Method and system for identifying risk of developing or progressing myopia - Patent application
By evaluating sensitivity parameters and using machine learning algorithms, the method and system enhance the accuracy of myopia risk assessment, allowing for timely interventions to manage myopia progression.
Patent Information
- Application Number
- JP2024524456
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2021-11-04
- Filing Date
- 2022-11-03
- Publication Date
- 2024-11-06
AI Technical Summary
Existing methods for predicting the onset and progression of myopia are inaccurate and unreliable, failing to account for key factors, making it difficult to effectively manage and control myopia development and progression.
A method and system that assess a subject's risk of myopia development or progression by evaluating sensitivity parameters, including refractive optical characteristics, lifestyle, genetic history, and personal information, using a predictive model based on machine learning algorithms to assign risk categories and calculate a final score.
Provides a more accurate and reliable means to identify the risk of myopia development or progression, enabling early intervention and personalized mitigation strategies.
Smart Images

Figure 2024541001000001_ABST
Abstract
Description
[Technical field]
[0001] Various aspects of the present disclosure relate to methods for identifying a risk of developing or progressing myopia over a time frame.Various aspects of the present disclosure further relate to a system for identifying a risk of developing or progressing myopia over a time frame. [Background technology]
[0002] Myopia, a form of refractive error, is a condition of the human eye in which incoming light does not focus directly on the retina but in front of it, resulting in images that appear out of focus when viewing distant objects but in focus when viewing close objects. Both low myopia (e.g., >-5D) and high myopia are associated with an increased risk of ocular pathology, severe visual impairment, and in extreme cases, blindness. Thus, the development of myopia and the prevention of myopic progression represent a serious burden in both the clinical and research areas of eye care.
[0003] Myopia is a complex condition that involves many factors, and long-term continuous follow-up is required to evaluate the rate of myopia progression. In addition, it is usually very difficult to predict the onset of myopia. Although some models allow prediction of the onset and progression of myopia, they have low accuracy and reliability. In particular, these models cannot explain a large portion of the variance observed in pre-myopic and myopic populations, suggesting that important factors are missing in these prediction models.
[0004] It is therefore desirable to find more accurate and reliable means of identifying the risk of developing or progressing myopia over a time frame in pre-myopic and myopic populations. Summary of the Invention [Problem to be solved by the invention]
[0005] It is an object of the present invention to provide a method and system for accurately and reliably identifying a subject's risk of developing or progressing myopia over a time frame. To this end, a method and system are provided in which the identification of a subject's risk of developing or progressing myopia over a time frame may be based on identified values of at least a sensitivity parameter of the subject. [Means for solving the problem]
[0006] A first aspect of the present disclosure relates to a method for determining the risk of developing or progressing myopia over a time frame. The method includes determining a value of at least one parameter related to a visual condition of a subject, the at least one parameter includes a sensitivity parameter of the subject, the sensitivity parameter relates to the sensitivity of the subject to a change in at least one refractive optical characteristic of at least one ophthalmic lens placed in front of at least one eye of the subject. The method also includes determining the risk of developing or progressing myopia of the subject over a time frame based on the determined value of the at least one parameter.
[0007] According to various embodiments, the at least one parameter related to the visual condition of the subject may further comprise a refractive optical parameter, a parameter related to the lifestyle, activity or behavior of the subject, a parameter related to the genetic history of the subject, an optical biometric parameter and / or a parameter related to personal information about the subject. In some embodiments, the parameter related to the visual condition of the subject may comprise all of the aforementioned parameters as well as a sensitivity parameter of said subject.
[0008] According to various embodiments, identifying the subject's risk of developing or progressing myopia over a time frame based on the determined values of the at least one parameter may include assigning a respective risk category selected from a plurality of predetermined risk categories to each of the at least one parameter based on the determined values of the respective parameter, and may further include identifying the subject's risk of developing or progressing myopia over the time frame based on the respective risk category assigned to each of the at least one parameter.
[0009] According to various embodiments, assigning a respective risk category to each of the at least one parameter based on the determined value of the respective parameter may include determining, for each parameter associated with a respective risk category, whether the determined value of the respective parameter matches a corresponding reference value or is within a corresponding reference value range.
[0010] According to various embodiments, reference values or reference value ranges for each parameter may be established based on a database containing information of the risk of myopia development or progression over a time frame for individuals within a population sample.
[0011] According to various embodiments, identifying the subject's risk of developing or progressing myopia over the time frame based on the respective risk categories assigned to each of the at least one parameter may include, for each risk category of the plurality of predefined risk categories, identifying a number of parameters among the at least one parameter to which the respective risk category is assigned, and may further include identifying the risk category among the plurality of predefined risk categories assigned to the greatest number of parameters as the subject's risk of developing or progressing myopia over the time frame.
[0012] According to various other embodiments, determining the risk of developing or progressing myopia in the subject over a time frame based on the respective risk categories assigned to each of the at least one parameter may include: assigning a weight to each one of the plurality of predefined risk categories; and, for each risk category of the plurality of predefined risk categories, determining the number of parameters of the at least one parameter to which the respective risk category is assigned. The method may further include: calculating a score for each risk category of the plurality of predefined risk categories by multiplying the weight assigned to the respective risk category by the number of parameters to which the risk category is assigned; calculating a final score by summing the calculated scores for the plurality of predefined risk categories; and, based on the final score, determining the risk of developing or progressing myopia in the subject over a time frame.
[0013] According to various embodiments, identifying the subject's risk of developing or progressing myopia over a time frame based on the final score may include comparing the final score to at least one first predetermined threshold.
[0014] According to various embodiments, the one or more pre-defined risk categories may include a low risk category, a medium risk category, and a high risk category.
[0015] According to various embodiments, identifying a subject's risk of developing or progressing myopia over a time frame based on the identified value of the at least one parameter may be established based on at least one predictive model based on a machine learning algorithm, which provides a relationship between the risk of developing or progressing myopia and the at least one parameter.
[0016] According to various embodiments, identifying the subject's risk of developing or progressing myopia over a time frame based on the determined value of the at least one parameter may include inputting the determined value of the at least one parameter into at least one predictive model based on a machine learning algorithm, calculating a value of a risk ratio using the at least one predictive model based on a machine learning algorithm, and identifying the subject's risk of developing or progressing myopia over a time frame based on the calculated value of the risk ratio. The calculated value of the risk ratio may provide a probability indicative of the subject's risk of developing or progressing myopia over a time frame and may be implemented using at least one predictive model based on a machine learning algorithm.
[0017] According to various embodiments, identifying the subject's risk of developing or progressing myopia over a time frame based on the risk ratio may include comparing the calculated value of the risk ratio to a second predetermined threshold.
[0018] According to various embodiments, the at least one parameter associated with the visual condition of the subject may include a first parameter indicative of the near refraction of the subject and a second parameter indicative of the near refraction sensitivity of the subject. The at least one parameter associated with the visual condition of the subject may also include a third parameter indicative of the far refraction of the subject and a fourth parameter indicative of the far refraction sensitivity of the subject. A fifth parameter indicative of an overlap of the far comfort range and the near comfort range of the subject may be identified. Identifying a value of the fifth parameter may include identifying a far comfort range and a near comfort range based on the identified values of the first to fourth parameters, identifying an overlap of the far and near comfort ranges, and assigning a value to the fifth parameter based on the identified overlap of the far and near comfort ranges.
[0019] According to various embodiments, identifying a risk of developing or progressing myopia may include identifying a likelihood of progression to a higher degree of myopia and / or a rate of progression of myopia.
[0020] According to various embodiments, the time frame can be about 6 months or less, about 1 year or less, about 2 years or less, about 3 years or less, about 4 years or less, or about 5 years or less.
[0021] A second aspect of the present disclosure relates to a system for identifying a risk of developing or progressing myopia over a time frame. The system includes a means for identifying a value of at least one parameter related to a visual condition of a subject, the at least one parameter including a sensitivity parameter of the subject, the sensitivity parameter relating to the sensitivity of the subject to a change in at least one refractive optical characteristic of at least one ophthalmic lens placed in front of at least one eye of the subject. The system further includes a means for identifying a risk of developing or progressing myopia of the subject over a time frame based on the identified value of the at least one parameter.
[0022] According to various embodiments, at least one of the means for determining a value of the at least one parameter and the means for determining a risk of developing or progressing myopia in the subject may include a circuit. In some embodiments, the means for determining a value of the at least one parameter and the means for determining a risk of developing or progressing myopia in the subject may be the same circuit.
[0023] According to various embodiments, the system may further include a computer program product including instructions for causing a computing system of the second aspect to perform the steps of the method of the first aspect.
