A myopia dynamic prediction and intervention evaluation method and system fusing physiological parameters and behavior visual range, an electronic device and a storage medium

Abstract

The present application relates to the field of ophthalmology, biomedical engineering and health information technology, and particularly relates to a myopia dynamic prediction and intervention evaluation method and system fusing physiological parameters and behavior visual distance, an electronic device and a storage medium, comprising collecting age, refractive state and eye use time distribution of a target individual at multiple preset visual distance levels; calling a preset age-myopia progression group benchmark model to obtain an annual progress reference value corresponding to the age; calling a preset visual distance-adjustment lag relative risk coefficient model to calculate an individual comprehensive adjustment lag load coefficient K based on the eye use time distribution; predicting the natural development trajectory of the individual based on the annual progress reference value and the comprehensive adjustment lag load coefficient K; simulating at least two intervention scenarios to generate comparative development trajectories; and outputting a comparison report containing the natural development trajectory and at least one post-intervention trajectory. The present application realizes accurate quantitative prediction of myopia risk.

Description

Technical Field

[0001] This invention relates to the fields of ophthalmology, biomedical engineering, and health information technology, and in particular to a method, system, electronic device, and storage medium for dynamic prediction and intervention assessment of myopia that integrates physiological parameters and behavioral visual distance. Background Technology

[0002] The global prevalence of myopia has become a major public health problem, and the prevalence of myopia among children and adolescents in my country remains high. The occurrence and progression of myopia is the result of a complex interaction of genetic susceptibility, physiological development, and environmental exposure factors. Among the many environmental factors, continuous close-range work, especially reading and writing at excessively close distances, is recognized as a key risk factor. Excessively close viewing distances lead to lag in accommodative response, creating a hyperopic defocus signal in the peripheral retina. This signal is considered the main driving force stimulating compensatory axial elongation.

[0003] The current clinical management of myopia faces the following key technical bottlenecks: 1. Risk quantification relies on a single dimension and neglects behavioral data: Existing assessment tools largely depend on static physiological indicators (such as refractive error, axial length, and family history) or age-based group averages for risk stratification. These methods completely ignore the individualized quantification and dynamic monitoring of the core modifiable variable—continuous visual distance. Because "poor posture" cannot be converted into a calculable biomechanical load, risk assessment remains qualitative, resulting in severely insufficient predictive accuracy.

[0004] 2. Disconnect between progression prediction models and interventionable behaviors: Once myopia develops, its annual progression rate varies significantly among individuals. Clinical observations have revealed that children of the same age and with similar initial refractive errors can experience annual progression rates that differ by 2-3 times. Existing models cannot explain or quantify this difference. Based on existing research and long-term clinical observations, this invention argues that, in addition to genetic background, an individual's persistent viewing habits are the core, quantifiable, and interventionable variable leading to this difference.

[0005] 3. Lack of prospective quantitative decision support for intervention programs: While optical interventions such as orthokeratology lenses and multifocal defocus lenses are effective, their efficacy varies significantly among individuals (literature reports a delay rate of approximately 30%-60%). Clinically, there is a common confusion regarding why the effects of wearing the same defocus lens differ from person to person. More importantly, no tool can provide quantitative predictions for the crucial question of whether simultaneously improving behavioral visual distance on top of optical intervention can produce a synergistic effect. This leads to clinical decisions relying on experience, potentially missing the optimal prevention and control opportunity or resulting in a waste of medical resources.

[0006] 4. Lack of effective tools for shifting the focus of "prevention of disease" forward: For children who are not myopic but have insufficient farsighted reserve, current technology can only provide qualitative warnings. It cannot accurately predict the specific age at which myopia may occur based on their specific and continuous poor viewing distance behavior (such as habitual reading at 20cm), thus making it difficult to promote truly effective early behavioral interventions.

[0007] Therefore, there is an urgent need in this field for an innovative method and system that can integrate individual physiological development patterns and dynamic behavioral data, establish quantitative models based on multidisciplinary principles, and realize intelligent decision support across the entire chain from risk warning and trajectory simulation to intervention optimization. Summary of the Invention

[0008] The purpose of this invention is to overcome the above-mentioned deficiencies of the prior art and to propose a calculation method and system for personalized dynamic prediction and evaluation of the risk of myopia, the rate of progression, and the effectiveness of intervention programs in children and adolescents by quantifying individual near-vision behavior parameters and combining physiological development models and optometry principles.

