Vision correction surgery recommendation method and device

Abstract

To assist doctors in making determination, and provide doctors, consultants, and subjects with objective recommendations and relevant information on eyesight correction surgery.SOLUTION: A recommendation method for eyesight correction surgery using the artificial intelligence according to the present invention includes the steps of: acquiring medical examination data of a subject; predicting the presence / absence of the conformity of the eyesight correction surgery of the subject from the medical examination data; predicting the presence / absence of the possibility of the eyesight correction surgery using the laser for the subject from the medical examination data when the eyesight correction surgery conforms to the subject; calculating a corneal shape factor prediction value after standard eyesight correction surgery of the subject and a corneal shape factor prediction value after custom eyesight correction surgery from the medical examination data so as to be used for determination on whether or not the custom eyesight correction surgery is necessary when the eyesight correction surgery is possible; and proposing the eyesight correction surgery corresponding to the subject from the medical examination data when the eyesight correction surgery using the laser is possible.SELECTED DRAWING: Figure 35

Description

[Technical Field]

[0001] The present invention relates to a method and apparatus for recommending vision correction surgery, and more particularly to a method and apparatus for recommending vision correction surgery to a subject or the like using artificial intelligence. [Background technology]

[0002] Vision correction surgery such as LASIK and LASEK is attracting the interest of many people with poor eyesight, regardless of age or gender. Interest in vision correction surgery is increasing day by day, with statistics showing that the number of people who have undergone vision correction surgery has reached 100,000.

[0003] However, patients considering vision correction surgery often find it difficult to determine which surgery is right for them. Patients must choose between LASIK, LASEK, small incision lenticular extraction (SMILE), and lens implantation. Even within LASIK, they must choose between surgical equipment options, such as iLASIK, Da Vinci LASIK, Crystal LASIK, Z LASIK, Bijou LASIK, and OptiLASIK, as well as surgical techniques, such as ContraVision, Extra LASIK, and Wavefront LASIK. Furthermore, the recommended amount of corneal ablation varies depending on the hospital and doctor, making the selection process even more difficult. Patients must rely on their doctor or consultant for information about the quality of their vision and side effects after surgery. Summary of the Invention [Problem to be solved by the invention]

[0004] One of the objectives is to assist doctors in making decisions and to provide doctors, consultants, patients, and others with objective information related to vision correction surgery.

[0005] Another challenge is recommending vision correction surgery to physicians, consultants, patients, and the like.

[0006] Another object is to provide doctors, consultants, patients, and others with reasons for recommending vision correction surgery.

[0007] The problems to be solved are not limited to those described above, and problems not mentioned should be clearly understood by a person having ordinary skill in the art to which the present invention pertains from the present specification and drawings. [Means for solving the problem]

[0008] According to one aspect, a method for recommending vision correction surgery using artificial intelligence performed by a computing device includes: acquiring medical examination data of a subject, the medical examination data including interview data and ocular characteristic data measurements; inputting a first group of data obtained from the medical examination data of the subject into a first prediction model to predict whether the subject is suitable for vision correction surgery; If the subject is suitable for vision correction surgery, inputting a second group of data obtained from the medical examination data of the subject into a second prediction model to predict whether the subject is suitable for vision correction surgery using a laser; If the subject is eligible for laser vision correction surgery, inputting a third group of data obtained from the subject's medical examination data into a third prediction model to calculate a predicted corneal shape factor value after standard vision correction surgery and a predicted corneal shape factor value after custom vision correction surgery for the subject, so that the third group of data is used to determine whether custom vision correction surgery is necessary. And If the subject is eligible for vision correction surgery using a laser, inputting a fourth group of data obtained from the medical examination data of the subject into a fourth prediction model to propose a vision correction surgery corresponding to the subject, A method for recommending vision corrective surgery is provided, in which the fourth prediction model is learned based on at least one of medical examination data of multiple patients who have undergone vision corrective surgery, the vision corrective surgery corresponding to the multiple patients, and the visual acuity of the multiple patients after the vision corrective surgery.

[0009] According to another aspect, a method for recommending vision correction surgery using artificial intelligence performed by a computing device includes: acquiring medical examination data of a subject, the medical examination data including interview data and ocular characteristic data measurements; inputting a first group of data obtained from the medical examination data of the subject into a first prediction model to predict whether the subject is suitable for vision correction surgery; If the subject is suitable for vision correction surgery, inputting a second group of data obtained from the medical examination data of the subject into a second prediction model to predict whether the subject is suitable for vision correction surgery using a laser; If the subject is eligible for laser vision correction surgery, inputting a third group of data obtained from the subject's medical examination data into a third prediction model to predict whether the subject will need custom vision correction surgery; and If the subject is eligible for vision correction surgery using a laser, inputting a fourth group of data obtained from the medical examination data of the subject into a fourth prediction model to propose a vision correction surgery corresponding to the subject, The step of predicting whether or not the subject needs custom vision corrective surgery includes predicting whether or not the subject needs custom vision corrective surgery based on a predicted value of a corneal shape factor after standard vision corrective surgery and a predicted value of a corneal shape factor after custom vision corrective surgery, A method for recommending vision corrective surgery is provided, in which the fourth prediction model is learned based on at least one of medical examination data of multiple patients who have undergone vision corrective surgery, the vision corrective surgery corresponding to the multiple patients, and the visual acuity of the multiple patients after the vision corrective surgery.

[0010] According to another aspect, a method for recommending vision correction surgery using artificial intelligence performed by a computing device includes: acquiring medical examination data of a subject, the medical examination data including interview data and ocular characteristic data measurements; inputting a first group of data obtained from the medical examination data of the subject into a first prediction model to predict whether the subject is suitable for vision correction surgery; If the subject is suitable for vision correction surgery, inputting a second group of data obtained from the medical examination data of the subject into a second prediction model to predict whether the subject is suitable for vision correction surgery using a laser; and If the subject is eligible for vision correction surgery using a laser, inputting a third group of data obtained from the medical examination data of the subject into a third prediction model to propose a vision correction surgery corresponding to the subject, the step of proposing the vision corrective surgery includes proposing the vision corrective surgery based on a predicted corneal shape factor value after a standard vision corrective surgery and a predicted corneal shape factor value after a custom vision corrective surgery of the subject; A method for recommending vision corrective surgery is provided, in which the third prediction model is learned based on at least one of medical examination data of multiple patients who have undergone vision corrective surgery, the vision corrective surgery corresponding to the multiple patients, and the visual acuity of the multiple patients after the vision corrective surgery.

[0011] According to another aspect, a method for recommending vision correction surgery using artificial intelligence, which is executed by a computing device, includes the steps of: acquiring medical examination data of a subject, the medical examination data including interview data and ocular characteristic data measurements; inputting a first group of data obtained from the medical examination data of the subject into a first prediction model to predict whether the subject is suitable for vision correction surgery; and If the subject is suitable for vision correction surgery, inputting a second group of data obtained from the subject's medical examination data into a second prediction model to propose a corresponding vision correction surgery for the subject; the step of proposing the vision corrective surgery includes proposing the vision corrective surgery based on a predicted corneal shape factor value after a standard vision corrective surgery and a predicted corneal shape factor value after a custom vision corrective surgery of the subject; A method for recommending vision corrective surgery is provided, in which the second prediction model is learned based on at least one of medical examination data of multiple patients who have undergone vision corrective surgery, the vision corrective surgery corresponding to the multiple patients, and the visual acuity of the multiple patients after the vision corrective surgery.

[0012] According to another aspect, a method for recommending vision correction surgery using artificial intelligence performed by a computing device includes: acquiring medical data of a subject, the medical data including interview data and ocular characteristic data measurements; and and inputting group data obtained from the subject's medical examination data into a prediction model to propose a corresponding vision correction surgery for the subject; the step of proposing the vision corrective surgery includes proposing the vision corrective surgery based on a predicted corneal shape factor value after a standard vision corrective surgery and a predicted corneal shape factor value after a custom vision corrective surgery of the subject; A method for recommending vision corrective surgery is provided in which the predictive model is trained based on at least one of medical examination data of multiple patients who have undergone vision corrective surgery, the vision corrective surgery corresponding to the multiple patients, and the visual acuity of the multiple patients after the vision corrective surgery.

[0013] The means for solving the problem are not limited to the above-mentioned means for solving the problem, and any means for solving the problem that are not mentioned should be clearly understood by a person having ordinary skill in the art to which the present invention pertains from the specification and drawings. [Effects of the Invention]

[0014] According to one embodiment, a method and an apparatus for implementing the method are provided for assisting doctors in making decisions and providing objective information related to vision correction surgery to doctors, consultants, patients, and the like.

[0015] According to another embodiment, artificial intelligence may be used to recommend vision correction surgery to physicians, consultants, patients, and the like.

[0016] According to another embodiment, artificial intelligence can be used to provide doctors, consultants, patients, and others with reasons for recommending vision correction surgery.

[0017] The effects are not limited to those described above, and effects not mentioned should be clearly understood by a person having ordinary skill in the art to which the present invention pertains from the specification and drawings. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a diagram of a vision correction surgery assistance system according to one embodiment. [Figure 2] FIG. 1 is a diagram illustrating a learning device / prediction device according to an embodiment. [Figure 3] FIG. 2 is a diagram illustrating a server device and a client device according to an embodiment. [Figure 4] FIG. 2 is a diagram illustrating the configuration of a server device and a client device according to an embodiment. [Figure 5] FIG. 1 is a diagram of a vision correction surgery-related model according to one embodiment. [Figure 6] 1A and 1B are diagrams illustrating the learning and prediction stages of a vision correction surgery-related model according to one embodiment. [Figure 7] FIG. 1 is a diagram relating to pre-processing of input and output data according to one embodiment. [Figure 8] FIG. 1 is a diagram of a vision correction surgery related model including serially connected sub-models according to one embodiment. [Figure 9] FIG. 1 is a diagram of a vision correction surgery related model including sub-models connected in parallel according to one embodiment. [Figure 10] FIG. 10 is a diagram of a predicted visual acuity image according to one embodiment. [Figure 11] FIG. 1 is a diagram of a predicted visual acuity image generation model using a filter according to one embodiment. [Figure 12] FIG. 1 is a diagram of a corneal topography image according to one embodiment. [Figure 13] FIG. 1 is a diagram of a causal analysis model for predictive outcome calculation including a vision correction surgery-related model according to one embodiment. [Figure 14] FIG. 10 is a diagram illustrating causes of calculation of a predicted result according to an embodiment. [Figure 15]FIG. 1 is a diagram of a serial connection of vision correction surgery-related models according to one embodiment. [Figure 16-19] FIG. 10 is a diagram illustrating calculation of the output of a vision correction surgery-related model based on the output of a corneal shape factor prediction model according to one embodiment. [Figure 20] FIG. 10 is a diagram illustrating calculation of the output of a vision corrective surgery-related model based on the output of a custom vision corrective surgery necessity prediction model according to one embodiment. [Figure 21-22] FIG. 10 is a diagram illustrating calculation of the output of a vision correction surgery-related model based on the output of a vision correction surgery proposal model according to one embodiment. [Figure 23] FIG. 10 is a diagram illustrating calculation of the output of a vision correction surgery-related model based on the output of a surgical parameter suggestion model according to one embodiment. [Figure 24-25] FIG. 10 is a diagram illustrating calculation of the output of a vision correction surgery-related model based on the output of a visual acuity prediction model according to one embodiment. [Figure 26-27] FIG. 10 is a diagram illustrating calculation of the output of a vision correction surgery-related model based on the output of a corneal topography image prediction model according to one embodiment. [Figure 28] FIG. 1 is a diagram illustrating a combination of three or more vision correction surgery-related models according to one embodiment. [Figure 29-30] FIG. 10 is a diagram illustrating calculation of the output of a vision correction surgery-related model based on the outputs of a corneal shape factor prediction model and a visual acuity prediction model according to one embodiment. [Figure 31] FIG. 10 is a diagram illustrating the merging of vision correction surgery-related models according to one embodiment. [Figure 32-34] FIG. 1 is a diagram of an implementation of vision correction surgery related model merging according to one embodiment. [Figure 35] 1A and 1B are diagrams relating to a first embodiment of a method for recommending vision correction surgery according to an embodiment. [Figure 36] FIG. 10 is a diagram relating to a second embodiment of a method for recommending vision correction surgery according to an embodiment. [Figure 37] FIG. 10 is a diagram relating to a third embodiment of a method for recommending vision correction surgery according to an embodiment. [Figure 38]FIG. 10 is a diagram relating to a fourth embodiment of the method for recommending vision correction surgery according to an embodiment. [Figure 39] FIG. 10 is a diagram relating to a fifth embodiment of a method for recommending vision correction surgery according to an embodiment. [Figure 40] FIG. 10 is a diagram relating to a sixth embodiment of the method for recommending vision correction surgery according to an embodiment. [Figure 41] 1A and 1B are diagrams relating to a first embodiment of a method for providing visualization information for vision correction surgery according to an embodiment. [Figure 42] FIG. 10 is a diagram relating to a second embodiment of the method for providing visualization information for vision correction surgery according to an embodiment. [Figure 43] FIG. 10 is a diagram relating to a third embodiment of a method for providing visualization information for vision correction surgery according to an embodiment. [Figure 44] FIG. 10 is a diagram relating to a fourth embodiment of the method for providing visualization information for vision correction surgery according to an embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0019] The examples described in this specification are intended to clearly explain the concept of the present invention to those skilled in the art to which the present invention pertains, and the present invention is not limited by the examples described in the specification, and the scope of the present invention should be interpreted as including modifications or variations that do not depart from the concept of the present invention.

