data.

[0140] According to one embodiment, the myopia progression suppression treatment method recommendation module (530) may include a myopia progression suppression treatment method recommendation model (531). The myopia progression suppression treatment method recommendation model (531) may be a learning model trained to output a recommended myopia progression suppression treatment method suitable for a subject based on third input data.

[0141] The model (531) for recommending a treatment method for suppressing myopia progression may be learned based on the visual acuity measurements and corneal condition measurements of each of the multiple subjects in the past, and the treatment method and treatment results for suppressing myopia progression applied to each of the multiple subjects in the past.

[0142] In one embodiment, the myopia progression suppression treatment method recommendation model (531) may be pre-trained on a different device or pre-trained on the same device based on third input data before being deployed on the prediction device or the testing device.

[0143] The third input data may include a visual acuity prediction value and a corneal condition prediction value of the subject at a specific point in time among the plurality of points in time.

[0144] The third input data may further include examination data at the time of measurement. The examination data may include examination data obtained from an ocular measurement device for the subject. Furthermore, the examination data may include various types of parameters as multiple examination data. For example, the examination data may include at least one of the following data: the subject's Spherical Equivalent (SE), Mean Keratometry (Km), pupil size, Intraocular Pressure (IOP), White-to-White (WHW), and Central Corneal Thickness (CCT).

[0145] In one embodiment, the examination data may include questionnaire data. Specifically, it may include data such as the subject's gender. The examination data may include the subject's medical records. For example, the examination data may include data on the prescription of glasses worn in the past.

[0146] The examination data may include measurement data about the cornea. For example, it may include corneal shape, corneal symmetry, corneal thickness measurement data, corneal structural tomography data, corneal topography data, corneal refraction, and corneal endothelial cell examination data.

[0147] The examination data may include measurement data regarding distances within the eye, etc. Specifically, it may include pupil size, eye length, and the distance of the space where the lens will be inserted.

[0148] The examination data may include data on ocular diseases and / or underlying conditions. For example, it may include data on the presence or absence of retinal diseases, such as glaucoma and retinal degeneration, cataracts, and diseases of the posterior surface of the iris.

[0149] The third output data may include information on recommending a myopia progression suppression treatment method suitable for the subject at the specific point in time. The myopia progression suppression treatment method recommendation information may indicate the type of myopia progression suppression treatment method. The specific point in time may be a specific point in time after the visual acuity or corneal condition measurement.

[0150] The specific point in time may be at least one of a plurality of future points in time, as illustrated in FIGS. 5A and 5B . The specific point in time may be a point in time at which a myopia progression suppression treatment method is determined to be necessary, as determined by a prediction device or a testing device based on the output results of the learning model illustrated in FIGS. 5A and 5B . In the following examples, the point in time at which a myopia progression suppression treatment method is determined to be necessary may be referred to as a first point in time or a type determination point in time.

[0151] The specific point in time may be, for example, a point in time determined by a vision prediction value at multiple future points in time and a corneal condition prediction value at multiple future points in time derived from FIGS. 5A and 5B.

[0152]

[0153] FIG. 5d illustrates a treatment outcome prediction module and its operation according to one embodiment.

[0154] According to one embodiment, the treatment outcome prediction module (540) may be implemented by a processor (e.g., processor (270) of FIG. 2) of a prediction device (e.g., prediction device (30) of FIG. 1) or an inspection device (e.g., inspection device (10) of FIG. 1).

[0155] According to one embodiment, the treatment outcome prediction module (540) can predict the treatment outcome when a specific myopia progression suppression treatment method is administered to a subject. The treatment outcome prediction module (540) can predict the treatment outcome for the subject based on a treatment outcome prediction model using input data. For example, the treatment outcome prediction module (540) can predict the treatment outcome of the subject according to the age of the subject for the input myopia progression suppression treatment method. The treatment outcome prediction module (540) can predict the treatment outcome of the subject according to the age of the subject at multiple future time points based on the predicted values ​​according to FIGS. 5A and 5B.