[0009] This invention provides a method for dynamic prediction and intervention assessment of myopia that integrates physiological parameters and behavioral visual distance, comprising the following steps: S10: Collect the target individual's age, refractive status, and the distribution of their eye use time at multiple preset visual distance levels; S20: Call the preset age-myopia progression group baseline model to obtain the annual progression reference value corresponding to age; call the preset viewing distance-accommodative lag relative risk coefficient model to calculate the individual comprehensive accommodative lag load coefficient K based on the distribution of eye use time; the risk coefficient model is based on the average viewing distance behavior level aligned with the data source of the group baseline model, where the coefficient is 1; S30: Based on the annual progress reference value and the comprehensive adjustment lag load coefficient K, predict the natural progression trajectory of myopia in an individual; S40: Based on the natural development trajectory, simulate and generate comparative development trajectories under at least two intervention scenarios. The simulation of the intervention scenarios shall at least involve the step of correcting the basic effectiveness of optical intervention based on the comprehensive adjustment hysteresis load coefficient K. S50: Output a report comparing the natural developmental trajectory with at least one post-intervention trajectory.

[0010] In some embodiments of this application, in step S20, in the relative risk coefficient model of sight distance-adjustment lag, the risk coefficients corresponding to sight distances of 20cm, 25cm, and 30cm are approximately 2.76, 2.00, and 1.33, respectively, and the risk coefficient corresponding to a sight distance greater than or equal to 33cm is less than 1.00.

[0011] In some embodiments of this application, step S20 further includes: when the refractive state is hyperopia, calling a preset age-hyperopia reserve model and combining it with the comprehensive accommodative lag load coefficient K to predict the individual's age of myopia onset.

[0012] In some embodiments of this application, in step S30, when predicting the natural progression trajectory of myopia, the predicted progression value ΔD_pred(t) = ΔD_base(t) × f(K) in the future year t is satisfied. Where ΔD_base(t) is the annual progress reference value, f(K) is a function that maps the comprehensive adjustment lag load coefficient K to the progress impact coefficient, and f(K) is positively correlated with K.

[0013] In some embodiments of this application, in step S40, when simulating a single optical intervention scenario, the basic effectiveness of optical intervention is corrected by an effectiveness decay model, and the actual control rate is Eff_actual=Eff_base×(1-D(K)). Where Eff_base is the base control law, D(K) is the decay factor calculated based on K, and the value of D(K) is positively correlated with K.

[0014] In some embodiments of this application, in step S40, a joint intervention scenario is also simulated, and the corresponding control rate is calculated by a synergy model. The joint control rate output by the synergy model is greater than the sum of the actual control rate of a single optical intervention after correction by the effectiveness decay model and the estimated control rate of simple behavioral improvement.

[0015] In some embodiments of this application, the preset viewing distance levels include at least four levels: 20cm, 25cm, 30cm, and ≥33cm.

[0016] In some embodiments of this application, a system for implementing a myopia prediction and intervention assessment method is also disclosed, comprising: The data interface module is used to collect user data; The model storage unit is used to store the age-myopia progression group baseline model, the visual distance-accommodation lag relative risk coefficient model, the age-hyperopia reserve model, the effectiveness decay model, and the synergistic effect model. The processing engine is used to perform prediction and simulation calculations; The report generation unit is used to generate and output comparison reports.

[0017] In some embodiments of this application, an electronic device is also disclosed, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the program to implement a method for dynamic prediction and intervention assessment of myopia.

[0018] In some embodiments of this application, a computer-readable storage medium is also disclosed, on which a computer program is stored, which, when executed by a processor, implements a method for dynamic prediction and intervention assessment of myopia.

[0019] The advantages and beneficial effects of this invention compared to the prior art are: 1. In response to the problem that existing technologies neglect core modifiable variables, this invention collects visual distance behavior data and calculates the comprehensive hysteresis load coefficient K, transforming qualitative factors such as poor posture into quantifiable biomechanical loads, thereby achieving a precise quantitative transformation of myopia risk from static physiological indicators to dynamic behavioral fusion.

