A myopia occurrence risk assessment method and device based on multi-index fusion

Abstract

The application discloses a myopia occurrence risk assessment method and device based on multi-index fusion, which comprises the following steps: first, acquiring visual parameter data information set of a user; then, performing multi-index fusion assessment processing on the visual parameter data information set to obtain myopia occurrence risk assessment result information; and finally, processing the myopia occurrence risk assessment result information to obtain target intervention scheme information. It can be seen that the application can comprehensively and accurately assess the myopia occurrence risk through multi-index fusion assessment, solves the technical problem of insufficient accuracy of single-index assessment in the prior art, realizes precise myopia prevention through personalized intervention scheme recommendation, solves the technical problem that personalized intervention cannot be realized in the prior art, and dynamically tracks the change of the myopia occurrence risk through multi-time-point detection and assessment, thereby solving the technical problem that the dynamic change of the risk cannot be reflected in the prior art.

Description

Technical Field

[0001] This invention relates to the field of visual detection technology, and in particular to a method and device for assessing the risk of myopia occurrence based on multi-index fusion. Background Technology

[0002] With the increasing severity of myopia among children and adolescents, myopia prevention has become a significant public health issue. Recent studies have found that peripheral defocus signals can independently induce emmetropization and myopia development in the eye. Peripheral defocus lenses, as a visual correction method based on peripheral defocus theory, can effectively control axial elongation and myopia progression. However, for children and adolescents who have not yet developed myopia or have insufficient hyperopic reserve, current technologies lack effective means to assess their risk of developing myopia, making early warning and personalized intervention difficult.

[0003] Existing myopia risk assessment techniques mainly fall into the following categories: The first category is based on a single indicator, assessing risk solely based on a single indicator such as refractive error or axial length; the second category is based on simple combination methods, simply adding or averaging multiple indicators; the third category is based on statistical regression methods, using traditional statistical methods such as linear regression or logistic regression for risk assessment; and the fourth category is based on experience-based methods, relying on the subjective assessment of the assessor's experience. However, these existing techniques have the following drawbacks: First, single-indicator-based methods cannot comprehensively reflect the risk of myopia development, resulting in limited accuracy; second, simple combination methods ignore the correlation and weight differences between different indicators, making it difficult to accurately quantify risk; third, statistical regression methods rely heavily on assumptions about data distribution, leading to decreased accuracy when these assumptions are not met; furthermore, experience-based methods are highly subjective, making standardization and automation difficult, and the assessment results lack repeatability. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a method and device for assessing the risk of myopia based on multi-indicator fusion, which solves the technical problem that the existing technology lacks effective technical means to assess the risk of myopia in children and adolescents who are not myopic but have insufficient hyperopic reserve, and that the existing assessment methods are usually based on only a single indicator or a simple combination, which is difficult to comprehensively and accurately assess the risk of myopia and cannot realize the recommendation of personalized intervention programs.

[0005] To address the aforementioned technical problems, a first aspect of this invention discloses a method for assessing the risk of myopia occurrence based on multi-indicator fusion, the method comprising: S1, acquire the user's visual parameter data set; the visual parameter data set includes refractive state parameter data, ocular structure parameter data, visual function parameter data, and eye use behavior parameter data; the refractive state parameter data includes equivalent spherical refractive power value, astigmatism value, and astigmatism axis value; the ocular structure parameter data includes axial length value and choroid thickness value set; the visual function parameter data includes best corrected visual acuity value and contrast sensitivity value set; the eye use behavior parameter data includes eye use habit parameter information set; S2, perform multi-index fusion evaluation processing on the visual parameter data information set to obtain myopia risk assessment result information; S3, process the myopia risk assessment results to obtain target intervention plan information.

[0006] As an optional implementation, in the first aspect of the present invention, the step of performing multi-index fusion evaluation processing on the visual parameter data information set to obtain myopia risk assessment result information includes: S21, perform data preprocessing and feature extraction on the visual parameter data information set to obtain a normalized visual parameter data information set; S22, perform static risk assessment and fusion processing on the normalized visual parameter data information set to obtain a first risk score, a second risk score, and a comprehensive risk score; S23, perform dynamic risk assessment processing on the visual parameter time-series data information set to obtain a dynamic risk score; S24, integrate the first risk score, the second risk score, the comprehensive risk score, and the dynamic risk score to obtain myopia risk assessment results.

[0007] As an optional implementation, in the first aspect of the present invention, the step of performing data preprocessing and feature extraction processing on the visual parameter data information set to obtain a normalized visual parameter data information set includes: S211, perform data preprocessing on the visual parameter data information set to obtain a preprocessed visual parameter data information set; S212, feature extraction and normalization are performed on the preprocessed visual parameter data information set to obtain a normalized visual parameter data information set.

[0008] As an optional implementation, in the first aspect of the present invention, the step of performing static risk assessment and fusion processing on the normalized visual parameter data information set to obtain a comprehensive risk score includes: S221, using the first risk assessment calculation model, the normalized equivalent spherical refractive power value, normalized axial length value and normalized average choroidal thickness value in the normalized visual parameter data information set are calculated and processed to obtain the first risk score value. The first risk assessment calculation model is as follows: ; ; ; ; ; In the formula, The first risk score is... The normalized equivalent spherical refractive power value is... The normalized axial length value, The normalized average choroid thickness value. , , and These are the first weight parameter, the second weight parameter, the third weight parameter, and the fourth weight parameter, respectively. For the interaction item weight parameter, , , and These are the first nonlinear exponent parameter, the second nonlinear exponent parameter, the third nonlinear exponent parameter, and the fourth nonlinear exponent parameter, respectively. This is the first correction parameter; S222, calculate and process the normalized best corrected visual acuity value, normalized average contrast sensitivity value and normalized eye use habit parameter information set in the normalized visual parameter data information set to obtain the second risk score value; S223, Using a comprehensive risk scoring calculation model, the first risk score value and the second risk score value are fused and calculated to obtain a comprehensive risk score value; The comprehensive risk scoring calculation model is as follows: ; ; ; ; In the formula, The comprehensive risk score is... The first risk score is... This is the second risk score. and These are the eighth and ninth weight parameters, respectively. For the interaction item weight parameter, To correct the parameters.

[0009] As an optional implementation, in the first aspect of the present invention, the step of performing dynamic risk assessment processing on the visual parameter time-series data information set to obtain a dynamic risk score includes: S231, perform trend analysis processing on the visual parameter time series data information set to obtain parameter change trend information; S232, Perform dynamic risk assessment calculation on the parameter change trend information to obtain a dynamic risk score.

