Myopia progress risk prediction system

Abstract

The invention belongs to the technical field of eye detection, and particularly relates to a myopia progress risk prediction system, which comprises a data acquisition module used for collecting a plurality of biological index data related to myopia progress, including but not limited to ocular axis length, corneal curvature, diopter, age, gender, lifestyle, genetic information and the like; the multi-factor analysis module is used for comprehensively analyzing multiple pieces of biological index data and modeling the individualized myopia progress risk based on a multi-factor interaction relationship; the regression algorithm module is used for collecting multiple pieces of biological index data; by analyzing multiple biological indexes at the same time, comprehensive evaluation of the myopia progress risk is achieved, compared with a traditional method which only depends on a single index for prediction, the system considers interaction of multiple factors, individual differences and environmental influences can be captured more comprehensively, and therefore prediction accuracy and reliability are remarkably improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of eye detection, and in particular to a myopia progression risk prediction system. Background Art

[0002] Myopia is a common eye disease worldwide, especially among adolescents and children. With the advent of the information age, changes in lifestyle habits such as excessive use of electronic products and prolonged close-up use of eyes have led to an increasing incidence of myopia year by year. Myopia not only affects visual quality, but may also cause a series of serious eye complications, such as retinal detachment and glaucoma, which can lead to blindness in severe cases. Therefore, how to effectively predict the progression of myopia, intervene early and take scientific preventive measures has become a hot topic in ophthalmology research.

[0003] 1. Traditional myopia risk assessment methods mostly rely on single biological indicators, such as refraction and axial length, for simple predictions. Although this method can provide a certain risk assessment, it lacks comprehensive analysis of multiple biological indicators and cannot fully consider individual differences and environmental factors. Therefore, its prediction accuracy and reliability are limited.

[0004] 2. Traditional methods often rely on expensive equipment and complex examinations, resulting in high system costs and difficulty in popularizing them in resource-limited areas and medical institutions;

[0005] 3. Existing myopia risk assessment systems focus more on static data analysis and ignore individualized real-time data updates and dynamic adjustments. They cannot accurately reflect the progression of myopia in individuals at different stages, and it is difficult to provide personalized intervention measures based on the different needs of users.

[0006] Therefore, a myopia progression risk prediction system is proposed to address the above problems. Summary of the Invention

[0007] (1) Technical problems solved

[0008] In view of the shortcomings of the existing technology, the present invention provides a myopia progression risk prediction system to solve the problems raised in the background technology.

[0009] (2) Technical solution

[0010] To achieve the above objectives, the present invention provides the following technical solutions: A myopia progression risk prediction system comprising:

[0011] A data collection module is used to collect multiple biological indicator data related to myopia progression, including but not limited to axial length, corneal curvature, refractive power, age, gender, lifestyle, genetic information, environmental factors, etc.;

[0012] A multi-factor analysis module is used to comprehensively analyze multiple biomarker data and model the individualized myopia progression risk based on the interaction between multiple factors;

[0013] A regression algorithm module is used to model the risk of myopia progression using a regression algorithm based on the collected data of multiple biological indicators, generate a multivariate regression model for quantitatively predicting the risk of myopia progression, and optimize it in combination with the multifactor analysis module;

[0014] A prediction model module is used to use the risk assessment data generated by the regression algorithm module in combination with a machine learning algorithm or a deep learning model to predict an individual's myopia progression risk and generate personalized prediction results;

[0015] A personalized adaptation module, which adjusts the prediction model based on real-time individual data to accommodate individual differences and provide more accurate predictions of myopia progression risk;

[0016] The interface display module is used to present the prediction results in a user-friendly manner, including the myopia progression risk score, predicted progression speed, and possible intervention recommendations, to facilitate user understanding and operation.

[0017] Preferably, the data acquisition module further comprises: a real-time tracking device for regularly collecting biological data related to myopia progression and transmitting the data to the data acquisition module.

