Screening and predicting system for mild cognitive impairment of glaucoma patient

Abstract

The invention discloses a system for screening and predicting mild cognitive impairment of a glaucoma patient, and belongs to the technical field of mild cognitive impairment, and the system comprises a data collection module which is used for collecting real-time data of the glaucoma patient; the analysis and screening module is used for analyzing the real-time data of the glaucoma patient and screening mild cognitive impairment; the degree prediction module is used for predicting the degree of the mild cognitive impairment of the glaucoma patient and determining a prediction result of the degree of the mild cognitive impairment of the glaucoma patient; and the treatment management and control module is used for performing personalized treatment management and control on the mild cognitive impairment of the glaucoma patient. The method solves the problem that the mild cognitive impairment treatment, management and control effects of the glaucoma patients are poor due to the fact that the mild cognitive impairment cannot be effectively screened and predicted for the glaucoma patients in the prior art. The method can effectively screen and predict the mild cognitive impairment of the glaucoma patient, can effectively prevent and control the disease development, and can improve the treatment and control effect of the mild cognitive impairment of the glaucoma patient.

Description

Technical Field

[0001] The present invention relates to the technical field of mild cognitive impairment, in particular to a system for screening and predicting mild cognitive impairment in glaucoma patients. Background Art

[0002] Glaucoma is a common ophthalmic disease characterized by degenerative changes of the optic disc and visual field damage. Studies in recent years have found that some glaucoma patients may have mild cognitive impairment in the early stages of the disease, and these patients may eventually become blind if not treated in time. Therefore, screening and predicting mild cognitive impairment in glaucoma patients can effectively prevent and control the progression of the disease, which has important clinical significance and social value.

[0003] The Chinese patent with publication number CN118711790A discloses a glaucoma auxiliary prediction method and system, which includes: processing the original image data using limited contrast adaptive histogram equalization and color standardization respectively; extracting image features related to glaucoma from the processed original image data; obtaining electronic medical records corresponding to the color fundus photograph; generating a knowledge graph based on the electronic medical records; and assisting the prediction of glaucoma based on the extracted image features and the generated knowledge graph. The method can improve the accuracy and reliability of glaucoma prediction; however, the patent has the following defects:

[0004] The existing methods cannot effectively screen and predict mild cognitive impairment in glaucoma patients, nor can they effectively prevent and control the progression of the disease, resulting in poor treatment and control of mild cognitive impairment in glaucoma patients. Summary of the invention

[0005] The purpose of the present invention is to provide a screening and prediction system for mild cognitive impairment in glaucoma patients, which can effectively screen and predict mild cognitive impairment in glaucoma patients, effectively prevent and control the progression of the disease, and improve the treatment and control effect of mild cognitive impairment in glaucoma patients, thereby solving the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The screening and prediction system for mild cognitive impairment in glaucoma patients includes:

[0008] Data collection module, used to collect real-time data of glaucoma patients;

[0009] Analysis and screening module, used to analyze real-time data of glaucoma patients and screen for mild cognitive impairment;

[0010] A degree prediction module is used to predict the degree of mild cognitive impairment of glaucoma patients and determine the prediction result of the degree of mild cognitive impairment of glaucoma patients;

[0011] The treatment control module is used to provide personalized treatment control for mild cognitive impairment in glaucoma patients.

[0012] Preferably, the real-time data of glaucoma patients includes:

[0013] Real-time data of ophthalmological examination: Using virtual reality and computer vision technology, the eyes of glaucoma patients are examined based on an eye tracker to obtain the eye movement trajectory characteristics of glaucoma patients when processing visual information, record the reverse saccade reaction time and reverse saccade error rate, and determine the real-time data of ophthalmological examination;

[0014] Real-time data of imaging examinations: Based on computer tomography or magnetic resonance imaging technology, the brain of glaucoma patients is examined to evaluate the brain structure and function of glaucoma patients, to check whether there are pathological changes related to mild cognitive impairment, and to determine the real-time data of imaging examinations;

[0015] Biomarker Identification Real-Time Data: By analyzing blood, saliva or tear samples from glaucoma patients, the presence of biomarkers associated with mild cognitive impairment, namely inflammatory factors or neurotransmitters, is identified in the samples to determine biomarker identification real-time data.

