Sclera mirror settlement prediction model generation method, application and computer system

Abstract

The invention discloses a hyperopia reserve prediction modeling method, which comprises the following steps: S1, obtaining a predictable time range of sclera lens settlement, the predictable time range being greater than a first fitting time point; s2, acquiring a first correction module of the prediction model according to the settlement value corresponding to the first fitting time point; s3, obtaining a first fitting module of the prediction model in a predictable time range; and S4, carrying out further data fitting verification by using the first fitting module and the first correction module to generate a sclera lens settlement prediction model. According to the scleroscope settlement prediction model generation method, the application and the computer system, the scleroscope settlement condition can be predicted, and scientific and convenient scleroscope design application guidance is provided for clinic.

Description

Technical Field

[0001] The present invention relates to the technical field of diopter measurement, and in particular to a scleral lens sedimentation prediction model generation method, application and computer system. Background Art

[0002] In recent years, scleral lenses (rigid gas-permeable contact lenses that are larger than corneal lenses) have become increasingly popular in the market due to their better wearing effect, and have achieved good application results in the frontier fields of ophthalmic disease treatment and restoration of irregular angle vision. The lens of a scleral lens passes over the cornea and limbus, contacts the bulbar conjunctiva, and forms a tear pool under the lens. The scleral lens can avoid direct contact with corneal tissue, minimize the movement of the lens on the surface of the eye, and reduce the interaction between the lens and the eyelid, helping to increase the user's wearing comfort.

[0003] Scleral lenses have achieved positive results in terms of eye health, comfort and vision, and current research is focusing on using scleral lenses on healthy corneas to address refractive errors, especially those corneas that cannot tolerate traditional RGP contact lenses.

[0004] At present, one direction of research on the wearing of scleral lenses focuses on the changes in the state of wearing scleral lenses and their corresponding evaluation. When the scleral lens is worn, it is fixed on the bulbar conjunctiva and Tenon's capsule, which are soft and compressible tissues. Therefore, with the weight of the scleral lens and the force of the eyelids every time you blink, the tear thickness behind the scleral lens will settle relative to the initial wearing state. At this time, the posterior scleral lens capsule tear thickness (PoLTT) changes with the dynamic wearing state.

[0005] It is a well-known phenomenon in the industry that scleral lenses gradually settle after being worn, but the amount of sedimentation and the period of sedimentation are related to many factors.

[0006] To this end, there is a continuous need in the art to develop a scleral lens sedimentation prediction model generation method, application and computer system. Summary of the invention

[0007] The purpose of the present invention is to provide a method for generating a scleral lens sedimentation prediction model, an application and a computer system. The present invention establishes a sample library, mines the data features in the sample library by means of big data analysis, and obtains a prediction of the scleral lens sedimentation value; in particular, by fitting the change curve of the sedimentation value and other related factors to model and predict the sedimentation value under long wearing time (PoLTT), a more accurate prediction scheme for the wearing evaluation of the scleral lens is provided, and scientific and convenient scleral lens design guidance is provided for clinical practice.

[0008] The present invention discloses a method for generating a scleral lens sedimentation prediction model, characterized in that the method comprises the following steps:

[0009] S1: Obtaining a predictable time range for scleral lens sedimentation, wherein the predictable time range is greater than a first fitting time point;

[0010] S2: obtaining a first correction module of the prediction model according to the sedimentation value corresponding to the first fitting time point;

[0011] S3: Acquire a first fitting module of the prediction model within the predictable time range;

[0012] S4: Perform further data fitting verification using the first fitting module and the first correction module to generate a scleral lens sedimentation prediction model.

[0013] Furthermore, the first fitting time point is obtained as follows:

[0014] A first measurement data set is obtained, wherein the first measurement data set corresponds to a plurality of sedimentation values ​​in a first acquisition time interval, the sedimentation values ​​in the first measurement data set are compared, and a time point at which a change gradient is less than a first threshold is selected as a first fitting time point.