[0156] The output data of the treatment outcome prediction module (540) may include the treatment outcomes of the subject at multiple future time points for the specific myopia progression suppression treatment method. Accordingly, the treatment outcome prediction module (540) may output a number of treatment outcomes corresponding to multiple future time points. Hereinafter, for convenience of explanation, the input data of the treatment outcome prediction module (540) will be referred to as the fourth input data, and the output data will be referred to as the fourth output data.

[0157] In one embodiment, the treatment outcome prediction module (540) may include a treatment outcome prediction model. The treatment outcome prediction model may be a model trained to output age-specific predicted treatment outcomes for a subject based on the fourth input data.

[0158] The treatment outcome prediction model may be learned based on at least the myopia progression suppression treatment method applied to each of the multiple subjects in the past, the visual acuity measurements and corneal measurements of each of the multiple subjects in the past before the myopia progression suppression treatment method was applied, and the visual acuity measurements of each of the multiple subjects in the past after the myopia progression suppression treatment method was applied.

[0159] The fourth input data may include a specific type of myopia progression suppression treatment method, a predicted value for the subject's corneal condition, and a predicted value for the subject's visual acuity. Specifically, the fourth input data may include a predicted value for the subject's visual acuity at multiple future time points and a predicted value for the subject's corneal condition at multiple future time points.

[0160] The fourth output data may include predicted treatment results of the subject at multiple future time points. The predicted treatment results may include predicted corrected visual acuity values ​​at each of the multiple future time points. The predicted treatment results may further include predicted corneal conditions after correction at each of the multiple future time points. The fourth output data may include a matching relationship between the multiple future time points and the predicted values. The predicted corneal conditions after correction may include at least one of corneal thickness, corneal curvature, or corneal topography.

[0161] In one embodiment, the prediction device or the testing device may output a recommended treatment time point based on the output predicted treatment result. The prediction device or the testing device may determine the recommended treatment time point based at least on the predicted corrected visual acuity value. For example, the prediction device or the testing device may determine the time point with the best predicted corrected visual acuity value as the recommended treatment time point. Alternatively, the prediction device or the testing device may determine and output multiple recommended treatment time points based on the output predicted treatment result. The recommended treatment time point may be referred to as the second time point in the following embodiments.

[0162]

[0163] FIG. 5e illustrates a treatment point recommendation module and its operation according to one embodiment.

[0164] According to one embodiment, the treatment timing recommendation module (550) can recommend a suitable time to administer a specific myopia progression suppression treatment method to a subject. The treatment timing recommendation module (550) can predict a suitable treatment time to apply the input myopia progression suppression treatment method to a subject based on a treatment timing recommendation model (551) using input data. The output data of the treatment timing recommendation module (550) can include the recommended treatment time. Hereinafter, for convenience of explanation, the input data of the treatment timing recommendation module (550) is referred to as fifth input data, and the output data is referred to as fifth output data.

[0165] In one embodiment, the treatment timing recommendation module (550) may include a treatment outcome prediction model (551). The treatment timing recommendation model (551) may be a learning model trained to output a recommended treatment timing suitable for applying a specific myopia progression suppression treatment method to a subject based on the fifth input data.

[0166] The treatment timing recommendation model (551) may be learned based on at least the myopia progression suppression treatment method applied to each of the plurality of subjects in the past, the time of application of the myopia progression suppression treatment method, the visual acuity measurement value and corneal measurement value of each of the plurality of subjects in the past before the myopia progression suppression treatment method was applied, and the visual acuity measurement value of each of the plurality of subjects in the past after the myopia progression suppression treatment method was applied.

[0167] The fifth input data may include a specific type of myopia progression suppression treatment method, a predicted value for the subject's corneal condition, and a predicted value for the subject's visual acuity. Specifically, the fifth input data may include a predicted value for the subject's visual acuity at multiple future time points and a predicted value for the subject's corneal condition at multiple future time points.