[0010] As an optional implementation, in the first aspect of the present invention, the step of performing trend analysis processing on the visual parameter time-series data information set to obtain parameter change trend information includes: S2311, The equivalent spherical lens diopter value sequence is analyzed and processed to obtain the diopter change slope value; S2312, Analyze and process the axial length value sequence to obtain the axial length growth slope value; S2313, The sequence of choroid thickness values ​​is analyzed and processed to obtain the slope value of the change in choroid thickness.

[0011] As an optional implementation, in the first aspect of the present invention, processing the myopia risk assessment results to obtain target intervention plan information includes: S31, determine whether the comprehensive risk score is greater than or equal to the first risk threshold, and obtain the first judgment result; If the first judgment result is yes, execute S32; If the first judgment result is negative, execute S34; S32, determine whether the comprehensive risk score is greater than or equal to the second risk threshold, and obtain the second judgment result; If the second judgment result is yes, execute S33; If the second judgment result is negative, execute S35; S33, perform a first processing on the equivalent spherical refractive power value to obtain first recommended lens parameter information, and determine the first recommended lens parameter information as target intervention plan information; S34, determine the plano lens parameter information as the target intervention plan information; S35, perform a second processing on the equivalent spherical refractive power value to obtain second recommended lens parameter information, and determine the second recommended lens parameter information as the target intervention plan information.

[0012] A second aspect of this invention discloses a myopia risk assessment device based on multi-index fusion, the device comprising: The acquisition module is used to acquire a user's visual parameter data set; the visual parameter data set includes refractive state parameter data, ocular structure parameter data, visual function parameter data, and eye use behavior parameter data; the refractive state parameter data includes equivalent spherical refractive power, astigmatism value, and astigmatism axis value; the ocular structure parameter data includes axial length and choroid thickness values; the visual function parameter data includes best corrected visual acuity and contrast sensitivity values; and the eye use behavior parameter data includes eye use habit parameters. The evaluation module is used to perform multi-index fusion evaluation processing on the visual parameter data information set to obtain myopia risk assessment results. The recommendation module is used to process the myopia risk assessment results to obtain target intervention plan information.

[0013] A third aspect of this invention discloses another myopia risk assessment device based on multi-index fusion, the device comprising: processor; A memory coupled to the processor stores executable program code; The processor calls the executable program code stored in the memory to execute the myopia risk assessment method based on multi-index fusion disclosed in the first aspect of the present invention.

[0014] The fourth aspect of the present invention discloses a computer-readable storage medium storing computer instructions, which, when invoked, are used to execute the myopia risk assessment method based on multi-index fusion disclosed in the first aspect of the present invention.

[0015] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: In this embodiment of the invention, firstly, a set of visual parameter data information of the user is acquired; then, the set of visual parameter data information is subjected to multi-index fusion evaluation processing to obtain myopia risk assessment result information; finally, the myopia risk assessment result information is processed to obtain target intervention plan information. It is evident that this application, through multi-index fusion evaluation, can comprehensively and accurately assess the risk of myopia, solving the technical problem of insufficient accuracy of single-index evaluation in existing technologies; through personalized intervention plan recommendation, it can achieve precise myopia prevention, solving the technical problem of the inability to achieve personalized intervention in existing technologies; through multi-time-point detection and evaluation, it can dynamically track changes in myopia risk, solving the technical problem of the inability to reflect dynamic changes in risk in existing technologies. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating a method for assessing the risk of myopia based on multi-indicator fusion, as disclosed in an embodiment of the present invention. Figure 2 This is a schematic diagram of a myopia risk assessment device based on multi-index fusion disclosed in an embodiment of the present invention; Figure 3 This is a schematic diagram of another myopia risk assessment device based on multi-index fusion disclosed in an embodiment of the present invention. Detailed Implementation

[0018] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion.

[0020] Specific features, structures, or characteristics described in connection with the embodiments may be included in at least one embodiment of the invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment that is mutually exclusive with other embodiments.

[0021] Example 1 Please see Figure 1 , Figure 1 This is a flowchart illustrating a method for assessing the risk of myopia based on multi-indicator fusion, as disclosed in an embodiment of the present invention. Figure 1 The described multi-indicator fusion-based myopia risk assessment method is applied in a myopia risk assessment device, such as a local server or cloud server for visual detection, etc., and the embodiments of the present invention are not limited thereto. Figure 1 As shown, this method for assessing the risk of myopia development based on multi-indicator fusion may include the following operations: S1, acquire the user's visual parameter data set; the visual parameter data set includes refractive state parameter data, ocular structure parameter data, visual function parameter data, and eye use behavior parameter data; the refractive state parameter data includes equivalent spherical refractive power value, astigmatism value, and astigmatism axis value; the ocular structure parameter data includes axial length value and choroid thickness value set; the visual function parameter data includes best corrected visual acuity value and contrast sensitivity value set; the eye use behavior parameter data includes eye use habit parameter data set.

[0022] It should be noted that the users referred to are children and adolescents who are not myopic and have insufficient hyperopic reserve, specifically those aged 6 to 15 years old with an equivalent spherical refractive power ranging from -0.25D to +0.75D, astigmatism less than 1.50D, uncorrected visual acuity of not less than 0.8 in one eye, and best corrected visual acuity of not less than 1.0 in one eye. The refractive state parameter data refers to parameters reflecting the optical refractive state of the eyeball. The ocular structure parameter data refers to parameters reflecting the biological structural dimensions of the eyeball. The visual function parameter data refers to parameters reflecting the state of visual function. The eye-use behavior parameter data refers to parameters reflecting the user's daily eye-use habits. The visual parameter data set can be baseline data obtained from a single test or time-series data obtained from multiple follow-up time points.

[0023] S2, perform multi-index fusion evaluation processing on the visual parameter data information set to obtain myopia risk assessment results.

[0024] It should be noted that the multi-index fusion assessment process refers to preprocessing the visual parameter data set, extracting features, conducting static risk assessment, dynamic risk assessment, and integrating the results to ultimately obtain a comprehensive myopia risk assessment result. The myopia risk assessment result includes a first risk score, a second risk score, a comprehensive risk score, and a dynamic risk score.

[0025] S3, process the myopia risk assessment results to obtain target intervention plan information.

[0026] It should be noted that the above processing refers to automatically recommending suitable intervention plans or adjusting existing intervention plans based on the comprehensive risk score, dynamic risk score, and individual visual parameters. The target intervention plan information includes recommended lens type information, recommended defocus power information, and plan adjustment suggestion information. The recommended lens type information includes plano lenses, microlens peripheral defocus lenses, and ring peripheral defocus lenses. The recommended defocus power information includes 0D, +1.50D, and +3.50D. The plan adjustment suggestion information is used to determine whether the intervention plan needs to be adjusted based on the dynamic risk score during follow-up assessment.