[0018] Preferably, the multi-factor analysis module adopts a multiple regression model to process the complex relationship between multiple biological indicators and myopia progression.

[0019] Preferably, the regression algorithm module preferentially adopts a ridge regression algorithm to quantitatively evaluate the contribution of each biological indicator to myopia progression and optimize the prediction results. The regression algorithm module is combined with a machine learning algorithm to dynamically adjust the prediction model to adapt it to individual differences of users and improve the accuracy of the prediction;

[0020] Ridge regression is a variant of linear regression. It handles multicollinearity by adding a regularization term to the loss function. Ridge regression adds a penalty term to the estimation of the regression coefficient to avoid overfitting. Its formula is:

[0021]

[0022] Where: λ is the regularization parameter, which controls the model complexity;

[0023] Machine learning algorithms are used for nonlinear relationship analysis.

[0024] Preferably, the prediction model module performs model training based on individual historical data and real-time data, and dynamically adjusts the prediction results according to the latest data.

[0025] Preferably, the individualized adaptation module includes an adaptive algorithm for continuously optimizing the prediction model so that it can adapt to the individual differences of different user groups. The individualized adaptation module dynamically updates the model parameters through incremental learning and recalculates the weights each time new data is input;

[0026] An adaptive algorithm is an algorithm that can automatically adjust its behavior or model parameters according to changes in input data. It can dynamically update its parameters or behavior based on new input or feedback information, and gradually improve its adaptability and processing effect to problems through continuous learning and adjustment.

[0027] Preferably, the interface display module includes a user interactive interface, allowing the user to input additional information such as their own living habits and diet, and further optimize the prediction results based on this information;

[0028] The user interactive interface includes: a main interface, a navigation bar that lists the main functional modules;

[0029] The user data entry module allows users to enter basic personal information through a form-based interface. As users enter data, the system checks the data format in real time and provides immediate feedback. It supports scanning users' ophthalmology reports or uploading electronic medical records. The system automatically extracts and updates relevant data, reducing the complexity of manual input;

[0030] In the risk prediction and analysis module, after the user enters the biological indicators, the system automatically calculates the risk index and generates a real-time analysis chart. When the user clicks on the prediction result, a detailed analysis report pops up, including the predicted myopia development trend, possible complications, and risk factors.

[0031] Personalized intervention recommendation module: based on the user's risk prediction results, the system automatically generates a personalized intervention plan.

[0032] Preferably, the prediction model module can output the possible risk level of myopia progression, progression speed and recommended intervention measures based on the user's biological data and behavioral data.

[0033] Preferably, the system further includes a database for storing multi-dimensional historical data, individualized prediction data, and model parameters to support long-term storage, updating, and analysis of data.

[0034] Beneficial effects

[0035] Compared with the existing technology, the present invention provides a myopia progression risk prediction system with the following beneficial effects:

[0036] 1. This invention achieves a comprehensive assessment of the risk of myopia progression by simultaneously analyzing multiple biological indicators. Compared with traditional methods that rely on only a single indicator for prediction, this system takes into account the interaction of multiple factors and can more comprehensively capture individual differences and environmental influences, thereby significantly improving the accuracy and reliability of predictions.

[0037] 2. This invention, through individualized data analysis, tailors the prediction model according to the user's biological characteristics and living habits, thereby enhancing the system's adaptability to individual differences.

[0038] 3. This invention, this system abandons the dependence on expensive equipment. Users only need to undergo routine eye examinations to obtain predictive data, which significantly reduces the cost of the system and makes it more economical and accessible in medical services.

[0039] 4. This invention, the system is equipped with a friendly user interface, which is simple, intuitive and easy to operate, and can provide a smooth experience for users at different levels. At the same time, the system supports multilingual versions, making it applicable across cultures and languages globally, and is particularly suitable for promotion and use in medical institutions in different countries and regions. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0041] Figure 1 It is a system flow chart of the present invention. DETAILED DESCRIPTION

[0042] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0043] Specific examples are given below.