[0168] The fifth output data may include a recommended treatment time point suitable for applying the type of myopia progression suppression treatment method included in the input data. The recommended treatment time point may be any one of multiple future time points described in FIGS. 5A and 5B . The recommended treatment time point may be a different time point from the type determination time point (or first time point) of FIG. 5C . The recommended treatment time point may be referred to as a second time point in the following examples.

[0169]

[0170] Fig. 6 is a flowchart of a future vision prediction method according to one embodiment.

[0171] Referring to Figure 6, future vision can be predicted based on the measured current vision.

[0172] The method illustrated in FIG. 6 is performed by a prediction device (e.g., prediction device (20)) described through the preceding FIGS. 1 to 5e. The operations performed by the prediction device below can be understood as being performed by a processor.

[0173] In operation S601, the prediction device can obtain age information of the subject. The input unit of the prediction device (e.g., input unit (31) of FIG. 3) can receive age information of the subject through a user interface. In addition, the prediction device can receive the degree of visual acuity influence factors through the user interface.

[0174] In operation S603, the prediction device may obtain vision information. The vision information may include a current vision measurement value. The prediction device may receive the vision information from a vision measurement device (e.g., the inspection device (10) of FIG. 1).

[0175] In operation S605, the prediction device can predict the future visual acuity of the subject. The visual acuity prediction unit (e.g., the visual acuity prediction unit (33) of FIG. 3) of the prediction device can predict the future visual acuity of the subject based on at least the current visual acuity measurement value. The prediction device can predict the visual acuity of the subject based on a visual acuity prediction model (e.g., the visual acuity prediction model (511) of FIG. 5A) using the subject's age information and the current visual acuity measurement value. The visual acuity prediction model can output a visual acuity prediction value of the subject. The visual acuity prediction model can output multiple visual acuity prediction values ​​according to the subject's age or year. In addition, operations related to predicting future visual acuity can refer to the description of FIG. 5A.

[0176] In operation S607, the prediction device can display the acquired vision prediction value through the display. The prediction device can display the vision prediction value according to age or year. For example, when the vision of an 8-year-old subject is measured, the prediction device can display the vision prediction value at each of the subject's ages of 9, 10, ..., and 100. The prediction device can display the vision prediction value in the form of a graph according to age or year. The prediction device can also display the current vision measurement value. For example, the graph output from the prediction device can display the subject's current age and current vision measurement value together.

[0177] According to one embodiment of the present invention, the prediction device can be used in ophthalmology clinics, optical shops, contact lens stores, and other settings that examine and treat myopia and astigmatism. The prediction device can provide the subject and their guardian with a predicted vision value based on their growth process. The subject can view the predicted vision results on a display device or in a report.

[0178] In the above description, operations S601 to S607 may be further divided into additional operations or combined into fewer operations, depending on the implementation example of the present invention. Furthermore, some operations may be omitted as needed, and the order of operations may be changed. Furthermore, the embodiment of FIG. 6 may be performed in various ways by combining or incorporating the embodiments described in FIGS. 7 to 10.

[0179]

[0180] Fig. 7 is a flowchart of a corneal condition prediction method according to one embodiment.

[0181] The method illustrated in FIG. 7 can be performed by a prediction device (e.g., the prediction device (40) of FIG. 1) described through FIGS. 1 to 5e above. The operations performed by the prediction device below can be understood as being performed by a processor.

[0182] Referring to FIG. 7, the prediction device can predict a future corneal condition based on the subject's age information and current corneal condition information.

[0183] In operation S701, the prediction device can obtain age information of the subject. The input unit (not shown) of the prediction device can receive age information of the subject through a user interface. The prediction device can further obtain basic data for measuring the current corneal condition. In the embodiment of FIG. 7, the case of measuring the corneal condition based on a fundus photograph is exemplified, but the present invention is not limited to this description, and various methods for measuring the corneal condition can be applied to various embodiments of the present invention.