[0024] The invention will be better understood with reference to the detailed description, taken in conjunction with the non-limiting examples and the accompanying drawings, in which: [Brief description of the drawings]
[0025] [Figure 1] 1 is an exemplary schematic diagram of a method 100 for identifying risk of developing or progressing myopia over a time frame, according to various embodiments. [Diagram 2]FIG. 2 illustrates an example of a subject's confidence probability function 200 used to identify a value of a subject's sensitivity parameter SRx, according to various embodiments. [Diagram 3] FIG. 3 is an exemplary schematic diagram of a method 300 for identifying a value of a fifth parameter indicative of the degree of overlap between a subject's far-distance comfort range and a near-distance comfort range, according to various embodiments. [Figure 4] FIG. 4 is an exemplary schematic diagram of a method 400 for identifying a subject's risk of developing or progressing myopia over a time frame based on identified values of at least one parameter, according to various embodiments. [Figure 5A] FIG. 5 is an exemplary schematic diagram of a method 500A for identifying a subject's risk of developing or progressing myopia over a time frame based on an identified value of at least one parameter, according to various embodiments. [Figure 5B] FIG. 5 is an exemplary schematic diagram of a method 500B for identifying a subject's risk of developing or progressing myopia over a time frame based on an identified value of at least one parameter, according to various embodiments. [Figure 6] FIG. 6 is an exemplary schematic diagram of a method 600 for identifying a subject's risk of developing or progressing myopia over a time frame based on identified values of at least one parameter, according to various embodiments. [Figure 7] FIG. 7 illustrates an example of a system 700 for identifying risk of developing or progressing myopia over a time frame, according to various embodiments. [Figure 8A] 4 shows a table of example conditions of use for methods 400, 500A and 500B for identifying a subject's risk of developing or progressing myopia over a time frame, according to various embodiments. [Figure 8B] 4 shows a table of example conditions of use for methods 400, 500A and 500B for identifying a subject's risk of developing or progressing myopia over a time frame, according to various embodiments. [Figure 9A] FIG. 13 shows a table of another example of conditions of use according to methods 300, 400, 500A and 500B for identifying a subject's risk of developing or progressing myopia over a time frame, according to various embodiments. [Figure 9B]FIG. 13 shows a table of another example of conditions of use according to methods 300, 400, 500A and 500B for identifying a subject's risk of developing or progressing myopia over a time frame, according to various embodiments. [Figure 9C] FIG. 13 shows a table of another example of conditions of use according to methods 300, 400, 500A and 500B for identifying a subject's risk of developing or progressing myopia over a time frame, according to various embodiments. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0026] The following detailed description refers to the accompanying drawings, which show, by way of example, specific details and embodiments in which the present disclosure may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the present disclosure. Other embodiments may be utilized, and structural and logical changes may be made, without departing from the scope of the present disclosure. The various embodiments are not necessarily mutually exclusive, as some embodiments may be combined with one or more other embodiments to form new embodiments.
[0027] The present disclosure illustratively described herein may be suitably implemented without any element or limitation not specifically disclosed herein. Thus, for example, the terms "comprise", "include", "contain", etc., are to be interpreted broadly without limitation. The word "comprise" or variations such as "comprises" or "comprises" are therefore understood to mean the inclusion of a stated integer or group of integers, but not the exclusion of any other integer or group of integers. In addition, the terms and expressions employed herein are used as terms of description, not of limitation, and the use of such terms and expressions is not intended to exclude any equivalents of the features shown and described or portions thereof, but it is recognized that various modifications are possible within the scope of the present disclosure. Thus, although the present disclosure has been specifically described with exemplary embodiments and optional features, it should be understood that modifications and variations of the present disclosure embodied herein may be used by those skilled in the art.
[0028] Features described in connection with an embodiment may be applicable to the same or similar features in other embodiments. Features described in connection with an embodiment may be applicable to other embodiments even if not explicitly described in these other embodiments. Furthermore, additional and / or combinations and / or alternatives to features described in connection with an embodiment may be applicable to the same or similar features in other embodiments.
[0029] In connection with the various embodiments, the articles "a," "an," and "the" when used in connection with a feature or element include a reference to one or more of the feature or element. As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.
[0030] Any reference signs in parentheses in the claims are intended to facilitate understanding of the disclosure and shall not be construed as limiting the scope of the claims.
[0031] According to various embodiments, the term "myopia," as used herein, may refer to a subject's refractive error, which may be measured in diopters (D). The term myopia may therefore include, inter alia, axial myopia resulting from an increase in the axial length of the eye, refractive myopia resulting from a condition of the refractive elements of the eye, curvature myopia resulting from an excess or increased curvature of one or more of the refractive surfaces of the eye, particularly the cornea, e.g., due to high corneal and crystalline lens powers in subjects with Cohen's syndrome, and refractive myopia resulting from a variation in the refractive index of one or more of the optic bodies.
[0032] According to various embodiments, the term "risk" as used herein may refer to the likelihood, probability or chance of the occurrence of a condition, such as the onset or progression of myopia for a subject over a time frame. Thus, the term "determining risk" may refer to a process or method of determining or predicting the likelihood or probability of the onset or progression of myopia for a subject over a time frame. According to various embodiments, determining the risk of the onset or progression of myopia for a subject over a time frame may be for one or both eyes of the subject.
[0033] According to various embodiments, the term "onset," as used herein, may refer to the initial occurrence or emergence of symptoms associated with myopia, such as decreased visual acuity and intermittent blurred vision. In the context of this disclosure, the onset of myopia over a time frame may refer to the initial occurrence of such symptoms in an emmetropic, e.g., pre-myopic or non-myopic, subject over a time frame.
[0034] According to various embodiments, the term "progression" as used herein may refer to the worsening of myopia of a myopic subject over a time frame. In other words, the subject already has myopia. In particular, the term progression may refer to the speed or rate of progression of myopia of a myopic subject over a time frame, for example, the progression from a spherical measurement of about -2.00D to about -3.00D or to about -6.00D over a period of time. In another example, the term progression may refer to the progression of a subject from low myopia to moderate myopia or high myopia, or from moderate myopia to high myopia.
[0035] According to various embodiments, the term "mild myopia" as used herein may correspond to a negative spherical equivalent of -3.00D or less, the term "moderate myopia" as used herein may correspond to a spherical equivalent of -3.00D to -6.00D, and the term "high myopia" may correspond to a negative spherical equivalent of -6.00D or more. The spherical equivalent may be a function of the spherical power, e.g., myopia, and the cylindrical power, e.g., astigmatism. For example, the spherical equivalent may be equal to the spherical power +0.5 (cylindrical power).
[0036] According to various embodiments, the term "value" as used herein may refer to a numerical value, e.g., a discrete numerical value or a range of numerical values. Alternatively or additionally, the term "value" may refer to a text, e.g., a string of text, e.g., "yes", "no", "duplicates", or "no duplicates".
[0037] According to various embodiments, the term "parameters related to visual conditions" as used herein may refer to parameters, e.g., factors, related to a visual condition or system of a subject. In the context of the present disclosure, the term parameters related to visual conditions may include parameters that affect or cause the onset or progression of myopia over a time frame for emmetropic or myopic subjects, respectively. For example, parameters related to visual conditions may include genetic factors, environmental factors, or a combination thereof.
[0038] According to various embodiments, the term "subject" as used herein may refer to an individual who is emmetropic, i.e., not myopic or pre-myopic, and thus determining risk may refer to determining the risk of developing myopia over a time frame for said emmetropic individual. According to various other embodiments, the term "subject" as used herein may refer to an individual who is myopic or refractively erroneous, and thus determining risk may refer to determining the risk of developing myopia over a time frame for said myopic individual.
[0039] According to various embodiments, the term "sensitivity parameter" as used herein may refer to the value of a sensitivity parameter of a subject, for example, a personalized sensitivity parameter. In some embodiments, the sensitivity parameter includes a specific sensitivity parameter. For example, the specific sensitivity parameter may be selected from the following: spherical sensitivity to a change in sphere of at least one ophthalmic lens for at least one eye of the subject, cylindrical and / or axial sensitivity to a change in cylindrical power and / or axis of at least one ophthalmic lens for at least one eye of the subject, spherical binocular sensitivity to a change in binocular balance of at least one ophthalmic lens for at least one eye of the subject, and additive sensitivity to an additive change of at least one ophthalmic lens placed in front of at least one eye of the subject. In some other embodiments, the sensitivity parameter includes a global sensitivity parameter, which refers to an average or weighted average of several single values of the specific sensitivity parameter.
[0040] FIG. 1 shows, by way of example, a schematic diagram of a method 100 for identifying a risk of developing or progressing myopia over a time frame. The method 100 includes, in step 110, identifying a value of at least one parameter associated with a visual condition of a subject. The at least one parameter associated with a visual condition of a subject includes a sensitivity parameter SRx of the subject, the sensitivity parameter SRx relating to the sensitivity of the subject to a change in at least one refractive optical characteristic of at least one ophthalmic lens placed in front of at least one eye of the subject. The method 100 further includes, in step 120, identifying a risk of developing or progressing myopia of the subject over a time frame based on the identified value of the at least one parameter.