[0015] The present invention discloses a method for generating a scleral lens sedimentation prediction model, which is characterized by comprising the following steps:

[0016] S10: Acquire a first measurement data set, wherein the first measurement data set corresponds to a plurality of settlement values ​​measured in a first time interval;

[0017] S20: Acquire a second measurement data set, wherein the second measurement data set is a second time interval segment relative to the first measurement data set;

[0018] S30: Compare the sedimentation values ​​in the second measurement data set and the first measurement data set, and select a first fitting time point and a corresponding measurement value at which a sedimentation value change is less than a threshold;

[0019] S40: an initial scleral lens sedimentation prediction model is obtained by fitting the first measurement data set up to the first fitting time point and the corresponding measurement values, and a scleral lens sedimentation prediction model is obtained by updating the initial scleral lens sedimentation prediction model.

[0020] Furthermore, the method specifically includes the following steps in step S40:

[0021] S41: Obtaining corresponding correction value parameters using the first fitting time point and the first threshold value to construct a first correction module in the scleral lens sedimentation prediction model;

[0022] S42: Obtaining a first fitting module by fitting in the first measurement data set;

[0023] S43: combining the first fitting module and the first correction module to obtain an initial scleral lens sedimentation prediction model, and updating the fitting verification with the time point after the first fitting time point and the corresponding sedimentation value to obtain the scleral lens sedimentation prediction model.

[0024] Furthermore, the first correction module is: d*Y 第一拟合时间点 ; The first fitting module is: a+b*t+c*t 2 ;

[0025] The scleral lens sedimentation prediction model is: Y = a + b*t + c*t 2 +d*Y 第一拟合时间点 ;

[0026] Wherein, t is the predicted time of the sedimentation value, where t is greater than the first fitting time point.

[0027] Further,

[0028] The scleral lens sedimentation prediction model is: Y = 27.124-0.648*t+0.001*t 2 +0.916*Y 30分钟 .

[0029] The present invention discloses a computer system for predicting scleral lens sedimentation, which is characterized by:

[0030] The computer system includes:

[0031] memory for storing instructions and data, and

[0032] A processor coupled to the memory, the processor executing the stored instructions to perform the following operations:

[0033] Get user data based on the interface;

[0034] The data includes: a first measurement data set of the user collected during a first stage of configuring the scleral lens;

[0035] Perform analysis based on some or all of the data to obtain settlement predictions for the user, and

[0036] The predicted subsidence value is used to guide the user's scleral lens design or adjustment plan.

[0037] Further,

[0038] The scleral lens sedimentation prediction model is: Y = a + b*t + c*t2 + d*Y 第一拟合时间点 ;

[0039] Wherein, t is the predicted time of the sedimentation value, where t is greater than the first fitting time point.

[0040] Further,

[0041] The scleral lens sedimentation prediction model is: Y=27.124-0.648*t+0.001*t2+0.916*Y30 minutes.

[0042] The present invention also discloses an application method of a scleral lens sedimentation prediction model, which is characterized in that a prediction time is obtained, a model generated by the above-mentioned sedimentation prediction model generation method is input, and a prediction value is obtained.

[0043] Compared with the prior art, the positive effects of the present invention are as follows:

[0044] The present invention proposes a scleral lens sedimentation prediction model generation method, application and computer system. First, a scleral lens sedimentation prediction method and system based on data prediction under long-term wear are proposed. By screening user data associated with actual measurement values ​​of users and training the relationship between associated type parameters to build a model, a scleral lens sedimentation prediction model is proposed, and a data-based scleral lens design guidance is provided. The scleral lens sedimentation prediction model proposed by the present invention is: Y = 27.124-0.648*t+0.001*t 2 +0.916*Y 30分钟 , where time t is greater than 30 minutes. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 A schematic diagram showing a flow chart of a method for generating a scleral lens sedimentation prediction model according to the present invention;

[0046] Figure 2 A schematic diagram showing a flow chart of another method for generating a scleral lens sedimentation prediction model according to the present invention; Figure 3 A schematic flow chart of step S40 is shown. DETAILED DESCRIPTION

[0047] Unless otherwise defined, technical or scientific terms used in the present specification and claims shall have the common meanings understood by persons having ordinary skills in the technical field to which the present invention belongs.