[0184] In operation S703, the prediction device may obtain corneal condition information of the current subject. The corneal condition information may include, for example, at least one of corneal thickness, corneal curvature, or corneal topography.

[0185] In operation S705, the prediction device can predict the future corneal condition of the subject based on the subject's age information and the current corneal condition information of the subject. The prediction device can predict the future corneal condition of the subject based on a corneal condition prediction model (e.g., the corneal condition prediction model (521) of FIG. 5b) using, for example, the subject's age information and the current corneal condition information of the subject.

[0186] The prediction device can output a corneal condition prediction value of the subject. The corneal condition prediction model can output multiple corneal condition prediction values ​​based on the subject's age or year. The corneal condition prediction value can include at least one of corneal thickness information, corneal curvature, or corneal topography.

[0187] In addition, for operations related to future state prediction, refer to the description in Fig. 5b.

[0188] In operation S707, the prediction device can display the acquired corneal condition prediction value through the display. The prediction device can display the corneal condition prediction value according to age or year. For example, when examining an 8-year-old subject, the prediction device can display the corneal condition prediction value at the subject's 9, 10, ..., 100 years of age, respectively. The prediction device can display the corneal condition prediction value in the form of a graph according to age or year. The prediction device can also display the corneal condition prediction value together. For example, the graph output from the prediction device can display the subject's current age and current corneal condition information together.

[0189] In the above description, operations S701 to S707 may be further divided into additional operations or combined into fewer operations, depending on the implementation example of the present invention. Furthermore, some operations may be omitted as needed, and the order of operations may be changed.

[0190] Additionally, the embodiment of FIG. 7 can be performed in various ways by combining or combining the embodiments described in FIGS. 6, 8, and 10.

[0191]

[0192] Figure 8 is a flowchart of a method for recommending a treatment method for inhibiting myopia progression according to one embodiment.

[0193] Referring to FIG. 8, the prediction device can recommend a myopia progression suppression treatment method for the subject based on the visual acuity prediction value and corneal condition prediction value of the subject.

[0194] The method illustrated in FIG. 8 can be performed by a prediction device (e.g., the prediction device (40) of FIG. 1) described through FIGS. 1 to 5e above. The operations performed by the prediction device below can be understood as being performed by a processor.

[0195] In operation S801, the prediction device can obtain a predicted future visual acuity value of the subject. The prediction device can obtain a predicted visual acuity value according to the subject's age. The predicted visual acuity value can be obtained based on a visual acuity prediction method as described in FIG. 6.

[0196] In operation S803, the prediction device can obtain a corneal condition prediction value of the subject. The prediction device can obtain a corneal condition prediction value according to the age of the subject. The corneal condition prediction value can be obtained based on a corneal condition prediction method as described in FIG. 7.

[0197] In operation S805, the prediction device may recommend a myopia progression suppression treatment method to the subject based on the visual acuity prediction value and the corneal condition prediction value. The prediction device may recommend a myopia progression suppression treatment method suitable for the subject from among a plurality of preset myopia progression suppression treatment methods. For example, the plurality of myopia progression suppression treatment methods may include at least one of DreamLens, atropine treatment, and myopia suppression spectacle treatment. Furthermore, in the case of DreamLens, the type of DreamLens may be included.

[0198] In the above description, operations S801 to S807 may be further divided into additional operations or combined into fewer operations, depending on the implementation example of the present invention. Furthermore, some operations may be omitted as needed, and the order of operations may be changed.

[0199] Additionally, the embodiment of FIG. 8 can be performed in various ways by combining or combining the embodiments described in FIGS. 6 to 7, FIG. 9, and FIG. 10.

[0200]

[0201] Figure 9 is a schematic flowchart of a method for recommending a treatment method for inhibiting myopia progression according to one embodiment of the present invention.