[0020] 2. To address the bottleneck of existing models failing to account for individual differences, this invention corrects the annual progression baseline based on the K value, accurately predicting the age of onset of myopia and the annual progression rate, thus solving the prediction problem of a 2-3 times difference in annual progression under the same conditions.

[0021] 3. To address the lack of forward-looking quantitative tools in existing technologies, this invention corrects the individual efficacy of optical intervention through an efficacy decay model and introduces a synergistic effect model to quantify the gains of joint intervention; at the same time, it provides accurate prediction of the age of myopia onset based on behavioral data for those with insufficient farsighted reserve, thus promoting the shift of the "prevention of disease" approach forward.

[0022] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0023] Figure 1 This is a flowchart of a method for dynamic prediction and intervention assessment of myopia that integrates physiological parameters and behavioral visual distance in an embodiment of the present invention. Figure 2 This is a structural diagram of a dynamic myopia prediction and intervention assessment system that integrates physiological parameters and behavioral visual distance, according to an embodiment of the present invention. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages disclosed in the embodiments of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely illustrative of the embodiments of the present invention and are not intended to limit the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of this application. Examples of embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout.

[0025] It should be noted that the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion, such as a process, method, system, product, or server that includes a series of steps or units, not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such process, method, product, or device.

[0026] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0027] like Figure 1 As shown, this invention provides a method for dynamic prediction and intervention assessment of myopia that integrates physiological parameters and behavioral visual distance, including the following steps: S10: Collect the target individual's age, refractive status, and the distribution of their eye use time at multiple preset visual distance levels; S20: Call the preset age-myopia progression group baseline model to obtain the annual progression reference value corresponding to age; call the preset viewing distance-accommodative lag relative risk coefficient model to calculate the individual comprehensive accommodative lag load coefficient K based on the distribution of eye use time; the risk coefficient model is based on the average viewing distance behavior level aligned with the data source of the group baseline model, where the coefficient is 1; S30: Based on the annual progress reference value and the comprehensive adjustment lag load coefficient K, predict the natural progression trajectory of myopia in an individual; S40: Based on the natural development trajectory, simulate and generate comparative development trajectories under at least two intervention scenarios. The simulation of the intervention scenarios shall at least involve the step of correcting the basic effectiveness of optical intervention based on the comprehensive adjustment hysteresis load coefficient K. S50: Output a report comparing the natural developmental trajectory with at least one post-intervention trajectory.

[0028] In some embodiments of this application, in step S20, in the relative risk coefficient model of sight distance-adjustment lag, the risk coefficients corresponding to sight distances of 20cm, 25cm, and 30cm are approximately 2.76, 2.00, and 1.33, respectively, and the risk coefficient corresponding to a sight distance greater than or equal to 33cm is less than 1.00.

[0029] In some embodiments of this application, step S20 further includes: when the refractive state is hyperopia, calling a preset age-hyperopia reserve model and combining it with the comprehensive accommodative lag load coefficient K to predict the individual's age of myopia onset.

[0030] This invention addresses the problem of existing technologies neglecting core, modifiable variables. By collecting visual distance behavior data and calculating the comprehensive regulatory lag load coefficient K, qualitative factors such as poor posture are transformed into quantifiable biomechanical loads, thereby achieving a precise quantitative transformation of myopia risk from static physiological indicators to dynamic behavioral integration.

[0031] In some embodiments of this application, in step S30, when predicting the natural progression trajectory of myopia, the predicted progression value ΔD_pred(t) = ΔD_base(t) × f(K) in the future year t is satisfied. Where ΔD_base(t) is the annual progress reference value, f(K) is a function that maps the comprehensive adjustment lag load coefficient K to the progress impact coefficient, and f(K) is positively correlated with K.

[0032] In some embodiments of this application, in step S40, when simulating a single optical intervention scenario, the basic effectiveness of optical intervention is corrected by an effectiveness decay model, and the actual control rate is Eff_actual=Eff_base×(1-D(K)). Where Eff_base is the base control law, D(K) is the decay factor calculated based on K, and the value of D(K) is positively correlated with K.

[0033] This invention addresses the bottleneck of existing models failing to account for individual differences by correcting the annual progression baseline based on the K value, accurately predicting the age of onset of myopia and the annual progression rate, thus solving the prediction problem of a 2-3 times difference in annual progression under the same conditions.