[0027] It should be noted that the above processing can be performed using rule matching methods, decision tree models, expert systems, rule-based recommendation algorithms, or multi-criteria decision-making methods. Specifically, the embodiments of the present invention do not limit the specific methods used.

[0028] As can be seen, the myopia risk assessment method based on multi-indicator fusion described in the embodiments of the present invention can comprehensively and accurately assess the risk of myopia by acquiring multi-dimensional visual parameter data of users, using a multi-indicator fusion assessment model to conduct a comprehensive risk assessment, and recommending personalized intervention plans based on the assessment results, thereby achieving precise myopia prevention.

[0029] In an optional embodiment, obtaining the user's visual parameter data information set includes: S11 performs refractive power detection on the user to obtain the equivalent spherical refractive power value, astigmatism value, and astigmatic axis value.

[0030] It should be noted that the above-mentioned refractive error detection and processing can be performed by an automated refractometer, such as NIDEKARK-1, Topcon KR-800, or Canon RK-F2, etc. The specific implementation of this invention is not limited.

[0031] S12, perform axial length detection processing on the user to obtain the axial length value.

[0032] It should be noted that the axial length value refers to the distance from the anterior surface of the cornea to the fovea centralis of the retina, and the unit is millimeters (mm). The above-mentioned axial length detection and processing can be performed by a non-contact biometer, such as AL-SCAN, OA-2000, or IOLMaster 700, etc., but the specific implementation of this invention is not limited.

[0033] S13, perform choroid thickness detection processing on the user to obtain a set of choroid thickness values.

[0034] It should be noted that the set of choroidal thickness values ​​includes choroidal thickness values ​​at multiple locations around the fovea of ​​the macula (such as 1 mm and 3 mm). The above-mentioned choroidal thickness detection and processing can be performed using optical coherence tomography (OCT) equipment, such as Heidelberg Spectralis OCT, Zeiss Cirrus HD-OCT, or Optovue RTVue, etc. Specifically, the embodiments of the present invention do not limit the specific methods used.

[0035] S14 performs optimal corrected visual acuity testing on the user to obtain the optimal corrected visual acuity value.

[0036] It should be noted that the optimal corrected visual acuity value refers to the best visual acuity level that a user can achieve after wearing the optimal corrected lenses, and is usually expressed using decimal notation (e.g., 1.0, 1.2) or LogMAR notation (e.g., 0.0, -0.1). The above-mentioned optimal corrected visual acuity testing and processing can be performed using visual acuity testing equipment, such as a standard logarithmic visual acuity chart, an ETDRS visual acuity chart, or an electronic visual acuity chart, etc. Specific examples are not limited in this embodiment of the invention.

[0037] S15, perform contrast sensitivity detection processing on the user to obtain a set of contrast sensitivity values.

[0038] It should be noted that the contrast sensitivity value set includes contrast sensitivity values ​​corresponding to different spatial frequencies (e.g., 1.5, 3, 6, 12, 18 cpd). Contrast sensitivity is an important indicator for evaluating visual function, reflecting the human eye's ability to recognize details under different contrast conditions. The above-mentioned contrast sensitivity detection processing can be performed using contrast sensitivity detection devices, such as CSV-1000, the Pelli-Robson contrast sensitivity table, or the FACT contrast sensitivity detection system, etc. Specifically, this embodiment of the invention does not limit the specific methods used.

[0039] S16, obtain the user's eye use habit questionnaire data information to obtain the eye use habit parameter information set.

[0040] It should be noted that the eye use habit parameter information set includes near-field eye use time, outdoor activity time, electronic screen usage time, and reading distance. The near-field eye use time refers to the cumulative time spent on near-field activities (such as reading, doing homework, using electronic devices, etc.) each day, measured in hours. The outdoor activity time refers to the cumulative time spent outdoors each day, measured in hours. The eye use habit questionnaire data can be collected through paper or electronic questionnaires.

[0041] It should be noted that the above-mentioned acquisition process can also be performed from a health record database or a cloud data storage platform. Specifically, the embodiments of the present invention do not limit this.

[0042] S17, Obtain the time series data set of visual parameters of the user at multiple follow-up time points.

[0043] It should be noted that the temporal data set of visual parameters includes sequences of equivalent spherical refractive power, axial length, and choroidal thickness collected at the baseline time point and multiple follow-up time points. The follow-up time points include 3 months, 6 months, 9 months, 12 months, 15 months, 18 months, 21 months, and 24 months after baseline. This temporal data set of visual parameters is used for subsequent dynamic risk assessment.

[0044] As can be seen, the myopia risk assessment method based on multi-index fusion described in the embodiments of the present invention can comprehensively collect various parameter data related to the risk of myopia by using a variety of professional testing equipment to obtain multi-dimensional visual parameters such as refractive power, axial length, choroidal thickness, best corrected visual acuity, and contrast sensitivity, and combining them with eye habit questionnaire data and time series data, thus providing a complete data foundation for subsequent multi-index fusion assessment.

[0045] In another optional embodiment, the step of performing multi-index fusion evaluation processing on the visual parameter data set to obtain myopia risk assessment results includes: S21, perform data preprocessing and feature extraction on the visual parameter data information set to obtain a normalized visual parameter data information set.

[0046] S22, perform static risk assessment and fusion processing on the normalized visual parameter data information set to obtain a first risk score, a second risk score, and a comprehensive risk score.

[0047] S23, perform dynamic risk assessment processing on the visual parameter time series data information set to obtain a dynamic risk score.

[0048] S24, integrate the first risk score, the second risk score, the comprehensive risk score, and the dynamic risk score to obtain myopia risk assessment results.

[0049] It should be noted that the myopia risk assessment results include the first risk score, the second risk score, the comprehensive risk score, and the dynamic risk score.

[0050] As can be seen, the myopia risk assessment method based on multi-indicator fusion described in the embodiments of the present invention ensures data quality through data preprocessing and feature extraction, and can comprehensively and accurately assess the risk of myopia by organically combining static risk assessment and dynamic risk assessment, thus achieving the unity of static assessment and dynamic tracking.

[0051] In another optional embodiment, the step of performing data preprocessing and feature extraction on the visual parameter data information set to obtain a normalized visual parameter data information set includes: S211, perform data preprocessing on the visual parameter data information set to obtain a preprocessed visual parameter data information set.