[0202] The method illustrated in FIG. 9 can be performed by a prediction device (e.g., the prediction device (40) of FIG. 1) described through FIGS. 1 to 5e above. The operations performed by the prediction device below can be understood as being performed by a processor.

[0203] Referring to FIG. 9, the prediction device can recommend a type of myopia progression suppression treatment method and treatment timing for the subject based on the visual acuity prediction value and corneal condition prediction value of the subject.

[0204] In operation S901, the prediction device can obtain a predicted visual acuity value of the subject. For example, the prediction device can obtain a predicted visual acuity value based on the subject's age. The predicted visual acuity value can be obtained based on the visual acuity prediction method described in FIG. 6. The prediction device can obtain a predicted visual acuity value of the subject corresponding to each of multiple future time points.

[0205] In operation S903, the prediction device may obtain a first point in time for determining a type of myopia progression suppression treatment method based on the visual acuity prediction value. The first point in time may be a point in time when the visual acuity prediction value satisfies a predetermined criterion. For example, the visual acuity prediction value may be a point in time when the predetermined criterion is met in diopter units.

[0206] In another embodiment, the prediction device may further obtain a change in the predicted visual acuity value. The prediction device may also obtain a first point in time for determining a type of myopia progression suppression treatment method based on the predicted visual acuity value and the change in the predicted visual acuity value. The first point in time may be a point in time when the predicted visual acuity value satisfies a first criterion related to or expressed in diopters, and the change in the predicted visual acuity value satisfies a second criterion.

[0207] If the visual acuity prediction value does not satisfy the above-mentioned criteria at any point in time, the prediction device may output only the visual acuity prediction value. If the visual acuity prediction value satisfies the above-mentioned criteria, the prediction device may perform the following process to recommend a treatment method to suppress myopia progression.

[0208] In operation S905, the prediction device can obtain a vision prediction value at a first time point and a corneal condition prediction value at the first time point. The prediction device can obtain a vision prediction value predicted for the first time point among a plurality of future time points.

[0209] The prediction device may obtain a predicted vision prediction value for the first time point after obtaining corneal condition prediction values ​​for multiple future time points. Alternatively, the prediction device may obtain only the corneal condition prediction value for the first time point after obtaining the first time point.

[0210] In operation S907, the prediction device may determine a recommended myopia progression suppression treatment method among a plurality of preset myopia progression suppression treatment methods based on the visual acuity prediction value at a first time point and the corneal condition prediction value at the first time point. The prediction device may obtain myopia progression suppression treatment method recommendation information based on a learning model (e.g., the myopia progression suppression treatment method recommendation model (531) of FIG. 5c) by taking the visual acuity prediction value at the first time point and the corneal condition prediction value at the first time point as input.

[0211] In operation S909, a recommended treatment time point (second time point) for applying the myopia progression suppression treatment method (or myopia progression suppression treatment method recommendation information) determined in S907 can be determined. The prediction device can determine the recommended treatment time point based on a plurality of future visual acuity prediction values, a plurality of future corneal condition prediction values, and the determined recommended myopia progression suppression treatment method. The prediction device can input a plurality of future visual acuity prediction values, a plurality of future corneal condition prediction values, and the determined recommended myopia progression suppression treatment method into a learning model (e.g., a treatment result prediction model (541) of FIG. 5D), and obtain a second time point, which is a recommended treatment time point, based on the learning model. In this case, the prediction device can predict the treatment results at the plurality of future time points based on the learning model. The prediction device can determine the recommended treatment time point based on the obtained predicted treatment results.

[0212] Alternatively, multiple future visual acuity prediction values, multiple future corneal condition prediction values, and a determined recommended myopia progression suppression treatment method may be input into a learning model (e.g., a treatment time point recommendation model (551) of FIG. 5e), and a second time point, which is a recommended treatment time point, may be obtained based on the learning model.

