Method and apparatus for constructing a model for predicting the evolution of vision-related parameters over time - Patent Application 20070122997

Abstract

The method for constructing a predictive model for predicting the evolution of at least one vision-related parameter over time for at least one person includes: obtaining, for at least one member of a group of individuals, continuous values ​​each corresponding to repeated measurements over time of at least one parameter of a first predetermined type (10); obtaining the evolution of the vision-related parameter over time for the member of the group of individuals (12); and constructing, by at least one processor, a predictive model, wherein the predictive model associates, for the member of the group of individuals, at least some of the continuous values ​​with the obtained evolution of the vision-related parameter over time, wherein the associating includes jointly processing at least some of the continuous values ​​associated with the same one of the first predetermined type of parameters, wherein the predictive model depends differently on each of the jointly processed values.

Description

[Technical Field]

[0001] The present invention relates to a method and apparatus for building a predictive model for predicting the evolution over time of at least one vision-related parameter of at least one person. [Background technology]

[0002] While some factors that affect a person's vision, such as genetic factors, cannot be changed by the individual, some other factors, such as lifestyle, behavior, and / or environmental factors, can be changed by anyone. For example, time spent outdoors, time spent performing close-up tasks, or nutrition can affect vision, for example, by causing the onset, progression, or reduction of myopia.

[0003] Wearable devices are known that can, for example, correct a person's reading and / or writing posture and collect myopia-related parameters.

[0004] However, known devices are often standardized and therefore assume that they are the same for everyone, i.e. that everyone has a similar risk of developing and progressing myopia, for example, which is not the case in reality.

[0005] Additionally, for many existing devices, the predicted myopia progression profile is calculated once and is not subsequently updated.

[0006] Thus, if a person's lifestyle, behavior, and / or environment changes after their predicted profile has been calculated, the unchanged predicted profile will be inconsistent and erroneous.

[0007] Therefore, when constructing a model to predict the evolution of one or more vision-related parameters of a person over time, it is necessary to take into account changes in modifiable parameters that affect the person's vision. Summary of the Invention [Problem to be solved by the invention]

[0008] SUMMARY OF THE INVENTION An object of the present invention is to overcome the above-mentioned drawbacks of the prior art. [Means for solving the problem]

[0009] Therefore, the present invention provides a method for constructing a predictive model for predicting the evolution over time of at least one vision-related parameter of at least one person, comprising: obtaining, for at least one member of the group of individuals, successive values ​​each corresponding to repeated measurements over time of at least one parameter of a first predetermined type; obtaining the evolution of at least one vision-related parameter over time for at least one member of a group of individuals; constructing a predictive model by at least one processor, the predictive model comprising associating, for at least one member of the group of individuals, at least a portion of the continuous values ​​with the obtained evolution over time of the at least one visual acuity-related parameter, wherein the associating comprises jointly processing at least a portion of the continuous values ​​associated with the same one of the at least one parameter of a first predetermined type; The prediction model provides a remarkable method in that it depends differently on each of the jointly processed values.

[0010] Thus, a predictive model is constructed by collecting data from a group of individuals, i.e., an entire panel of individuals, and taking into account possible modifications of the parameters measured for those individuals over time. By making the predictive model depend differently on each of these jointly processed values, i.e., by taking into account both the continuous values ​​themselves and the results of jointly processing continuous values ​​of the parameters, it is possible to obtain a highly accurate and consistent dynamic predictive model. That is, swapping the inputs corresponding to those successive jointly processed values, for example, by swapping values ​​obtained at different dates and times, may affect the predictive model that is constructed.

[0011] The enhanced predictive capabilities potentially provided by the above-described methods for building predictive models can be attributed in particular to the time-dependent personal visual sensitivity of the person considered, which is a specific expression of their personal chronotype.

[0012] In general, chronotype is a human attribute that reflects the time of day when their bodily functions (hormone levels, body temperature, cognitive ability, diet, and sleep) are active, changing, or reaching a certain level. It is considered an important predictor of sleep timing, sleep consistency, sleep duration, sleep need, sleep quality, morning sleepiness, and adaptability to shift work.

[0013] The enhanced predictive capabilities may alternatively or additionally result from the implicit consideration of time-dependent environmental parameters that are not explicitly entered as inputs but whose continuous values ​​depend on the time at which they are obtained. These may include, in particular, light spectral distribution, light ray direction, light radiance and / or light coherence and / or diffusion properties, whether associated with natural lighting, artificial lighting, or both.