[0020] The terms used in this specification are currently commonly used and general terms that are selected as much as possible in consideration of the functions of the present invention, but these may differ depending on the intentions, practices, or the emergence of new technologies of those skilled in the art to which the present invention pertains. However, when a specific term different from these is used with a definition of a specific meaning, the meaning of that term will be separately described. Therefore, the terms used in this specification should be interpreted based on the substantive meaning of the term and the overall content of this specification, rather than simply the name of the term.

[0021] The drawings in this specification are intended to facilitate explanation of the present invention, and the shapes shown in the drawings are exaggerated as necessary to facilitate understanding of the present invention, and therefore the present invention is not limited by the drawings.

[0022] In this specification, if it is determined that a detailed description of a known configuration or function of the present invention may obscure the gist of the present invention, the detailed description thereof will be omitted as necessary. Furthermore, numbers (e.g., first, second, etc.) used in the description of this specification may refer to different configurations or may correspond to the same configuration.

[0023] Hereinafter, a method and apparatus for recommending vision correction surgery to a subject based on medical examination data will be described. In particular, a method and apparatus for generating a model for recommending vision correction surgery using artificial intelligence and recommending vision correction surgery to a subject using the generated model will be described.

[0024] Also described is a method and apparatus for providing visualized information related to vision correction surgery to a subject based on medical examination data. In particular, a method and apparatus for generating a model for providing visualized information on vision correction surgery, such as providing a predicted visual acuity image after vision correction surgery, predicting a corneal topography image, and analyzing the cause of the predicted result, using artificial intelligence, and providing the visualized information on vision correction surgery to a subject using the generated model is described.

[0025] In this specification, vision correction surgery should be broadly interpreted as surgery to correct the patient's vision, including not only surgeries that correct vision through laser-assisted corneal ablation, such as LASIK, LASEK, and small incision lenticule extraction (SMILE), but also vision correction surgeries that do not use lasers, such as lens insertion.

[0026] In addition, in this specification, visual acuity includes visual acuity that can be measured based on the subject's judgment and visual acuity that can be measured through an eye test, etc. For example, visual acuity can be measured using an eye chart. Alternatively, visual acuity can include lower-order aberrations beyond basic refraction, such as myopia, hyperopia, and astigmatism, as well as higher-order aberrations such as spherical aberration, coma aberration, and trefoil aberration. In addition, visual acuity can include uncorrected visual acuity and corrected visual acuity.

[0027] According to one aspect, a method for recommending vision correction surgery using artificial intelligence performed by a computing device includes: acquiring medical examination data of a subject, the medical examination data including interview data and ocular characteristic data measurements; inputting a first group of data obtained from the medical examination data of the subject into a first prediction model to predict whether the subject is suitable for vision correction surgery; If the subject is suitable for vision correction surgery, inputting a second group of data obtained from the medical examination data of the subject into a second prediction model to predict whether the subject is suitable for vision correction surgery using a laser; If the subject is eligible for laser vision correction surgery, inputting a third group of data obtained from the subject's medical examination data into a third prediction model to calculate a predicted corneal shape factor value after standard vision correction surgery and a predicted corneal shape factor value after custom vision correction surgery for the subject, so that the third group of data is used to determine whether custom vision correction surgery is necessary. And If the subject is eligible for vision correction surgery using a laser, inputting a fourth group of data obtained from the medical examination data of the subject into a fourth prediction model to propose a vision correction surgery corresponding to the subject, A method for recommending vision corrective surgery is provided, in which the fourth prediction model is learned based on at least one of medical examination data of multiple patients who have undergone vision corrective surgery, the vision corrective surgery corresponding to the multiple patients, and the visual acuity of the multiple patients after the vision corrective surgery.

[0028] Here, the step of proposing the vision correction surgery may include proposing the vision correction surgery based on a predicted visual acuity of the subject after the vision correction surgery.

[0029] Here, the step of proposing the vision correction surgery may include calculating a predicted visual acuity value of the subject after the vision correction surgery corresponding to each of a plurality of vision correction surgeries and proposing the vision correction surgery.

[0030] Here, the step of proposing a vision correction surgery may include calculating a plurality of predicted visual acuity values ​​corresponding to a plurality of different times and proposing the vision correction surgery.

[0031] Here, the method for recommending vision corrective surgery may further include predicting whether or not the subject needs custom vision corrective surgery based on the calculated predicted corneal shape factor values ​​after standard vision corrective surgery and the predicted corneal shape factor values ​​after custom vision corrective surgery.

[0032] Here, the step of suggesting the vision corrective surgery may suggest the vision corrective surgery based on the calculated predicted corneal shape factor after standard vision corrective surgery and the predicted corneal shape factor after custom vision corrective surgery.

[0033] Here, when the fourth prediction model is trained taking into account the vision correction surgery preferences of the plurality of patients, the fourth group data may include the vision correction surgery preferences of the patients.

[0034] Here, at least one of the first prediction model, the second prediction model, the third prediction model, and the fourth prediction model includes a plurality of sub-models, and a result value can be calculated based on the results of the plurality of sub-models.

[0035] Here, at least one of the first group data, the second group data, the third group data, and the fourth group data may be characterized in that it contains at least a portion of the medical examination data of the subject as is, or contains a new type of data calculated from at least a portion of the medical examination data of the subject.

[0036] Here, the corneal shape factor predicted value may include at least one of an index of height decentration (IHD) predicted value, an index of surface variance (ISV) predicted value, and an index of vertical asymmetry (IVA) predicted value.

[0037] Here, the medical examination data may further include genetic information.

[0038] According to another aspect, a method for recommending vision correction surgery utilizing artificial intelligence performed by a computing device includes: acquiring medical examination data of a subject, the medical examination data including interview data and ocular characteristic data measurements; inputting a first group of data obtained from the medical examination data of the subject into a first prediction model to predict whether the subject is suitable for vision correction surgery; If the subject is suitable for vision correction surgery, inputting a second group of data obtained from the medical examination data of the subject into a second prediction model to predict whether the subject is suitable for vision correction surgery using a laser; If the subject is eligible for laser vision correction surgery, inputting a third group of data obtained from the subject's medical examination data into a third prediction model to predict whether the subject will need custom vision correction surgery; and If the subject is eligible for vision correction surgery using a laser, inputting a fourth group of data obtained from the medical examination data of the subject into a fourth prediction model to propose a vision correction surgery corresponding to the subject, The step of predicting whether or not the subject needs custom vision corrective surgery includes predicting whether or not the subject needs custom vision corrective surgery based on a predicted value of a corneal shape factor after standard vision corrective surgery and a predicted value of a corneal shape factor after custom vision corrective surgery, A method for recommending vision corrective surgery can be provided in which the fourth prediction model is learned based on at least one of medical examination data of multiple patients who have undergone vision corrective surgery, the vision corrective surgery corresponding to the multiple patients, and the visual acuity of the multiple patients after the vision corrective surgery.

[0039] According to another aspect, a method for recommending vision correction surgery using artificial intelligence performed by a computing device includes: acquiring medical examination data of a subject, the medical examination data including interview data and ocular characteristic data measurements; inputting a first group of data obtained from the medical examination data of the subject into a first prediction model to predict whether the subject is suitable for vision correction surgery; If the subject is suitable for vision correction surgery, inputting a second group of data obtained from the medical examination data of the subject into a second prediction model to predict whether the subject is suitable for vision correction surgery using a laser; and If the subject is eligible for vision correction surgery using a laser, inputting a third group of data obtained from the subject's medical examination data into a third prediction model to propose a vision correction surgery corresponding to the subject; the step of proposing the vision corrective surgery includes proposing the vision corrective surgery based on a predicted corneal shape factor value after a standard vision corrective surgery and a predicted corneal shape factor value after a custom vision corrective surgery of the subject; A method for recommending vision corrective surgery can be provided in which the third prediction model is learned based on at least one of medical examination data of multiple patients who have undergone vision corrective surgery, the vision corrective surgery corresponding to the multiple patients, and the visual acuity of the multiple patients after the vision corrective surgery.

[0040] According to another aspect, a method for recommending vision correction surgery using artificial intelligence performed by a computing device includes: acquiring medical examination data of a subject, the medical examination data including interview data and ocular characteristic data measurements; inputting a first group of data obtained from the medical examination data of the subject into a first prediction model to predict whether the subject is suitable for vision correction surgery; and If the subject is suitable for vision correction surgery, inputting a second group of data obtained from the subject's medical examination data into a second prediction model to propose a corresponding vision correction surgery for the subject; the step of proposing the vision corrective surgery includes proposing the vision corrective surgery based on a predicted corneal shape factor value after a standard vision corrective surgery and a predicted corneal shape factor value after a custom vision corrective surgery of the subject; A method for recommending vision corrective surgery can be provided in which the second prediction model is learned based on at least one of medical examination data of multiple patients who have undergone vision corrective surgery, the vision corrective surgery corresponding to the multiple patients, and the visual acuity of the multiple patients after the vision corrective surgery.

[0041] According to another aspect, a method for recommending vision correction surgery using artificial intelligence performed by a computing device includes: acquiring medical data of a subject, the medical data including interview data and ocular characteristic data measurements; and and inputting group data obtained from the subject's medical examination data into a prediction model to propose a corresponding vision correction surgery for the subject; the step of proposing the vision corrective surgery includes proposing the vision corrective surgery based on a predicted corneal shape factor value after a standard vision corrective surgery and a predicted corneal shape factor value after a custom vision corrective surgery of the subject; A method for recommending vision corrective surgery can be provided in which the predictive model is trained based on at least one of medical examination data of multiple patients who have undergone vision corrective surgery, the vision corrective surgery corresponding to the multiple patients, and the visual acuity of the multiple patients after the vision corrective surgery.

[0042] According to another aspect, a method for providing a predicted visual acuity image after vision correction surgery using artificial intelligence executed by a computing device includes: acquiring medical examination data of a subject, the medical examination data including interview data and ocular characteristic data measurements; inputting a first group of data acquired from the medical examination data of the subject into a first prediction model to calculate predicted values ​​of ocular characteristic data of the subject after vision correction surgery, the predicted values ​​of ocular characteristic data including at least one of predicted visual acuity and predicted corneal shape factor; and generating a predicted visual acuity image based on the predicted ocular characteristic data value; The first prediction model may be trained based on at least one of pre-operative ocular characteristic data measurements of a plurality of patients who have undergone vision correction surgery, surgical parameters of the vision correction surgery performed on the plurality of patients, and post-operative ocular characteristic data measurements of the plurality of patients, and a method for providing a predicted vision image may be provided.

[0043] Here, the step of generating the predicted visual acuity image may include a step of calculating or selecting a filter based on the predicted value of the ocular characteristic data, and a step of applying the filter to the original image to generate the predicted visual acuity image.

[0044] Here, the ocular characteristic data predicted value may include a first ocular characteristic data predicted value and a second ocular characteristic data predicted value, and the predicted visual acuity image may include a first predicted visual acuity image generated based on the first ocular characteristic data predicted value, and a second predicted visual acuity image generated based on the second ocular characteristic data predicted value and different from the first predicted visual acuity image.

[0045] Here, the first ocular characteristic data predicted value and the second ocular characteristic data predicted value may correspond to the ocular characteristic data predicted value after standard vision correction surgery and the ocular characteristic data predicted value after custom vision correction surgery, respectively, and the first predicted visual acuity image and the second predicted visual acuity image may correspond to the predicted visual acuity image after standard vision correction surgery and the predicted visual acuity image after custom vision correction surgery, respectively.

[0046] Here, the predicted vision image may include information on at least one of the subject's predicted vision clarity, light blur, contrast sensitivity, night vision, glare, double vision, and afterimage after vision correction surgery.

[0047] Here, the method for providing a predicted visual acuity image further includes a step of inputting a second group of data obtained from the subject's medical examination data into a second prediction model to predict the corneal topography image of the subject after vision correction surgery, and the second prediction model can be trained based on at least one of pre-operative corneal topography images of a plurality of subjects who have undergone vision correction surgery, surgical parameters of the vision correction surgery performed on the plurality of subjects, and post-operative corneal topography images of the plurality of subjects.