[0213] According to one embodiment, input data of the learning model includes information about a plurality of future visual acuity prediction values, a plurality of future corneal condition prediction values, and a recommended myopia progression suppression treatment method and time point, and the learning model can obtain a time point corresponding to a treatment result satisfying a predetermined criterion as a recommended treatment time point.

[0214] The prediction device can display multiple future visual acuity prediction values, multiple future corneal condition prediction values, recommended myopia progression suppression treatment methods, and time points for applying the myopia progression suppression treatment methods through a display. The prediction device can output the multiple visual acuity prediction values ​​and the multiple corneal condition prediction values ​​in the form of a graph through the display. The prediction device can display the recommended treatment time points on the graph. The prediction device can also display the recommended myopia progression suppression treatment methods on the graph adjacent to the recommended treatment time points.

[0215] The second time point may not coincide with the first time point. For example, the second time point may be earlier or later than the first time point.

[0216] In the above description, operations S901 to S909 may be further divided into additional operations or combined into fewer operations, depending on the implementation example of the present invention. Furthermore, some operations may be omitted as needed, and the order of operations may be changed. Furthermore, the embodiment of FIG. 9 may be performed in various ways by combining or incorporating the embodiments described in FIGS. 6 to 8 and FIG. 10.

[0217]

[0218] Figure 10 is a schematic flowchart of a method for recommending a treatment method for inhibiting myopia progression according to one embodiment of the present invention.

[0219] The method illustrated in FIG. 10 can be performed by a prediction device (e.g., the prediction device (40) of FIG. 1) described through FIGS. 1 to 5e above. The operations performed by the prediction device below can be understood as being performed by a processor.

[0220] Referring to FIG. 10, the prediction device can determine the type of myopia progression suppression treatment method based on multiple visual acuity prediction values ​​and corneal condition prediction values ​​of the subject.

[0221] In operation S901, the prediction device can obtain a vision prediction value of the subject at multiple future points in time and a corneal condition prediction value of multiple future points in time. The prediction device can obtain a vision prediction value according to the age of the subject. The vision prediction value can be obtained based on the vision prediction method described in FIG. 6. The prediction device can obtain a corneal condition prediction value according to the age of the subject. The corneal condition prediction value can be obtained based on the corneal condition prediction method described in FIG. 7.

[0222] In operation S1003, the prediction device can determine the type of myopia progression suppression treatment method based on the acquired visual acuity prediction values ​​for multiple future time points and the corneal condition prediction values ​​for multiple future time points. Since the type of myopia progression suppression treatment method is determined directly based on both the visual acuity prediction values ​​and the corneal condition prediction values, this is compared with FIG. 9, in which the type of myopia progression suppression treatment method is determined based on the corneal condition prediction values ​​at the time points determined by the visual acuity prediction values.

[0223] In operation S1005, the prediction device can determine a recommended treatment time point for applying the myopia progression suppression treatment method (or myopia progression suppression treatment method recommendation information) determined in operation S1003. The prediction device can determine the recommended treatment time point based on a plurality of future visual acuity prediction values, a plurality of future corneal condition prediction values, and the determined recommended myopia progression suppression treatment method. The prediction device can input a plurality of future visual acuity prediction values, a plurality of future corneal condition prediction values, and the determined recommended myopia progression suppression treatment method into a learning model (e.g., a treatment result prediction model (541) of FIG. 5D), and obtain a recommended treatment time point based on the learning model. In this case, the prediction device can predict a treatment result at the plurality of future time points based on the learning model. The prediction device can determine the recommended treatment time point based on the obtained predicted treatment result.

[0224] Alternatively, multiple future visual acuity prediction values, multiple future corneal condition prediction values, and a determined recommended myopia progression suppression treatment method may be input into a learning model (e.g., a treatment time recommendation model (551) of FIG. 5e), and a recommended treatment time point may be obtained based on the learning model.

[0225] The prediction device can display multiple future visual acuity prediction values, multiple future corneal condition prediction values, a recommended myopia progression suppression treatment method, and a recommended treatment timing through a display.