[0052] It should be noted that the data preprocessing includes outlier detection, missing value handling, and data cleaning. Outlier detection refers to detecting outliers in each parameter value within the visual parameter data set, identifying data points that exceed the normal physiological range. Missing value handling refers to filling in or marking missing visual parameter data. Data cleaning refers to removing duplicate data and correcting obviously erroneous data. The preprocessed visual parameter data set includes preprocessed refractive state parameter data, ocular structure parameter data, visual function parameter data, and eye behavior parameter data.

[0053] S212, feature extraction and normalization are performed on the preprocessed visual parameter data information set to obtain a normalized visual parameter data information set.

[0054] It should be noted that the feature extraction process refers to extracting key features from the original visual parameter data, such as calculating the average choroidal thickness value by averaging the set of choroidal thickness values, and calculating the average contrast sensitivity value by averaging the set of contrast sensitivity values. The normalization process refers to normalizing visual parameter data of different dimensions and ranges based on a risk threshold, uniformly converting them to the same numerical range (such as 0-1), and obtaining normalized equivalent spherical refractive power, normalized axial length, normalized average choroidal thickness, normalized best corrected visual acuity, normalized average contrast sensitivity, and normalized eye use habit parameter information set, for subsequent weighted fusion calculations.

[0055] As can be seen, implementing the myopia risk assessment method based on multi-indicator fusion described in the embodiments of the present invention can ensure data quality and unify data format through data preprocessing and feature extraction, providing a standardized data foundation for subsequent risk assessment calculations.

[0056] In an optional embodiment, the step of performing feature extraction and normalization on the preprocessed visual parameter data information set to obtain a normalized visual parameter data information set includes: S2121, the average value of the choroid thickness value set in the preprocessed visual parameter data information set is calculated to obtain the average choroid thickness value.

[0057] It should be noted that the average choroidal thickness value is the arithmetic mean of all choroidal thickness values ​​in the set of choroidal thickness values. The choroid is the vascular membrane in the middle layer of the eyeball wall, and its thickness is closely related to the occurrence and development of myopia. Thinning of the choroid usually indicates an increased risk of myopia.

[0058] S2122, the average value of the contrast sensitivity value set in the preprocessed visual parameter data information set is calculated to obtain the average contrast sensitivity value.

[0059] It should be noted that the average contrast sensitivity value is the arithmetic mean of the contrast sensitivity values ​​corresponding to all spatial frequencies in the set of contrast sensitivity values. Contrast sensitivity is an important indicator for assessing visual function; decreased contrast sensitivity may indicate a decline in visual function and an increased risk of myopia.

[0060] S2123, normalize the parameter values, the average choroid thickness value, and the average contrast sensitivity value in the preprocessed visual parameter data information set to obtain the normalized visual parameter data information set.

[0061] It should be noted that the normalization process refers to converting visual parameter data with different dimensions and ranges into the same numerical range (such as the 0-1 range) to facilitate subsequent weighted fusion calculations. The normalized visual parameter data information set includes normalized equivalent spherical refractive power, normalized axial length, normalized average choroidal thickness, normalized best corrected visual acuity, normalized average contrast sensitivity, and a normalized set of eye use habit parameters. The normalized equivalent spherical refractive power value refers to the value obtained by normalizing the original equivalent spherical refractive power value based on a risk threshold; the normalized axial length value refers to the value obtained by normalizing the original axial length value based on a risk threshold; the normalized mean choroidal thickness value refers to the value obtained by normalizing the original mean choroidal thickness value based on a risk threshold; the normalized best corrected visual acuity value refers to the value obtained by normalizing the original best corrected visual acuity value based on a risk threshold; the normalized mean contrast sensitivity value refers to the value obtained by normalizing the original mean contrast sensitivity value based on a risk threshold; and the normalized eye use habit parameter information set refers to the parameter information set obtained by normalizing the original eye use habit parameter information set (including near-vision time, outdoor activity time, etc.) based on a risk threshold. Subsequent risk assessment calculations will use the above-mentioned normalized data for calculation.

[0062] As can be seen, the myopia risk assessment method based on multi-indicator fusion described in the embodiments of the present invention can extract key features from the original data and unify the data format through feature extraction and normalization processing, providing a standardized data foundation for subsequent risk assessment calculations.

[0063] In another optional embodiment, the static risk assessment and fusion processing of the normalized visual parameter data information set to obtain a comprehensive risk score includes: S221, using the first risk assessment calculation model, the normalized equivalent spherical refractive power value, normalized axial length value and normalized average choroidal thickness value in the normalized visual parameter data information set are calculated and processed to obtain the first risk score value. The first risk assessment calculation model is as follows: ; ; ; ; ; In the formula, The first risk score is... The normalized equivalent spherical refractive power value is... The normalized axial length value, The normalized average choroid thickness value. , , and These are the first weight parameter, the second weight parameter, the third weight parameter, and the fourth weight parameter, respectively. For the interaction item weight parameter, , , and These are the first nonlinear exponent parameter, the second nonlinear exponent parameter, the third nonlinear exponent parameter, and the fourth nonlinear exponent parameter, respectively. This is the first correction parameter.

[0064] It should be noted that the first risk assessment calculation model is used to quantify the contribution of ocular morphology indicators to the risk of myopia. By introducing nonlinear transformations, interaction terms, and ratio terms in the form of harmonic averages, it can more accurately capture the complex relationships between indicators. The formula uses... , and It can reflect the degree of deviation of each indicator from the normal range and the level of risk. In the formula... The nonlinear risk contribution of the equivalent spherical refractive power is represented by a power function. (Usually greater than 1) High-risk situations are amplified; when the refractive error deviates from the normal value, the risk increases non-linearly. This indicates the non-linear risk contribution of axial length. The longer the axial length, the greater the risk, which is consistent with the non-linear relationship between axial length growth and the risk of myopia. This represents the nonlinear risk contribution of choroidal thinning; the thinner the choroid (i.e., the greater the risk contribution), the greater the risk contribution. The smaller, The larger the value, the higher the risk; high-risk situations are amplified through power functions. The product interaction term representing refractive error and axial length amplifies the risk when both deviate from normal values ​​(i.e., both are large), reflecting the synergistic effect between the two. The harmonic mean interaction term representing axial length and choroidal thickness captures the synergistic effect of their negative correlation on risk. This interaction term amplifies risk when axial length increases and choroidal thickness decreases. Typical values ​​for the first, second, third, and fourth weighting parameters and the interaction term weighting parameter are 0.22, 0.28, 0.18, 0.12, and 0.20, respectively; typical values ​​for the first, second, third, and fourth nonlinear exponent parameters are 1.8, 2.0, 1.6, and 1.5, respectively; the first correction parameter, used to avoid a denominator of zero, is typically set to 0.05.