[0048] Here, the method for providing a predicted visual acuity image may further include calculating a dependency of the predicted value of eyeball characteristic data on the first group of data.

[0049] Here, the eyeball characteristic data predicted value includes a first eyeball characteristic data predicted value and a second eyeball characteristic data predicted value, the dependency includes a dependency coefficient corresponding to at least a portion of the first group of data, and the dependency coefficient includes a first dependency coefficient corresponding to the first eyeball characteristic data predicted value and a second dependency coefficient corresponding to the second eyeball characteristic data predicted value and different from the first dependency coefficient.

[0050] Here, the first ocular characteristic data predicted value and the second ocular characteristic data predicted value correspond to the ocular characteristic data predicted value after standard vision corrective surgery and the ocular characteristic data predicted value after custom vision corrective surgery, respectively, and the first dependence coefficient and the second dependence coefficient may correspond to the dependency of the ocular characteristic data predicted value after standard vision corrective surgery on the first group of data and the dependency of the ocular characteristic data predicted value after custom vision corrective surgery on the first group of data, respectively.

[0051] Here, the method for providing an expected visual acuity image may further include outputting a dependent coefficient greater than a predetermined value among the dependent coefficients, or outputting a predetermined number of dependent coefficients. Here, the corneal shape factor predicted value may include at least one of an index of height decentration (IHD) predicted value, an index of surface variance (ISV) predicted value, and an index of vertical asymmetry (IVA) predicted value.

[0052] Here, the visual acuity prediction value may include at least one of a lower-order aberration prediction value and a higher-order aberration prediction value.

[0053] According to an embodiment, the vision correction surgery assistance system may include a learning device and a prediction device. Here, the learning device and the prediction device may be a computing device including at least one control unit. Examples of the computing device may include, but are not limited to, a desktop, a laptop, a tablet PC, or a smartphone.

[0054] FIG. 1 is a diagram illustrating a vision correction surgery assistance system 10 according to one embodiment. Referring to FIG. 1, a learning device 100 can learn and / or generate a model (hereinafter referred to as a "vision correction surgery-related model") that calculates information related to vision correction surgery based on learning data. Here, the learning data is data necessary for learning and / or generating a vision correction surgery-related model, such as numbers, letters, images, etc., and there is no limitation on the representation method. For example, the learning data can include medical examination data and surgical parameters of a patient who has undergone vision correction surgery.

[0055] The prediction device 300 can calculate a prediction result, which is information related to vision correction surgery, based on the vision correction surgery-related model generated through the learning device 100 and input data. Here, the input data is data that is the basis for calculating the prediction result, such as numbers, letters, images, etc., and there is no limitation on the representation method thereof.

[0056] Specific examples of training data, input data, prediction results, and vision correction surgery-related models will be described later.

[0057] Although the learning device 100 and the prediction device 300 are illustrated as separate devices in FIG. 1, the learning device 100 and the prediction device 300 may be the same device. For example, a vision correction surgery-related model may be trained / generated within the same device, and a prediction result may be calculated using the model. Alternatively, at least a portion of the configuration of the learning device 100 and at least a portion of the configuration of the prediction device 300 may be the same configuration.

[0058] Additionally, a vision correction surgery assistance system according to an embodiment may include multiple learning devices and / or multiple prediction devices.

[0059] 2 is a diagram illustrating a learning device / prediction device according to an embodiment. Referring to FIG. 2, the learning device / prediction device according to an embodiment may include a memory unit (5000) and a control unit (1000).

[0060] The learning device / prediction device according to one embodiment may include a control unit 1000 for controlling its operation. The control unit 1000 may include one or more of a central processing unit (CPU), a random access memory (RAM), a graphic processing unit (GPU), one or more microprocessors, and other electronic components capable of processing input data according to predetermined logic.

[0061] The control unit 1000 can read the system program and various processing programs stored in the memory unit 5000. For example, the control unit 1000 can load data processing processes for executing the learning and prediction steps of a vision correction surgery-related model, which will be described later, into RAM and execute various processes according to the loaded programs. In one example, the control unit 1000 can execute learning of a vision correction surgery-related model. In another example, the control unit 1000 can generate prediction results using a vision correction surgery-related model.

[0062] The learning device / prediction device according to an embodiment may include a memory unit 5000. The memory unit 5000 may store data required for learning, a learning model, and a learned vision correction surgery-related model. The memory unit 5000 may store parameters, variables, etc. of the vision correction surgery-related model.

[0063] The memory unit (5000) can be implemented as a non-volatile semiconductor memory, a hard disk, a flash memory, a RAM, a ROM (Read Only Memory), an EEPROM (Electrically Erasable Programmable Read-Only Memory), or other tangible non-volatile recording medium.

[0064] The memory unit (5000) can store various processing programs, parameters for executing the processing of the programs, data resulting from such processing, etc. For example, the memory unit (5000) can store a data processing program for executing the learning and prediction steps of a vision correction surgery-related model, which will be described later, a diagnostic processing program, parameters for executing each program, and data obtained by executing such programs (e.g., processed data or prediction results), etc.

[0065] The learning device / prediction device according to one embodiment may further include a communication unit (9000). The communication unit (9000) may communicate with an external device. For example, the communication unit (9000) of the learning device may communicate with the communication unit (9000) of the prediction device. The communication unit (9000) may perform wired or wireless communication. The communication unit (9000) may perform bi-directional or uni-directional communication. The learning device / prediction device shown in FIG. 2 is merely an example, and the configuration of the learning device / prediction device is not limited to this.

[0066] The vision correction surgery assistance system according to one embodiment may include a server device and a client device. Figure 3 is a diagram illustrating a server device (500) and client devices (700a, 700b) according to one embodiment. In one embodiment, the server device 500 may correspond to the learning device / prediction device described above. In one embodiment, the server device 500 may train, store, and / or execute vision correction surgery-related models.

[0067] In one embodiment, the client devices (700a, 700b) may correspond to the trainer / predictor described above. In one embodiment, the client devices (700a, 700b) may train, store, and / or execute vision correction surgery-related models.

[0068] According to one embodiment, the client devices 700a, 700b can obtain the trained vision correction surgery-related model from the server device 500. For example, the client devices 700a, 700b can download the vision correction surgery-related model from the server device 500 over a network. According to one embodiment, the server device 500 can calculate a predicted result based on input data received from the client devices 700a and 700b. For example, the client devices 700a and 700b can receive information about a subject and transmit it to the server device 500, and the server device 500 can calculate a predicted result based on the subject information through a vision correction surgery-related model. According to one embodiment, the server device 500 can receive input data from multiple client devices 700a and 700b.

[0069] According to one embodiment, the server device (500) can transmit the calculated prediction results to the client devices (700a, 700b). For example, the client devices (700a, 700b) can provide the prediction results obtained from the server device (500) to doctors, consultants, subjects, etc. According to one embodiment, the server device (500) can obtain feedback from the client devices (700a, 700b). According to one embodiment, the server device (500) can transmit the prediction results to multiple client devices (700a, 700b).

[0070] According to one embodiment, the client devices (700a, 700b) can request prediction results from the server device (500).

[0071] According to an embodiment, the client devices (700a, 700b) can transmit received data to the server device (500). According to an embodiment, the client devices (700a, 700b) can modify at least a portion of the received data and transmit the modified data to the server device (500). According to an embodiment, the client devices (700a, 700b) can provide prediction results obtained from the server device (500) to doctors, consultants, subjects, etc. According to an embodiment, the client devices (700a, 700b) can modify at least a portion of the prediction results obtained from the server device (500) and provide the prediction results to doctors, consultants, subjects, etc.

[0072] Although FIG. 3 shows the relationship between one server device (500) and two client devices (700a, 700b), this is not limited thereto and can equally be applied to one or more server devices (500) and one or more client devices (700a, 700b).

[0073] FIG. 4 is a diagram illustrating the configuration of a server device 500 and a client device 700 according to an embodiment. Referring to FIG. 4, the server device 500 and the client device 700 may include memory units 5000a and 5000b, control units 1000a and 1000b, and communication units 9000a and 9000b. The server device 500 and the client device 700 may transmit and acquire information through the communication units 9000a and 9000b. In one example, the client device 700 may acquire a learned vision correction surgery-related model from the communication unit 9000a of the server device 500 through its communication unit 9000b. In another example, the client device (700) may transmit input data to the communication unit (9000a) of the server device (500) through its communication unit (9000b), and the server device (500) may transmit the prediction result to the communication unit (9000b) of the client device (700) through its communication unit (9000a).

[0074] As described above, the vision correction surgery-related model is a model that calculates various information that is taken into consideration when performing vision correction surgery, before, during, and after the surgery.

[0075] 5 is a diagram illustrating a vision correction surgery-related model (M) according to one embodiment. Referring to FIG. 5, the vision correction surgery-related model (M) may include a surgery suitability prediction model (M10), a laser surgery suitability prediction model (M11), a corneal shape factor prediction model (M12), a custom vision correction surgery necessity prediction model (M13), a vision correction surgery recommendation model (M14), a surgery parameter recommendation model (M15), a visual acuity prediction model (M16), a predicted visual acuity image generation model (M17), a corneal topography image prediction model (M18), and a predicted result calculation cause analysis model (M19). Each model will be described in detail below.

[0076] At least some of the vision correction surgery-related models (M) can be trained and / or generated using the same learning device. For example, the surgery suitability prediction model (M10) and the laser surgery suitability prediction model (M11) can be trained and / or generated using the same learning device. Alternatively, at least some of the vision correction surgery-related models (M) can be trained and / or generated using different learning devices.

[0077] At least some of the vision correction surgery-related models (M) may be executed by the same prediction device. For example, the surgery suitability prediction model (M10) and the laser surgery suitability prediction model (M11) may be executed by the same prediction device. Alternatively, at least some of the vision correction surgery-related models (M) may be executed by different prediction devices.

[0078] The vision correction surgery-related model according to an embodiment may be trained and / or implemented using an artificial intelligence model / algorithm and is not limited by its training and / or implementation method. For example, the vision correction surgery-related model may be trained and / or implemented using various machine-running models / algorithms and deep-running models / 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.

[0079] According to an embodiment, a vision correction surgery-related model may be trained and / or generated through a training phase. The vision correction surgery-related model trained and / or generated through the training phase may calculate a prediction result through a prediction phase.

[0080] 6 is a diagram illustrating a learning step (S10) and a prediction step (S30) of a vision correction surgery-related model according to an embodiment. Referring to FIG. 6, the learning step (S10) may include a learning data acquisition step (S110) and a model learning step (S150).

[0081] The learning data acquisition step (S110) may be a step of acquiring learning data, which is data for the learning device to learn and / or generate a vision correction surgery-related model.

[0082] The model training step (S150) may be a step of training and / or generating a vision correction surgery-related model. In the model training step (S150), a training device may train and / or generate the model based on training data acquired in the training data acquisition step. For example, model parameters constituting the vision correction surgery-related model may be changed in the model training step (S150). The accuracy of the model may be improved by changing the parameters.

[0083] The vision corrective surgery-related model may be trained based on vision corrective surgery-related information of patients who have undergone vision corrective surgery. For example, the model may be trained based on at least one of pre-vision examination data of patients who have undergone vision corrective surgery, surgical parameters of the vision corrective surgery performed on the patients, and post-vision examination data of the patients.

[0084] Referring to FIG. 6, the prediction step (S30) may include an input data acquisition step (S310) and a model execution step (S350).

[0085] The input data acquisition step (S310) may be a step of acquiring input data that is used by the prediction device to calculate a prediction result using a vision correction surgery-related model.

[0086] The model execution step (S350) may be a step of calculating a prediction result based on the vision correction surgery-related model learned and / or generated in the learning step (S10) and the input data. For example, the prediction device may output a prediction result based on the input data and model parameters obtained from the learning device.

[0087] The input data for the vision correction surgery-related model may include all information acquired for the subject, or may include at least a portion of the information acquired for the subject, and the input data may be the same or different for different vision correction surgery-related models.

[0088] The prediction results of the vision correction surgery-related model may vary depending on the training data, or the accuracy of the vision correction surgery-related model may vary depending on the training data.

[0089] The predicted result may vary depending on the type of true value included in the training data. For example, the predicted result may vary depending on whether the true value takes into account the subjective will of the subject. Here, the subjective will of the subject may include preferences, such as whether or not the subject prefers a particular vision correction surgery, and ability to pay, such as whether or not the subject will pay a certain amount of money for the vision correction surgery. When the subjective will of the subject is not taken into account, the predicted result may be a medically suggested result. On the other hand, when the subjective will of the subject is taken into account, the predicted result may be the same as or different from the medically suggested result.