[0048] The technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings and embodiments of the present invention.

[0049] In addition, the terms "first", "second", etc. are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", etc. may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "plurality" means two or more.

[0050] The VSL scleral lens in the embodiment of the present invention has a diameter of 15.6 mm, and the lens adopts a toric peripheral design with a toric volume of 125 μm.

[0051] The scleral lens settlement referred to in the present invention mainly refers to the situation where the scleral lens is worn and fixed in contact with, for example, the bulbar conjunctiva and the Tenon's capsule (that is, even if the scleral lens is not in contact with the cornea, it still needs to be in contact with eye tissue when worn). These are soft and compressible tissues. Therefore, with the weight of the scleral lens and the force of the eyelids when blinking, the thickness of the posterior capsule of the scleral lens will settle relative to the initial wearing state. At this time, the thickness of the posterior capsule of the scleral lens (PoLTT) changes with the dynamic wearing state. Usually, this change is unknown, which makes the scleral lens have factors that affect the wearing design during design and application.

[0052] According to one embodiment of the present invention, a scleral lens has a diameter of 15.6 mm, wherein the lens adopts a toric peripheral design, wherein the toric volume is 125 microns.

[0053] The inspection data collected by the scleral lens subsidence prediction method and system of the present invention include but are not limited to: topographic measurement, endothelial examination, BCVA, and eye health assessment.

[0054] In fact, many factors may affect the fixation of scleral lenses, including lens design, diameter, eye condition and physical condition. Age may also affect the degree of lens sedimentation. The present invention proposes for the first time to use a scleral lens sedimentation prediction method to obtain the sedimentation of scleral lenses over a period of time, so as to make a preliminary assessment of the wearing condition of scleral lenses.

[0055] like Figure 1 As shown in, the present invention discloses a method for generating a scleral lens sedimentation prediction model, characterized in that the method comprises the following steps:

[0056] S1: Obtain the predictable time range of scleral lens sedimentation, the predictable time range is greater than the first fitting time point;

[0057] S2: obtaining a first correction module of the prediction model using the sedimentation value corresponding to the first fitting time point;

[0058] S3: obtaining a first fitting module of a prediction model within a predictable time range;

[0059] S4: further performing data fitting and verification using the first fitting module and the first correction module to generate a scleral lens sedimentation prediction model.

[0060] Furthermore, the first fitting time point is obtained as:

[0061] A first measurement data set is obtained, wherein the first measurement data set corresponds to a plurality of sedimentation values ​​in a first acquisition time interval, the sedimentation values ​​in the first measurement data set are compared, and a time point at which the change gradient is less than a first threshold is selected as a first fitting time point.

[0062] like Figure 2 As shown in, the present invention discloses a method for generating a scleral lens sedimentation prediction model, which is characterized by comprising the following steps:

[0063] S10: Acquire a first measurement data set, wherein the first measurement data set corresponds to a plurality of settlement values ​​measured in a first time interval;

[0064] S20: Acquire a second measurement data set, wherein the second measurement data set is a second time interval segment relative to the first measurement data set;

[0065] S30: Compare the sedimentation values ​​in the second measurement data set and the first measurement data set, and select a first fitting time point and a corresponding measurement value at which a sedimentation value change is less than a threshold;

[0066] S40: an initial scleral lens sedimentation prediction model is obtained by fitting the first measurement data set up to the first fitting time point and the corresponding measurement values, and a scleral lens sedimentation prediction model is obtained by updating the initial scleral lens sedimentation prediction model.

[0067] Furthermore, if Figure 3 As shown in FIG. , the method specifically includes the following steps in step S40:

[0068] S41: Obtaining corresponding correction value parameters using the first fitting time point and the first threshold value to construct a first correction module in the scleral lens sedimentation prediction model;

[0069] S42: Obtaining a first fitting module by fitting in the first measurement data set;

[0070] S43: combining the first fitting module and the first correction module to obtain an initial scleral lens sedimentation prediction model, and updating the fitting verification with the time point after the first fitting time point and the corresponding sedimentation value to obtain the scleral lens sedimentation prediction model.