[0034] In some embodiments of this application, in step S40, a joint intervention scenario is also simulated, and the corresponding control rate is calculated by a synergy model. The joint control rate output by the synergy model is greater than the sum of the actual control rate of a single optical intervention after correction by the effectiveness decay model and the estimated control rate of simple behavioral improvement.

[0035] To address the lack of forward-looking quantitative tools in existing technologies, this invention corrects the individual efficacy of optical interventions through an efficacy decay model and introduces a synergistic effect model to quantify the gains of joint interventions. At the same time, it provides accurate predictions of the age of myopia onset based on behavioral data for individuals with insufficient farsighted reserve, thus promoting the shift of the "prevention of disease" approach forward.

[0036] In some embodiments of this application, the preset viewing distance levels include at least four levels: 20cm, 25cm, 30cm, and ≥33cm.

[0037] In some embodiments of this application, such as Figure 2 As shown, a system for implementing a myopia prediction and intervention assessment method is also disclosed, comprising: The data interface module is used to collect user data; The model storage unit is used to store the age-myopia progression group baseline model, the visual distance-accommodation lag relative risk coefficient model, the age-hyperopia reserve model, the effectiveness decay model, and the synergistic effect model. The processing engine is used to perform prediction and simulation calculations; The report generation unit is used to generate and output comparison reports.

[0038] In some embodiments of this application, an electronic device is also disclosed, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the program to implement a method for dynamic prediction and intervention assessment of myopia.

[0039] In some embodiments of this application, a computer-readable storage medium is also disclosed, on which a computer program is stored, which, when executed by a processor, implements a method for dynamic prediction and intervention assessment of myopia.

[0040] The following specific embodiment will be used for verification: The first step is to build the core quantization model: The technical basis of this invention lies in a series of interrelated quantitative models built on multidisciplinary data and principles.

[0041] 1. Age-based baseline model for myopia progression (physiological development baseline).

[0042] The data stored in this model (ΔD_base) serves as the "anchor" for predictions. It is derived from the statistical average of annual myopia progression in children of different age groups reported in large-scale epidemiological studies (such as SCORM, ATS, etc.). This value reflects the average rate of progression in a specific period and region under prevalent mixed visual-sight behavior habits, and is a realistic benchmark that includes "average behavioral risk," rather than an ideal physiological baseline.

[0043] Example data (based on an Asian children's cohort): 6-8 years old: approximately -0.75D to -1.00D / year; 9-12 years old (high-speed period): approximately -1.00D to -1.25D / year; 13-15 years old: approximately -0.75D to -1.00D / year; 15-18 years old: approximately -0.25D to -0.50D / year.

[0044] 2. Age-hyperopia reserve model (physiological status assessment).

[0045] This model provides the normal range or median of hyperopic reserve for children of different ages. It serves as the basis for determining whether the current refractive state deviates from the normal trajectory and for predicting the onset of myopia. Example: The normal median hyperopic reserve for a 6-year-old child is approximately +1.50D ± 0.50D.

[0046] 3. Visibility-Adjustment Lag Relative Risk Coefficient Model (Core of Behavioral Risk Quantification).

[0047] This model is key to achieving behavioral quantification. Its innovation lies in defining a risk reference system aligned with the "group benchmark model".

[0048] Baseline Definition: The implicit average visual distance behavior level of the research population that generated the above "Population Baseline Model" data is set as a relative risk coefficient K=1.0. For simplicity, this level can be equivalent to a visual distance of 33 cm.

[0049] Quantitative Relationship: Based on the accommodation demand formula (1 / visual distance (meters)) and a large amount of clinical accommodation lag measurement data, a risk multiple of other visual distances relative to this benchmark is established. Preferred Implementation Parameters: 20cm viewing distance: K_20≈2.76; 25cm viewing distance: K_25≈2.00; 30cm sight distance (reference): K_30=1.33; For viewing distances ≥33cm: K_33≤1.00 (e.g., 0.8); Individual integrated coefficient calculation: K_integrated = Σ(Percentage of time spent at each viewing distance level × Corresponding K value). This coefficient directly answers: "How many times greater is this user's behavioral risk compared to the average risk of their peers?"

[0050] 4. A model for the attenuation of the effectiveness of behavioral visual distance on optical intervention (innovative model A).