[0014] Furthermore, the fact that the predictive model depends differently on each of the jointly processed values ​​makes it possible to identify and / or have better knowledge of parameters that influence the predictive model without being explicitly entered. Chronobiology (in relation to sleep cycle records and their characteristics) and light orientation can be examples of such parameters.

[0015] The present invention also provides an apparatus for constructing a predictive model for predicting the evolution over time of at least one vision-related parameter of at least one person, comprising: at least one input adapted to receive continuous values ​​corresponding respectively to repeated measurements over time of at least one parameter of a first predetermined type for at least one member of the group of individuals and to the evolution over time of at least one vision-related parameter for at least one member of the group of individuals; and at least one processor configured to build a predictive model, comprising associating at least a portion of the continuous values ​​with the obtained evolution over time of the at least one vision-related parameter for at least one member of the group of individuals, and jointly processing at least a portion of the continuous values ​​associated with the same one of the at least one parameter of a first predetermined type; The predictive model also provides a notable device in that it depends differently on each of the jointly processed values.

[0016] The present invention further provides a computer program product for constructing a predictive model for predicting the evolution over time of at least one vision-related parameter of at least one person, the computer program product being accessible to a processor and when executed by the processor causing the processor to: one or more instruction sequences that cause the system to build a predictive model, the predictive model comprising: associating at least a portion of the continuous values ​​that each correspond to repeated measurements over time of at least one parameter of a first predetermined type for at least one member of the group of individuals with the evolution over time of at least one vision-related parameter for at least one member of the group of individuals, and jointly processing at least a portion of the continuous values ​​that are associated with the same one of the at least one parameter of the first predetermined type; A computer program product is provided that is notable in that the predictive model depends differently on each of the jointly processed values.

[0017] The present invention further provides a non-transitory computer-readable storage medium accessible to a processor and which, when executed by the processor, causes the processor to: storing one or more sequences of instructions for constructing a predictive model, the predictive model comprising associating at least a portion of successive values ​​each corresponding to repeated measurements over time of at least one parameter of a first predetermined type for at least one member of the group of individuals with the evolution over time of at least one vision-related parameter for at least one member of the group of individuals, the predictive model comprising jointly processing at least a portion of successive values ​​associated with the same one of the at least one parameter of the first predetermined type; A non-transitory computer-readable storage medium is provided that is notable in that the predictive model depends differently on each of the jointly processed values.

[0018] The advantages of the apparatus, the computer program product, and the computer-readable storage medium are similar to those of the method, so they will not be repeated here.

[0019] The apparatus, the computer program and the computer readable storage medium for building a predictive model are advantageously configured to perform the method for building a predictive model in any of its modes of execution.

[0020] For a more detailed understanding of the description provided herein and its advantages, reference is now made to the following brief description taken in conjunction with the accompanying drawings and detailed description, wherein like reference numerals represent like parts. [Brief explanation of the drawings]

[0021] [Figure 1] FIG. 2 is a flow diagram illustrating steps of a method for building a predictive model according to the present invention in certain embodiments. [Figure 2] 1 is a graph showing a myopia progression risk profile based on a prediction model obtained by a method for building a prediction model according to the present invention in certain embodiments. [Figure 3] FIG. 1 is a flow diagram illustrating steps of a prediction method resulting from the use of a predictive model constructed in accordance with the present invention in certain embodiments. [Figure 4] 3 is the graph of FIG. 2 with added monitoring indicators. [Figure 5] A set of two graphs showing examples of multiple risk profiles including predicted evolution over time obtained by implementing a prediction method resulting from the use of a predictive model constructed according to the present invention in a specific embodiment. [Figure 6] 1 is a graph showing two myopia development risk profiles based on a predictive model obtained by a method for constructing a predictive model according to the present invention in a specific embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0022] In the following description, the drawings may not necessarily be to scale, and certain features may be shown in generalized or schematic form for clarity and conciseness or for informational purposes. In addition, while the making and use of various embodiments are discussed in detail below, it should be understood that, as described herein, many inventive concepts are provided that may be embodied in a variety of contexts. The embodiments discussed herein are merely representative and do not limit the scope of the invention. It will also be apparent to those skilled in the art that all technical features defined in relation to a process, individually or in combination, can be substituted for an apparatus, and conversely, all technical functions related to an apparatus, individually or in combination, can be substituted for a process.