[0044] Example

[0045] like Figure 1 As shown, the system includes:

[0046] Data collection module: collects multi-dimensional data of users through smart wearable devices, mobile phone applications and manual input. The data includes the following categories;

[0047] Biological indicator data: including refractive power, axial length, corneal thickness, etc., obtained through ophthalmic examination equipment;

[0048] Lifestyle data: including daily close-up eye use time, reading habits, frequency of electronic product use, outdoor activity time, etc., tracked and recorded through mobile phone applications or wearable devices;

[0049] Environmental factor data: including light intensity, air humidity, temperature, etc., collected in real time using smart devices such as smart light bulbs and environmental monitoring instruments;

[0050] By combining hardware devices with mobile applications, we ensure the accuracy and comprehensiveness of data collection;

[0051] Data Analysis Module: The data collection module transmits acquired biological indicators, living habits, and environmental data to the data analysis module. This module uses advanced regression model analysis, machine learning algorithms, and data mining techniques to establish a multidimensional data association model to predict individual myopia risks from different perspectives.

[0052] Regression model analysis: Based on existing historical data, a mathematical model of individual myopia progression is established through regression analysis to predict the trend of refractive power changes and the rate of myopia progression;

[0053] Machine learning algorithms: Combined with support vector machines, decision trees and other algorithms, this algorithm analyzes the main factors affecting myopia progression and continuously optimizes the prediction model based on historical user data and real-time feedback;

[0054] The data analysis module can generate personalized risk assessment reports, comprehensively analyze the user's myopia risk level, and issue corresponding warnings;

[0055] Personalized intervention module: Based on the risk assessment results generated by the data analysis module, the personalized intervention module provides users with specific intervention suggestions to help them manage their eye health. The personalized intervention module includes:

[0056] Eye time management: The system recommends appropriate eye rest strategies based on the user's daily eye habits;

[0057] Outdoor activity recommendations: Based on environmental data, users are advised to engage in a certain amount of outdoor activities every day to slow the progression of myopia;

[0058] Eye exercises and vision training: The system provides users with professional eye exercises and vision training suggestions based on their individual eye health conditions, promoting blood circulation in the eyes and relaxing eye muscles.

[0059] Real-time feedback and dynamic adjustment module: The real-time feedback module continuously optimizes intervention measures based on user feedback and new data input, ensuring that the system can dynamically adjust the user's intervention plan;

[0060] The system operation process includes the following steps:

[0061] Step 1: When the user logs into the system for the first time, they enter their basic personal information and undergo a preliminary physical examination. The system automatically collects the user's vision, axial length, refractive power and other biological indicators;

[0062] Step 2: The system continuously tracks the user's lifestyle data through the data collection module and collects data on external factors related to the development of myopia;

[0063] Step 3: After data collection is completed, the system inputs this data into the data analysis module for regression analysis. This module analyzes the individual's possible future myopia progression based on the user's current vision and lifestyle data, combined with historical data, and calculates the corresponding risk value;

[0064] Step 4: Based on the analysis results, the personalized intervention module provides users with intervention recommendations, including daily eye use time, lighting requirements, rest and exercise arrangements, etc. The system will dynamically adjust the intervention plan based on the user's real-time data;

[0065] Step 5: The system regularly updates the user's myopia progression data and updates risk predictions and intervention measures based on the new data to ensure the accuracy of the system's predictions and the real-time nature of interventions.

[0066] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention, and such changes and modifications fall within the scope of the invention as claimed.