[0065] S222, calculate and process the normalized best corrected visual acuity value, normalized average contrast sensitivity value and normalized eye use habit parameter information set in the normalized visual parameter data information set to obtain the second risk score value; It should be noted that the above calculation process can be performed using the second risk assessment calculation model, or it can be performed using a linear weighted model, a neural network model, or a decision tree model. Specifically, the embodiments of the present invention do not limit the specifics.

[0066] The second risk assessment calculation model is as follows: ; ; ; ; ; In the formula, This is the second risk score. The normalized best corrected visual acuity value, The normalized average contrast sensitivity value is... The normalized near-vision time value in the normalized eye habit parameter information set. This refers to the normalized outdoor activity time value within the normalized eye use habit parameter information set. , , , and These are the fourth, fifth, sixth, seventh, and eighth weight parameters, respectively. The weight parameter for the second interaction term. , , and These are the fifth, sixth, seventh, and eighth nonlinear exponent parameters, respectively. and These are the second and third correction parameters, respectively.

[0067] It should be noted that the second risk assessment calculation model is used to quantify the contribution of visual function indicators and eye use behavior indicators to the risk of myopia. By introducing nonlinear transformation, multi-indicator fusion interaction terms and complementary relationship interaction terms, it can more accurately capture the complex relationship between visual function and eye use behavior. This represents the nonlinear risk contribution to best-corrected visual acuity when visual acuity decreases ( (Increased) risk grows exponentially; This represents the nonlinear risk contribution of contrast sensitivity; as contrast sensitivity decreases ( (Increase) Risk amplification, which is reflected through a power function to demonstrate a nonlinear relationship; This represents the non-linear risk contribution of near-field eye use time; the longer the eye use time ( The larger the risk (the greater the risk), the exponentially higher it becomes. The non-linear risk contribution represents insufficient outdoor activity time; the less outdoor activity time ( The smaller, The larger the value, the higher the risk; high-risk situations are amplified through power functions. This represents the fusion interaction term between visual function indicators (best-corrected visual acuity and contrast sensitivity) and near-vision time, capturing the synergistic relationship among the three through a harmonic average. When visual function declines ( and Larger) and longer periods of close-range eye use ( When the risk is relatively high, the risks are amplified. An interaction term representing the complementary relationship between near-field eye use and outdoor activity time is used to capture the synergistic effect of this complementary relationship on risk through a harmonic average. When near-field eye use time is long and outdoor activity time is short, this interaction term amplifies the risk. Typical values ​​for the fourth, fifth, sixth, seventh, and eighth weighting parameters and the second interaction term weighting parameter are 0.16, 0.16, 0.24, 0.18, 0.14, and 0.12, respectively; typical values ​​for the fifth, sixth, seventh, and eighth nonlinear exponent parameters are 1.7, 1.6, 1.9, and 1.5, respectively; the second and third correction parameters are used to avoid a denominator of zero and are typically set to 0.05.

[0068] S223, Using a comprehensive risk scoring calculation model, the first risk score value and the second risk score value are fused and calculated to obtain a comprehensive risk score value; The comprehensive risk scoring calculation model is as follows: ; ; ; ; In the formula, The comprehensive risk score is... The first risk score is... This is the second risk score. and These are the eighth and ninth weight parameters, respectively. For the interaction item weight parameter, To correct the parameters.

[0069] It should be noted that the comprehensive risk score calculation model is used to integrate morphological risk scores and functional behavioral risk scores to obtain a comprehensive risk score value, which provides a quantitative basis for subsequent personalized intervention program recommendations. The interaction term is used to detect the synergistic effect between the two risk dimensions. When the risk scores of both dimensions are high, the interaction term amplifies the comprehensive risk score, reflecting the cumulative effect of risk factors. Through the comprehensive risk score calculation model, the refractive structural risk score obtained from the first risk assessment calculation and the functional behavioral risk score obtained from the second risk assessment calculation can be organically integrated to form a comprehensive myopia occurrence risk assessment result. The typical values ​​for the eighth and ninth weight parameters are 0.55 and 0.45, respectively; the interaction term weight parameter is usually set to 0.15 to 0.25; the correction parameter is used to avoid a denominator of zero and is usually set to 0.01.

[0070] As can be seen, by implementing the multi-indicator fusion-based myopia risk assessment method described in the embodiments of the present invention, the risk of myopia can be comprehensively assessed from multiple dimensions through the fusion of the first risk assessment, the second risk assessment, and the comprehensive risk score, thus achieving a static risk assessment based on multi-indicator fusion.

[0071] In another optional embodiment, the step of performing dynamic risk assessment processing on the visual parameter time-series data information set to obtain a dynamic risk score includes: S231, perform trend analysis processing on the visual parameter time series data information set to obtain parameter change trend information.

[0072] It should be noted that the trend analysis processing refers to performing linear regression analysis on the time-series data of each visual parameter to calculate the slope value of the parameter change. The parameter change trend information includes the slope value of refractive error change, the slope value of axial length growth, and the slope value of choroidal thickness change.

[0073] S232, Perform dynamic risk assessment calculation on the parameter change trend information to obtain a dynamic risk score; It should be noted that the above processing can be performed using a dynamic risk assessment calculation model, or it can be performed using a linear weighted model, a time series forecasting model, an exponential smoothing model, or a moving average model. Specifically, the embodiments of the present invention are not limited to this.

[0074] The dynamic risk assessment calculation model is as follows: ; ; ; ; In the formula, The dynamic risk score value is... The slope value of the diopter change, The threshold for the slope of the change in refractive power. The slope value of the axial length growth. The threshold for the slope of axial length growth. The slope value of the change in choroid thickness. The threshold for the slope of the choroid thickness change. , and These are the tenth, eleventh, and twelfth weight parameters, respectively.

[0075] It should be noted that the dynamic risk assessment calculation model is used to quantify the impact of visual parameter change trends on the risk of myopia. The refractive error change slope threshold... Typically set to -0.5D / year, this represents the maximum acceptable rate of refractive error change towards myopia; the axial elongation slope threshold... The threshold value is typically set at 0.4 mm / year, representing the maximum acceptable rate of axial elongation; the choroidal thickness change slope threshold is also mentioned. It is usually set to -20. / year represents the maximum acceptable rate of choroidal thinning. When the actual slope value exceeds these thresholds, the normalization term is set to 1, indicating that the indicator has reached the highest risk level. The typical values ​​for the tenth, eleventh, and twelfth weighted parameters are 0.35, 0.40, and 0.25, respectively, with the axial length growth slope having the highest weight because axial length growth is the most direct indicator of myopia development.