[0041] FIG. 2 shows an example of a subject's confidence probability function 200 used to determine the value of the subject's sensitivity parameter SRx. The subject's confidence probability function 200 may be represented as a graph of the confidence of the choice made by the subject as a function of the optical characteristic value of the lens placed in front of the subject's eye. The subject's confidence probability function 200 is defined as the product of the subject's answer and the probability of the confidence as a function of the estimated parameter value, and may be obtained based on the subject's choice for the variation of at least one refractive optical characteristic of at least one ophthalmic lens placed in front of at least one eye of the subject. In other words, the subject's confidence probability function 200 reflects the subject's confidence when choosing between two visual conditions or between two different lenses placed in succession in front of the subject's eyes. This may be determined from standard optometry, e.g., Jackson Cross Cylinder method with or without fixed Jackson Cross Cylinder, dichromatic test, perceptual assessment test, binocular balance test or other optometry methods known to those skilled in the art.
[0042] For example, the subject may be asked to choose between two visual states or between two different lenses successively placed in front of the subject's eye, e.g., choice 1 and choice 2 on the confidence probability function 200. A confidence value of 0% is the value obtained when the subject is unable to choose between the two visual states or two lenses, e.g., when the subject is unable to perceive any difference in the quality of the image seen in each visual state, e.g., choice 1 or choice 2. This may be represented by the value "0", "don't know" or "null" during the eye test. A confidence value of -100% is the value obtained when the subject is confident that the first of the two visual states or the first lens, e.g., choice 1, provides a better quality of the image seen. This may be represented by the value "-1" during the eye test. A confidence value of +100% is the value obtained when the subject is confident that the second visual state or the second lens, e.g., choice 2, provides a better quality of the image seen, which may be represented by the value "+1" during the eye test. Any uncertain answers may also be represented by a value between "-1 or +1" depending on the estimated or measured confidence.
[0043] The subject's confidence probability function 200 is then calculated by averaging all the answers estimated for a particular optical characteristic value, and then interpolating to any non-estimated values. A dead zone 210 can be defined corresponding to values of the optical characteristic of the lens for which the confidence probability falls within a predefined range of uncertainty. In some embodiments, the uncertainty range is the range [-70%, 70%], [-60%, 60%], or preferably [-50%, 50%] or [-40%, 40%]. In other words, the dead zone 210 is defined and limited by a high level 220 and a low level 230, which are two boundaries below which the confidence probability falls below a predefined range, for example [-50%, 50%].
[0044] The value of the sensitivity parameter SRx may then be defined to be equal to half the magnitude of the deadband 210, as represented by Equation 1.
number
[0045] In other words, the dead zone 210 may correspond to a range of values of the optical characteristic that are acceptable to the subject or within which the subject is unable to determine which lens provides better vision. The value of the sensitivity parameter SRx may then be identified from the subject's belief probability function 200 as half the width of the dead zone 210 of optical characteristic changes within which the subject is insensitive to changes in the values of the optical characteristic of the lens placed in front of the subject's eye.
[0046] A method for determining the value of the sensitivity parameter SRx is known from document WO 2020 / 016398 A1. A method for determining the belief probability function is known from document WO 2018 / 015381 A1.
[0047] Accommodative lag, e.g., the degree to which a subject's eye(s) cannot focus accurately in response to a visual stimulus, has been shown to strongly increase after the onset of myopia, and myopic subjects have been shown to be less susceptible to blurred vision than emmetropes (Rosenfield M. et al. Optom. Vis. Sci. 1999, 76(5):303-307). Currently, optometric measurement methods such as "les optimales convexes et concaves" from "variations dioptriques" provide estimates of the sensitivity parameter SRx. However, these optometric measurement methods include additional tests with complex instructions that may not be fully understood by the subject, especially children. According to various embodiments, the subject's accommodative lag may be related to the subject's dead zone 210 on the subject's confidence probability function 200 and thus the value of the subject's sensitivity parameter SRx.
[0048] Advantageously, determining the value of a subject's sensitivity parameter SRx based on the subject's belief probability function 200 provides a direct and simple method of determining the sensitivity parameter SRx in a precise and accurate manner without requiring additional measurements or instructions that may be complicated for the subject, particularly for young children.
[0049] 1, step 110 of method 100 may further include determining a value of at least one parameter related to the visual condition of the subject. According to various embodiments, the at least one parameter may further include a refractive optical parameter, a parameter related to the lifestyle, activity or behavior of the subject, a parameter related to the genetic history of the subject, an optical biometric parameter, and / or a parameter related to personal information about the subject.
[0050] According to various embodiments, the refractive optical parameters of the subject may include an objective measurement of the subject's refractive error, such as a spherical power obtained during an eye examination. The parameters may be obtained using any eye examination device, such as an ophthalmometer, a refractometer, an autorefractometer, and / or a retinoscope. In a further example, the refractive optical parameters may include or be the previous time frame for the myopic subject, such as the rate of myopia progression in the previous year, for example, from low myopia to moderate myopia or high myopia in the previous year.
[0051] According to various embodiments, the subject's lifestyle, activity or behavior parameters may include the subject's exposure level to sufficient light. For example, the subject's lifestyle, activity or behavior parameters may include environmental factors such as the subject's physical activity level, duration of precise work, and / or education level. In some embodiments, the subject's lifestyle, activity or behavior parameters may be the subject's time spent outdoors per day, such as the time engaged in physical exercise or outdoor play sessions. In some other embodiments, the subject's lifestyle, activity or behavior parameters may be the average exposure to sunlight or natural light per day, the intensity of natural light exposure, the average UV index, latitude, or any combination thereof. Without being bound by theory, it has been observed that insufficient light exposure, insufficient time spent outdoors per day, long periods spent near vision, and higher education levels increase the risk of myopia onset or progression over a time frame. Thus, the amount of time spent outdoors is associated with a preventative effect against the onset of myopia, which may be at least partially attributed to the effect of prolonged exposure to sunlight on retinal dopamine production and release.
[0052] According to various embodiments, the parameter of the genetic history of the subject can include or be the number of myopic parents that the subject has.In another example, the parameter of the genetic history of the subject can include or be the number of myopic relatives, such as grandparents, that the subject has.Without being bound by theory, it has been shown that the risk of developing and progressing myopia over a time frame can be inherited from one's parents, and a family history of myopia correlates with an increased risk of developing or progressing myopia over a time frame.
[0053] According to various embodiments, the optical biometric parameters may include objective measurements of the subject's axial length (in mm), vitreous chamber depth (in mm), choroidal thickness (in μm), and may further include other corneal characteristics including corneal hysteresis. The parameters may be obtained during the eye examination using any ophthalmic device, such as an ophthalmometer, refractometer, autorefractometer, and / or retinoscope.
[0054] According to various embodiments, the parameters relating to the personal information of the subject may include or be the subject's gender, age, ethnic background, or a combination thereof. It is further envisioned that the parameters relating to the personal information of the subject may also include underlying diseases such as diabetes, childhood arthritis, uveitis, and systemic lupus erythematosus. It has been observed that myopia is more common in individuals with said diseases, such as children.
[0055] Thus, step 110 of method 100 may comprise determining a value of at least one parameter associated with the visual condition of the subject, which may comprise the subject's sensitivity parameter SRx, the subject's refractive optical parameters, parameters relating to the subject's lifestyle, activity or behavior, parameters relating to the subject's genetic history, optical biometric parameters and / or parameters relating to personal information about the subject. In some embodiments, step 110 of method 100 comprises determining values of all the aforementioned parameters associated with the visual condition of the subject.
[0056] According to various embodiments, the at least one parameter related to the subject's visual condition may also include a fifth parameter indicative of the degree of overlap between the subject's far distance comfort range and near distance comfort range.
[0057] FIG. 3 shows, by way of example, a schematic diagram of a method 300 for identifying a value of a fifth parameter indicative of the degree of overlap between the subject's far-distance comfort range and the near-distance comfort range. In step 310, the method 300 may include identifying a first parameter indicative of the subject's near-distance refraction. For example, the first parameter, e.g., the subject's near-distance refraction, may correspond to the subject's near-vision prescription and may be obtained during the subject's eye examination. Step 310 may also include identifying a third parameter indicative of the subject's far-distance refraction. For example, the third parameter, e.g., the subject's far-distance refraction, may correspond to the subject's far-vision prescription obtained during the subject's eye examination.