[0090] If the first training data and the second training data are acquired at different hospitals, or acquired from different doctors, or acquired at different times, the first model trained and / or generated based on the first training data and the second model trained and / or generated based on the second training data may be different from each other. As a result, the first prediction result output by the first model and the second prediction result output by the second model may be different from each other. Furthermore, the accuracies of the first model and the second model may be different from each other.

[0091] However, the same vision correction surgery-related model can be trained and / or generated even if the training data is different, or the same prediction results can be calculated using vision correction surgery-related models trained and / or generated using different training data.

[0092] The training data, input data, and prediction results (hereinafter referred to as "input / output data") may include variables such as medical examination data and surgical parameters. The medical examination data and surgical parameters may be expressed in various ways, such as numbers, letters, images, etc., and are not limited to these representation methods. Furthermore, the images are not limited to their dimensions, such as two-dimensional or three-dimensional images.

[0093] The medical examination data may include interview data, which is information obtained by questioning without using equipment or examination, eyeball characteristic data, which is information about the eyeball obtained through equipment or examination, and genetic information.

[0094] The interview data may include the same variables as the subject's gender, age, race, living environment such as area of ​​residence, demographic characteristics such as occupation, income, educational background, education, and family size, medical and family history such as high blood pressure and diabetes, and preferences for vision correction surgery.

[0095] The ocular characteristic data may include any type of information about the eye, for example, the ocular characteristic data may include variables such as visual acuity, intraocular pressure, and / or retinal test results.

[0096] The ocular characteristic data may include information about the physical shape of the eye. In one example, the ocular characteristic data may include variables such as white-to-white (WTW) distance, angle-to-angle (ATA) distance, internal anterior chamber depth (ACD), sulcus-to-sulcus (STS) distance, and pupil size. In another example, the ocular characteristic data may include information about the shape of the cornea, such as corneal shape factors and corneal topography images. Here, the corneal shape factors are numerical values ​​that indicate the physical shape of the cornea, and may include variables such as the index of surface variance (ISV), index of vertical asymmetry (IVA), keratoconus index (KI), central keratoconus index (CKI), minimum radius of curvature (Rmin), index of height asymmetry (IHA), index of height decentration (IHD), and central cornea thickness. The corneal topography image is an image relating to the shape of the cornea, and may include a corneal topography diagram, an anterior corneal curvature image, a posterior corneal curvature image, a corneal thickness diagram, and the like.

[0097] The ocular characteristic data may be acquired using, but is not limited to, tomography, topography, optical coherence tomography (OCT), ultrasound biomicroscopy (UBM) equipment such as Pentacam, CASIA2, AL-Scan, and OQAS. Information that can be acquired through the above equipment and similar equipment and information derived therefrom may be included in the ocular characteristic data.

[0098] Genetic information can be obtained through genetic testing, etc. Genetic information can be used to determine whether a subject is suitable for vision correction surgery or to predict side effects after vision correction surgery. For example, genetic information can be used to predict whether a subject will develop corneal abnormalities.

[0099] Surgical parameters are variables related to the execution of vision correction surgery, and may include variables that can be changed during vision correction surgery, such as the type of vision correction surgery, such as LASIK, LASEK, small incision lenticular extraction, lens insertion, standard vision correction surgery, custom vision correction surgery, etc., corneal flap thickness, corneal flap diameter, flap side cut angle, corneal cutting profile, ocular suction time, surgical range (optic zone), hinge position, hinge angle, and hinge structure, such as hinge width.

[0100] Standard vision correction surgery may refer to vision correction surgery to correct low-order aberrations, and custom vision correction surgery may refer to vision correction surgery to correct low-order and high-order aberrations.

[0101] The types of surgical parameters considered by patients undergoing standard vision correction surgery and custom vision correction surgery may differ. For example, the types of surgical parameters considered by patients undergoing custom vision correction surgery may include the types of surgical parameters considered by patients undergoing standard vision correction surgery.

[0102] The number of surgical parameters that change depending on the patient in standard vision corrective surgery may be different from the number in custom vision corrective surgery. Standard vision corrective surgery and custom vision corrective surgery may be distinguished by the number of surgical parameters that change depending on the patient. The number of surgical parameters that change depending on the patient (hereinafter referred to as the "reference value") that distinguishes standard vision corrective surgery from custom vision corrective surgery may be a predetermined value. For example, if the number of surgical parameters that change depending on the patient is equal to or greater than the reference value, the surgery may be custom vision corrective surgery, and if it is less than the reference value, the surgery may be standard vision corrective surgery.

[0103] Standard and custom vision correction surgeries may vary depending on the hospital, doctor, and / or time period performing the vision correction surgery. For example, base prices may vary depending on the hospital, doctor, and / or time period.

[0104] Custom vision correction surgery can include ContourVision surgery and Wavefront surgery.

[0105] Custom vision correction surgery can improve the quality of vision compared to standard vision correction surgery. Vision quality is a comprehensive term that refers to the quality of vision, and can be determined based on not only visual acuity measured using an eye chart, low-order aberrations, and high-order aberrations, but also clarity of vision, light blur, contrast sensitivity, night vision, glare, double vision, afterimages, and other inconveniences.

[0106] The input / output data may include not only measured values ​​that can be acquired / measured through interviews, medical examinations, etc., but also predicted values ​​that can be calculated through vision correction surgery-related models, etc. For example, the ocular characteristic data may include not only measured values ​​of the subject's ocular characteristic data acquired / measured through pre-vision surgery examinations, etc., but also predicted values ​​of the subject's ocular characteristic data after vision correction surgery, calculated through vision correction surgery-related models, etc.

[0107] The input / output data may be preprocessed before being input to the vision correction surgery-related model. For example, a learning device may preprocess the acquired input / output data before using it to learn the vision correction surgery-related model. Alternatively, a prediction device may preprocess the acquired input / output data before inputting it to the vision correction surgery-related model to calculate a prediction result.

[0108] Preprocessing should be interpreted broadly to include any changes made to input or output data and is not limited to the examples disclosed herein.

[0109] The preprocessing may include selecting at least some of the variables that include the input / output data, such as feature selection. For example, the preprocessing may include t-test, Gini index, information gain, relief, DistAUC, signal to noise, MRMR, Fisher score, Laplacian score, SPEC, etc.

[0110] Preprocessing may include generating new variables from at least some of the variables containing the input and output data, such as feature extraction. For example, preprocessing may include principle component analysis, linear discriminant analysis, canonical correlation analysis, singular value decomposition, ISOMAP, locally linear embedding, etc. For other examples, preprocessing may include generating spectra from numerical values ​​or generating images from numerical values.

[0111] Preprocessing may include methods for handling missing values, such as missing value handling, when variables required by a vision correction surgery-related model (or a learning device and / or a predictor) are not included in the input / output data. For example, preprocessing may include handling missing values ​​using the mean or mode of the corresponding variable.

[0112] The accuracy of a vision correction surgery-related model can be improved through preprocessing. In one example, the accuracy of a vision correction surgery-related model that includes a feature selection step may be better than the accuracy of a model that does not include the feature selection step. In another example, the accuracy of a vision correction surgery-related model that generates an image from numerical values ​​and calculates a predicted result based on the image may be better than the accuracy of a vision correction surgery-related model that calculates a predicted result based on the numerical values.

[0113] 7 is a diagram illustrating preprocessing of input and output data according to one embodiment. Referring to FIG. 7, input and output data may be preprocessed (S500) and then input to a vision correction surgery-related model. The vision correction surgery-related model may calculate a prediction result based on the preprocessed input and output data (S700).

[0114] The vision correction surgery-related model can include multiple sub-models, each of which can calculate a predicted outcome based on input data.

[0115] A vision correction surgery related model may include sub-models linked in series and / or parallel, such as an ensemble model.

[0116] The vision correction surgery-related model may include a plurality of sub-models connected in series. Here, "sub-models connected in series" may include calculating the output of at least one sub-model based on the output of at least one sub-model, such as when the output of a first sub-model becomes the input of a second sub-model. Alternatively, "sub-models connected in series" may include passing through a plurality of sub-models in order to obtain a predicted result from input data through the vision correction surgery-related model.

[0117] 8 is a diagram illustrating a vision correction surgery-related model (M) including serially connected sub-models (M1, M2) according to one embodiment. Referring to FIG. 8, the vision correction surgery-related model (M) may include a first sub-model (M1) and a second sub-model (M2) connected in series. The first sub-model (M1) calculates an output based on input / output data, and the second sub-model (M2) calculates a prediction result based on the output of the first sub-model (M1).

[0118] The vision correction surgery-related model may include multiple sub-models connected in parallel, where the sub-models being connected in parallel may include the output of a sub-model not affecting the output of another sub-model, such as the output of a first sub-model not depending on the output of a second sub-model.

[0119] The inputs of the parallel-connected sub-models may be the same, or the inputs of the parallel-connected sub-models may be different. For example, the first medical data input to the first sub-model may be different from the second medical data input to the second sub-model.

[0120] The first medical data may include at least some other variables than the second medical data, for example, the first medical data may include a vision correction surgery preference, but the second medical data may not include a vision correction surgery preference.

[0121] The first medical examination data may include the same type of variables as the second medical examination data, but the values ​​may be different. For example, the first medical examination data and the second medical examination data may include corneal thickness, but the values ​​may be different because the methods for obtaining the values ​​are different (e.g., the corneal thickness is measured using different devices).

[0122] The vision correction surgery-related model may include an output sub-model that calculates an output based on the outputs of multiple sub-models connected in parallel. In one example, if the outputs of the multiple sub-models are the same, the output sub-model may provide the same output. In another example, if the outputs of the multiple sub-models are different, the output sub-model may output a result that takes into account the outputs of the multiple sub-models at a certain ratio, or may provide a specific output from among the multiple outputs. In yet another example, the output sub-model may output a result generated based on the outputs of the multiple sub-models.

[0123] 9 is a diagram illustrating a vision correction surgery-related model (M) including sub-models (M1, M2) connected in parallel according to one embodiment. Referring to FIG. 9, the vision correction surgery-related model (M) may include a first sub-model (M1) and a second sub-model (M2) connected in parallel. The vision correction surgery-related model (M) may also include an output sub-model (M3) that calculates an output based on the outputs of the first sub-model (M1) and the second sub-model (M2). The first sub-model (M1) and the second sub-model (M2) calculate a first output and a second output, respectively, based on input / output data, and the output sub-model (M3) may calculate a prediction result based on the first output and the second output.

[0124] An example of a vision surgery related model that includes sub-models connected in parallel may include, but is not limited to, an ensemble.

[0125] The following describes specific examples of vision correction surgery-related models.

[0126] The surgery suitability prediction model can predict whether or not a subject is suitable for vision correction surgery. The surgery suitability prediction model can predict whether or not a subject is suitable for surgery based on input data.

[0127] The appropriateness of vision correction surgery means medical appropriateness. Accordingly, the input data of the surgery appropriateness prediction model does not need to include the subject's preference for vision correction surgery. Alternatively, the surgery appropriateness prediction model can predict the appropriateness of surgery without considering the subject's preference for vision correction surgery.

[0128] The suitability for surgery may include whether surgery is possible and whether surgery is necessary. In one example, the surgery suitability prediction model may determine a subject who has good vision and does not need surgery as a surgery unsuitable subject. In another example, the surgery suitability prediction model may determine a subject whose vision cannot be improved by vision correction surgery as a surgery unsuitable subject.

[0129] The suitability of surgery can be output as surgery suitable / unsuitable, or the suitability of surgery can be output as a numerical value or visualized.

[0130] The laser surgery eligibility prediction model can predict whether a subject is eligible for laser vision correction surgery. Here, laser vision correction surgery refers to surgery that corrects vision through corneal ablation using a laser. The laser surgery eligibility prediction model can predict whether a subject is eligible for laser surgery based on input data.

[0131] The feasibility of laser-based vision correction surgery means medical feasibility. Accordingly, the input data of the laser surgery feasibility prediction model does not need to include the subject's preference for vision correction surgery. Alternatively, the laser surgery feasibility prediction model can predict the feasibility of laser surgery without considering the subject's preference for vision correction surgery.

[0132] The feasibility of laser surgery can be output as either possible or impossible, or the feasibility of laser surgery can be output as a numerical value or visualized.

[0133] The corneal shape factor prediction model can predict the corneal shape factor of a subject after vision correction surgery. The model can predict one or more corneal shape factors. The corneal shape factor prediction model can predict the corneal shape factor based on input data.

[0134] Input data for the corneal shape factor prediction model can include surgical parameters. For example, the input data can include the type of surgery as a surgical parameter. The model can predict corneal shape factors corresponding to the input surgical parameters. In one example, if the input data includes LASIK, LASEK, and small-incision lenticular extraction as surgical parameters, the output of the model can include a predicted corneal shape factor after LASIK, a predicted corneal shape factor after LASEK, and a predicted corneal shape factor after small-incision lenticular extraction. In another example, if the input data includes standard vision correction surgery and custom vision correction surgery as surgical parameters, the output of the model can include a predicted corneal shape factor after standard vision correction surgery and a predicted corneal shape factor after custom vision correction surgery.