Claims

1. A myopia progression risk prediction system, characterized in that: The system comprises: A data collection module is used to collect multiple biological indicator data related to myopia progression, including but not limited to axial length, corneal curvature, refractive power, age, gender, lifestyle, genetic information, environmental factors, etc.; A multi-factor analysis module is used to comprehensively analyze multiple biomarker data and model the individualized myopia progression risk based on the interaction between multiple factors; A regression algorithm module is used to model the risk of myopia progression using a regression algorithm based on the collected data of multiple biological indicators, generate a multivariate regression model for quantitatively predicting the risk of myopia progression, and optimize it in combination with the multifactor analysis module; A prediction model module is used to use the risk assessment data generated by the regression algorithm module in combination with a machine learning algorithm or a deep learning model to predict an individual's myopia progression risk and generate personalized prediction results; A personalized adaptation module, which adjusts the prediction model based on real-time individual data to accommodate individual differences and provide more accurate predictions of myopia progression risk; The interface display module is used to present the prediction results in a user-friendly manner, including the myopia progression risk score, predicted progression speed, and possible intervention recommendations, to facilitate user understanding and operation.

2. A myopia progression risk prediction system according to claim 1, characterized in that: The data acquisition module further includes a real-time tracking device for regularly collecting biological data related to myopia progression and transmitting the data to the data acquisition module.

3. The myopia progression risk prediction system according to claim 1, characterized in that: The multi-factor analysis module adopts a multiple regression model to process the complex relationship between multiple biological indicators and myopia progression.

4. The myopia progression risk prediction system according to claim 1, wherein: The regression algorithm module preferentially uses the ridge regression algorithm to quantitatively evaluate the contribution of each biological indicator to myopia progression and optimize the prediction results. The regression algorithm module is combined with the machine learning algorithm to dynamically adjust the prediction model to adapt it to individual differences of users and improve the accuracy of the prediction; Ridge regression is a variant of linear regression. It handles multicollinearity by adding a regularization term to the loss function. Ridge regression adds a penalty term to the estimation of the regression coefficient to avoid overfitting. Its formula is: Where: λ is the regularization parameter, which controls the model complexity; Machine learning algorithms are used for nonlinear relationship analysis.

5. The myopia progression risk prediction system according to claim 1, characterized in that: The prediction model module performs model training based on individual historical data and real-time data, and dynamically adjusts the prediction results according to the latest data.

6. The myopia progression risk prediction system according to claim 1, characterized in that: The individualized adaptation module includes an adaptive algorithm for continuously optimizing the prediction model to adapt it to the individual differences of different user groups. The individualized adaptation module dynamically updates the model parameters through incremental learning and recalculates the weights each time new data is input; An adaptive algorithm is an algorithm that can automatically adjust its behavior or model parameters according to changes in input data. It can dynamically update its parameters or behavior based on new input or feedback information, and gradually improve its adaptability and processing effect to problems through continuous learning and adjustment.

7. The myopia progression risk prediction system according to claim 1, characterized in that: The interface display module includes a user interactive interface, allowing users to input additional information such as their living habits and diet, and further optimize the prediction results based on this information; The user interactive interface includes: a main interface, a navigation bar that lists the main functional modules; The user data entry module allows users to enter basic personal information through a form-based interface. As users enter data, the system checks the data format in real time and provides immediate feedback. It supports scanning users' ophthalmology reports or uploading electronic medical records. The system automatically extracts and updates relevant data, reducing the complexity of manual input. In the risk prediction and analysis module, after the user enters the biological indicators, the system automatically calculates the risk index and generates a real-time analysis chart. When the user clicks on the prediction result, a detailed analysis report pops up, including the predicted myopia development trend, possible complications, and risk factors. Personalized intervention recommendation module: based on the user's risk prediction results, the system automatically generates a personalized intervention plan.

8. The myopia progression risk prediction system according to claim 1, characterized in that: The prediction model module can output the possible risk level of myopia progression, progression speed and recommended intervention measures based on the user's biological data and behavioral data.

9. The myopia progression risk prediction system according to claim 1, characterized in that: The system also includes a database for storing multi-dimensional historical data, individualized prediction data, and model parameters to support long-term storage, updating, and analysis of data.

Images