[0058] Step 320 of method 300 may include identifying a second parameter indicative of the subject's near refraction sensitivity, and may further include identifying a fourth parameter indicative of the subject's far refraction sensitivity. The near and far refraction sensitivities may be identified using the subject's near and far confidence probability functions, respectively. The method of identifying the subject's near and far confidence probability functions may be the same as that used to obtain the subject's sensitivity parameter SRx described above with reference to FIG. 2. In brief, the subject's near and far confidence probability functions may be calculated by averaging the answers estimated for a particular optical feature value, e.g., myopic and far vision prescriptions, respectively. The myopic and far vision prescription confidence probability functions may then be interpolated to any non-estimated values. The near and far deadbands may be defined on the subject's near and far confidence probability functions, respectively. The near and far deadbands may correspond to values of the lens' optical feature for which the probability of confidence is included in a predefined range of uncertainty, e.g., [-50%, 50%]. In other words, the near and far refraction dead zones may be defined and limited by high and low levels on the near or far confidence probability function, respectively, which are the two boundaries where the confidence probability falls below a predetermined range, e.g., [-50%, 50%]. The near or far refraction sensitivity values, e.g., the second and fourth parameters, respectively, may then be defined as being equal to half the near or far dead zone size. Alternatively, the near and far refraction sensitivities, e.g., the second and fourth parameters, may both be defined as being equal to a global sensitivity parameter, which may be calculated from various specific sensitivity parameters SRx measured, e.g., in either near or far conditions, or both, e.g., in near and far conditions.
[0059] In some embodiments, either near refraction sensitivity, e.g., the second parameter, or far refraction sensitivity, e.g., the fourth parameter, may be measured, and either parameter may be used to identify the risk of myopia development or progression of a subject over a time frame, e.g., via a predictive model that provides a relationship between the risk of myopia development or progression and the second or fourth parameter. Thus, the time required to perform the measurement and obtain the second or fourth parameter may be advantageously reduced. For example, in the case of small children, the time required to perform the measurement may be a relevant criterion. In some other embodiments, both near and far refraction sensitivity, e.g., the second and fourth parameters, may be measured, and used to identify the risk of myopia development or progression of a subject over a time frame.
[0060] In step 330, the method 300 may include determining a near distance comfort range, which may be determined based on the subject's near vision prescription, e.g., the first parameter, and the near distance refractive sensitivity, e.g., the second parameter, obtained in steps 310 and 320, respectively. The near distance comfort range may be calculated according to Equation 2. Near comfort range = myopia prescription ± (K_near × near refractive sensitivity) - (2) In Equation 2, the coefficient (K_near) may represent a subject-specific, e.g., personalized, coefficient. The associated confidence interval for the near comfort range is given by 2 x K_near x near refraction sensitivity. The coefficient K_near and the associated confidence interval may depend on the near refraction sensitivity, e.g., a function of the second parameter, e.g., the width of a Gaussian function. In some embodiments, a 95% confidence interval may be used. In this case, K_near may be 1.96, assuming a Gaussian distribution for the near refraction sensitivity. Alternatively, other confidence intervals, such as 50%, 90%, 98% or 99%, may be used.
[0061] Step 330 of method 300 may also include determining a distance comfort range in a manner similar to the near comfort range. The distance comfort range may be based on the distance prescription, e.g., the third parameter, and the distance refractive sensitivity, e.g., the fourth parameter, obtained in steps 310 and 320, respectively. The distance comfort range may be calculated according to Equation 3. Distance comfort range = hyperopia prescription ± (K_far × distance refractive sensitivity) (3) In Equation 3, the coefficient (K_far) may represent a subject-specific, e.g., personalized, coefficient. The associated confidence interval for the far distance comfort range is given by 2 x K_far x far distance refraction sensitivity. The coefficient K_far and associated confidence interval may depend on the far distance refraction sensitivity, e.g., a function of the fourth parameter, e.g., the width of a Gaussian function. In some embodiments, a 95% confidence interval may be used. In this case, K_far may be 1.96, assuming a Gaussian distribution for the near distance refraction sensitivity. Alternatively, other confidence intervals, such as 50%, 90%, 98% or 99%, may be used.
[0062] Step 340 of method 300 may include determining an overlap of the near and far comfort ranges. In other words, step 340 may include determining whether the far comfort range overlaps with the near comfort range. In some embodiments, if the far and near comfort ranges are determined to overlap, step 340 may further include determining whether the far refraction, e.g., the third parameter determined in step 310, is within the near comfort range determined in step 330.
[0063] In step 350, method 300 may include assigning a value to a fifth parameter indicative of the degree of overlap of the near and far comfort zones that may be identified in step 340. For example, values that may be assigned to the fifth parameter may include, but are not limited to: "no overlap", "some overlap", and "some overlap but far refraction is not in the near comfort zone". Alternatively, values that may be assigned to the fifth parameter may include a percentage overlap of the near and far comfort zones.
[0064] As shown above, the at least one parameter related to the visual condition may include a fifth parameter indicating the degree of overlap between the far distance comfort range and the near distance comfort range that may be determined using the method 300. Without being bound by theory, it has been observed that when the far distance and near distance comfort ranges overlap, the subject has a low risk of developing or progressing to myopia over a time frame. Conversely, when the far distance and near distance comfort ranges do not overlap, the subject has a significant risk of developing myopia, for example, a significant risk of developing myopia for a subject who has not become myopic over a time frame or a significant risk of progressing to a higher degree of myopia over a time frame (Drobe B. et al. Ophthal. Physiol. Opt. 1995, 15, 375-378). Thus, the fifth parameter may provide an additional factor to improve the predictive power of existing or new myopia development or progression models.
[0065] In non-limiting embodiments, examples of parameters related to the visual condition of the subject may further include parameters related to the subject's visual acuity or visual deficiency, for example, hyperopia, astigmatism, presbyopia or any other visual disease, such as an eye disease resulting in vision problems, such as myopic macular degeneration, retinal detachment and glaucoma.
[0066] Step 120 of FIG. 1 involves identifying a subject's risk of developing or progressing myopia over a time frame based on the identified values of at least one aforementioned parameter related to the subject's visual condition.
[0067] According to various embodiments, identifying a subject's risk of developing or progressing myopia may include identifying a likelihood of progression to a higher degree of myopia within a time frame. The likelihood of progression may be expressed in the form of a risk ratio, such as a percentage or ratio, or may be expressed as a categorical risk, such as a low risk, a medium risk, or a high risk of progressing to a higher degree of myopia. In some embodiments, a higher degree of myopia may include low myopia, moderate myopia, or high myopia. For example, for an emmetropic subject, identifying a subject's risk of developing or progressing may include identifying a risk of the subject progressing from non-myopia to low myopia over a time frame. As a further example, for an emmetropic subject, identifying a subject's risk may include predicting the age at which the subject may develop myopia. In another example, for a myopic subject, identifying a subject's risk of developing or progressing may include identifying a risk of the subject progressing to a higher degree of myopia within a time frame, such as from low myopia to moderate myopia or high myopia. As a further example, for a myopic subject, identifying the subject's risk includes predicting the age at which the subject will progress from low myopia to moderate myopia or high myopia.
[0068] According to various embodiments, identifying a subject's risk of developing or progressing myopia can include identifying a rate of progression of myopia. The rate of progression can include predicting a change in myopic power within a time frame. The predicted change in myopic power can be about 1D or less, about 1-2D, about 2-3D, about 3-4D, about 4-5D, about 5-6D, about 6-7D, about 7-8D, about 8-9D, or about 9-10D.
[0069] According to various embodiments, determining the risk of developing or progressing myopia of a subject is over a time frame, i.e., it is relative. The time frame for predicting the risk of developing or progressing myopia of a subject can be the same time frame in which a database containing information on the risk of developing or progressing myopia is established, such as the time frame of a longitudinal study as described below. For example, the time frame can include, but is not limited to, about 6 months, about 1 year, about 2 years, about 3 years, about 4 years, about 5 years, about 8 years, or about 10 years. In some embodiments, the time frame is 5 years or less. That is, the probability of the subject's progression to higher degrees of myopia and / or the rate of progression of myopia is established for the indicated time frame.
[0070] Referring again to step 120 of FIG. 1, identifying the risk of myopia development or progression of the subject over a time frame based on the determined value of at least one parameter may be established based on at least one predictive model providing a relationship between the risk of myopia development or progression and at least one parameter according to various embodiments. In other words, the risk of myopia development or progression of the subject over a time frame may be implemented and identified using a predictive model that may be implemented using a machine learning algorithm. For example, one or more neural networks may be trained by inputting a set of determined values of parameters related to the visual condition of a large number of individuals, e.g., a population sample, that may have the same or similar profile, e.g., sensitivity parameter SRx, age, genetic history, refractive parameters, and building a correlation table or any database that includes information on the relationship between the risk of myopia development or progression and at least one parameter related to the visual condition. In one embodiment, said database or correlation table may include or be a longitudinal study that established a correlation between the risk of myopia development or progression over a time frame and at least one parameter related to the visual condition.