[0135] The corneal shape factor prediction model can predict corneal shape factors corresponding to predetermined surgical parameters, regardless of whether its input data includes surgical parameters. For example, if the model is trained to predict corneal shape factors after standard vision corrective surgery and after custom vision corrective surgery, the model can output predicted corneal shape factors after standard vision corrective surgery and predicted corneal shape factors after custom vision corrective surgery even if the input data of the model does not include surgical parameters.

[0136] Table 1 shows the output of a corneal shape factor prediction model according to one embodiment. Referring to Table 1, the corneal shape factor prediction model can output the IHD, ISV, and IVA values ​​of a subject. The corneal shape factor prediction model can also include the subject's IHD, ISV, and IVA measurement values ​​obtained before vision correction surgery, predicted IHD, ISV, and IVA values ​​expected after standard vision correction surgery, and predicted IHD, ISV, and IVA values ​​expected after custom vision correction surgery.

[0137] JPEG0007741914000001.jpg34170

[0138] The custom vision corrective surgery need prediction model can predict whether a subject needs custom vision corrective surgery. The custom vision corrective surgery need prediction model can predict the need for custom vision corrective surgery based on input data.

[0139] The custom vision corrective surgery need prediction model can predict the need for custom vision corrective surgery without taking into account the subject's vision corrective surgery preferences. Alternatively, the custom vision corrective surgery need prediction model can predict the need for custom vision corrective surgery while taking into account the subject's vision corrective surgery preferences. The output of the custom vision corrective surgery need prediction model can change depending on whether or not the subject's vision corrective surgery preferences are taken into account.

[0140] The custom vision correction surgery necessity prediction model can determine whether a subject needs custom vision correction surgery based on ocular characteristic data such as corneal shape factors and corneal topography images.

[0141] The custom vision corrective surgery need prediction model can determine the need for custom vision corrective surgery based on the absolute numerical value of the corneal shape factor. For example, the custom vision corrective surgery need prediction model can predict that a subject needs custom vision corrective surgery if the corneal shape factor is outside a certain range.

[0142] The custom vision corrective surgery need prediction model can determine the need for custom vision corrective surgery based on the relative values ​​of the corneal shape factors. For example, the custom vision corrective surgery need prediction model can determine the need for custom vision corrective surgery by comparing the difference between the corneal shape factors after standard vision corrective surgery and the corneal shape factors after custom vision corrective surgery.

[0143] The vision corrective surgery recommendation model can recommend a vision corrective surgery for a subject. In one example, the model can output a single vision corrective surgery. In another example, the model can output multiple vision corrective surgeries. In yet another example, the model can output multiple vision corrective surgeries along with information regarding their priority.

[0144] The vision correction surgery suggestion model can suggest vision correction surgery based on input data.

[0145] The vision corrective surgery corresponding to the subject means a vision corrective surgery calculated by the vision corrective surgery proposal model without considering the subject's vision corrective surgery preference. Alternatively, the vision corrective surgery corresponding to the subject means a vision corrective surgery calculated by the vision corrective surgery proposal model while considering the subject's vision corrective surgery preference. The output of the vision corrective surgery proposal model can change depending on whether the subject's vision corrective surgery preference is considered.

[0146] An output of the vision correction surgery recommendation model may be a consideration of custom vision correction surgery needs, such as standard LASIK, custom LASIK, standard LASEK, custom LASEK, standard small incision lenticular extraction, custom small incision lenticular extraction, etc.

[0147] Alternatively, the output of the vision correction surgery suggestion model may be that the need for custom vision correction surgery was not considered. For example, the output may be that the need for custom vision correction surgery was not considered, such as LASIK, LASEK, small incision lenticular extraction, lens implantation, etc.

[0148] The vision corrective surgery recommendation model can recommend a vision corrective surgery based on the quality of vision after the vision corrective surgery. For example, the model can recommend a vision corrective surgery based on predicted vision after the vision corrective surgery corresponding to a plurality of vision corrective surgeries.

[0149] Table 2 is the output of a vision correction surgery suggestion model according to one embodiment. Referring to Table 2, the vision correction surgery suggestion model can output LASIK, LASEK, and small incision lenticular extraction surgeries along with information on priority, such as suitability. In the case of Table 2, the value corresponding to small incision lenticular extraction is greater than the values ​​corresponding to LASIK and LASEK, which means that the vision correction surgery suggestion model recommends small incision lenticular extraction as the first priority. In addition to the method shown in Table 2, information on priority can be output in various ways to indicate priority.

[0150] JPEG0007741914000002.jpg37170

[0151] The surgical parameter suggestion model can suggest surgical parameters. The model can suggest one or more surgical parameters. The surgical parameter suggestion model can suggest surgical parameters based on input data.

[0152] Input data for the surgical parameter suggestion model may include data in the form of an image. Here, the image may be an image acquired through measurement and / or inspection using a device along with a corneal topography. Alternatively, the image may be an image generated through interpolation, extrapolation, artificial intelligence, etc. based on measured values. For example, the image may be an image generated from corneal shape factors.

[0153] The surgical results of vision correction surgery performed based on surgical parameters suggested by the surgical parameter suggestion model based on an image may be better than the surgical results of vision correction surgery performed based on surgical parameters suggested based on numerical values. For example, the surgical results of vision correction surgery performed based on surgical parameters suggested by the model based on corneal topography images may be better than the surgical results of vision correction surgery performed based on surgical parameters suggested based on corneal shape factors such as IHD, ISV, and IVA. Here, the surgical results refer to the quality of post-operative vision. Alternatively, the surgical results refer to the shape of the post-operative cornea.

[0154] The visual acuity prediction model can predict a subject's visual acuity after vision correction surgery. The visual acuity prediction model can output a visual acuity prediction value based on input data. The model can predict one or more visual acuities.

[0155] Input data for the visual acuity prediction model may include surgical parameters. For example, the input data may include the type of surgery as a surgical parameter. The model may predict visual acuity corresponding to the input surgical parameters. In one example, if the input data includes LASIK, LASEK, and small-incision lenticular extraction as surgical parameters, the output of the model may include predicted visual acuity after LASIK, predicted visual acuity after LASEK, and predicted visual acuity after small-incision lenticular extraction. In another example, if the input data includes standard vision correction surgery and custom vision correction surgery as surgical parameters, the output of the model may include predicted visual acuity after standard vision correction surgery and predicted visual acuity after custom vision correction surgery.

[0156] A visual acuity prediction model can predict visual acuity corresponding to predetermined surgical parameters, regardless of whether its input data includes surgical parameters. For example, if the model is trained to predict visual acuity after standard vision corrective surgery and visual acuity after custom vision corrective surgery, the model can output predicted visual acuity values ​​after standard vision corrective surgery and predicted visual acuity values ​​after custom vision corrective surgery, even if the input data of the model does not include surgical parameters.

[0157] The visual acuity prediction model can predict visual acuity corresponding to multiple different times. For example, the model can predict visual acuity corresponding to a first time and a second time after vision correction surgery. Examples of multiple different times include, but are not limited to, one day, one week, one month, six months, and one year after vision correction surgery.

[0158] The visual acuity prediction model can predict the subject's visual acuity recovery rate based on predicted visual acuity values ​​corresponding to multiple different times. For example, the model can predict the visual acuity recovery rate based on a first time and a second time after vision correction surgery.

[0159] The predicted visual acuity image generation model can predict the visual field of a subject after vision correction surgery. The model can generate a visualized image of the quality of the subject's vision after vision correction surgery (hereinafter referred to as the "predicted visual acuity image"). By outputting the predicted visual acuity image, vision correction surgery can be more easily explained to the subject. By visualizing and outputting the visual field after vision correction surgery, the model can more clearly understand the expected results after vision correction surgery, which can be useful in selecting vision correction surgery.

[0160] Input data for the predicted vision image generation model may include surgical parameters. For example, the input data may include the type of surgery as a surgical parameter. The model may predict a predicted vision image corresponding to the input surgical parameters. In one example, if the input data includes LASIK, LASEK, and small-incision lenticular extraction as surgical parameters, the output of the model may include a predicted vision image after LASIK, a predicted vision image after LASEK, and a predicted vision image after small-incision lenticular extraction. In another example, if the input data includes standard vision correction surgery and custom vision correction surgery as surgical parameters, the output of the model may include a predicted vision image after standard vision correction surgery and a predicted vision image after custom vision correction surgery. In yet another example, if the input data includes multiple surgical zones (optic zones), the output of the model may include multiple predicted vision images corresponding to the multiple surgical zones.

[0161] The predicted visual acuity image generation model can generate predicted visual acuity images corresponding to predetermined surgical parameters, regardless of whether its input data includes surgical parameters. For example, if the model is trained to generate predicted visual acuity images after standard vision corrective surgery and predicted visual acuity images after custom vision corrective surgery, the model can output predicted visual acuity images after standard vision corrective surgery and predicted visual acuity images after custom vision corrective surgery even if the input data of the model does not include surgical parameters.

[0162] The predicted vision image may include information on at least one of the subject's predicted vision sharpness, light blur, contrast sensitivity, night vision, glare, double vision, and afterimages after vision correction surgery. 10A and 10B are diagrams illustrating predicted visual acuity images according to an embodiment. Referring to FIG. 10A, predicted visual acuity images (I1, I2) can visualize and represent information related to the clarity of visual acuity. Referring to FIG. 10B, predicted visual acuity images (I3, I4, I5, I6) can visualize and represent information related to light blurring. Each of the multiple predicted vision images may correspond to different surgical parameters. Referring to FIG. 10a, the first predicted vision image (I1) may correspond to the clarity of vision after custom vision correction surgery, and the second predicted vision image (I2) may correspond to the clarity of vision after standard vision correction surgery. Referring to FIG. 10b, the third through sixth predicted vision images (I3-I6) may correspond to different surgical zones. For example, the surgical zone of the third predicted vision image (I3) may be larger than the surgical zones of the fourth through sixth predicted vision images (I4-I6).

[0163] According to an embodiment, the predicted visual acuity image may be generated through filtering using a filter. Here, filtering may refer to generating a filtered image by convolving an image with a filter, as a concept commonly used in the field of image processing. Examples of filters include, but are not limited to, an average filter, a weighted average filter, a low-pass filter, a Gaussian filter, a median filter, a bilateral filter, a blurring filter, a high-pass filter, an unsharp masking filter, a high-boost filter, and a sharpening filter.

[0164] 11 is a diagram illustrating a predicted visual acuity image generation model (M17) using a filter according to an embodiment. Referring to FIG. 11, the predicted visual acuity image generation model (M17) can include a first sub-model (M171) and a second sub-model (M172).

[0165] The first sub-model (M171) can calculate and / or select a filter based on input data. In one example, the input data includes predicted ocular characteristic data values ​​after vision correction surgery of the subject, and the first sub-model (M171) can calculate and / or select a filter based on the predicted ocular characteristic data values. In another example, the input data includes measured ocular characteristic data values ​​and surgical parameters of the subject, and the first sub-model (M171) can calculate and / or select a filter based on the measured ocular characteristic data values ​​and the surgical parameters.

[0166] The second sub-model (M172) can generate a predicted visual acuity image based on the filter calculated and / or selected by the first sub-model (M171). For example, the second sub-model (M172) can generate a predicted visual acuity image by applying the filter to an original image. Here, the original image can be input from outside the predicted visual acuity image generation model (M17) as a base image for generating the predicted visual acuity image, or can be included in the model (M17).

[0167] The corneal topography image prediction model can predict a corneal topography image of a subject after vision correction surgery. The model can predict one or more corneal topography images. The corneal topography image prediction model can generate a corneal topography image based on input data.

[0168] Input data for the corneal topography image prediction model can include surgical parameters. For example, the input data can include the type of surgery as a surgical parameter. The model can predict corneal topography images corresponding to the input surgical parameters. In one example, if the input data includes LASIK, LASEK, and small-incision lenticular extraction as surgical parameters, the output of the model can include a post-LASIK corneal topography image, a post-LASIK corneal topography image, and a post-small-incision lenticular extraction corneal topography image. In another example, if the input data includes standard vision correction surgery and custom vision correction surgery as surgical parameters, the output of the model can include a post-standard vision correction surgery corneal topography image and a post-custom vision correction surgery corneal topography image.

[0169] The corneal topography image prediction model can generate corneal topography images corresponding to predetermined surgical parameters, regardless of whether its input data includes surgical parameters. For example, if the model is trained to generate corneal topography images of visual acuity after standard vision corrective surgery and corneal topography images of custom vision corrective surgery, the model can output corneal topography images of standard vision corrective surgery and corneal topography images of custom vision corrective surgery even if the input data of the model does not include surgical parameters.