[0016] Preferably, real-time data of glaucoma patients are analyzed and mild cognitive impairment is screened, including:

[0017] Standard data for glaucoma patients with mild cognitive impairment were prespecified;

[0018] Among them, the standard data of glaucoma patients include standard data of ophthalmological examination, standard data of imaging examination and standard data of biomarker identification;

[0019] Based on the standard data of glaucoma patients, the real-time data of glaucoma patients are analyzed, and mild cognitive impairment is screened to determine the screening results of mild cognitive impairment in glaucoma patients;

[0020] Among them, when the real-time data of the glaucoma patient is within the standard data range of the glaucoma patient, the screening result of the mild cognitive impairment of the glaucoma patient is that the glaucoma patient has mild cognitive impairment behavior;

[0021] Among them, when the real-time data of the glaucoma patient is not within the standard data range of the glaucoma patient, the screening result of mild cognitive impairment in the glaucoma patient is that the glaucoma patient does not have mild cognitive impairment behavior.

[0022] Preferably, the degree prediction module comprises:

[0023] A data collection unit for collecting historical data on mild cognitive impairment in glaucoma patients;

[0024] A model training unit, used to train a prediction model for the degree of mild cognitive impairment in glaucoma patients;

[0025] The degree prediction unit is used to predict the degree of mild cognitive impairment in glaucoma patients.

[0026] Preferably, the data collection unit comprises:

[0027] A historical data extraction module is used to extract the collected historical data of mild cognitive impairment in glaucoma patients;

[0028] A garbled data screening module is used to check whether there is garbled data in the historical data of mild cognitive impairment of the glaucoma patient;

[0029] A garbled code element information extraction module is used to obtain the number of garbled code data when there is garbled code data in the historical data of mild cognitive impairment of glaucoma patients, mark the number of garbled code data as the number of observations, and extract the weight value and garbled code character corresponding to each garbled code data;

[0030] A garbled code influence factor acquisition module is used to obtain the garbled code influence factor by using the weight value and garbled code character corresponding to each garbled code data;

[0031] The garbled code impact factor is obtained by the following formula:

[0032]

[0033] Among them, L represents the garbled code impact factor; n represents the number of garbled code data; U mi Indicates the number of characters corresponding to the i-th garbled data; U ci Indicates the number of characters of normal data corresponding to the i-th garbled data; i Indicates the weight value corresponding to the i-th garbled data; λ b Indicates the standard deviation of the weight values ​​corresponding to n garbled data; min Indicates the minimum weight value corresponding to n garbled data; U b Indicates the standard deviation of the number of characters corresponding to n garbled data; U min Indicates the minimum number of characters corresponding to n garbled data;

[0034] A factor value comparison module, used for comparing the garbled code influence factor with a preset garbled code factor threshold;

[0035] The secondary quality determination module is used to re-retrieve the garbled data when the garbled code influence factor exceeds a preset garbled code factor threshold, and to perform a secondary quality determination on the re-retrieved historical data of mild cognitive impairment in glaucoma patients.

[0036] Preferably, the secondary quality determination module includes:

[0037] A garbled data retrieval module, used for re-retrieving the garbled data to obtain the garbled data when the garbled influence factor exceeds a preset garbled factor threshold;

[0038] A first number comparison module is used to compare the number of the garbled data with a preset data number threshold;

[0039] A first abnormal alarm module is used to issue an abnormal alarm for historical data quality when the number of garbled data exceeds a preset data number threshold;

[0040] A second number comparison module is used to compare the number of the garbled data with the observed number;

[0041] A second abnormal alarm module is used to issue an abnormal alarm for historical data quality when the number of garbled data exceeds the observed number;

[0042] A secondary garbled element extraction module is used to retrieve the weight value and garbled character corresponding to each garbled data when the number of garbled data is lower than the number of observations and lower than a preset data number threshold;

[0043] A module for retrieving the influence factor of random characters is used to retrieve the influence factor of random characters;

[0044] A secondary garbled code factor acquisition module is used to obtain the secondary garbled code factor by using the garbled code influence factor and the weight value and garbled code character corresponding to each current garbled code data;

[0045] The secondary garbled factor is obtained by the following formula:

[0046]

[0047] Among them, L x represents the secondary garbled factor; m represents the number of garbled codes corresponding to the secondary garbled code; λ ei Indicates the weight value corresponding to the i-th garbled data of the secondary garbled code; 01max Indicates the maximum weight value corresponding to n garbled data; λ 02max Indicates the maximum weight value of the m garbled data corresponding to the secondary garbled code; U mei Indicates the length of the number of characters corresponding to the i-th garbled data of the secondary garbled code; bIndicates the standard deviation of the weight values ​​corresponding to n garbled data; U cei The length of the number of characters of the normal data corresponding to the i-th garbled data of the secondary garbled code; P x Indicates the ratio of garbled codes that occur for the first time and are repeated for the second time; L indicates the garbled code impact factor; L0 indicates the preset garbled code factor threshold;

[0048] a third number comparison module, used for comparing the secondary garbled code factor with a preset secondary garbled code factor threshold;

[0049] The third abnormal alarm module is used to issue an abnormal alarm for the quality of historical data when the secondary garbled code factor exceeds a preset secondary garbled code factor threshold.