[0071] Furthermore, the first correction module is: d*Y 第一拟合时间点 ; The first fitting module is: a+b*t+c*t 2 ;

[0072] The prediction model of scleral lens sedimentation is: Y = a + b*t + c*t2 + d*Y 第一拟合时间点 ;

[0073] Wherein, t is the predicted time of the sedimentation value, where t is greater than the first fitting time point.

[0074] In other embodiments, the present invention proposes a method for obtaining a scleral lens sedimentation prediction model, which comprises the following steps:

[0075] S100: Acquire a first measurement data set, wherein the first measurement data set corresponds to a plurality of scleral post-lens tear thickness values ​​measured in a first time interval, wherein the plurality of values ​​correspond to scleral post-lens tear thickness measurement values ​​collected in a plurality of time intervals;

[0076] S200: Acquire a second measurement data set, wherein the second measurement data set is a second time interval relative to the first measurement data set, and corresponds to a plurality of scleral lens posterior capsule tear thickness values,

[0077] The multiple data collection time intervals corresponding to the multiple values ​​are consistent with the first time interval of the first measurement data set, or are inconsistent. In the case of inconsistency, a part of the time intervals is used to collect the PoLTT measurement values;

[0078] S300: correspondingly comparing the measured values ​​of PoLTT in the first measurement data set, and selecting a first fitting time point and a corresponding measured value at which the gradient of the PoLTT value change is less than a first threshold;

[0079] S400: Obtain a scleral lens sedimentation prediction model by fitting the first measurement data set up to the first fitting time point and the corresponding measurement values.

[0080] In step S300, a second fitting time point and a corresponding measurement value are selected at which the gradient of the PoLTT value change is less than a second threshold;

[0081] Wherein, the first fitting time point is less than the second fitting time point; the first threshold is greater than the second threshold;

[0082] The first fitting time point and the first threshold correspond to the basic blocks for constructing the sedimentation prediction model, so as to determine the critical time point at which the sedimentation of the user wearing the scleral lens can be stably predicted;

[0083] The second fitting time point and the second threshold correspond to the critical point Y at which the sedimentation value of the user wearing the scleral lens reaches a stable state. 佩戴稳定 ; or perform fitting with the values ​​in the second measurement data set to determine the critical point Y at which the user's scleral lens sedimentation value reaches a stable state 佩戴稳定 Generally speaking, Y 佩戴稳定 -Y 佩戴稳定 The difference between the two values ​​is used to obtain the stable settlement value of the scleral lens wearing settlement.

[0084] In this way, between the first fitting time point where the sedimentation value can be stably predicted and the second fitting time point where the sedimentation value reaches a stable state, there is no need to use complex tests. The predicted value of the user wearing the scleral lens can be predicted by the sedimentation prediction model, thereby minimizing the complexity of the scleral lens wearing prescription in clinical applications and improving the user experience and promotability of the scleral lens.

[0085] Step S400 specifically includes the following steps:

[0086] S410: Obtain corresponding correction value parameters using the first fitting time point and the first threshold value to construct a correction module in the scleral lens sedimentation prediction model; specifically: a1×Y 预测临界时间点 ;

[0087] S420: fitting the first measurement data set to obtain a variable polynomial;

[0088] S430: Combine the polynomial module and the correction module to verify and obtain the scleral lens sedimentation prediction model.

[0089] The first fitting time point is preferably within 180 to 240 minutes, and more preferably within 20 to 30 minutes.

[0090] The second time period is preferably 30 to 90 days, more preferably 30 days.

[0091] The correction value when the first fitting time point is 240 minutes is 0.121 mm.

[0092] In fact, the amount of sedimentation did not increase further after 90 days, reflecting the long-term stability of the scleral lens and the significant improvement in the compressive resistance of the flexible tissue after a certain period of wearing.