[0023] The terms "comprise" (and its grammatical variations such as "comprises" and "comprising"), "have" (and its grammatical variations such as "has" and "having"), "contain" (and its grammatical variations such as "contains" and "containing"), and "include" (and its grammatical variations such as "includes" and "including") are open-ended linking verbs. They are used to specify the presence of a stated feature, integer, step, or component, or group thereof, but do not exclude the presence or addition of one or more other features, integers, steps, or components, or group thereof. Consequently, a method or step within a method that "comprises," "has," "contains," or "includes" one or more steps or elements is not limited to having only those one or more steps or elements.

[0024] As shown in Figure 1, a method for constructing a predictive model for predicting the evolution over time of at least one vision-related parameter for at least one individual includes a step 10 of obtaining, for at least one member of a group of individuals, successive values ​​each corresponding to repeated measurements over time of at least one parameter of a first predetermined type.

[0025] As a non-limiting example, a vision-related parameter to consider may be a person's level of myopia, expressed in diopters for the left and / or right eye. It may also be visual aptitude or any other parameter related to a person's visual deficiency, such as hyperopia, astigmatism, presbyopia, or any visual disease, such as eye diseases that may result in visual problems, including myopic macular degeneration, retinal detachment, and glaucoma. In addition to refractive error (expressed in diopters), ocular biometric measurements such as axial length (mm), vitreous chamber depth (mm), choroidal thickness (expressed in μm), and corneal properties are other examples of vision-related parameters.

[0026] A group of individuals may include any number of individuals who may have no common characteristics with each other, or who may have one or more common characteristics such as, by way of non-limiting example, gender and / or date of birth and / or country of birth and / or past family history and / or ethnicity.

[0027] In either case, such fixed parameters for at least one member of the group of individuals may be input into the predictive model either in the preliminary step 8 of initialization, or at any later stage of the method. Input of such fixed parameters is optional. The fixed parameters may be available individually to members of the group of individuals, or collectively to subgroups of the group of individuals.

[0028] The continuous values ​​are not necessarily continuous in time.

[0029] The first type of parameters to be considered relate, for example, to the lifestyle or activity or behaviour of the individual or person to be considered.

[0030] As non-limiting examples, parameters of the first type may include duration spent outdoors or indoors, distance between the eyes and the text being read or written, duration of reading or writing, light intensity or spectrum, duration of sleep cycle, or frequency or duration of wearing the visual device.

[0031] More generally, parameters of the first type are any parameters that are likely to affect the evolution of the selected vision-related parameter and that can be measured repeatedly at different time points.

[0032] The measurements may be taken by various kinds of sensors adapted to detect the parameters considered, possibly together with time stamps.

[0033] For example, a light sensor, which may be included in a smart eyewear device or a smartphone, may be used to measure the intensity or spectrum of ambient light. An inertial motion unit (IMU), located, for example, in a head accessory, may be used to detect posture. The IMU may also be used to measure time spent performing outdoor activities. GPS may be used to detect outdoor activities or whether an individual is in a rural or urban environment. A camera or frame sensor may be used to detect the frequency and / or duration of wearing the glasses. A memory may be used to register the date of the current visual device, given that older visual devices may affect visual aptitude.

[0034] After step 10, step 12 of obtaining the evolution of the selected visual acuity related parameter over time is carried out for the same individuals of the group of individuals for which continuous values ​​have been obtained.

[0035] Such progress over time may be obtained by repeatedly measuring selected vision-related parameters for those individuals over time and / or by collecting information regarding the values ​​of the vision-related parameters provided by the individuals via any suitable interface to a processor that builds the predictive model.

[0036] The measurement frequency may be different for the various parameters measured in step 10 and may be independent of the measurement frequency in step 12 .

[0037] For example, the first type of parameter may be measured at least once a day. Alternatively, the smart frame may be used to measure the first type of parameter at a frequency higher than 1 Hz.

[0038] As an optional feature, an additional step 14 may then be performed of obtaining information regarding the changed values ​​of one or more parameters of a second predetermined type for at least one of those individuals for which continuous values ​​have been obtained.

[0039] The second type of parameter is any periodic or random event that is likely to affect the evolution of the selected vision-related parameter and that can be obtained at least once.

[0040] As non-limiting examples, the second type of parameter may be a move from an urban area to a rural area, a change in correction type, a change in corrective lens power, or pregnancy.