[0051] This model quantifies the "counteracting" effect of adverse behaviors on the effectiveness of optical intervention. Its core principle is that excessively close viewing distances (high K_integrated) lead to high accommodative hysteresis, which may interfere with the ideal defocus signal generated by the defocus lens design, thus weakening its control effectiveness.

[0052] Model format: Actual control rate = Basic control rate × (1 - Decay(K_integrated)); Example of decay factor Decay: Decay=min(0.7,β) (K_integrated-1)), where β is the calibration coefficient (e.g., 0.3). If K_integrated=2.38, then Decay≈0.41, meaning the performance may be reduced by about 41%.

[0053] 5. Synergistic effect model of optical-behavioral joint intervention (innovation model B).

[0054] This model quantifies the "enabling" effect of "behavioral improvement" on the effectiveness of "optical intervention," i.e., the "1+1>2" effect. The principle is that behavioral improvement (increasing the viewing distance) creates a working environment that is closer to the design intent of optical intervention, thereby potentially releasing potential that has been suppressed by undesirable behaviors.

[0055] Example of a model: Joint control rate = Basic control rate × (1 - Decay(K_target)) + α × ΔEff_B; Where K_target is the improved behavior coefficient, ΔEff_B is the control rate gain brought about by the behavior improvement itself, and α is the synergistic gain coefficient (α>1, for example 1.2-1.5).

[0056] The second step involves demonstrating the predictive implementation examples and decision-making value: Taking a 7-year-old child with a hyperopic reserve of +0.75D, but who is accustomed to learning at a visual distance of 20-25cm as an example, the system conducts a full-cycle simulation: Step S200 (Natural Process Prediction): The calculated value is K_integrated = 2.38 (the risk is 2.38 times the average level).

[0057] Prediction: Age_onset ≈ 7.8 years (approximately 9 months later). System prompt: "If current habits are maintained, myopia will occur much earlier; if improved to the average viewing distance (30cm), the onset time can be delayed to approximately 9.5 years."

[0058] Step S300 (Intervention scenario simulation up to age 18): The system generates four comparison curves: Natural Development Curve (red): Based on the continued high-risk behavior, the predicted myopia level by age 18 may reach -8.00D or higher, indicating an extremely high risk of high myopia. Simple Behavioral Intervention Curve (green): Assuming successful improvement and maintenance of visual distance at ≥33cm from age 7, the predicted myopia level by age 18 may be within -1.50D, demonstrating the significant potential of early behavioral intervention. Single Optical Intervention Curve (blue): Assuming defocus lenses are worn after age 8 (basic effectiveness 55%), but the behavior remains unchanged, due to reduced effectiveness (actual control rate ≈32%), the predicted myopia level by age 18 is approximately -5.50D. Combined Intervention Curve (purple): Assuming defocus lenses are worn after age 8 and visual distance is improved simultaneously, the predicted myopia level by age 18 can be controlled within -3.00D, calculated using a synergistic effect model.

[0059] Step S400 (Decision Report): The report highlights that "for this user, the primary and most cost-effective strategy is to immediately implement intensive behavioral interventions. This could not only delay the onset of myopia but is also a decisive factor in the effectiveness of any future optical interventions." The report uses quantitative charts to visually demonstrate the significant long-term differences resulting from different choices.

[0060] The third step is to implement the system: This system can be deployed as a cloud-based SaaS platform, a local hospital workstation, or integrated into smart optometry equipment. It connects to IoT devices such as smart learning lights and posture correctors via API to achieve automatic collection of behavioral data. The core algorithm module is well-encapsulated and supports online calibration and updates of model parameters.

[0061] This invention transforms the vague behavioral concept of "persistent poor visual distance" into a precise and calculable "biomechanical load coefficient" through optometry principles. It achieves truly personalized dynamic prediction: based on an individual's real-time physiological state (age, refractive error) and persistent behavioral data, it dynamically predicts the specific time point of myopia onset and the future trajectory of refractive error development. It constructs a "digital sandbox" for intervention effectiveness: creating an intervention effect simulation engine that can not only evaluate the effects of single measures but also quantitatively reveal the "attenuation effect of behavioral visual distance on the effectiveness of optical intervention" and the "synergistic effect of combined optical and behavioral interventions," providing a forward-looking and data-driven decision-making basis for formulating optimal individualized prevention and control plans.