[0226] The second time point may not coincide with the first time point. For example, the second time point may be earlier or later than the first time point.

[0227] In the above description, operations S1001 to S1005 may be further divided into additional operations or combined into fewer operations, depending on the implementation example of the present invention. Furthermore, some operations may be omitted as needed, and the order of operations may be changed. Furthermore, the embodiment of FIG. 10 may be performed in various ways by combining or incorporating the embodiments described in FIGS. 6 to 9.

[0228]

[0229] Although all components constituting the embodiments of the present invention have been described as being combined or operating in combination, the present invention is not necessarily limited to such embodiments. That is, within the scope of the present invention, all components may be selectively combined and operated one or more times.

[0230] Meanwhile, the various embodiments described herein may be implemented by hardware, middleware, microcode, software, and / or a combination thereof. For example, the various embodiments may be implemented in one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, other electronic units designed to perform the functions presented herein, or a combination thereof.

[0231] Additionally, for example, various embodiments may be embodied or encoded in a computer-readable medium containing instructions. Instructions embodied or encoded in the computer-readable medium may cause a programmable processor or other processor to perform a method when the instructions are executed, for example. The computer-readable medium includes a computer storage medium, which may be any available medium that can be accessed by a computer. For example, such a computer-readable medium may include a RAM, a ROM, an EEPROM, a CD-ROM or other optical disk storage medium, a magnetic disk storage medium, or other magnetic storage devices.

[0232] Such hardware, software, firmware, etc. may be implemented within the same device or within separate devices to support the various operations and functions described herein. Additionally, components, units, modules, components, etc. described as “units” in the present invention may be implemented together or individually as separate but interoperable logic devices. The depiction of different features for modules, units, etc. is intended to highlight different functional embodiments and does not necessarily imply that they must be realized by separate hardware or software components. Rather, the functionality associated with one or more modules or units may be performed by separate hardware or software components, or integrated into common or separate hardware or software components.

[0233] Although operations are depicted in the drawings in a particular order, this should not be construed as requiring that these operations be performed in the particular order depicted, or in any sequential order, or that all depicted operations be performed to achieve the desired results. In certain circumstances, multitasking and parallel processing may be advantageous. Furthermore, the distinction between various components in the embodiments described above should not be construed as requiring such distinction in all embodiments, and it should be understood that the components depicted may generally be integrated together into a single software product or packaged into multiple software products.

[0234] The electronic device, server, or external device according to the various embodiments of the present document described above may include, for example, at least one of a smartphone, a tablet PC, a mobile phone, a video phone, a desktop PC, a laptop PC, a personal digital assistant (PDA), a portable multimedia player (PMP), an MP3 player, a mobile medical device, a camera, or a wearable device.

[0235] According to various embodiments, the wearable device may include at least one of an accessory type (e.g., a watch, a ring, a bracelet, an anklet, a necklace, glasses, contact lenses, or a head-mounted device (HMD)), a fabric or clothing-integrated type (e.g., an electronic garment), a body-attached type (e.g., a skin pad or tattoo), or a bio-implant type (e.g., an implantable circuit).

[0236] In some embodiments, the electronic device or external device may be a home appliance. The home appliance may include, for example, at least one of a television, a digital video disk player (DVD player), an audio device, a refrigerator, an air conditioner, a vacuum cleaner, an oven, a microwave oven, a washing machine, an air purifier, a set-top box, a home automation control panel, a security control panel, a TV box, a game console, an electronic dictionary, an electronic key, a camcorder, or an electronic picture frame.