[0041] During a next step 16, performed by at least one processor, at least a portion of the successive values ​​obtained in step 10 is associated with the evolution over time obtained in step 12. Such a portion of the successive values ​​is a selected sequence of values ​​taken from among the previously obtained values. The selected values ​​are not necessarily consecutive in time. In a particular embodiment, the selected sequence comprises at least three consecutive values.

[0042] Furthermore, at least some of the fixed parameters mentioned above may also be taken into account in the association process.

[0043] If optional step 14 is omitted, the association performed in step 16 includes jointly processing the above-mentioned portion of consecutive values ​​obtained for the same parameter of the first type. As a non-limiting example, such joint processing may include calculating the mean and / or standard deviation value of a predetermined number of consecutive values ​​of the same parameter of the first type over a predetermined period of time. It may also include a set of consecutive values ​​over a predetermined period of time, which may then be averaged over the predetermined period of time.

[0044] If optional step 14 has been performed, the association performed in step 16 comprises associating the modified values ​​of the second type of parameter with the obtained evolution over time of the selected vision-related parameter, together with the above-mentioned part of the continuous values.

[0045] Therefore, regardless of whether optional step 14 is performed or not, a correlation table or any other database means may be constructed and stored in a non-transitory computer readable storage medium such as a read only memory (ROM) and / or a random access memory (RAM), with the obtained parameter values ​​corresponding to the determined evolution of the selected vision-related parameters over time.

[0046] According to the present disclosure, in addition to the jointly processed values, the correlation table or other database means takes into account each of those individually obtained continuous values, or at least some of them, i.e. at least two, preferably at least three. In other words, the predictive model differs as a function of each of those continuous values, i.e. the predictive model depends differently not only on the result of the joint processing but also on each of those jointly processed values.

[0047] The predictive model may depend differently on each of the values ​​jointly processed through the joint processing. For example, the average may depend on characteristic weights associated with each different continuous value, e.g., a greater weight for 12 PM than for 9 PM. In an alternative implementation that can be combined with the previous one, the joint processing and differential consideration of the continuous values ​​are performed separately. For example, a set of continuous values ​​forms one predictive input, and some of those values ​​form additional predictive inputs.

[0048] The order in which steps 8, 10, 12, 14, and 16 are described is a non-limiting example. They may be performed in any other order. For example, association step 16 may be started as soon as some of the continuous values ​​and some of the evolution over time of the visual acuity-related parameters have been obtained, and steps 10, 12, and 14 may be performed simultaneously as step 16 continues.

[0049] The predictive model building method may be implemented in a server.

[0050] The predictive model construction device according to the present invention comprises at least one input adapted to receive continuous values ​​for at least one member of the group of individuals as described above, as well as the evolution over time of the considered vision-related parameter for said member of the group of individuals, The device also comprises at least one processor configured to construct a predictive model as described above.

[0051] Such an apparatus may comprise a display unit and / or a smartphone or a smart tablet or smart eyewear in addition to the server if the method is implemented in a remote and centralized manner on the server.

[0052] In certain embodiments of the predictive model construction method, the group of individuals may also include a person for whom the evolution over time of one or more vision-related parameters is to be predicted by a predictive model constructed according to the construction method described herein, i.e., for whom steps 10, 12, 16, and possibly also step 14, are performed.

[0053] In certain embodiments, the processor used in step 16 may implement a machine learning algorithm, i.e., one or more neural networks may be trained by inputting a series of continuous values ​​for a large number of individuals and constructing a correlation table or any other database means containing a large number of data for better accuracy of the predictive model.

[0054] In such an embodiment, the association of step 16 may be performed by assigning weights to node connections within the neural network.

[0055] Self-reported parameters provided by individuals in the group may also be considered by the predictive model building.

[0056] By way of non-limiting example, self-reported parameters may be input into the machine learning algorithm, such as, by way of non-limiting example, respective gender, ethnic group, number of myopic parents, school grades, IQ test results, data from social networks, refractive values ​​of visual instruments, or genetic risk scores related to visual defects or diseases. Such self-reported parameters then modify the predictive model. Other fixed parameters and parameters of the first and / or second type, as well as the evolution of the vision-related parameters of the group of individuals over time, may also be self-reported.

[0057] To input the self-reported parameters or the second type of parameters, the device for building the predictive model may include a display means already used to obtain the first type of parameter measurements and / or a smartphone or smart tablet, or any other type of user interface, including an audio interface.