[0076] As can be seen, the myopia risk assessment method based on multi-indicator fusion described in the embodiments of the present invention can accurately assess the dynamic changes in myopia risk through trend analysis and dynamic risk assessment calculation model, providing a technical basis for adjusting intervention programs.

[0077] In an optional embodiment, the step of performing trend analysis processing on the visual parameter time-series data information set to obtain parameter change trend information includes: S2311, The equivalent spherical lens diopter value sequence is analyzed and processed to obtain the diopter change slope value.

[0078] It should be noted that the above analysis refers to linear fitting with time as the independent variable and the equivalent spherical refractive power as the dependent variable, calculating the slope of the regression line. The linear regression analysis can be performed using the least squares method, polynomial regression, exponential regression, or moving average method; specifically, this embodiment of the invention does not limit the method. The unit of the refractive power change slope value is D / year, with positive values ​​indicating a change towards hyperopia and negative values ​​indicating a change towards myopia.

[0079] S2312, The axial length value sequence is analyzed and processed to obtain the axial length growth slope value.

[0080] It should be noted that the above analysis and processing can be performed using the least squares method, multinomial regression, exponential regression, or moving average method; specifically, the embodiments of this invention are not limited to any particular method. The unit of the axial length growth slope value is mm / year, with a positive value indicating axial length growth. The annual axial length growth of normal children and adolescents is approximately 0.1-0.2 mm. When the axial length growth slope value is greater than 0.3 mm / year, it indicates a higher risk of myopia.

[0081] S2313, The sequence of choroid thickness values ​​is analyzed and processed to obtain the slope value of the change in choroid thickness.

[0082] It should be noted that the above analysis and processing can be performed using the least squares method, multinomial regression, exponential regression, or moving average method; specifically, the embodiments of this invention are not limited to any particular method. The unit of the slope value of the choroidal thickness change is μm / year, and a negative value indicates choroidal thinning. Choroidal thinning is usually associated with the occurrence and development of myopia.

[0083] As can be seen, by implementing the multi-indicator fusion-based myopia risk assessment method described in this embodiment of the invention, the trend of parameter changes can be accurately calculated by performing linear regression analysis on the time-series data of each visual parameter, providing a quantitative basis for dynamic risk assessment.

[0084] In an optional embodiment, processing the myopia risk assessment results to obtain target intervention plan information includes: S31, determine whether the comprehensive risk score is greater than or equal to the first risk threshold, and obtain the first judgment result; If the first judgment result is yes, execute S32; If the first judgment result is negative, execute S34.

[0085] It should be noted that the first risk threshold is used to distinguish between high risk and low to medium risk, and is usually set to 0.6. When the comprehensive risk score is greater than or equal to the first risk threshold, it indicates that the user belongs to the high-risk group for myopia and requires active intervention.

[0086] S32, determine whether the comprehensive risk score is greater than or equal to the second risk threshold, and obtain the second judgment result; If the second judgment result is yes, execute S33; If the second judgment result is negative, execute S35.

[0087] It should be noted that the second risk threshold is used to distinguish between high risk and extremely high risk, and is usually set to 0.8. When the comprehensive risk score is greater than or equal to the second risk threshold, it indicates that the user belongs to the extremely high risk group for developing myopia and requires intensive intervention.

[0088] S33, perform a first processing on the equivalent spherical refractive power value to obtain first recommended lens parameter information, and determine the first recommended lens parameter information as target intervention plan information.

[0089] S34, determine the plano lens parameter information as the target intervention plan information.

[0090] It should be noted that when the comprehensive risk score is less than the first risk threshold, it indicates that the user belongs to a low-risk group, and it is recommended to wear regular plano glasses for vision protection without the need for peripheral defocus intervention. The plano lens parameters include a recommended defocus power of 0D and a recommended lens type of plano lens.

[0091] S35, perform a second processing on the equivalent spherical refractive power value to obtain second recommended lens parameter information, and determine the second recommended lens parameter information as the target intervention plan information.

[0092] It should be noted that the second processing refers to recommending +1.50D peripheral defocus lenses for high-risk individuals. This recommendation process can be performed using rule-based matching methods, decision tree models, expert systems, or rule-based recommendation algorithms; specifically, this embodiment of the invention does not limit the specific methods. The second recommended lens parameter information includes a recommended defocus power of +1.50D and recommended lens type information as a ring-shaped peripheral defocus lens.

[0093] As can be seen, by implementing the multi-indicator fusion-based myopia risk assessment method described in this embodiment of the invention, through multi-level threshold judgment and personalized parameter recommendation, it can automatically recommend suitable intervention programs based on the user's comprehensive risk score and individual visual parameters, thereby achieving precise and personalized myopia prevention.

[0094] In an optional embodiment, the first processing of the equivalent spherical refractive power value to obtain first recommended lens parameter information includes: S331, determine whether the equivalent spherical lens diopter value is greater than or equal to the diopter threshold, and obtain a third determination result; When the third judgment result is yes, the microlens-type peripheral defocus lens information is determined to be the recommended lens type information; When the third judgment result is negative, the information on the circular peripheral defocus lens is determined to be the recommended lens type information.

[0095] It should be noted that the refractive power threshold is usually set to 0D. When the equivalent spherical refractive power is greater than or equal to 0D, it indicates that the user still has some hyperopic reserve and is suitable for wearing microlens-type peripheral defocus lenses; when the equivalent spherical refractive power is less than 0D, it indicates that the user is close to myopia and is suitable for wearing ring-shaped peripheral defocus lenses.

[0096] S332, confirm +3.50D as the recommended defocus value.

[0097] S333, integrate the recommended lens type information and the recommended defocus power information to obtain the first recommended lens parameter information.

[0098] It should be noted that the first recommended lens parameter information includes recommended lens type information and recommended defocus power information. The +3.50D peripheral defocus lens can create a relative myopic defocus at the periphery of the retina, and regulate eye development through peripheral defocus signals, thus delaying the onset of myopia.

[0099] As can be seen, by implementing the multi-index fusion-based myopia risk assessment method described in the embodiments of the present invention, and by selecting the appropriate lens type according to the equivalent spherical refractive power value, a personalized high-intensity defocus intervention plan can be provided for extremely high-risk individuals.