[0050] Preferably, the historical data of mild cognitive impairment in glaucoma patients includes:

[0051] Behavioral data of mild cognitive impairment in glaucoma patients: Conduct behavioral surveys on the daily living habits, social interactions, and emotional regulation of glaucoma patients to understand their cognitive and behavioral characteristics and obtain behavioral data of mild cognitive impairment in glaucoma patients;

[0052] Cognitive data of mild cognitive impairment in glaucoma patients: The Montreal Cognitive Function Scale was used to test the cognitive function of glaucoma patients to evaluate their memory, attention, language, executive function, recall and orientation, arithmetic, visual memory, processing speed, delayed recall and grammar to determine the cognitive data of mild cognitive impairment in glaucoma patients.

[0053] Preferably, training a prediction model for the degree of mild cognitive impairment in glaucoma patients comprises:

[0054] Data division: The collected historical data of mild cognitive impairment in glaucoma patients were divided into training set and test set according to the ratio of 7:3;

[0055] Model training: Based on deep learning technology, the deep learning model is trained using a training set to determine the prediction model for the degree of mild cognitive impairment in glaucoma patients;

[0056] Model testing: Use the test set to perform performance testing on the mild cognitive impairment prediction model for glaucoma patients to determine whether the mild cognitive impairment prediction model for glaucoma patients can achieve the expected effect and to determine the optimal mild cognitive impairment prediction model for glaucoma patients.

[0057] Preferably, the degree of mild cognitive impairment in glaucoma patients is predicted, including:

[0058] Acquire real-time data of mild cognitive impairment in glaucoma patients, including real-time behavioral data and cognitive data of mild cognitive impairment in glaucoma patients;

[0059] Input the real-time data of mild cognitive impairment in glaucoma patients into the optimal prediction model of mild cognitive impairment in glaucoma patients;

[0060] Based on the optimal prediction model for the degree of mild cognitive impairment in glaucoma patients, the real-time data of mild cognitive impairment in glaucoma patients are analyzed and predicted, the degree of mild cognitive impairment in glaucoma patients is judged, and the prediction results of the degree of mild cognitive impairment in glaucoma patients are determined.

[0061] Preferably, personalized treatment and management of mild cognitive impairment in glaucoma patients is performed; including:

[0062] To obtain the prediction results of mild cognitive impairment in patients with glaucoma;

[0063] Based on the prediction results of the degree of mild cognitive impairment in glaucoma patients, develop a personalized treatment and control plan for mild cognitive impairment in glaucoma patients;

[0064] Among them, for mild glaucoma patients with mild cognitive impairment, psychological therapy and cognitive training are used to treat and control the mild cognitive impairment of glaucoma patients;

[0065] Among them, for severe glaucoma patients with mild cognitive impairment, psychological therapy, cognitive training and drug therapy are used to treat and control the mild cognitive impairment of glaucoma patients;

[0066] When conducting treatment and control on mild cognitive impairment in glaucoma patients, the treatment and control effects of mild cognitive impairment in glaucoma patients are monitored and tracked in real time, and the treatment and control plan is adjusted in real time based on the treatment and control effects.

[0067] Compared with the prior art, the present invention has the following beneficial effects:

[0068] 1. The present invention determines the real-time data of glaucoma patients by collecting real-time data of ophthalmological examinations, real-time data of imaging examinations and real-time data of biomarker identification of glaucoma patients, analyzes the real-time data of glaucoma patients based on standard data of glaucoma patients, screens for mild cognitive impairment, determines the screening results of mild cognitive impairment in glaucoma patients, and can achieve preliminary screening of mild cognitive impairment in glaucoma patients.