[0093] The scleral lens subsidence prediction model obtained according to the fitting process in S4 is specifically:

[0094] Y=27.124-0.648*t+0.001*t 2 +0.916*Y 30分钟 ;

[0095] Where t is the time point of the PoLTT value to be predicted, and Y 30分钟 is the measured value of PoLTT corresponding to 30 minutes under the first measurement data set.

[0096] In the specific implementation of step S1, the first time interval is: 0 min, 30 min, 60 min, 90 min, 120 min, 150 min, 180 min, 240 min.

[0097] Preferably, the first time interval is: 0 min, 30 min, 60 min, 120 min, 240 min.

[0098] In a specific implementation of step S2, the time period corresponding to the collected data value is preferably: 0 min, 240 min.

[0099] In some embodiments of the present invention,

[0100] The first fitting time point and the first threshold correspond to:

[0101] The second fitting time point and the second threshold correspond to:

[0102] In one embodiment of the present invention, 26 patients (4 males and 22 females) with an average age of 27.3±4.2 years old and an average spherical equivalent (SE) of -5.42±2.87D were included.

[0103] There was significant variability in the change in PoLTT over time. At the dispensing visit, the mean initial PoLTT was 0.257 ± 0.058 mm and after 240 minutes of wear it was 0.136 ± 0.051 mm. Figure 3 The change of PoLTT over time is shown in Figure 2. The average settlement at 240 minutes was 0.121 ± 0.034 mm, at which time the settlement value of the first stage of wearing reached stability.

[0104] The prediction model of PoLTT over time is Y=27.124-0.648*t+0.001*t 2 +0.916*Y 30分钟 (R2 = 0.927), where Y represents PoLTT at t minutes after lens insertion, Y 30分钟 Represents a lens deployed in PoLTT for 30 minutes.

[0105] After three months of wearing, the average initial PoLTT was 0.266±0.086 mm, and after 240 minutes of wearing, it was 0.168±0.063 mm. The average settlement at 240 minutes was 0.098±0.055 mm (paired t test, t=10.945, P<0.001).

[0106] The experimental results of the specific implementation method showed that there was no significant difference in the initial PoLTT on the first day and three months after lens implantation (paired t-test, t=-0.246, P=0.807), and the PoLTT of 240 minutes in the third month was higher than that on the first day (mean difference=0.030, 95%CI:0.021-0.040, t=-6.575, P<0.001).

[0107] Based on the above modeling method, the present invention further proposes a method for predicting scleral lens sedimentation, which comprises the following steps:

[0108] Obtaining the predicted critical time point value for configuring the user's scleral lens; the acquisition of the above data includes: collecting a first measurement data set of the user;

[0109] Obtaining a settlement prediction model for the user through a first model analysis based on the above data;

[0110] Specifically: Y = a + b*t + c*t 2 +d*Y 预测临界时间点 ;

[0111] Among them, t is the predicted time of the settlement value, and t is greater than the predicted critical time point.

[0112] Furthermore, the prediction model is specifically:

[0113] Y=27.124-0.648*t+0.001*t 2 +0.916*Y 30分钟 .

[0114] The present invention further discloses a computer system for predicting scleral lens sedimentation value, characterized in that:

[0115] The computer system includes:

[0116] memory for storing instructions and data, and

[0117] A processor coupled to the memory, the processor executing the stored instructions to perform the following operations:

[0118] Get user data based on the interface;

[0119] The data includes: a first measurement data set of the user collected during a first stage of configuring the scleral lens;

[0120] Perform analysis based on some or all of the data to obtain settlement predictions for the user, and

[0121] The predicted subsidence value is used to guide the user's scleral lens design or adjustment plan.

[0122] The above description of the embodiments is to facilitate the understanding and application of the present invention by those skilled in the art. It is obvious that those skilled in the art can easily make various modifications to these embodiments and apply the general principles described herein to other embodiments without having to pay creative labor. Therefore, the present invention is not limited to the embodiments herein, and improvements and modifications made by those skilled in the art based on the contents disclosed by the present invention without departing from the scope and spirit of the present invention are within the scope of the present invention.