[0237] In another embodiment, the electronic device, external device, or wearable device may include at least one of various medical devices (e.g., various portable medical measuring devices (such as a blood glucose meter, a heart rate meter, a blood pressure meter, or a body temperature meter), magnetic resonance angiography (MRA), magnetic resonance imaging (MRI), computed tomography (CT), a camera, or an ultrasound machine), a navigation device, a satellite navigation system (Global Navigation Satellite System (GNSS)), an event data recorder (EDR), a flight data recorder (FDR), an automobile infotainment device, a home robot, or an internet of things device (e.g., a light bulb, various sensors, an electric or gas meter, a sprinkler device, a fire alarm, a thermostat, a streetlight, an exercise machine, a hot water tank, a heater, a boiler, or the like).

[0238]

[0239] As described above, the best practice embodiments have been disclosed in the drawings and specifications. While specific terminology has been used herein, it is solely for the purpose of describing the present invention and is not intended to limit the scope of the invention as defined in the claims. Therefore, those skilled in the art will understand that various modifications and equivalent embodiments are possible. Therefore, the true technical protection scope of the present invention should be determined by the technical spirit of the appended claims.

Claims

1. A method for recommending a treatment method for suppressing myopia progression using a learning model performed by a processor of a device, An operation of obtaining age information of the subject, a visual acuity measurement value of the subject, and a corneal condition measurement value of the subject through the above processor; An operation of obtaining a plurality of vision prediction values ​​corresponding to a plurality of future points in time based on a first learning model using the age information of the subject and the vision measurement value of the subject through the processor; An operation of obtaining a plurality of corneal condition prediction values ​​corresponding to the plurality of future points in time based on a second learning model using the age information of the subject and the corneal condition measurement values ​​of the subject through the processor; An operation of obtaining a recommended myopia progression suppression treatment method to be applied to the subject from among a plurality of preset myopia progression suppression treatment methods through the above processor; and An operation of obtaining a recommended treatment time point for the recommended myopia progression suppression treatment method among the plurality of future time points based on a third learning model using the recommended myopia progression suppression treatment method, the plurality of visual acuity prediction values, and the plurality of corneal condition prediction values ​​through the processor, method.

2. In claim 1, An operation of obtaining a recommended myopia progression suppression treatment method to be applied to the subject among the plurality of preset myopia progression suppression treatment methods is as follows: An operation of obtaining a specific time point for determining the recommended myopia progression suppression treatment method among the plurality of future time points based on the plurality of visual acuity prediction values ​​through the processor; An operation of obtaining, through the processor, a vision prediction value corresponding to the specific point in time among the plurality of vision prediction values ​​and a corneal state prediction value corresponding to the specific point in time among the plurality of corneal state prediction values; and An operation of determining the recommended myopia progression suppression treatment method based on a visual acuity prediction value corresponding to the specific point in time and a corneal condition prediction value corresponding to the specific point in time, method.

3. In claim 1, The above multiple myopia progression suppression treatment methods include at least one of DreamLens, atropine treatment, or myopia suppression spectacle treatment. method.

4. In claim 1, An operation of outputting the plurality of visual acuity prediction values ​​and the plurality of corneal condition prediction values ​​in the form of a graph through a display; and Including an action of displaying the above recommended treatment time point on the above graph, method.

5. At least one processor; Includes a memory for storing a first learning model, a second learning model, and a third learning model, The processor is configured to obtain age information of a subject, a visual acuity measurement value of the subject, and a corneal condition measurement value of the subject, and obtain a plurality of visual acuity prediction values ​​corresponding to a plurality of future time points based on the first learning model using the age information of the subject and the visual acuity measurement value of the subject, and obtain a plurality of corneal condition prediction values ​​corresponding to the plurality of future time points based on the second learning model using the age information of the subject and the corneal condition measurement value of the subject, and obtain a recommended myopia progression suppression treatment method to be applied to the subject among a plurality of preset myopia progression suppression treatment methods, and obtain a recommended treatment time point for the recommended myopia progression suppression treatment method among the plurality of future time points based on a third learning model using the recommended myopia progression suppression treatment method, the plurality of visual acuity prediction values, and the plurality of corneal condition prediction values. Recommended treatment method for suppressing myopia progression.

Images