[0071] According to various embodiments, the machine learning algorithm may be selected from the group consisting of, for example, supervised, semi-supervised and unsupervised learning: Support Vector Machines (SVM), Naive Bayes Classification, Random Forests, Artificial Neural Networks, Decision Trees, K-Means, Learning Vector Quantization, Self-Organizing Maps, Graphical Models, preferably regression algorithms, such as linear, multivariate, logistic, association rule learning, deep learning, dimensionality reduction and ensemble selection algorithms.
[0072] In a non-limiting embodiment, it is contemplated that the self-reported parameters may be calculated by at least one predictive model. For example, the self-reported parameters may include data from a social network or a genetic risk score associated with a visual defect or disease. Such self-reported parameters may then modify the predictive model.
[0073] A method for constructing at least one predictive model based on a machine learning algorithm may be known from WO 2020 / 126513.
[0074] 4-5B show schematic diagrams of methods 400, 500A and 500B for identifying a subject's risk of developing or progressing myopia over a time frame based on categorical risk, according to various embodiments of the present invention. In other words, a predictive model for identifying a subject's risk of developing or progressing myopia over a time frame includes or can be a categorical model. In particular, the predictive model can include one or more predefined risk categories including at least a low risk category, a medium risk category and a high risk category.
[0075] According to various embodiments, each of the predefined risk categories includes a reference value or a reference value range associated with a respective parameter, for example, the low risk, medium risk and high risk categories each include a reference value or a reference value range associated with at least one parameter related to the subject's visual condition, such as a sensitivity parameter SRx, a refractive optical parameter, a parameter related to the subject's lifestyle, activity or behavior, a parameter related to the subject's genetic history, an optical biometric parameter, a parameter related to personal information about the subject and / or a fifth parameter indicative of the degree of overlap of the subject's near and far comfort zones.
[0076] According to various embodiments, the term "individuals in a population sample," as used herein, may refer to a group, e.g., any number of individuals, who may share at least one common characteristic with each other. For example, individuals in a population sample may share the same or similar refractive optical parameters, age, ethnic background, genetic history, lifestyle, activity or behavior, optical biometric parameters, sensitivity parameters SRx, and / or parameters including information regarding the degree of overlap of near and far comfort ranges.
[0077] According to various embodiments, the reference value or reference value range can be established based on a database that includes information on the risk of myopia development or progression over a time frame for individuals in a population sample.For example, the database can be established based on a longitudinal study of the risk of myopia development or progression over a period of time for individuals in a population sample, such as children under 12 years old.The database can thus include information related to the risk of myopia development or progression over a time frame, in relation to certain parameters related to visual conditions, such as the sensitivity parameter SRx, a fifth parameter indicating the overlap of the subject's near and far comfort zones, refractive optical parameters, parameters related to the individual's genetic history, optical biometric parameters, and parameters related to the individual's lifestyle, activity or behavior.
[0078] FIG. 4 shows, as an example, a schematic diagram of a method 400 for identifying a risk of myopia development or progression of a subject over a time frame based on the identified values of the respective parameters. In step 410, the method 400 includes identifying whether the identified values of the respective parameters obtained in step 110 of FIG. 1 match or fall within a corresponding reference value range for each parameter associated with each risk category. For example, step 410 may include identifying whether the identified value of the sensitivity parameter SRx is equal to or falls within a corresponding reference value range for the reference value range of the sensitivity parameter SRx for each of the low risk category, the medium risk category and the high risk category. The reference value or the reference value range may be established from a database including information of the risk of myopia development or progression over a time frame for individuals in a population sample. In other words, the low risk, the medium risk and the high risk categories each include a reference value or a reference value range for each parameter associated with a visual condition, and step 410 includes identifying whether the identified value of the parameter associated with the visual condition of the subject is equal to or falls within a reference value range.
[0079] Step 420 of method 400 may include assigning each of the at least one parameter to a risk category selected from a plurality of predefined risk categories based on step 410, which may include determining whether the determined value of each parameter corresponds to or is within a corresponding reference value range for each parameter associated with each risk category. For example, if the determined value of each parameter corresponds to or is within a corresponding reference value range for each risk category, the parameter may be assigned to the respective risk category. That is, if the determined value of a parameter, for example a sensitivity parameter SRx, is equal to or within the respective reference value range of the low risk, medium risk or high risk category, the parameter is assigned to that category.
[0080] Step 430 of method 400 may include identifying a subject's risk of developing or progressing myopia over a time frame based on respective risk categories assigned to each of the at least one parameter, as described with reference to FIGS. 5A and 5B.
[0081] 5A shows a schematic diagram of an exemplary method 500A for identifying a subject's risk of developing or progressing myopia over a time frame based on a respective risk category assigned to each of at least one parameter. In one embodiment, identifying a subject's risk of developing or progressing myopia over a time frame may include, in step 510, for each risk category of a plurality of predetermined risk categories, identifying a number of parameters among the at least one parameter to which the respective risk category is assigned. In other words, step 510 includes identifying a total number of parameters in each of the low, medium, and high risk categories. For example, the predictive model may include instructions for calculating a sum, e.g., a total number, of parameters in each of the low, medium, and high risk categories.
[0082] Method 500A may further include, in step 512, identifying the risk category among a plurality of predefined risk categories that is assigned to the greatest number of parameters as the risk of developing or progressing myopia of the subject over the time frame. That is, step 512 includes comparing the total number of parameters within each of the predefined risk categories, e.g., comparing the total number of parameters between each of low, medium, and high risk categories, and identifying the particular risk category with the greatest total number of parameters as the risk of developing or progressing myopia of the subject over the time frame. For example, if the low risk category includes two parameters that fall within the category, and the medium and high risk categories each include one parameter, the risk of developing or progressing myopia of the subject over the time frame may be identified as low risk.
[0083] 5B shows, by way of example, a schematic diagram of another method 500B for identifying a subject's risk of developing or progressing myopia over a time frame based on respective risk categories assigned to each of at least one parameter. In another embodiment, identifying a subject's risk of developing or progressing myopia over a time frame may include, in step 520, assigning a weight to each one of a plurality of predefined risk categories. For example, a quantitative, e.g., numerical value, may be assigned to each of the low, medium, and high risk categories. As a further example, the low risk category may be assigned a weight of "0", the medium risk category may be assigned a weight of "1", and the high risk category may be assigned a weight of "2".
[0084] Method 500B may also include, at step 522, for each risk category of the plurality of predetermined risk categories, identifying a number of parameters of the at least one parameter to which the respective risk category is assigned. Step 522 may be the same as step 510 of method 500A. Repetitive description is omitted for brevity. Briefly, step 522 includes identifying a total number of parameters in each of the low, medium and high risk categories.
[0085] Step 524 of method 500B may include calculating, for each of the plurality of predetermined risk categories, a score by multiplying a weight assigned to the respective risk category by the number of parameters to which the risk category is assigned. For example, a score for each of the low, medium, and high risk categories may be calculated by multiplying a weight assigned to the respective risk category (at step 520) by the total number of parameters assigned to the respective risk category (at step 522).
[0086] Step 526 of method 500B may then include calculating a final score by summing the scores calculated for a number of predefined risk categories, for example, the final score is calculated by adding up the individual scores determined in the previous step 524 for each of the low, medium and high risk categories.
[0087] To identify the subject's risk of developing or progressing myopia over a time frame, the method 500B may include, in step 528, comparing the final score to at least one first predetermined threshold. The first predetermined threshold may be established based on a database including information regarding the risk of developing or progressing myopia over a time frame for individuals in a population sample. For example, the final score may be compared to at least one first predetermined threshold, such as thresholds for a low risk category, a medium risk category, and a high risk category, and may include identifying whether the final score is equal to, greater than, or less than the at least one first predetermined threshold.
[0088] Step 530 of method 500B may then include identifying the subject's risk of developing or progressing myopia over the time frame based on a comparison of the final score to at least one first predetermined threshold. For example, if in the previous step 528 the final score was identified as being equal to or greater than a first predetermined threshold for a high risk category, the subject's risk of developing or progressing myopia over the time frame may be identified as being high risk.
[0089] 6 shows, by way of example, a schematic diagram of a method 600 for identifying a subject's risk of developing or progressing myopia over a time frame based on a determined value of at least one parameter, according to various embodiments. The method 600 may include, in step 610, inputting the determined value of the at least one parameter (in step 110) into at least one predictive model based on a machine learning algorithm. For example, step 610 may include, among others, inputting the determined value of the sensitivity parameter SRx and / or a fifth parameter indicative of the degree of overlap of the subject's distance and near comfort zones into the predictive model based on a machine learning algorithm.