[0170] Input data for the corneal topography image prediction model can include a corneal topography image of a subject measured before vision correction surgery. Figure 12 is a diagram illustrating a corneal topography image according to one embodiment. Referring to Figure 12, the corneal topography image prediction model (M18) can predict a corneal topography image (CI2) of a subject after vision correction surgery based on a corneal topography image (CI1) of the subject measured before vision correction surgery. Although Figure 12 illustrates only the corneal topography image (CI1) being input to the model (M18), other input data can also be input.

[0171] The prediction result calculation cause analysis model can analyze the causes of the calculation of the prediction result generated by the vision correction surgery-related model. The model can calculate the dependency of the vision correction surgery-related model on input data. Here, the dependency can include how a specific variable of the input data affects the prediction result.

[0172] The prediction result calculation cause analysis model may output a prediction result calculation cause. The model may output one or more prediction result calculation causes. For convenience of explanation, the following description will be given assuming that the prediction result calculation cause is expressed as a numerical value such as a dependency coefficient. However, the prediction result calculation cause is not limited to this and may be expressed in any manner, such as a numerical value, an image, text, or a combination thereof.

[0173] The causal analysis model for calculating a predicted outcome may output at least some of the dependency coefficients, for example, the model may output all of the calculated dependency coefficients.

[0174] The prediction result calculation cause analysis model may output the calculated dependency coefficients that fall within a certain range. For example, the model may output the calculated dependency coefficients that are greater than a predetermined value. Alternatively, the model may output the calculated dependency coefficients whose absolute values ​​are greater than a predetermined value.

[0175] The prediction result calculation cause analysis model can output a predetermined number of dependency coefficients. For example, the model can output a predetermined number of dependency coefficients.

[0176] The causal analysis model for calculating predicted results may include an analytical model for predicting the suitability of surgery, an analytical model for predicting the suitability of laser surgery, an analytical model for predicting the cause of corneal shape factors, an analytical model for predicting the need for custom vision correction surgery, an analytical model for proposing vision correction surgery, an analytical model for proposing surgery parameters, an analytical model for predicting the cause of visual acuity, an analytical model for generating predicted vision images, and an analytical model for predicting corneal topography images. For example, the analytical model for predicting the cause of visual acuity may calculate how variables included in the input data of the visual acuity prediction model affect the visual acuity prediction model's prediction of visual acuity. Alternatively, the analytical model for predicting the cause of visual acuity may calculate the dependency of the visual acuity prediction value calculated by the visual acuity prediction model on the input data of the visual acuity prediction model.

[0177] The cause analysis model for calculating the predicted outcome may include at least a portion of a vision correction surgery-related model. For example, the cause analysis model for visual acuity prediction may include a visual acuity prediction model.

[0178] 13 is a diagram illustrating a predicted outcome calculation cause analysis model (M19) including a vision correction surgery-related model (M192) according to one embodiment. Referring to FIG. 27, the predicted outcome calculation cause analysis model (M19) can include an input data disturbance model (M191), a vision correction surgery-related model (M192), and a predicted outcome analysis model (M193).

[0179] The input data perturbation model (M191) can output perturbed input data based on input data. The model (M191) can output one or more perturbed input data. Here, perturbing the input data means changing the input data, such as changing the values ​​of at least some variables included in the input data. For example, if the variables are numerical values, perturbation means increasing or decreasing the numerical values. Alternatively, if the variables are images, perturbation means increasing or decreasing the pixel values ​​of at least some pixels of the image.

[0180] The vision corrective surgery-related model (M192) can output a first prediction result corresponding to the input data and a second prediction result corresponding to the disturbed input data based on input data and disturbed input data. For example, if the vision corrective surgery-related model (M192) included in the prediction result calculation cause analysis model (M19) is a visual acuity prediction model, the first prediction result and the second prediction result may be different visual acuity prediction values. Furthermore, if there are multiple disturbed input data, the model can output multiple prediction results corresponding to the multiple disturbed input data.

[0181] The prediction result analysis model (M193) can output the cause of calculation of the prediction result based on the prediction result. For example, the model (M193) can calculate the cause of calculation of the prediction result based on the difference between a first prediction result calculated from unperturbed input data and a second prediction result calculated from perturbed input data. Specifically, the model (M193) can calculate the dependency of the first prediction result on the first variable based on the difference between the first prediction result and a second prediction result calculated from input data perturbed by a first variable.

[0182] FIG. 14 is a diagram illustrating causes of calculation of a prediction result according to one embodiment, specifically, causes of visual acuity prediction. Referring to FIG. 14, the causes of calculation of a prediction result may be displayed using numerical values ​​and images. The same characters as Cornea_Back_Rmin (V1), Astigmatism (V2), Mono (V3), Nearsightedness (V4), Op_flag (V5), and Pupil_Dia (V6) shown in FIG. 14 may correspond to variables included in the input data. The values ​​5.95 (N1), -0.5 (N2), 0 (N3), -1.37 (N4), 2 (N5), 3.1 (N6), etc., shown corresponding to the characters may correspond to the numerical values ​​of variables included in the input data.

[0183] The dependency of the prediction result on variables may be visualized. For example, the dependency may be indicated by the length, color, direction, etc. of the arrow. Referring to FIG. 14, the length of the arrow may correspond to the absolute value of the dependency coefficient. The direction and color of the arrow may correspond to the sign of the dependency coefficient. In FIG. 14, the visual acuity prediction value (OV) is 1.18, and it can be interpreted that Cornea_Back_Rmin (V1), Astigmatism (V2), Mono (V3), and Nearsightedness (V4) have a positive effect on the visual acuity prediction value, and Op_flag (V5) and Pupul_Dia (V6) have a negative effect on the visual acuity prediction value.

[0184] Examples of the cause analysis model for calculating the predicted results include, but are not limited to, LIME (Local Interpretable Model-agnostic Explanations).

[0185] Vision correction surgery related models can be combined with one another. The models can be combined by at least one of serial connection and parallel connection.

[0186] The phrase "vision correction surgery-related models are connected in series" may include calculating an output of at least one vision correction surgery-related model based on an output of at least another vision correction surgery-related model.

[0187] The vision correction surgery-related models being connected in parallel may include an output of a vision correction surgery-related model not affecting an output of a different vision correction surgery-related model.

[0188] Below, an example of a combination of models related to vision correction surgery will be examined.

[0189] 15 is a diagram illustrating a serial connection of vision corrective surgery-related models according to one embodiment. Referring to FIG. 15, a first vision corrective surgery-related model (Ma) and a second vision corrective surgery-related model (Mb) can be combined in a serial connection. The first vision corrective surgery-related model (Ma) can calculate a first prediction result based on first input data, and the second vision corrective surgery-related model (Mb) can calculate a second prediction result based on second input data.

[0190] 16 to 19 are diagrams relating to calculation of the output of a vision correction surgery-related model based on the output of a corneal shape factor prediction model according to one embodiment.

[0191] Referring to Figure 16, the custom vision correction surgery necessity prediction model (M13) can predict the subject's need for custom vision correction surgery based on the corneal shape factor output by the corneal shape factor prediction model (M12) after receiving the second input data, and the first input data.

[0192] Referring to Figure 17, the vision correction surgery proposal model (M14) can propose vision correction surgery for the subject based on the corneal shape factor output by the corneal shape factor prediction model (M12) after receiving the second input data, and the first input data.

[0193] Referring to Figure 18, the predicted visual acuity image generation model (M17) can generate a predicted visual acuity image of the subject after vision correction surgery based on the corneal shape factor output by the corneal shape factor prediction model (M12) after receiving the second input data, and the first input data.

[0194] Referring to Figure 19, the corneal topography image prediction model (M18) can predict the corneal topography image of the subject after vision correction surgery based on the corneal shape factor output by the corneal shape factor prediction model (M12) after receiving the second input data, and the first input data.

[0195] 20 is a diagram illustrating calculation of the output of a vision corrective surgery-related model based on the output of a custom vision corrective surgery necessity prediction model according to one embodiment. Referring to FIG. 20, the vision corrective surgery recommendation model (M14) can recommend a vision corrective surgery for a subject based on the custom vision corrective surgery necessity output by the custom vision corrective surgery necessity prediction model (M13) after receiving the second input data, and the first input data.

[0196] 21 and 22 are diagrams relating to calculation of the output of a vision correction surgery-related model based on the output of a vision correction surgery proposal model according to one embodiment.

[0197] Referring to Figure 21, the corneal shape factor prediction model (M12) can predict the corneal shape factor of the subject after the vision correction surgery based on the vision correction surgery output by the vision correction surgery proposal model (M14) after receiving the second input data and the first input data.

[0198] Referring to Figure 22, the visual acuity prediction model (M16) can calculate the predicted visual acuity value of the subject after the vision correction surgery based on the vision correction surgery output by the vision correction surgery proposal model (M14) after receiving the second input data, and the first input data.

[0199] The predicted visual acuity image generation model can generate a predicted visual acuity image of the subject after the vision corrective surgery based on the vision corrective surgery output by the vision corrective surgery proposal model after receiving the second input data, and the first input data.

[0200] The corneal topography image prediction model can predict the vision correction surgery output by the vision correction surgery proposal model after receiving the second input data, and the corneal topography image of the subject after the vision correction surgery based on the first input data.

[0201] FIG. 23 is a diagram illustrating calculation of the output of a vision correction surgery-related model based on the output of a surgery parameter suggestion model, according to one embodiment.

[0202] Referring to Figure 23, the visual acuity prediction model (M16) can calculate the predicted visual acuity of the subject after vision correction surgery based on the surgical parameters output by the surgical parameter proposal model (M15) after receiving the second input data and the first input data.

[0203] The corneal shape factor prediction model can predict the corneal shape factor of the subject after vision correction surgery based on the surgical parameters output by the surgical parameter proposal model after receiving the second input data, and the first input data.

[0204] The predicted visual acuity image generation model can generate a predicted visual acuity image of the subject after vision correction surgery based on the surgical parameters output by the surgical parameter proposal model after receiving the second input data and the first input data.

[0205] The corneal topography image prediction model can predict the corneal topography image of the subject after vision correction surgery based on the surgical parameters output by the surgical parameter proposal model after receiving the second input data, and the first input data.

[0206] 24 and 25 are diagrams relating to calculation of the output of a vision correction surgery-related model based on the output of a visual acuity prediction model according to one embodiment.

[0207] Referring to Figure 24, the vision correction surgery proposal model (M14) can propose a vision correction surgery appropriate for the subject based on the vision prediction value output by the vision prediction model (M16) after receiving the second input data, and the first input data.

[0208] Referring to Figure 25, the predicted visual acuity image generation model (M17) can generate a predicted visual acuity image of the subject after vision correction surgery based on the visual acuity prediction value output by the visual acuity prediction model (M16) after receiving the second input data and the first input data.

[0209] 26-27 are diagrams relating to calculation of the output of a vision correction surgery-related model based on the output of a corneal topography image prediction model, according to one embodiment.

[0210] Referring to Figure 26, the custom vision correction surgery necessity prediction model (M13) can predict the subject's need for custom vision correction surgery based on the corneal topography image output by the corneal topography image prediction model (M18) after receiving the second input data, and the first input data.

[0211] Referring to Figure 27, the vision correction surgery proposal model (M14) can propose vision correction surgery for the subject based on the corneal topography image output by the corneal topography image prediction model (M18) after receiving the second input data and the first input data.

[0212] The corneal shape factor prediction model can predict the corneal shape factor of the subject after vision correction surgery based on the corneal topography image output by the corneal topography image prediction model after receiving second input data, and the first input data.

[0213] The predicted visual acuity image generation model can generate a predicted visual acuity image of the subject after vision correction surgery based on the corneal topography image output by the corneal topography image prediction model after receiving second input data, and the first input data.

[0214] Three or more vision corrective surgery-related models may be combined in series and / or in parallel. FIG. 28 is a diagram illustrating a combination of three or more vision corrective surgery-related models according to one embodiment. Referring to FIG. 28, the first vision corrective surgery-related model (Ma) can calculate a second prediction result output by the second vision corrective surgery-related model (Mb) receiving second input data, a third prediction result output by the third vision corrective surgery-related model (Mc) receiving third input data, and a first prediction result input by the first input data. Here, the first vision corrective surgery-related model (Ma) can be considered to be connected in series with the second vision corrective surgery-related model (Mb) and the third vision corrective surgery-related model (Mc). Furthermore, the second vision corrective surgery-related model (Mb) and the third vision corrective surgery-related model (Mc) can be considered to be connected in parallel.

[0215] 29 and 30 are diagrams relating to calculation of the output of a vision corrective surgery-related model based on the outputs of a corneal shape factor prediction model and a visual acuity prediction model according to one embodiment.