[0069] 2. The present invention collects behavioral data and cognitive data of mild cognitive impairment in glaucoma patients, determines historical data of mild cognitive impairment in glaucoma patients, trains a prediction model for the degree of mild cognitive impairment in glaucoma patients based on deep learning technology, analyzes and predicts real-time data of mild cognitive impairment in glaucoma patients based on the prediction model for the degree of mild cognitive impairment in glaucoma patients, judges the degree of mild cognitive impairment in glaucoma patients, and determines the prediction result of the degree of mild cognitive impairment in glaucoma patients, thereby realizing the prediction of the degree of mild cognitive impairment in glaucoma patients.

[0070] 3. The present invention develops a personalized treatment and control plan for mild cognitive impairment in glaucoma patients based on the predicted results of the degree of mild cognitive impairment in glaucoma patients, performs treatment and control on the mild cognitive impairment in glaucoma patients, and when performing treatment and control on the mild cognitive impairment in glaucoma patients, monitors and tracks the treatment and control effects of mild cognitive impairment in glaucoma patients in real time, and adjusts the treatment and control plan in real time based on the treatment and control effects, which can effectively prevent and control the progression of the disease and improve the treatment and control effects of mild cognitive impairment in glaucoma patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 The module schematic diagram of the system for screening and predicting mild cognitive impairment in glaucoma patients of the present invention;

[0072] Figure 2 A flowchart for screening mild cognitive impairment in glaucoma patients of the present invention;

[0073] Figure 3 It is a structural schematic diagram of the degree prediction module of the present invention. DETAILED DESCRIPTION

[0074] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0075] In order to solve the existing problem of inability to effectively screen and predict mild cognitive impairment in glaucoma patients, inability to effectively prevent and control the progression of the disease, and resulting in poor treatment and control of mild cognitive impairment in glaucoma patients, please refer to Figure 1-Figure 3 , this embodiment provides the following technical solutions:

[0076] The mild cognitive impairment screening and prediction system for glaucoma patients includes: data collection module, analysis and screening module, degree prediction module and treatment control module.

[0077] It should be noted that the real-time data of ophthalmic examination, imaging examination and biomarker identification of glaucoma patients are collected through the data acquisition module to determine the real-time data of glaucoma patients; the real-time data of glaucoma patients are analyzed through the analysis and screening module, and mild cognitive impairment is screened to determine the screening results of mild cognitive impairment in glaucoma patients, which can achieve preliminary screening of mild cognitive impairment in glaucoma patients.

[0078] It should be noted that by predicting the degree of mild cognitive impairment in glaucoma patients through the degree prediction module, judging the degree of mild cognitive impairment in glaucoma patients, and determining the prediction results of the degree of mild cognitive impairment in glaucoma patients, the degree of mild cognitive impairment in glaucoma patients can be predicted.

[0079] It should be noted that by formulating personalized treatment and control plans for mild cognitive impairment in glaucoma patients through the treatment and control module, and conducting treatment and control on mild cognitive impairment in glaucoma patients, the progression of the disease can be effectively prevented and controlled, and the treatment and control effects of mild cognitive impairment in glaucoma patients can be improved.

[0080] In this embodiment, as a preferred technical solution of the present invention, the real-time data of glaucoma patients includes:

[0081] Real-time data of ophthalmological examination: Using virtual reality and computer vision technology, the eyes of glaucoma patients are examined based on an eye tracker to obtain the characteristics of eye movement trajectory of glaucoma patients when processing visual information, record the reverse saccade reaction time and reverse saccade error rate, and determine the real-time data of ophthalmological examination;

[0082] Real-time data of imaging examinations: Based on computer tomography or magnetic resonance imaging technology, the brain of glaucoma patients is examined to evaluate the brain structure and function of glaucoma patients, to check whether there are pathological changes related to mild cognitive impairment, and to determine the real-time data of imaging examinations;

[0083] Biomarker Identification Real-Time Data: By analyzing blood, saliva or tear samples from glaucoma patients, the presence of biomarkers associated with mild cognitive impairment, namely inflammatory factors or neurotransmitters, is identified in the samples to determine biomarker identification real-time data.

[0084] It should be noted that virtual reality technology encompasses computers, electronic information, and simulation technology. Its basic implementation method is based on computer technology, utilizing and integrating the latest developments in three-dimensional graphics technology, multimedia technology, simulation technology, display technology, servo technology, and other high-tech technologies. With the help of computers and other equipment, it creates a realistic three-dimensional virtual world with multiple sensory experiences such as vision, touch, and smell, thereby giving people in the virtual world a sense of being immersed in the world.