[0100] In another optional embodiment, the processing of the myopia risk assessment results to obtain target intervention plan information further includes: S36, determine whether the dynamic risk score is greater than or equal to the dynamic risk threshold, and obtain the fourth judgment result; When the fourth judgment result is yes, plan adjustment suggestion information is generated, and the plan adjustment suggestion information is determined to be part of the target intervention plan information; When the fourth judgment result is negative, intervention effect evaluation information is generated.

[0101] It should be noted that the dynamic risk threshold is typically set to 0.5. When the dynamic risk score is greater than or equal to the dynamic risk threshold, it indicates that the current intervention plan is ineffective, the trend of visual parameter changes is unsatisfactory, and the intervention plan needs to be adjusted, such as upgrading the +1.50D defocus lens to a +3.50D defocus lens, or upgrading the plano lens to a defocus lens. When the dynamic risk score is less than the dynamic risk threshold, it indicates that the current intervention plan is effective, the trend of visual parameter changes is good, and the current intervention plan can continue. The intervention effect evaluation information includes two states: "effective" and "needs adjustment". The plan adjustment suggestion information includes specific plan adjustment suggestions, such as "suggest upgrading to a +3.50D peripheral defocus lens" or "suggest increasing outdoor activity time", etc.

[0102] As can be seen, by implementing the myopia risk assessment method based on multi-indicator fusion described in the embodiments of the present invention, through dynamic risk threshold judgment and scheme adjustment suggestion generation, the intervention effect can be automatically evaluated and adjustment suggestions can be given according to the changing trend of visual parameters, thus realizing closed-loop myopia prevention and management.

[0103] Example 2 Please see Figure 2 , Figure 2 This is a schematic diagram of a myopia risk assessment device based on multi-index fusion disclosed in an embodiment of the present invention. Figure 2 The described multi-indicator fusion-based myopia risk assessment device can be applied to visual inspection equipment, local servers, or cloud servers, etc., and the embodiments of this invention are not limited thereto. Figure 2 As shown, this myopia risk assessment device based on multi-indicator fusion may include: The acquisition module 201 is used to acquire a set of visual parameter data information of the user; the set of visual parameter data information includes refractive state parameter data information, ocular structure parameter data information, visual function parameter data information, and eye use behavior parameter data information; the refractive state parameter data information includes equivalent spherical refractive power value, astigmatism value, and astigmatism axis value; the ocular structure parameter data information includes a set of axial length values ​​and choroid thickness values; the visual function parameter data information includes a set of best corrected visual acuity values ​​and contrast sensitivity values; and the eye use behavior parameter data information includes a set of eye use habit parameter information.

[0104] The evaluation module 202 is used to perform multi-index fusion evaluation processing on the visual parameter data information set to obtain myopia risk assessment result information; The recommendation module 203 is used to process the myopia risk assessment results to obtain target intervention plan information.

[0105] As can be seen, the myopia risk assessment device based on multi-indicator fusion described in the embodiments of the present invention can comprehensively and accurately assess the risk of myopia by acquiring multi-dimensional visual parameter data information of users through the acquisition module, performing multi-indicator fusion assessment processing through the assessment module, and recommending personalized intervention plans through the recommendation module, thereby achieving precise myopia prevention.

[0106] In an optional embodiment, the acquisition module 201 includes: The diopter measurement unit is used to perform diopter measurement and processing on the user to obtain the equivalent spherical diopter value, astigmatism value, and astigmatism axis value; An axial length detection unit is used to perform axial length detection processing on the user to obtain an axial length value; The choroidal membrane detection unit is used to perform choroidal membrane thickness detection processing on the user to obtain a set of choroidal membrane thickness values; A vision testing unit is used to perform optimal corrected vision testing on the user to obtain the optimal corrected vision value; A contrast sensitivity detection unit is used to perform contrast sensitivity detection processing on the user to obtain a set of contrast sensitivity values; The questionnaire collection unit is used to acquire the user's eye use habit questionnaire data information and obtain an eye use habit parameter information set.

[0107] In another alternative embodiment, the evaluation module 202 includes: The preprocessing feature extraction unit is used to perform data preprocessing and feature extraction on the visual parameter data information set to obtain a normalized visual parameter data information set. The static assessment and fusion unit is used to perform static risk assessment and fusion processing on the normalized visual parameter data information set to obtain a comprehensive risk score. The dynamic evaluation unit is used to perform dynamic risk assessment processing on the time-series data information set of visual parameters to obtain a dynamic risk score value. The integration unit is used to integrate the first risk score, the second risk score, the comprehensive risk score, and the dynamic risk score to obtain the myopia risk assessment result information.

[0108] In yet another optional embodiment, the recommendation module 203 includes: A risk assessment unit is used to determine whether the comprehensive risk score is greater than or equal to a first risk threshold, and to obtain a first assessment result. A high-intensity recommendation unit is used to perform high-intensity defocus lens parameter recommendation processing on the equivalent spherical refractive power value when the first judgment result is yes and the comprehensive risk score value is greater than or equal to the second risk threshold, so as to obtain the first recommended lens parameter information. A medium-intensity recommendation unit is used to perform medium-intensity defocus lens parameter recommendation processing on the equivalent spherical refractive power value when the first judgment result is yes and the comprehensive risk score value is less than the second risk threshold, so as to obtain the second recommended lens parameter information. The plano lens recommendation unit is used to determine the plano lens parameter information as the target intervention scheme information when the first judgment result is negative.

[0109] Example 3 Please see Figure 3 , Figure 3 This is a schematic diagram of another myopia risk assessment device based on multi-index fusion disclosed in an embodiment of the present invention. Figure 3 The described multi-indicator fusion-based myopia risk assessment device can be applied to visual inspection equipment, local servers, or cloud servers, etc., and the embodiments of this invention are not limited thereto. Figure 3 As shown, this myopia risk assessment device based on multi-indicator fusion may include: Processor 301; A memory 302 containing executable program code is coupled to the processor 301; The processor 301 calls the executable program code stored in the memory 302 to execute some or all of the steps of the myopia risk assessment method based on multi-index fusion in Embodiment 1.

[0110] Example 4 This invention discloses a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements some or all of the steps of a multi-indicator fusion-based myopia risk assessment method according to Embodiment 1.

[0111] The computer-readable storage medium includes read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electronically erasable rewritable read-only memory (EEPROM), read-only optical disc (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0112] Example 5 This invention discloses a computer program product, which includes a computer program stored on a computer-readable storage medium. The computer program includes program instructions, which, when executed by a computer, cause the computer to perform some or all of the steps of a multi-indicator fusion-based myopia risk assessment method according to Embodiment 1.