[0058] The predictive model constructed by the methods described above may be utilized in a number of ways to provide an individual with information regarding the predicted progression of one or more vision-related parameters of that individual over time.

[0059] If the selected vision-related parameter is, for example, the risk of developing or progressing a given visual defect, the predictive model may be used to show the evolution of that risk over time in the form of a profile graph.

[0060] 2 and 6 show such graphs in one embodiment where the vision impairment is myopia.

[0061] In Figure 2 the evolution of the monitored person's myopia level is depicted as a function of time.

[0062] In Figure 6, the risk of developing myopia is plotted as a function of time.

[0063] In Figure 2, the solid curve shows the actual measured myopia progression profile, the dashed curve shows the predicted myopia risk profile that updates as a function of the dynamic predicted progression correction, and the dotted curve shows the predicted myopia risk profile before inputting the corrected values ​​of the input parameters.

[0064] The first type of parameter is measured as the time spent performing near vision tasks. Starting at time T1, the risk of myopia progression increases with increasing time spent performing such tasks, reflected by a sharp rise in the predicted myopia risk profile (dotted curve). At time T2, the monitored person moves from an urban area to a rural area, reflected by a gradual plateau in the predicted myopia risk profile.

[0065] It can be seen that the predicted profile corresponds closely to the actual measured evolution profile, as opposed to the predicted profile which has not been updated to take into account parameter modifications from T1 and T2.

[0066] In Figure 6, at an initial point in time, two scenarios are considered in predicting the risk of developing myopia. In the first scenario, the monitored person continues to live in an urban area while maintaining near-screen work habits, which induces myopia at future time T3, followed by a relatively rapid increase in the predicted myopia level over time. In the second scenario, the monitored person moves to live in a rural area and adopts modified near-screen work habits, which leads to a greater myopia induction at future time T4 than at T3, and a slightly lower myopia progression. This quantifies the lower myopia progression risk in the second scenario compared to the first scenario.

[0067] More generally, the proposed predictive model building method may be used in a method for predicting the evolution over time of at least one vision-related parameter of at least one person, as shown in Figure 3. The prediction method comprises a step 30 of obtaining successive values ​​for the person, each corresponding to repeated measurements over time of at least one parameter of a first type, and a step 36 of predicting by at least one processor the evolution over time of the vision-related parameter of the person from the successive values ​​obtained in step 30 by using the above-described predictive model associated with a group of individuals.

[0068] Step 30 is performed for the person in the same manner as step 10 for the individuals in the group.

[0069] Similar to optional initialization step 8 in Figure 1, optional initialization step 28 may collect fixed parameters for the person, such as gender and / or date of birth and / or country of birth and / or family history and / or ethnicity. Step 28 may be performed either in a preliminary step of initialization or later at any stage of the prediction method.

[0070] In certain implementations, the prediction step 36 may be preceded by an optional step 34 of obtaining information about modified values ​​of at least one parameter of a second type for the person.

[0071] The prediction step 36 uses a predictive model.

[0072] If optional step 34 is omitted, prediction step 36 comprises associating at least a portion of the continuous values ​​for the person with the predicted evolution over time of the person's selected vision-related parameter, the associating operation comprising jointly processing said portion of the continuous values ​​associated with the same parameter of a first type.

[0073] Such a portion of the sequence of values ​​is a selected sequence of values ​​taken from among previously obtained values. The selected values ​​are not necessarily consecutive in time. In a particular implementation, the selected sequence comprises at least three consecutive values.

[0074] If optional step 34 has been performed, prediction step 36 further includes associating the predicted evolution over time of the selected vision-related parameters for the person with the above-mentioned portion of the continuous values ​​of the first type of parameters for the person, as well as with the changed values ​​of the second type of parameters.

[0075] According to the present disclosure, regardless of whether optional step 34 is performed or not, for the forecast model, the forecast development takes into account not only the results of the joint processing of those successive values ​​or at least some of them, i.e. at least two, preferably at least three, but also each of those successive values ​​or at least some of them, so that the forecast development differs as a function of each of those successive values, i.e. the forecast model depends differently with respect to each of those jointly processed values.

[0076] A prediction device according to the present disclosure comprises at least one input adapted to receive continuous values ​​for at least one person as described above. The device also comprises at least one processor configured to predict the evolution over time of the considered vision-related parameter of the person as described above.