[0090] The method 600 may also include, in step 620, calculating the value of the risk ratio using at least one predictive model based on a machine learning algorithm. As described above, the machine learning algorithm may include a correlation table or any database that includes information on the relationship between the risk of myopia development or progression over a time frame and at least one parameter related to the visual condition. According to various embodiments, the value of the risk ratio may be calculated based on a machine learning algorithm. For example, the machine learning algorithm may include a multi-factor equation that correlates the risk of myopia development or progression over a time frame with each at least one parameter related to the visual condition for individuals in the population sample. Thus, the calculated value of the risk ratio determined in step 620 provides a probability indicative of the subject's risk of myopia development or progression over a time frame and is implemented using at least one predictive model based on a machine learning algorithm.
[0091] At step 630, the method 600 may include identifying the subject's risk of developing or progressing myopia over the time frame based on the calculated value of the risk ratio. For example, the calculated value of the risk ratio may be expressed as a risk percentage (%) that provides an indicative probability of the subject's risk of developing or progressing myopia over the time frame. As a further example, the risk ratio may be expressed as being a value ranging from 0 to 100 or alternatively 0.0 to 1.0 over the time frame.
[0092] In some embodiments, method 600 may include an additional step 640 that includes comparing the calculated value of the risk ratio to a second predetermined threshold. The second predetermined threshold may be established based on a database that includes information regarding the risk of myopia development or progression over a time frame for individuals in a population sample. In an example, the second predetermined threshold may be a threshold that indicates that a subject may be at moderate or high risk of myopia development or progression.
[0093] According to various embodiments, the methods 100, 300, 400, 500A, 500B and 600 for identifying a subject's risk of developing or progressing myopia over a time frame may be based on at least one predictive model based on a machine learning algorithm, which provides a relationship between the risk of developing or progressing myopia and each parameter, as described above. In some embodiments, the risk may be identified as a categorical risk, such as low, medium or high risk. Alternatively, the risk may be identified as a continuous risk, such as a percentage or risk ratio. In some embodiments, the risk of developing or progressing myopia over a time frame may include both categorical and continuous risks.
[0094] FIG. 7 shows an example of a system 700 for identifying the risk of developing or progressing myopia over a time frame. The system 700 includes a means 710 for identifying a value of at least one parameter associated with a visual condition of a subject, which may include at least one circuit, e.g., a microprocessor. For example, the means 710 for identifying a value of at least one parameter associated with a visual condition of a subject may include any optometric device, such as a computer-controlled machine used during optometry to provide an objective measurement of the subject's refractive error, e.g., an ophthalmometer, a refractometer, an autorefractometer, and / or a retinoscope. For example, the optometric device may be used to identify the subject's refractive optical parameters, a first parameter and a third parameter indicative of the subject's near and far refraction, respectively.
[0095] According to various embodiments, the means 710 for determining the value of at least one parameter related to the visual condition of the subject also includes determining a sensitivity parameter SRx of the subject, the sensitivity parameter SRx relating to the sensitivity of the subject to a change in at least one refractive optical characteristic of at least one ophthalmic lens placed in front of at least one eye of the subject. Thus, the at least one circuit may be configured to determine the value of the sensitivity parameter SRx, for example, including instructions. In some embodiments, the at least one circuit may further determine a second parameter indicative of the near-distance refraction sensitivity of the subject, a fourth parameter indicative of the far-distance refraction sensitivity of the subject, and a fifth parameter indicative of the overlap of the far-distance and near-distance comfort ranges of the subject. The method for determining the value of the sensitivity parameter SRx and the second, fourth, and fifth parameters has been described above, and repeated description will be omitted for the sake of brevity.
[0096] According to various embodiments, the means 710 for determining a value of at least one parameter related to the visual condition of the subject may also be configured to receive other parameters related to the visual condition of the subject. For example, the means 710 for determining a value of at least one parameter related to the visual condition of the subject may include an interface 712 configured to receive an input of the subject. As a further example, the interface 712 may be a display on the means 710 for determining a value of at least one parameter related to the visual condition of the subject, such as a microprocessor. Thus, the subject (or a third party) may input other parameters related to the visual condition, such as parameters related to the lifestyle, activity or behavior of the subject, parameters related to the genetic history of the subject, optical biometric parameters and / or parameters related to personal information of the subject.
[0097] According to various embodiments, the circuitry may include analog circuits or components, digital circuits or components, or hybrid circuits or components. Any other type of implementation of the respective functions described in more detail below may also be understood as a "circuitry" according to alternative embodiments. A digital circuitry may be understood as any type of logic implementation entity, which may be a dedicated circuitry or a processor that executes software, firmware, or any combination thereof stored in a memory. Thus, in various embodiments, a "circuitry" may be a digital circuitry, e.g., a hardwired logic circuitry, or a programmable processor, e.g., a programmable logic circuitry such as a microprocessor (e.g., a complex instruction set computer (CISC) processor or a reduced instruction set computer (RISC) processor). A "circuitry" may also include a processor that executes software, e.g., a computer program of any kind, e.g., a virtual machine code such as Java, for example.
[0098] The system 700 further includes a means 720 for determining the risk of the subject's myopia development or progression over a time frame based on the determined value of the at least one parameter. The means 720 for determining the risk of the subject's myopia development or progression over a time frame may include at least one circuit configured to perform steps of methods 400, 500A, 500B, and 600. According to various embodiments, the means 720 for determining the risk of the subject's myopia development or progression over a time frame, e.g., a circuit or a microprocessor, may include a computer program or instructions. In one example, the computer program or instructions may be executed to perform steps of methods 400, 500A, 500B to determine whether the subject's risk of myopia development or progression over a time frame is of a low risk, medium risk, or high risk category. In another example, the instructions may be executed to perform steps of method 600 to calculate a risk ratio value providing a probability indicative of the subject's risk of myopia development or progression over a time frame. According to various embodiments, the computer program or instructions may be implemented with at least one predictive model based on a machine learning algorithm.
[0099] According to various embodiments, the means 710 for determining the value of at least one parameter associated with the visual condition of the subject and the means 720 for determining the risk of onset or progression of the subject may include a circuit, e.g., a microprocessor. In one embodiment, the means 710 for determining the value of at least one parameter associated with the visual condition of the subject and the means 720 for determining the risk of onset or progression of the subject may be implemented in the same circuit, e.g., a microprocessor. For example, the means 720 for determining the risk of onset or progression of the subject, e.g., instructions and computer programs for performing steps of methods 400, 500A, 500B and 600, may be implemented in the same circuit as the means 710 for determining the value of at least one parameter associated with the visual condition of the subject, so as to perform step 110 of methods 100 and 300. As a further example, the means 720 for determining the risk of onset or progression of the subject may be implemented in the optometry device 710 used to determine the value of at least one parameter associated with the visual condition of the subject.
[0100] Advantageously, including the means 710 for determining a value of at least one parameter related to a visual condition of a subject and the means 720 for determining a subject's risk of onset or progression over a time frame in the same circuit provides a direct and simple way of determining risk in said subject, e.g. an operator operating the circuit does not need to perform any additional steps to determine said risk.
[0101] In some embodiments, the means 710 for determining the value of at least one parameter associated with the visual condition of the subject and the means 720 for determining the risk of onset or progression of the subject may each include a circuit. In other words, the means 710 for determining the value of at least one parameter associated with the visual condition of the subject and the means 720 for determining the risk of onset or progression of the subject may be implemented in separate circuits. For example, the means 710 for determining the value of at least one parameter associated with the visual condition of the subject may be acquired and calculated on an optometry device, and the means 720 for determining the risk of onset or progression of the subject may be implemented on another microprocessor. In this embodiment, the determined value of the at least one parameter associated with the visual condition of the subject acquired in step 110 may be transmitted to the circuit according to a predefined wireless communication protocol to determine the risk of onset or progression of myopia in the subject over a time frame 720. Examples of predefined wireless communication protocols include global system for mobile communication (GSM), enhanced data GSM environment (EDGE), wideband code division multiple access (WCDMA), code division multiple access (CDMA), time division multiple access (TDMA), wireless fidelity (Wi-Fi), voice over Internet protocol (VoIP), worldwide interoperability for microwave access (Wi-MAX), Wi-Fi direct (WFD), ultra-wideband (UWB), infrared data association (IrDA), Bluetooth, ZigBee, SigFox, LPWan, LoRaWan, GPRS, 3G, 4G, LTE and 5G communication systems. Thus, each of the circuits may include the necessary hardware required to support wireless transmission. Alternatively, it is envisaged that the determined value of at least one parameter related to the visual condition of the subject may be transmitted via wired means.
[0102] According to various embodiments, a computer program product may include instructions that cause system 700 to perform the steps of methods 100, 300, 400, 500A, 500B, and 600. The steps of methods 100, 300, 400, 500A, 500B, and 600 may be used to identify a subject's risk of developing or progressing myopia over a time frame.