[0216] Referring to Figure 29, the vision correction surgery proposal model (M14) can propose vision correction surgery corresponding to the subject based on the corneal shape factor output by the corneal shape factor prediction model (M12) after receiving the second input data, the visual acuity prediction value output by the visual acuity prediction model (M16) after receiving the third input data, and the first input data.

[0217] Referring to Figure 30, the predicted visual acuity image generation model (M17) can generate a predicted visual acuity image of the subject after vision correction surgery based on the corneal shape factor output by the corneal shape factor prediction model (M12) after receiving the second input data, the visual acuity predicted value output by the visual acuity prediction model (M16) after receiving the third input data, and the first input data.

[0218] Vision correction surgery related models can be merged together. Multiple vision correction surgery related models can be merged into a single model that performs at least some of the functions of the individual models.

[0219] FIG. 31 is a diagram illustrating the merging of vision corrective surgery-related models according to one embodiment. Referring to FIG. 31, a first vision corrective surgery-related model and a second vision corrective surgery-related model may be merged to form one model (Mab). The one model (Mab) may calculate a prediction result based on input data. Here, the prediction result may include information corresponding to at least one of a first prediction result corresponding to the output of the first vision corrective surgery-related model and a second prediction result corresponding to the output of the second vision corrective surgery-related model. For example, the prediction result may include at least one of the first prediction result and the second prediction result. Alternatively, the prediction result may include information corresponding to at least one of the first prediction result and the second prediction result.

[0220] Although FIG. 31 illustrates the case where two models are merged, the present invention is not limited to this and it is also possible to merge three or more models.

[0221] 32-34 are diagrams of an implementation of vision surgery related model merging according to one embodiment. Referring to Figure 32, the corneal shape factor prediction model and the custom vision corrective surgery need prediction model can be merged. The merged model (M25) can calculate a prediction result based on input data. The prediction result can include information corresponding to at least one of the corneal shape factor and the need for custom vision corrective surgery. For example, the prediction result can include at least one of the corneal shape factor and the need for custom vision corrective surgery.

[0222] Referring to Figure 33, the custom vision corrective surgery necessity prediction model and the vision corrective surgery recommendation model may be merged. The merged model (M27) may calculate a prediction result based on input data. The prediction result may include information corresponding to at least one of the custom vision corrective surgery necessity and the vision corrective surgery. For example, the prediction result may include at least one of the custom vision corrective surgery necessity and the vision corrective surgery.

[0223] Referring to Figure 34, the laser surgery feasibility prediction model, the custom vision corrective surgery necessity prediction model, and the vision corrective surgery recommendation model can be merged. The merged model (M38) can calculate a prediction result based on input data. The prediction result can include information corresponding to at least one of the laser surgery feasibility, the necessity of custom vision corrective surgery, and vision corrective surgery. For example, the prediction result can include at least one of the laser surgery feasibility, the necessity of custom vision corrective surgery, and vision corrective surgery.

[0224] Below, examples of recommended methods for vision correction surgery will be examined.

[0225] The vision corrective surgery recommendation method may be implemented using one or more vision corrective surgery-related models. When the method is implemented using a plurality of vision corrective surgery-related models, whether or not at least one vision corrective surgery-related model is executed may depend on the prediction result of at least one other vision corrective surgery-related model. For example, whether or not a second vision corrective surgery-related model is executed may depend on the prediction result of a first vision corrective surgery-related model.

[0226] Each step of the vision correction surgery recommendation method described below can be performed by a prediction device.

[0227] FIG. 35 is a diagram relating to a first embodiment of a method for recommending vision correction surgery according to one embodiment.

[0228] Referring to FIG. 35, a method for recommending vision correction surgery according to one embodiment may include a step of acquiring medical examination data of a subject (S1100), a step of predicting whether the subject is suitable for vision correction surgery (S1200), a step of predicting whether the subject is suitable for vision correction surgery using a laser (S1300), a step of calculating a predicted corneal shape factor value of the subject (S1400), and a step of proposing vision correction surgery suitable for the subject (S1500).

[0229] The step of acquiring medical data of the subject (S1100) may include a computing device acquiring the medical data including interview data and ocular characteristic data measurements.

[0230] The step of predicting whether the subject is suitable for vision corrective surgery (S1200) may include inputting a first group of data obtained from the subject's medical examination data into a first prediction model to predict whether the subject is suitable for vision corrective surgery. The first prediction model may be a surgery suitability prediction model. The surgery suitability prediction model can predict whether the subject is suitable for vision corrective surgery based on the first group of data.

[0231] The step of predicting whether the subject is a candidate for laser-based vision correction surgery (S1300) may include inputting a second group of data acquired from the subject's medical examination data into a second prediction model to predict whether the subject is a candidate for laser-based vision correction surgery. Whether or not the step (S1300) is performed may depend on whether the subject is a candidate for vision correction surgery. For example, the step (S1300) may be performed if the subject is a candidate for vision correction surgery. The second prediction model may be a laser surgery candidate prediction model. The laser surgery candidate prediction model can predict whether the subject is a candidate for laser surgery based on the second group of data.

[0232] The step of calculating the predicted corneal shape factor of the subject (S1400) may include inputting a third group of data obtained from the subject's medical examination data into a third prediction model to calculate the predicted corneal shape factor after standard vision correction surgery and the predicted corneal shape factor after custom vision correction surgery of the subject. Whether or not the step (S1400) is performed may depend on whether the subject is eligible for vision correction surgery using a laser. For example, the step (S1400) may be performed if the subject is eligible for vision correction surgery using a laser. The third prediction model may be a corneal shape factor prediction model. The third prediction model may predict the corneal shape factor based on the third group of data. In this case, the need for custom vision correction surgery may be determined based on the corneal shape factor.

[0233] The step of proposing a vision corrective surgery for the subject (S1500) may include inputting a fourth group of data acquired from the subject's medical examination data into a fourth prediction model to propose a vision corrective surgery for the subject. Whether or not the step (S1500) is performed may depend on whether the subject is eligible for vision corrective surgery using a laser. For example, the step (S1500) may be performed if the subject is eligible for vision corrective surgery using a laser. The fourth prediction model may be trained based on at least one of medical examination data of multiple subjects who have undergone vision corrective surgery, the vision corrective surgery corresponding to the multiple subjects, and the visual acuity of the multiple subjects after the vision corrective surgery. The fourth prediction model may be a vision corrective surgery proposing model. The fourth prediction model may propose a vision corrective surgery for the subject based on the fourth group of data.

[0234] Referring to FIG. 35 , the vision correction surgery may be one that does not take into account the predicted corneal shape factor and / or the need for custom vision correction surgery. For example, the vision correction surgery may include LASIK, LASEK, and small-incision lenticular extraction. Furthermore, because lens insertion is not always possible even when laser vision correction surgery is possible, the vision correction surgery may include lens insertion. This also applies to other embodiments and implementations of this specification. In this case, the vision correction surgery that takes into account the predicted corneal shape factor and / or the need for custom vision correction surgery can be determined by the doctor and / or consultant. For example, the doctor and / or consultant can determine the vision correction surgery that takes into account the need for custom vision correction surgery, such as standard LASIK, standard LASEK, standard small-incision lenticular extraction, custom LASIK, custom LASEK, or custom small-incision lenticular extraction, based on the predicted corneal shape factor and the vision correction surgery output by the vision correction surgery recommendation method of FIG. 35 .

[0235] FIG. 36 is a diagram relating to a second embodiment of a method for recommending vision correction surgery according to an embodiment.

[0236] Referring to FIG. 36, a method for recommending vision correction surgery according to one embodiment may include a step of acquiring medical examination data of a subject (S2100), a step of predicting whether the subject is suitable for vision correction surgery (S2200), a step of predicting whether the subject is suitable for vision correction surgery using a laser (S2300), a step of calculating a predicted corneal shape factor value of the subject (S2400), and a step of proposing vision correction surgery suitable for the subject (S2500).

[0237] The method for recommending vision correction surgery in FIG. 36 is similar to that in FIG. 35, so differences from FIG. 35 will be mainly described.

[0238] Referring to FIG. 36 , the step of proposing a vision correction surgery for the subject (S2500) may suggest a vision correction surgery based on the predicted corneal shape factor after standard vision correction surgery and the predicted corneal shape factor after custom vision correction surgery, which are calculated in the step of calculating the predicted corneal shape factor of the subject. The vision correction surgery may be performed taking into consideration the need for custom vision correction surgery. For example, the vision correction surgery may include standard LASIK, standard LASEK, standard small incision lenticular extraction, custom LASIK, custom LASEK, and custom small incision lenticular extraction. The vision correction surgery may also include lens implantation.

[0239] FIG. 37 is a diagram relating to a third embodiment of a method for recommending vision correction surgery according to an embodiment.

[0240] Referring to FIG. 37, a method for recommending vision correction surgery according to one embodiment may include a step of acquiring medical examination data of a subject (S3100), a step of predicting whether the subject is suitable for vision correction surgery (S3200), a step of predicting whether the subject is suitable for vision correction surgery using a laser (S3300), a step of predicting whether the subject needs custom vision correction surgery (S3400), and a step of proposing vision correction surgery corresponding to the subject (S3500).

[0241] The recommended method for vision correction surgery in FIG. 37 is similar to that in FIG. 35, so differences from FIG. 35 will be mainly described. Referring to FIG. 37 , the step of predicting whether the subject needs custom vision corrective surgery (S3400) may include inputting a third group of data acquired from the subject's medical examination data into a third prediction model to predict whether the subject needs custom vision corrective surgery. Whether step (S3400) is performed may depend on whether the subject is eligible for laser vision corrective surgery. For example, step (S3400) may be performed if the subject is eligible for laser vision corrective surgery. The third prediction model may be a model for predicting the need for custom vision corrective surgery. The third prediction model may predict the need for custom vision corrective surgery based on the third group of data. The step may predict the need for custom vision corrective surgery based on the subject's predicted corneal shape factor after standard vision corrective surgery and the predicted corneal shape factor after custom vision corrective surgery.

[0242] The step of predicting whether the subject needs custom vision corrective surgery (S3400) and the step of proposing corresponding vision corrective surgery to the subject (S3500) may be coupled. For example, the output of the step of proposing corresponding vision corrective surgery to the subject (S3500) may be calculated based on the output of the step of predicting whether the subject needs custom vision corrective surgery (S3400). Alternatively, the output of the step of predicting whether the subject needs custom vision corrective surgery to the subject (S3400) may be calculated based on the output of the step of proposing corresponding vision corrective surgery to the subject (S3500).

[0243] In one example, the step of proposing a vision correction surgery corresponding to the subject (S3500) may suggest a vision correction surgery based on the need for custom vision correction surgery calculated in the step of predicting whether the subject needs custom vision correction surgery (S3400). For example, the vision correction surgery may include standard LASIK, standard LASEK, standard small incision lenticular extraction, custom LASIK, custom LASEK, and custom small incision lenticular extraction. The vision correction surgery may also include lens implantation.

[0244] In another example, the step of predicting whether the subject needs custom vision corrective surgery (S3400) may output a second vision corrective surgery based on the first vision corrective surgery calculated in the step of proposing a vision corrective surgery corresponding to the subject (S3500). Here, the first vision corrective surgery may be one in which the need for custom vision corrective surgery is not taken into consideration, and the second vision corrective surgery may be one in which the need for custom vision corrective surgery is taken into consideration.

[0245] In another example, in predicting whether or not the subject needs custom vision corrective surgery (S3400), whether or not to perform the surgery may be determined based on the type of the first vision corrective surgery calculated in proposing vision corrective surgery corresponding to the subject (S3500). For example, if the first vision corrective surgery is of a first type, the custom vision corrective surgery necessity prediction model may not be executed, and if the first vision corrective surgery is of a second type, the custom vision corrective surgery necessity prediction model may be executed.

[0246] The first and second types can be distinguished by whether or not corneal ablation is performed using a laser. For example, the first type may be a non-laser vision correction surgery such as lens implantation, and the second type may be a laser vision correction surgery such as LASIK, LASEK, or small incision lenticular extraction.

[0247] The first and second types may be distinguished based on whether or not a procedure allows custom surgery. For example, the first type may be a vision correction procedure that does not allow custom surgery, and the second type may be a vision correction procedure that allows custom surgery. Here, whether or not a procedure allows custom surgery may be determined based on predetermined criteria. However, such criteria may vary depending on technological developments, hospitals, surgical equipment, the circumstances and judgment of physicians, etc. For example, if custom small-incision lenticular extraction is not available, the first type may include small-incision lenticular extraction and lens implantation, and the second type may include LASIK and LASEK. However, if custom small-incision lenticular extraction is available, the first type may include lens implantation, and the second type may include LASIK, LASEK, and small-incision lenticular extraction.