[0077] Such a device may comprise a display unit and / or a smartphone or smart tablet or smart eyewear or smart eyewear that may be the same as the display unit and / or a smartphone or smart tablet or smart eyewear or server provided in the predictive model construction device. If the predictive method is implemented in a remote, centralized manner in a server, the output from the server is communicated to a user via a communications network, possibly via a wireless or cellular communications link.

[0078] In certain implementations of the prediction method, the group of individuals to which the predictive model is associated may also include a person for whom the evolution over time of one or more vision-related parameters is to be predicted by a predictive model constructed according to the construction method described herein, i.e., for whom steps 10, 12, 16, and possibly also step 14, are performed.

[0079] If self-reported parameters are provided by individuals in the group, the same self-reported parameters about the individual may also be input into the predictive model, such as the individual's gender, ethnicity, number of myopic parents, school grades, IQ test results, data from social networks, refractive values ​​from visual instruments, or genetic risk scores associated with visual defects or diseases.

[0080] Other advantageous aspects of the prediction method relate to the numerous possibilities for interacting with the person, in particular by providing the person (and / or other people, such as the person's parents if the person is a child) with feedback regarding the predicted evolution over time of at least one vision-related parameter of the person.

[0081] As a first possibility for interacting with the person, the predicted evolution over time of selected vision-related parameters of the person may be made available in the form of a graph of the type shown in Figure 2, which may be visualized, for example, on the screen of a smartphone or smart tablet through a mobile application.

[0082] As another possibility for interacting with the person, the prediction method may comprise triggering the sending of one or more warning messages to the person based on the predicted evolution over time of the vision-related parameter considered by the person, in which the content and / or frequency of the warning messages may vary according to the level of risk regarding the vision-related parameter considered by the person.

[0083] For example, if the vision-related parameter considered for a person is the risk of developing or progressing myopia, a person with a high risk of myopia may be warned about reading too close at a trigger threshold of less than 30 cm, whereas a person with a low risk of myopia may be warned at a trigger threshold of less than 20 cm.

[0084] Such trigger thresholds may change over time for a given person depending on the evolution of the predicted myopia risk for that person over time.

[0085] The frequency of the warning messages may vary as well.

[0086] The warning message may, for example, prompt, recommend, or remind the person in time to adopt or maintain healthy eye habits, which helps the person maintain visual fitness. Thus, the person can change their behavior based on such timely reminders or prompts. A very simple visualization allows the person to know whether their behavior is beneficial or harmful to eye health.

[0087] If the vision-related parameter considered is myopia level, the reminder or prompt may discourage activities that pose a risk of myopia development or progression and / or encourage activities that have a protective effect against myopia development or progression.

[0088] The table below shows examples of activities and corresponding actions carried out by a smartphone or smart tablet included in a prediction device according to the invention in the example of myopia.

[0089] [Table 1]

[0090] As another possibility for interacting with the person, as shown in FIG. 4, the prediction method may include providing the person with a monitoring indicator having a first state when the predicted progression of the person's vision-related parameter over time is less favorable than the actually measured progression of the person's vision-related parameter over time, or having a second state when the predicted progression of the person's vision-related parameter over time is more favorable than the actually measured progression of the person's vision-related parameter over time.

[0091] Thus, in the graph of Figure 4, which shows the same curve as Figure 2, the hand-shaped monitoring indicator has its thumb pointing up in both areas referenced by "A" to reflect the fact that in those areas the predicted evolution of the person's myopia level over time is less favorable than the actual measured evolution of their myopia level over time, and has its thumb pointing down in the area referenced by "B" to reflect the fact that the predicted evolution of the person's myopia level over time is more favorable than the actual measured evolution of their myopia level over time.

[0092] As another possibility for interacting with the person, multiple optimized targets or graphs showing a risk profile can be provided to the person and / or the person's parents based on several scenarios showing both good and bad eye use habits to recommend behavioral changes, such as playing outdoors, and to encourage healthy habits, such as habits that help prevent the onset of myopia or slow the progression of myopia, when the vision-related parameter is myopia level or risk. For example, the predictive model calculates and presents an ideal myopia risk profile graph, which is optimized based on the recommended activity if the person performs the recommended activity, such as going outdoors and spending more time outdoors.

[0093] FIG. 5 shows an example of such multiple risk profiles when the vision-related parameter is myopia level.

[0094] The graph on the left of Figure 5 shows the evolution of a person's myopia level over time when the person has a low risk of myopia progression.