[0103] According to various embodiments, the methods and systems of the present invention may further include providing recommendations for mitigating risk to non-myopic or myopic subjects. For example, mitigation options may be recommended if a subject is identified as having a moderate or high risk of developing myopia over a time frame or a high or rapid rate of myopia progression. Mitigation options may include, but are not limited to: lenses configured to control myopia progression; atropine eye drops; corneal refractive correction; multifocal soft contact lenses; spectacle lenses designed to slow myopia progression; changes in the subject's lifestyle, activity, or behavior, such as increasing the number of days per day spent outdoors in natural light, reducing the time spent performing tasks involving close vision, changes in the subject's nutrition, or any combination thereof; recommendations to perform further testing on the subject, such as further eye exams, genetic testing, imaging of one or both eyes of the individual, screening for eye disorders or conditions, or any combination thereof.
[0104] Advantageously, the present invention uses the value of the sensitivity parameter SRx of a subject as a novel factor for identifying the risk of developing or progressing myopia of a subject over a time frame. Specifically, the lack of sensitivity to refraction, i.e., the value of the sensitivity parameter SRx and / or the value of the near and far refraction sensitivity parameters, provide a direct indication of the level of image degradation that a subject can perceive and that is directly related to the development or progression of myopia. As a result, the value of the sensitivity parameter SRx and additionally the overlap of the subject's far and near comfort zones (based on the subject's far and near refraction sensitivity) provide additional factors that improve the predictive power of existing or new myopia prediction models. Identification of the risk of developing or progressing myopia for a subject allows early intervention to reduce said risk. EXAMPLES
[0105] The systems 700 and methods 400, 500A, 500B, 600 disclosed herein are further described in the following examples, which are provided by way of illustration and are not intended to limit the scope of the present disclosure.
[0106] The reference values or reference value ranges in the tables shown in Figures 8A-9C provide exemplary preferred thresholds for the sensitivity limits in each category. For example, the sensitivity limits of the sensitivity parameter SRx may range from 0 to 0.15D for the low risk category, 0.15 to 0.3D for the medium risk category, and more than 0.3D for the high risk category. Alternatively, the sensitivity limits of the sensitivity parameter SRx may range from 0.1 to 0.2D for the low risk category, 0.2 to 0.4D for the medium risk category, and more than 0.4D for the high risk category. As indicated above, the reference values or reference value ranges for each parameter, e.g., parameters related to the genetic history of the subject, refractive optical parameters, and the sensitivity parameter SRx, may be established based on a database containing information on the risk of myopia development or progression over a time frame for individuals in a population sample.
[0107] Example 1. Pre-myopic subjects and use of the sensitivity parameter SRx 8A and 8B show a table of example conditions of use for the method 400, 500A and 500B for identifying a subject's risk of developing or progressing myopia over a time frame. In this example, the subject may be an 8-year-old girl. Referring to FIG. 8A, the subject may be identified as being non-myopic, for example, if the subject's refractive optical parameters obtained based on an eye exam are plano (indicated by a circle). Other parameters may include the subject's genetic history and parameters related to the subject's lifestyle, activity or behavior. In this example, the subject indicates that the subject has one myopic parent (indicated by a circle) and the subject's parameters related to lifestyle, activity or behavior, namely, spending more than 2 hours outdoors per day (indicated by a circle). The parameters may be input into a myopia development prediction model as shown in FIG. 8A.
[0108] As can be seen from Fig. 8A, the subject has one factor, such as refractive optical parameters, that puts the subject in high risk category, one factor, such as genetic history, that puts the subject in medium risk category, and one factor, such as lifestyle, activity or behavior, that puts the subject in low risk category.The reference value or reference value range in each of the low risk, medium risk and high risk categories can be established based on a database that includes the information of the risk of myopia development or progression over a time frame for individuals in a population sample.Since each risk category, such as multiple predetermined risk categories, includes one factor, it can be difficult to identify the risk of myopia development or progression of the subject over a time frame.
[0109] The sensitivity parameter SRx of the subject can then be further identified. In this example, the sensitivity parameter SRx of the subject can be identified as having a value of 0.37D. With reference to FIG. 8B, it can be seen that the sensitivity parameter SRx of the subject of 0.37D falls within the high risk category, and thus the high risk category now includes two factors, for example, the refractive optical parameter and the sensitivity parameter SRx, and the medium risk and low risk categories each include one parameter. The subject can then be identified as having a high risk of developing myopia within a time frame, and appropriate options to reduce said risk can be recommended. For example, a low dose of atropine eye drops can be prescribed, or the subject can be recommended to increase the amount of time spent outdoors per day.
[0110] Alternatively, the subject's risk of developing or progressing myopia over a time frame may be identified using method 500B, which includes assigning weights to each of low, medium, and high risk categories. For example, the low risk category may include a weight of "0", the medium risk category may include a weight of "1", and the high risk category may include a weight of "2" (step 520 of method 500). By performing steps 522 and 526, a final score of 5 may be calculated, for example, final score = (0) (1) + (1) (1) + (2) (2). Step 528 may include comparing the final score to at least one first predefined threshold. For example, the final score may be compared to a first predefined threshold for each of the low, medium, and high risk categories, and in step 530, the subject's risk of developing or progressing myopia over a time frame may be identified.
[0111] Alternatively, a subject's risk of developing or progressing myopia over a time frame may be identified by calculating a risk ratio value, e.g., a percentage, according to method 600 performed using at least one predictive model based on a machine learning algorithm.
[0112] Thus, as shown in FIG. 8B, it can be seen that the use of the sensitivity parameter SRx as an additional parameter in an existing myopia prediction model advantageously improves the predictive power of the model.
[0113] Example 2. Myopic subject and use of the sensitivity parameter SRx and the fifth parameter 9A, 9B and 9C show tables of example conditions of use according to the methods 300, 400, 500A and 500B for identifying a subject's risk of developing or progressing myopia over a time frame. In this example, the subject may be a 6-year-old boy. With reference to FIG. 9A, the subject may be identified as having low hyperopia, for example, where the subject's refractive optical parameters, obtained based on an eye exam, are in the range of 0.25-0.50D (shown by the circles). Other parameters may include the subject's genetic history and parameters related to the subject's lifestyle, activities or behavior. In this example, the subject indicates that the subject does not have any myopic parents (shown by the circles) and that the subject spends less than 1 hour outdoors per day (shown by the circles). The parameters may be input into a myopia development prediction model as shown in FIG. 9A.
[0114] As can be seen from Fig. 9A, the subject has one factor, such as lifestyle, activity or behavior, that puts the subject in high risk category, one factor, such as refractive parameters, that puts the subject in medium risk category, and one factor, such as genetic history, that puts the subject in low risk category.Since each of the multiple predefined risk categories includes one factor, it may be difficult to identify the subject's risk of developing or progressing myopia over a time frame.
[0115] The subject's sensitivity parameter SRx may then be further identified. In this example, the subject's sensitivity parameter SRx may be identified to have a value in the range of 0.15-0.3D, which corresponds to a sensitivity parameter SRx in the medium risk category. As shown in FIG. 9B, the subject may be identified as having a medium risk of myopia progression within the time frame. However, there is still one factor that places it in the high risk category.
[0116] Thus, a first and third parameter of the subject indicative of the subject's near and far refraction may be obtained (step 310), which in this example may be measured as +0.5D and +2.0D, respectively. In step 320, a second and fourth parameter indicative of the subject's near and far refraction sensitivity may be determined, which in this example may be calculated as equal to 0.5D and 0.2D, respectively. Step 330 includes determining the far and near comfort ranges according to Equations 2 and 3, using subject specific coefficients K_near and K_far as 2. For example, the far and near comfort ranges may be determined as follows: Long distance comfort range = 0.5 ± (2 × 0.2) = [+0.9 ~ +0.1] D Close distance comfort range = 2.0 ± (2 × 0.5) = [+3.0 ~ +1.0] D In step 340, the overlap between the far distance comfort range and the near distance comfort range may be determined, and in step 350, a value may be assigned to a fifth parameter indicative of the overlap of the far and near distance comfort ranges. In this example, it is found that there is no overlap between the far distance comfort range and the comfort range, e.g., the value assigned to the fifth parameter may be "no overlap," which falls within the high risk category, as shown in FIG. 9C.
[0117] Thus, based on steps 510 and 512 of method 500A, a subject may be identified as having a high risk of rapid myopia progression within a time frame and appropriate options to mitigate said risk may be recommended. In other words, the predictive power of the myopia model may be improved by an additional parameter indicative of the degree of overlap between the subject's near and far comfort ranges, identified based on the subject's near and far refractive sensitivities.