[0248] FIG. 38 is a diagram relating to a fourth embodiment of a method for recommending vision correction surgery according to an embodiment.

[0249] Referring to Figure 38, a method for recommending vision correction surgery according to one embodiment may include a step of acquiring medical examination data of a subject (S4100), a step of predicting whether the subject is suitable for vision correction surgery (S4200), a step of predicting whether the subject is suitable for vision correction surgery using a laser (S4300), and a step of proposing vision correction surgery suitable for the subject (S4400).

[0250] The step of acquiring the subject's medical examination data (S4100), the step of predicting whether the subject is suitable for vision correction surgery (S4200), and the step of predicting whether the subject is suitable for vision correction surgery using a laser (S4300) in Figure 38 are the same as those in Figure 35, so explanations thereof will be omitted.

[0251] The step of suggesting corresponding vision correction surgery for the subject (S4400) may include inputting a third group of data obtained from the subject's medical examination data into a third prediction model and suggesting corresponding vision correction surgery for the subject.

[0252] Whether or not step S4400 is performed may depend on whether the subject is eligible for laser-based vision correction surgery. For example, step S4400 may be performed if the subject is eligible for laser-based vision correction surgery. Step S4400 may suggest vision correction surgery based on the predicted corneal shape factor after standard vision correction surgery and the predicted corneal shape factor after custom vision correction surgery.

[0253] The third prediction model may be a model that combines a custom vision corrective surgery necessity prediction model and a vision corrective surgery recommendation model. The third prediction model may be trained based on at least one of medical examination data of a plurality of patients who have undergone vision corrective surgery, the vision corrective surgery corresponding to the plurality of patients, and the visual acuity of the plurality of patients after the vision corrective surgery. The third prediction model may output information regarding at least one of the custom vision corrective surgery necessity and the vision corrective surgery based on the third group data. For example, the output of the third prediction model may include at least one of the custom vision corrective surgery necessity and the vision corrective surgery.

[0254] FIG. 39 is a diagram relating to a fifth embodiment of a method for recommending vision correction surgery according to an embodiment.

[0255] Referring to Figure 39, a method for recommending vision correction surgery according to one embodiment may include a step of acquiring medical examination data of a subject (S5100), a step of predicting whether the subject is suitable for vision correction surgery (S5200), and a step of proposing vision correction surgery corresponding to the subject (S5300).

[0256] The step of acquiring the subject's medical examination data (S5100) and the step of predicting whether the subject is suitable for vision correction surgery (S5200) in Figure 39 are the same as those in Figure 35, so the description thereof will be omitted.

[0257] The step of suggesting corresponding vision correction surgery for the subject (S5300) may include inputting a second group of data obtained from the subject's medical examination data into a second prediction model and suggesting corresponding vision correction surgery for the subject.

[0258] Whether or not step (S5300) is performed may depend on whether the subject is suitable for vision correction surgery. For example, step (S5300) may be performed if the subject is suitable for vision correction surgery. Step (S5300) may suggest vision correction surgery based on the predicted corneal shape factor values ​​after standard vision correction surgery and the predicted corneal shape factor values ​​after custom vision correction surgery.

[0259] The second prediction model may be a model that combines a laser surgery feasibility prediction model, a custom vision correction surgery necessity prediction model, and a vision corrective surgery recommendation model. The second prediction model may be trained based on at least one of medical examination data of a plurality of patients who have undergone vision corrective surgery, the vision corrective surgery corresponding to the plurality of patients, and the visual acuity of the plurality of patients after the vision corrective surgery. The second prediction model may output information regarding at least one of the laser surgery feasibility, the necessity of custom vision corrective surgery, and the vision corrective surgery based on the second group of data. For example, the output of the second prediction model may include at least one of the laser surgery feasibility, the necessity of custom vision corrective surgery, and the vision corrective surgery.

[0260] FIG. 40 is a diagram relating to a sixth embodiment of a method for recommending vision correction surgery according to an embodiment. Referring to FIG. 40, a method for recommending vision correction surgery according to one embodiment may include a step of acquiring medical examination data of a subject (S6100) and a step of proposing vision correction surgery corresponding to the subject (S6200).

[0261] The step of acquiring medical examination data of the subject in FIG. 40 (S6100) is the same as in FIG. 35, so a description thereof will be omitted.

[0262] The step of proposing a vision corrective surgery for the subject (S6200) may include inputting group data obtained from the subject's medical examination data into a prediction model and proposing a vision corrective surgery for the subject. The step (S6200) may suggest a vision corrective surgery based on the subject's predicted corneal shape factor after standard vision corrective surgery and the predicted corneal shape factor after custom vision corrective surgery.

[0263] The prediction model may be a model that combines a surgery suitability prediction model, a laser surgery feasibility prediction model, a custom vision correction surgery necessity prediction model, and a vision correction surgery recommendation model. The prediction model may be trained based on at least one of medical examination data of a plurality of patients who have undergone vision correction surgery, the vision correction surgery corresponding to the plurality of patients, and the visual acuity of the plurality of patients after the vision correction surgery. The prediction model may output information regarding at least one of surgery suitability, laser surgery feasibility, custom vision correction surgery necessity, and vision correction surgery based on input data. For example, the output of the prediction model may include at least one of surgery suitability, laser surgery feasibility, custom vision correction surgery necessity, and vision correction surgery.

[0264] The above-mentioned combination and / or merging of the vision correction surgery recommendation method and vision correction surgery related models is merely an example, and the vision correction surgery recommendation method can be realized and the vision correction surgery related models can be combined and / or merged in various other ways.

[0265] An embodiment of a method for providing visualization information for vision correction surgery will be described below.

[0266] The method for providing vision correction surgery visualization information may be implemented using one or more vision correction surgery-related models. When the method is implemented using a plurality of vision correction surgery-related models, whether or not at least one vision correction surgery-related model is executed may depend on the prediction result of at least one other vision correction surgery-related model. For example, whether or not a second vision correction surgery-related model is executed may depend on the prediction result of a first vision correction surgery-related model.

[0267] The method for providing visual information for vision correction surgery may include a method for providing a predicted visual acuity image, a method for providing a corneal topography image, and a method for providing a cause for calculating a predicted result.

[0268] The method for providing a predicted visual acuity image may be implemented through a predicted visual acuity image generation model, the method for providing a corneal topography image may be implemented through a corneal topography image prediction model, and the method for providing a cause of predicted result calculation may be implemented through a cause analysis model of predicted result calculation.

[0269] Each step of the method for providing visualization information for vision correction surgery described below can be performed by a prediction device.

[0270] FIG. 41 is a diagram relating to a first embodiment of a method for providing visualization information for vision correction surgery according to an embodiment. 41, a method for providing visualization information for vision correction surgery according to one embodiment may include a step of acquiring medical examination data of a subject (S7100), a step of calculating predicted values ​​of eyeball characteristic data after vision correction surgery of the subject (S7200), and a step of generating a predicted vision image (S7300). In addition, although not shown, the method for providing visualization information for vision correction surgery according to one embodiment may further include a step of outputting the predicted vision image.

[0271] The step of acquiring medical data of the subject (S7100) may include a computing device acquiring the medical data including interview data and ocular characteristic data measurements.

[0272] The step (S7200) of calculating predicted values ​​of ocular characteristic data after the subject's vision correction surgery may include inputting a first group of data obtained from the subject's medical examination data into a first prediction model, and calculating predicted values ​​of ocular characteristic data including at least one of predicted values ​​of visual acuity and predicted values ​​of corneal shape factors after the subject's vision correction surgery.

[0273] The first prediction model may be trained based on at least one of pre-operative ocular characteristic data measurements of a plurality of patients who have undergone vision corrective surgery, surgical parameters of the vision corrective surgery performed on the plurality of patients, and post-operative ocular characteristic data measurements of the plurality of patients. The first prediction model may include at least one of a visual acuity prediction model and a corneal shape factor prediction model. Alternatively, the first prediction model may be a model in which the visual acuity prediction model and the corneal shape factor prediction model are combined. The first prediction model may calculate a predicted value of the patient's ocular characteristic data after vision corrective surgery based on the first group data.

[0274] The step of generating a predicted visual acuity image (S7300) may include generating the predicted visual acuity image based on the predicted ocular characteristic data value.

[0275] FIG. 42 is a diagram relating to a second embodiment of the method for providing visualization information for vision correction surgery according to an embodiment. Referring to FIG. 42, a method for providing visualization information for vision correction surgery according to one embodiment may further include a step of calculating and / or selecting a filter based on predicted values ​​of eyeball characteristic data (S7600), and a step of applying the filter to the original image (S7700).

[0276] The step of calculating and / or selecting a filter based on the predicted ocular characteristic data (S7600) can be performed by the first sub-model (M171) of FIG.

[0277] The step of applying a filter to the original image (S7700) may include applying a filter to the original image to generate a predicted vision image, which may be performed by the second sub-model (M172) of FIG.

[0278] FIG. 43 is a diagram relating to a third embodiment of a method for providing visualization information for vision correction surgery according to an embodiment. Referring to FIG. 43, the method for providing visualization information for vision correction surgery according to one embodiment may further include a step of predicting a corneal topography image after vision correction surgery of the subject (S7400).

[0279] The step of predicting the corneal topography image of the subject after vision correction surgery (S7400) may include inputting a second group of data obtained from the subject's medical examination data into a second prediction model to predict the corneal topography image of the subject after vision correction surgery.

[0280] The second prediction model can be trained based on at least one of pre-operative corneal topography images of a plurality of patients who have undergone vision correction surgery, surgical parameters of the vision correction surgery performed on the plurality of patients, and post-operative corneal topography images of the plurality of patients. The second prediction model may be a corneal topography image prediction model. The second prediction model can predict the corneal topography image of the patient after vision correction surgery based on the second group data.

[0281] FIG. 44 is a diagram relating to a fourth embodiment of the method for providing visualization information for vision correction surgery according to an embodiment. 44, the method for providing visualization information for vision correction surgery according to an embodiment may further include a step of calculating the dependency of the predicted value of eyeball characteristic data on the first group of data (S7500). Also, although not shown, the method for providing visualization information for vision correction surgery according to an embodiment may further include a step of outputting a dependency coefficient.

[0282] The step of outputting the dependency coefficients may include outputting dependency coefficients that are greater than a predetermined value among the dependency coefficients, or outputting a predetermined number of dependency coefficients.

[0283] Methods according to the embodiments may be embodied in the form of program instructions that can be executed by various computing devices and recorded on a computer-readable medium. The computer-readable medium may include, alone or in combination, program instructions, data files, data structures, and the like. The program instructions recorded on the medium may be specially designed and constructed for the embodiments, or may be publicly available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tape; optical media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions include not only machine language code, such as produced by a compiler, but also high-level language code executed by a computing device using an interpreter, etc. The hardware devices may be configured to operate as one or more software modules to perform the operations of the embodiments, or vice versa.

[0284] The above describes the configuration and features of the present invention based on examples, but it is clear to those skilled in the art that this does not limit the present invention and that various changes or modifications can be made within the spirit and scope of the present invention, and therefore, it is clear that such changes or modifications fall within the scope of the claims. As mentioned above, the relevant matters have been described in terms of the best mode for carrying out the present invention.

Claims

[Claim 1] 1. A method for recommending vision correction surgery utilizing artificial intelligence executed by a computing device, comprising: acquiring medical examination data of a subject, the medical examination data including interview data and ocular characteristic data measurements; inputting a first group of data obtained from the medical examination data of the subject into a first prediction model to predict whether the subject is suitable for vision correction surgery; If the subject is suitable for vision correction surgery, inputting a second group of data obtained from the medical examination data of the subject into a second prediction model to predict whether the subject is suitable for vision correction surgery using a laser; If the subject is eligible for laser-based vision correction surgery, inputting a third group of data obtained from the subject's medical examination data into a third prediction model to suggest a type of vision correction surgery corresponding to the subject; The step of suggesting a type of vision correction surgery corresponding to the subject includes: calculating, via the third prediction model, one or more predicted corneal shape factors for the subject after standard vision correction surgery that corrects low-order aberrations and one or more predicted corneal shape factors for the subject after custom vision correction surgery that corrects low-order aberrations and high-order aberrations; The corneal shape factor predicted values ​​include a predicted index of height decentration (IHD), a predicted index of surface variance (ISV), a keratoconus index (KI), a central keratoconus index (CKI), a minimum radius of curvature (Rmin), an index of height asymmetry (IHA), a central corneal thickness, and a vertical asymmetry index (VAS). asymmetry; IVA) predictive value, A method for recommending vision correction surgery, comprising proposing a type of vision correction surgery corresponding to the subject based on the calculated predicted values ​​of one or more corneal shape factors after standard vision correction surgery and one or more predicted values ​​of one or more corneal shape factors after custom vision correction surgery.

Images