Claims

1. A method for generating a scleral lens sedimentation prediction model, characterized in that: The method comprises the following steps: S1: Obtaining a predictable time range for scleral lens sedimentation, wherein the predictable time range is greater than a first fitting time point; S2: obtaining a first correction module of the prediction model according to the sedimentation value corresponding to the first fitting time point; S3: Obtaining a first fitting module of the prediction model within the predictable time range; S4: Perform further data fitting verification using the first fitting module and the first correction module to generate a scleral lens sedimentation prediction model.

2. The method for generating a scleral lens sedimentation prediction model as described in claim 1, characterized in that: The first fitting time point is obtained as follows: A first measurement data set is obtained, wherein the first measurement data set corresponds to a plurality of sedimentation values ​​in a first acquisition time interval, the sedimentation values ​​in the first measurement data set are compared, and a time point at which a change gradient is less than a first threshold is selected as a first fitting time point.

3. A method for generating a scleral lens sedimentation prediction model, characterized in that: The steps include: S10: Acquire a first measurement data set, wherein the first measurement data set corresponds to a plurality of settlement values ​​measured in a first time interval; S20: Acquire a second measurement data set, wherein the second measurement data set is a second time interval segment relative to the first measurement data set; S30: Compare the sedimentation values ​​in the second measurement data set and the first measurement data set, and select a first fitting time point and a corresponding measurement value at which a sedimentation value change is less than a threshold; S40: an initial scleral lens sedimentation prediction model is obtained by fitting the first measurement data set up to the first fitting time point and the corresponding measurement values, and a scleral lens sedimentation prediction model is obtained by updating the initial scleral lens sedimentation prediction model.

4. The method for generating a scleral lens sedimentation prediction model as described in claim 3, characterized in that: The method specifically comprises the following steps in step S40: S41: Obtaining corresponding correction value parameters using the first fitting time point and the first threshold value to construct a first correction module in the scleral lens sedimentation prediction model; S42: Obtaining a first fitting module by fitting in the first measurement data set; S43: combining the first fitting module and the first correction module to obtain an initial scleral lens sedimentation prediction model, and updating the fitting verification with the time point after the first fitting time point and the corresponding sedimentation value to obtain the scleral lens sedimentation prediction model.

5. The method for generating a scleral lens sedimentation prediction model according to any one of claims 1 to 4, characterized in that: The first correction module is: d*Y 第一拟合时间点 ; The first fitting module is: a+b*t+c*t 2 ; The scleral lens sedimentation prediction model is: Y = a + b*t + c*t 2 +d*Y 第一拟合时间点 ; Wherein, t is the predicted time of the sedimentation value, where t is greater than the first fitting time point.

6. The method for generating a scleral lens sedimentation prediction model as claimed in claim 5, characterized in that: The scleral lens sedimentation prediction model is: Y = 27.124-0.648*t+0.001*t 2 +0.916*Y 30分钟 .

7. A computer system for predicting scleral lens sedimentation, characterized in that: The computer system includes: memory for storing instructions and data, and A processor coupled to the memory, the processor executing the stored instructions to perform the following operations: Get user data based on the interface; The data includes: a first measurement data set of the user collected during a first stage of configuring the scleral lens; Perform analysis based on some or all of the data to obtain settlement predictions for the user, and The predicted subsidence value is used to guide the user's scleral lens design or adjustment plan.

8. The computer system for predicting scleral lens subsidence according to claim 7, characterized in that: The scleral lens sedimentation prediction model is: Y = a + b*t + c*t2 + d*Y 第一拟合时间点 ; Wherein, t is the predicted time of the sedimentation value, where t is greater than the first fitting time point.

9. The computer system for predicting scleral lens subsidence according to claim 8, characterized in that: The scleral lens sedimentation prediction model is: Y=27.124-0.648*t+0.001*t2+0.916*Y30 minutes.

10. A method for applying a scleral lens sedimentation prediction model, characterized in that: Obtain the predicted time, input the model generated by the settlement prediction model generation method according to any one of claims 1 to 4, and obtain the predicted value.

Images