[0118] Alternatively, the subject's risk of developing or progressing myopia over a time frame may be identified using method 500B, which includes the steps of: assigning 520 a weight to each of the low, medium and high risk categories; determining 522, for each risk category of a plurality of predefined risk categories, the number of parameters of the at least one parameter to which the respective risk category is assigned; calculating 524, for each risk category of the plurality of predefined risk categories, a score by multiplying the weight assigned to the respective risk category by the number of parameters to which the risk category is assigned; calculating 526 a final score by summing the calculated scores for the plurality of predefined risk categories; comparing 528 the final score to at least one first predefined threshold; and identifying 530 the subject's risk of developing or progressing myopia over a time frame based on the final score.
[0119] Alternatively, a subject's risk of developing or progressing myopia over a time frame may be identified by calculating a risk ratio value, e.g., a percentage, according to method 600 implemented using a predictive model based on a machine learning algorithm.
[0120] Therefore, as shown in Fig. 9C, it can be seen that the use of the sensitivity parameter SRx and the fifth parameter indicating the overlap between the subject's near distance comfort range and the far distance comfort range as an additional parameter in the myopia prediction model advantageously improves the predictive power of the model.Alternatively, the fifth parameter can be the only or main identifying factor in the myopia prediction model.For example, even if the parameters in other categories, such as genetic history, the parameters related to the subject's lifestyle, activity or behavior, the refractive optical parameters and / or the sensitivity parameter SRx value, may be in low risk category, if the fifth parameter is in high risk category, the subject may be at high risk of rapid myopia progression in a time frame.
[0121] Example 3. Progression of myopia In this example, the subject may be an 11-year-old myopic male. The subject has indicated that the prescription, e.g., refractive optical parameters, have remained the same as in the previous year, e.g., stable refraction, but complains of intermittent blurred vision after engaging in precision work for extended periods of time.
[0122] In this example, the optometrist (or clinician) only has some parameters, i.e., personal information about the subject, such as age and / or gender, and the myopia progression rate in the previous year (which is a weak indicator). However, the optometrist may have access to the subject's sensitivity parameter SRx, which, for example, was measured to be 0.52D for the subject based on the previous sensitivity parameter SRx, which places the subject in a high-risk category, indicating that the subject is likely prone to rapid myopia progression despite stable refraction. The use of the subject's sensitivity parameter SRx may therefore provide an additional powerful parameter to improve the predictive power of existing myopia prediction models, especially when the optometrist has limited information about the subject.
[0123] Although the present disclosure has been particularly shown and described with reference to certain embodiments, it should be understood by those skilled in the art that various changes in form and details can be made therein without departing from the spirit and scope of the invention as defined by the appended claims. The scope of the present invention is therefore indicated by the appended claims and is therefore intended to embrace all modifications that come within the meaning and range of equivalents of the claims.
Claims
1. 1. A method (100) for identifying a risk of developing or progressing myopia over a time frame, comprising: - determining (110) a value of at least one parameter related to a visual condition of a subject, said at least one parameter comprising a sensitivity parameter (SRx) of said subject, said sensitivity parameter (SRx) relating to the sensitivity of said subject to a change in at least one refractive optical characteristic of at least one ophthalmic lens placed in front of at least one eye of said subject; - determining (120) a risk of developing or progressing said myopia in said subject over said time frame based on said determined value of said at least one parameter; The method (100) comprising:
2. 2. The method (100) of claim 1, wherein the at least one parameter related to the visual condition of the subject further comprises a refractive optical parameter, a parameter related to the lifestyle, activity or behavior of the subject, a parameter related to the genetic history of the subject, an optical biometric parameter and / or a parameter related to personal information about the subject.
3. Identifying (120) the subject's risk of developing or progressing myopia over the time frame based on the determined value of the at least one parameter, - assigning (420) to each of said at least one parameter a respective risk category selected from a plurality of predefined risk categories based on said determined value of each of said parameters; - identifying (430) a risk of development or progression of said myopia in said subject over said time frame based on each of said risk categories assigned to each of said at least one parameter; The method (100) of claim 1 or 2, further comprising:
4. Assigning (420) each of the at least one parameter to a respective risk category based on the determined value of each of the parameters may include: - determining (410) for each of the parameters associated with each of the risk categories whether the determined value of each of the parameters corresponds to a corresponding reference value or lies within a corresponding reference value range; The method (100) of claim 3, comprising:
5. 5. The method (100) of claim 4, wherein the reference value or reference value range for each of the parameters is established based on a database comprising information of the risk of development or progression of the myopia over the time frame for individuals within a population sample.
6. Identifying (420) the subject's risk of developing or progressing myopia over the time frame based on each of the risk categories assigned to each of the at least one parameter, comprising: - for each risk category of said plurality of predetermined risk categories, determining (510) the number of parameters of said at least one parameter to which said respective risk category is assigned; - identifying (512) a risk category from said plurality of predefined risk categories that is assigned to a maximum number of parameters as a risk of development or progression of said myopia in said subject over said time frame; The method (100) of any one of claims 3 to 5, comprising:
7. Identifying (420) the subject's risk of developing or progressing myopia over the time frame based on each of the risk categories assigned to each of the at least one parameter, comprising: - assigning (520) a weight to each one of said plurality of predetermined risk categories; - for each risk category of said plurality of predetermined risk categories, determining (522) the number of parameters of said at least one parameter to which said respective risk category is assigned; - calculating (524) for each risk category of said plurality of predetermined risk categories a score by multiplying said weight assigned to each of said risk categories by the number of parameters to which said risk category is assigned; - calculating (526) a final score by summing the scores calculated for the plurality of predefined risk categories; - identifying (530) the subject's risk of developing or progressing myopia over the time frame based on the final score; The method (100) of any one of claims 3 to 5, comprising:
8. 8. The method (100) of claim 7, wherein identifying (530) the subject's risk of developing or progressing myopia over the time frame based on the final score comprises comparing (528) the final score to at least one first predetermined threshold.
9. The method (100) according to any one of claims 1 to 8, wherein identifying (120) the subject's risk of developing or progressing myopia over the time frame based on the determined value of the at least one parameter is established based on at least one predictive model based on a machine learning algorithm, providing a relationship between the risk of developing or progressing myopia and the at least one parameter.
10. Identifying (120) the subject's risk of developing or progressing myopia over the time frame based on the determined value of the at least one parameter, - inputting (610) said determined values of said at least one parameter into said at least one predictive model based on said machine learning algorithm; - calculating (620) a value of a risk ratio using said at least one predictive model based on said machine learning algorithm; - identifying (630) a risk of developing or progressing myopia in said subject over said time frame based on said calculated value of said risk ratio; Further comprising:
10. The method of claim 9, wherein the calculated value of the risk ratio provides a probability indicative of the subject's risk of developing or progressing myopia over the time frame and is performed using the at least one predictive model based on the machine learning algorithm.
11. 11. The method of claim 10, wherein identifying (630) the subject's risk of developing or progressing myopia over the time frame based on the risk ratio comprises comparing the calculated value of the risk ratio to at least one second predetermined threshold.
12. The at least one parameter related to the visual condition of the subject is a first parameter (310) representative of the near-field refraction of said object; a second parameter (320) indicative of the near-distance refractive sensitivity of said object; a third parameter (310) representative of the far-field refraction of the object; a fourth parameter (320) representative of the subject's long-distance refractive sensitivity; a fifth parameter (350) indicative of the overlap of the far-distance comfort zone and the near-distance comfort zone of said object; Including, The determining (350) of the value of the fifth parameter may further comprise: determining (330) said far distance comfort range and said near distance comfort range based on said determined values of said first to fourth parameters; - determining (340) said overlap of said far and near comfort zones; - assigning (350) a value to said fifth parameter based on said determined overlap of said far-distance and near-distance comfort zones; The method (100) of any one of claims 1 to 11, comprising:
13. 1. A system (700) for identifying risk of myopia development or progression over a time frame, comprising: - means (710) for determining a value of at least one parameter related to a visual condition of a subject, said at least one parameter comprising a sensitivity parameter (SRx) of said subject, said sensitivity parameter (SRx) relating to the sensitivity of said subject to a change in at least one refractive optical characteristic of at least one ophthalmic lens placed in front of at least one eye of said subject; - means (720) for identifying a risk of development or progression of said myopia in said subject over said time frame based on said identified value of said at least one parameter; A system (700) comprising:
14. 14. The system (700) of claim 13, wherein at least one of the means for determining the value of the at least one parameter and the means for determining the subject's risk of developing or progressing myopia comprises a circuit.
15. A computer program product comprising instructions for causing a system (700) according to claim 13 or 14 to perform the steps of the method (100, 300, 400, 500A, 500B, 600) according to any one of claims 1 to 12.
Citation Information
Patent Citations
Ophthalmologic apparatus and ophthalmologic information processing program
JP2019170706A
Myopia progression diagnostic device, myopia progression discrimination method, program, and storage medium
JP5667730B1
Method for determining a value of a global sensitivity parameter of a subject, methods using this value and system for determining said value
US20210311325A1
Accurate prediction and treatment of myopic progression by artificial intelligence
WO2020083382A1