[0095] The graph on the right of Figure 5 shows the evolution of a person's level of myopia over time when the person is at high risk of myopia progression.

[0096] In both graphs, the solid curve portion of each graph shows the actual measured myopia progression profile up to the current time, and the dashed curve shows the predicted myopia risk profile beyond that current time, which are updated as a function of modifications of the dynamic prediction model in response to changes in the person's eye use habits and / or behavior. The two dotted curves on each graph show the myopia risk profile in scenarios in which the person does or does not follow recommendations to change their eye use habits and / or behavior. The upper dotted curve corresponds to the scenario in which the person does not follow the recommendations, and the lower dotted curve corresponds to the scenario in which the person follows the recommendations.

[0097] The dotted curves may be accompanied by an explanatory message such as, for example, "Continuing close-up work for long periods of time increases the risk of myopia," for the upper dotted curve, and "Going outside and playing reduces the risk of myopia," for the lower dotted curve.

[0098] As another possibility for interacting with the person, the prediction method may comprise providing the person with a maximum value for a reduction or slowing down of the progression of the person's visual impairment as a function of a change in the value of at least one parameter of a first and / or second predetermined type for the person.

[0099] For example, if a person's myopia progression is initially estimated to be about 1 diopter per year, if the person adopts the healthiest behaviors and / or activities and / or environments, the person may be able to achieve the maximum reduction in myopia progression.For example, the maximum amount of time spent outdoors and a long reading distance may reduce myopia progression to 0.4 diopters per year, resulting in a maximum reduction in myopia progression of 0.6 diopters per year.Conversely, if a person's behaviors and / or activities and / or environments are not optimal, it may lead to a reduction in myopia progression of only 0.3 diopters per year, which corresponds to a 50% reduction in the maximum possible reduction.

[0100] Any of the methods described above may be computer-implemented, i.e. a computer program product accessible to a processor and comprising one or more sequences of instructions which, when executed by the processor, cause the processor to perform the method steps for building a predictive model and / or the method steps for predicting the evolution over time of at least one vision-related parameter as discussed above.

[0101] The predictive models may be used remotely, for example in the cloud, or locally in the smart frame. Model updates and recalculations may be advantageously performed in the cloud.

[0102] The instruction sequences may be stored on one or several computer-readable storage media, including a location in the cloud.

[0103] To construct the predictive model, the processor may receive successive values ​​from various sensors, e.g., via a wireless or cellular communication link, each corresponding to repeated measurements over time of a first predetermined type of parameter for a member of a group of individuals and / or a person.

[0104] While exemplary methods and apparatus have been described in detail herein, those skilled in the art will recognize that various substitutions and modifications may be made without departing from the scope of what is described and defined by the appended claims.

Claims

1. 1. A method for constructing a predictive model for predicting the evolution over time of at least one vision-related parameter of at least one person, the method being executed by a computer including at least one processor, the method comprising: obtaining, for at least one member of a group of individuals, successive values ​​each corresponding to repeated measurements over time of at least one parameter of a first predetermined type related to lifestyle or activity or behavior; obtaining, via the computer interface, the evolution of said at least one vision-related parameter over time for said at least one member of said group of individuals; building the predictive model by the at least one processor, the predictive model comprising associating, for the at least one member of the group of individuals, at least a portion of the continuous values ​​with the obtained temporal evolution of the at least one visual acuity-related parameter, the associating comprising processing together the at least a portion of the continuous values ​​associated with the same one of the at least one parameter of the first predetermined type; Including, If the successive values ​​processed together produce an altered result due to a change in the at least one parameter of a first predetermined type, the predictive model is modified in response to at least a portion of the successive values ​​related to the same parameter so as to depend differently on each of the successive values ​​processed together by assigning a characteristic weight to each of the different successive values ​​processed together in order to predict the evolution of the at least one vision-related parameter over time.

2. 2. The method of claim 1, further comprising, prior to constructing the predictive model, obtaining information regarding changed values ​​of at least one parameter of a second predetermined type relating to any regular or random events for the at least one member of the group of individuals, and the constructing further comprising associating the changed values, together with at least a portion of the continuous values, with the obtained evolution over time of the at least one vision-related parameter for the at least one member of the group of individuals.

3. The method of claim 1 or 2, wherein the at least some of the consecutive values ​​comprises at least three of the consecutive values.