[0113] The system embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0114] Through the detailed description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, including read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electronically erasable rewritable read-only memory (EEPROM), read-only optical disc (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0115] Finally, it should be noted that the myopia risk assessment method and device based on multi-index fusion disclosed in the embodiments of the present invention are merely preferred embodiments of the present invention and are only used to illustrate the technical solutions of the present invention, not to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for assessing the risk of myopia occurrence based on multi-indicator fusion, characterized in that, The method includes: S1, acquire the user's visual parameter data set; the visual parameter data set includes refractive state parameter data, ocular structure parameter data, visual function parameter data, and eye use behavior parameter data; the refractive state parameter data includes equivalent spherical refractive power value, astigmatism value, and astigmatism axis value; the ocular structure parameter data includes axial length value and choroid thickness value set; the visual function parameter data includes best corrected visual acuity value and contrast sensitivity value set; the eye use behavior parameter data includes eye use habit parameter information set; S2, perform multi-index fusion evaluation processing on the visual parameter data information set to obtain myopia risk assessment result information; S3, process the myopia risk assessment results to obtain target intervention plan information.

2. The method for assessing the risk of myopia occurrence based on multi-indicator fusion according to claim 1, characterized in that, The multi-index fusion evaluation process performed on the visual parameter data set to obtain myopia risk assessment results includes: S21, perform data preprocessing and feature extraction on the visual parameter data information set to obtain a normalized visual parameter data information set; S22, perform static risk assessment and fusion processing on the normalized visual parameter data information set to obtain a first risk score, a second risk score, and a comprehensive risk score; S23, perform dynamic risk assessment processing on the visual parameter time-series data information set to obtain a dynamic risk score; S24, integrate the first risk score, the second risk score, the comprehensive risk score, and the dynamic risk score to obtain myopia risk assessment results.

3. The method for assessing the risk of myopia occurrence based on multi-indicator fusion according to claim 2, characterized in that, The step of performing data preprocessing and feature extraction on the visual parameter data information set to obtain a normalized visual parameter data information set includes: S211, perform data preprocessing on the visual parameter data information set to obtain a preprocessed visual parameter data information set; S212, feature extraction and normalization are performed on the preprocessed visual parameter data information set to obtain a normalized visual parameter data information set.

4. The method for assessing the risk of myopia occurrence based on multi-indicator fusion according to claim 2, characterized in that, The static risk assessment and fusion processing of the normalized visual parameter data set to obtain a comprehensive risk score includes: S221, using the first risk assessment calculation model, the normalized equivalent spherical refractive power value, normalized axial length value and normalized average choroidal thickness value in the normalized visual parameter data information set are calculated and processed to obtain the first risk score value. The first risk assessment calculation model is as follows: ; ; ; ; ; In the formula, The first risk score is... The normalized equivalent spherical refractive power value is... The normalized axial length value, The normalized average choroid thickness value. , , and These are the first weight parameter, the second weight parameter, the third weight parameter, and the fourth weight parameter, respectively. For the interaction item weight parameter, , , and These are the first nonlinear exponent parameter, the second nonlinear exponent parameter, the third nonlinear exponent parameter, and the fourth nonlinear exponent parameter, respectively. This is the first correction parameter; S222, calculate and process the normalized best corrected visual acuity value, normalized average contrast sensitivity value and normalized eye use habit parameter information set in the normalized visual parameter data information set to obtain the second risk score value; S223, Using a comprehensive risk scoring calculation model, the first risk score value and the second risk score value are fused and calculated to obtain a comprehensive risk score value; The comprehensive risk scoring calculation model is as follows: ; ; ; ; In the formula, The comprehensive risk score is... The first risk score is... This is the second risk score. and These are the eighth and ninth weight parameters, respectively. For the interaction item weight parameter, To correct the parameters.

5. The method for assessing the risk of myopia occurrence based on multi-indicator fusion according to claim 2, characterized in that, The dynamic risk assessment processing of the time-series visual parameter data set to obtain a dynamic risk score includes: S231, perform trend analysis processing on the visual parameter time series data information set to obtain parameter change trend information; S232, Perform dynamic risk assessment calculation on the parameter change trend information to obtain a dynamic risk score.

6. The method for assessing the risk of myopia occurrence based on multi-indicator fusion according to claim 5, characterized in that, The step of performing trend analysis on the time-series data set of visual parameters to obtain parameter change trend information includes: S2311, The equivalent spherical lens diopter value sequence is analyzed and processed to obtain the diopter change slope value; S2312, Analyze and process the axial length value sequence to obtain the axial length growth slope value; S2313, The sequence of choroid thickness values ​​is analyzed and processed to obtain the slope value of the change in choroid thickness.

7. The method for assessing the risk of myopia occurrence based on multi-indicator fusion according to claim 1, characterized in that, The process of processing the myopia risk assessment results to obtain target intervention plan information includes: S31, determine whether the comprehensive risk score is greater than or equal to the first risk threshold, and obtain the first judgment result; If the first judgment result is yes, execute S32; If the first judgment result is negative, execute S34; S32, determine whether the comprehensive risk score is greater than or equal to the second risk threshold, and obtain the second judgment result; If the second judgment result is yes, execute S33; If the second judgment result is negative, execute S35; S33, perform a first processing on the equivalent spherical refractive power value to obtain first recommended lens parameter information, and determine the first recommended lens parameter information as target intervention plan information; S34, determine the plano lens parameter information as the target intervention plan information; S35, perform a second processing on the equivalent spherical refractive power value to obtain second recommended lens parameter information, and determine the second recommended lens parameter information as the target intervention plan information.

8. A myopia risk assessment device based on multi-indicator fusion, characterized in that, The device includes: The acquisition module is used to acquire a user's visual parameter data set; the visual parameter data set includes refractive state parameter data, ocular structure parameter data, visual function parameter data, and eye use behavior parameter data; the refractive state parameter data includes equivalent spherical refractive power, astigmatism value, and astigmatism axis value; the ocular structure parameter data includes axial length and choroid thickness values; the visual function parameter data includes best corrected visual acuity and contrast sensitivity values; and the eye use behavior parameter data includes eye use habit parameters. The evaluation module is used to perform multi-index fusion evaluation processing on the visual parameter data information set to obtain myopia risk assessment results. The recommendation module is used to process the myopia risk assessment results to obtain target intervention plan information.

9. A myopia risk assessment device based on multi-indicator fusion, characterized in that, The device includes: processor; A memory coupled to the processor stores executable program code; The processor calls the executable program code stored in the memory to execute the myopia risk assessment method based on multi-index fusion as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions, which, when invoked, are used to execute the myopia risk assessment method based on multi-indicator fusion as described in any one of claims 1-7.

Images