[0062] In this application, unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. In case of any inconsistency, the meaning set forth in this specification or derived from the content described herein shall prevail. Furthermore, the terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit the scope of this application.

[0063] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the technical solutions of the present invention, and these modifications or equivalent substitutions cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for dynamic prediction and intervention assessment of myopia that integrates physiological parameters and behavioral visual distance, characterized in that, Includes the following steps: S10: Collect the target individual's age, refractive status, and the distribution of their eye use time at multiple preset visual distance levels; S20: Call the preset age-myopia progression group benchmark model to obtain the annual progression reference value corresponding to the age; call the preset viewing distance-accommodative lag relative risk coefficient model to calculate the individual comprehensive accommodative lag load coefficient K based on the eye use duration distribution; the risk coefficient model is based on the average viewing distance behavior level aligned with the data source of the group benchmark model, where the coefficient is 1; S30: Based on the annual progress reference value and the comprehensive adjustment lag load coefficient K, predict the natural myopia development trajectory of the individual; S40: Based on the natural development trajectory, simulate and generate comparative development trajectories under at least two intervention scenarios, wherein the simulation of the intervention scenarios involves at least the step of correcting the basic effectiveness of optical intervention based on the comprehensive adjustment hysteresis load coefficient K; S50: Output a report comparing the natural developmental trajectory with at least one post-intervention trajectory.

2. The method for dynamic prediction and intervention assessment of myopia integrating physiological parameters and behavioral visual distance according to claim 1, characterized in that, In step S20, in the relative risk coefficient model of sight distance-adjustment lag, the risk coefficients corresponding to sight distances of 20cm, 25cm, and 30cm are approximately 2.76, 2.00, and 1.33, respectively, and the risk coefficient corresponding to a sight distance greater than or equal to 33cm is less than 1.

00.

3. The method for dynamic prediction and intervention assessment of myopia integrating physiological parameters and behavioral visual distance according to claim 1, characterized in that, Step S20 further includes: when the refractive state is hyperopia, calling a preset age-hyperopia reserve model and combining it with the comprehensive accommodative lag load coefficient K to predict the individual's age of myopia onset.

4. The method for dynamic prediction and intervention assessment of myopia integrating physiological parameters and behavioral visual distance according to claim 1, characterized in that, In step S30, when predicting the natural progression trajectory of myopia, the predicted progression value ΔD_pred(t) = ΔD_base(t) × f(K) in the future year t is satisfied. Where ΔD_base(t) is the annual progress reference value, f(K) is a function that maps the comprehensive adjustment lag load coefficient K to the progress impact coefficient, and f(K) is positively correlated with K.

5. The method for dynamic prediction and intervention assessment of myopia integrating physiological parameters and behavioral visual distance according to claim 1, characterized in that, In step S40, when simulating a single optical intervention scenario, the correction of the basic effectiveness of optical intervention is achieved through an effectiveness decay model, and the actual control rate is Eff_actual=Eff_base×(1-D(K)). Where Eff_base is the base control law, D(K) is the decay factor calculated based on K, and the value of D(K) is positively correlated with K.

6. The method for dynamic prediction and intervention assessment of myopia integrating physiological parameters and behavioral visual distance according to claim 5, characterized in that, In step S40, a joint intervention scenario is also simulated, and the corresponding control rate is calculated by the synergy model. The joint control rate output by the synergy model is greater than the sum of the actual control rate of the single optical intervention after correction by the effectiveness decay model and the estimated control rate of the simple behavior improvement.

7. The method for dynamic prediction and intervention assessment of myopia integrating physiological parameters and behavioral visual distance according to claim 1, characterized in that, The preset viewing distance levels include at least four levels: 20cm, 25cm, 30cm, and ≥33cm.

8. A myopia prediction and intervention assessment system for implementing the method of any one of claims 1-7, characterized in that, include: The data interface module is used to collect user data; The model storage unit is used to store the age-myopia progression group baseline model, the visual distance-accommodation lag relative risk coefficient model, the age-hyperopia reserve model, the effectiveness decay model, and the synergistic effect model. The processing engine is used to perform the prediction and simulation calculations; The report generation unit is used to generate and output the comparison report.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory, characterized in that, When the processor executes the program, it implements the method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-7.

Images