4. The method according to any one of claims 1 to 3, wherein said at least one person belongs to said group of persons.

5. 2. The method of claim 1, wherein the at least one parameter is a period of time spent outdoors or indoors, a distance between the eyes and the text being read or written, a reading or writing period, a light intensity or spectrum, or a frequency or duration of wearing a visual device.

6. The method of any one of claims 1 to 5, wherein said constructing further takes into account self-reported parameters.

7. The method according to any one of claims 1 to 6, wherein said at least one parameter of said first predetermined type is measured at least once a day.

8. The method according to any one of claims 1 to 7, wherein the at least one parameter of the first predetermined type is measured more frequently than once per second.

9. 9. The method of claim 1, wherein said constructing uses a machine learning algorithm that learns from a correlation table or any other database means containing a large number of data constructed by inputting the continuous values ​​for a large number of individuals.

10. 1. An apparatus for constructing a predictive model for predicting the evolution over time of at least one vision-related parameter of at least one person, comprising: at least one input adapted to receive continuous values ​​corresponding respectively to repeated measurements over time of at least one parameter of a first predetermined type for at least one member of a group of individuals and to the evolution over time of said at least one vision-related parameter for said at least one member of said group of individuals; at least one processor configured to construct the predictive model, the predictive model comprising associating a portion of the continuous values ​​with the obtained evolution over time of the at least one visual acuity-related parameter for the at least one member of the group of individuals, the associating comprising determining that at least one parameter of the first predetermined type influences the evolution of the at least one visual acuity-related parameter, and processing together the portion of the continuous values ​​associated with the same one of the at least one parameter of the first predetermined type; Equipped with the at least one parameter of the first predetermined type is a lifestyle or activity or behavioral parameter; If the continuous values ​​processed together produce an altered result due to a change in the at least one parameter of a first predetermined type, the predictive model is modified in response to at least a portion of the continuous values ​​related to the same parameter so as to depend differently on each of the continuous values ​​processed together by assigning a characteristic weight to each of the different continuous values ​​processed together in order to predict the evolution of the at least one vision-related parameter over time.

11. 11. The device according to claim 10, wherein the device comprises a display means and / or a smartphone, a smart tablet or smart eyewear.

12. 1. A computer program for constructing a predictive model for predicting the evolution over time of at least one vision-related parameter of at least one person, the computer program being accessible to a processor and, when executed by said processor, causing said processor to: one or more instruction sequences that cause the predictive model to be constructed, the predictive model comprising: associating a portion of successive values ​​that each correspond to repeated measurements over time of at least one parameter of a first predetermined type for at least one member of a group of individuals with an obtained evolution over time of the at least one visual acuity-related parameter for the at least one member of the group of individuals, the associating determining that the at least one parameter of the first predetermined type influences the evolution of the at least one visual acuity-related parameter; and processing together the portion of the successive values ​​that are associated with the same one of the at least one parameter of the first predetermined type; the at least one parameter of the first predetermined type is a lifestyle or activity or behavioral parameter; If the continuous values ​​processed together produce an altered result due to a change in the at least one parameter of a first predetermined type, the predictive model is modified in response to at least a portion of the continuous values ​​related to the same parameter so as to be differently dependent on each of the continuous values ​​processed together by assigning a characteristic weight to each of the different continuous values ​​processed together in order to predict the evolution of the at least one vision-related parameter over time.

13. A non-transitory computer-readable storage medium that is accessible to and that, when executed by a processor, causes the processor to: storing one or more instruction sequences for constructing a predictive model, the predictive model comprising: associating a portion of successive values ​​each corresponding to repeated measurements over time of at least one parameter of a first predetermined type for at least one member of a group of individuals with an obtained evolution over time of at least one visual acuity-related parameter for the at least one member of the group of individuals, the associating determining that the at least one parameter of the first predetermined type influences the evolution of the at least one visual acuity-related parameter; and processing together the portion of the successive values ​​associated with the same one of the at least one parameter of the first predetermined type; the at least one parameter of the first predetermined type is a lifestyle or activity or behavioral parameter; If the continuous values ​​processed together produce an altered result due to a change in the at least one parameter of a first predetermined type, the predictive model is modified in response to at least a portion of the continuous values ​​related to the same parameter so as to depend differently on each of the continuous values ​​processed together by assigning a characteristic weight to each of the different continuous values ​​processed together in order to predict the evolution of the at least one vision-related parameter over time.

Images