[0085] It should be noted that the eye tracker is an important instrument for basic research in psychology. It is used to record the characteristics of eye movement trajectories when people process visual information. It is widely used in research in the fields of attention, visual perception, reading, etc. The structure of a modern eye tracker generally includes four systems, namely the optical system, the pupil center coordinate extraction system, the scene and pupil coordinate superposition system, and the image and data recording and analysis system. There are three basic types of eye movements: fixation, saccades, and following movements. Eye movements can reflect the selection pattern of visual information, which is of great significance for revealing the psychological mechanism of cognitive processing. From the research report, the commonly used data or parameters for psychological research using eye trackers mainly include: fixation point trajectory diagram, eye movement time, average speed time and distance of saccade direction, pupil size and blinking.

[0086] Therefore, the eyes of glaucoma patients were examined based on an eye tracker to obtain the eye movement trajectory characteristics of glaucoma patients when processing visual information, record the reverse saccade reaction time and reverse saccade error rate, and determine the real-time data of ophthalmic examination.

[0087] It should be noted that biomarkers refer to biochemical indicators that can mark changes or possible changes in the structure or function of systems, organs, tissues, cells and subcellular structures, and have a very wide range of uses. Biomarkers can be used to diagnose diseases, determine disease stages, or evaluate the safety and effectiveness of new drugs or new therapies in target populations.

[0088] In this embodiment, as a preferred technical solution of the present invention, real-time data of glaucoma patients is analyzed and mild cognitive impairment is screened, including:

[0089] Standard data for glaucoma patients with mild cognitive impairment were prespecified;

[0090] Among them, the standard data of glaucoma patients include standard data of ophthalmological examination, standard data of imaging examination and standard data of biomarker identification;

[0091] Based on the standard data of glaucoma patients, the real-time data of glaucoma patients are analyzed, and mild cognitive impairment is screened to determine the screening results of mild cognitive impairment in glaucoma patients;

[0092] Among them, when the real-time data of the glaucoma patient is within the standard data range of the glaucoma patient, the screening result of the mild cognitive impairment of the glaucoma patient is that the glaucoma patient has mild cognitive impairment behavior;

[0093] Among them, when the real-time data of the glaucoma patient is not within the standard data range of the glaucoma patient, the screening result of mild cognitive impairment in the glaucoma patient is that the glaucoma patient does not have mild cognitive impairment behavior.

[0094] It should be noted that, based on the standard data of glaucoma patients, the real-time data of glaucoma patients are analyzed, and mild cognitive impairment is screened to determine the screening results of mild cognitive impairment in glaucoma patients, which can achieve preliminary screening of mild cognitive impairment in glaucoma patients.

[0095] In this embodiment, as a preferred technical solution of the present invention, the degree prediction module includes:

[0096] A data collection unit for collecting historical data on mild cognitive impairment in glaucoma patients;

[0097] In this embodiment, as a preferred technical solution of the present invention, the historical data of mild cognitive impairment of glaucoma patients includes:

[0098] Behavioral data of mild cognitive impairment in glaucoma patients: Conduct behavioral surveys on the daily living habits, social interactions, and emotional regulation of glaucoma patients to understand their cognitive and behavioral characteristics and obtain behavioral data of mild cognitive impairment in glaucoma patients;

[0099] Cognitive data of mild cognitive impairment in glaucoma patients: The Montreal Cognitive Function Scale was used to test the cognitive function of glaucoma patients to evaluate their memory, attention, language, executive function, recall and orientation, arithmetic, visual memory, processing speed, delayed recall and grammar to determine the cognitive data of mild cognitive impairment in glaucoma patients.

[0100] A model training unit, used to train a prediction model for the degree of mild cognitive impairment in glaucoma patients;

[0101] In this embodiment, as a preferred technical solution of the present invention, training a prediction model for the degree of mild cognitive impairment in glaucoma patients includes:

[0102] Data division: The collected historical data of mild cognitive impairment in glaucoma patients were divided into training set and test set according to the ratio of 7:3;

[0103] Model training: Based on deep learning technology, the deep learning model is trained using a training set to determine the prediction model for the degree of mild cognitive impairment in glaucoma patients;

[0104] Model testing: Use the test set to perform performance testing on the mild cognitive impairment prediction model for glaucoma patients to determine whether the mild cognitive impairment prediction model for glaucoma patients can achieve the expected effect and to determine the optimal mild cognitive impairment prediction model for glaucoma patients.

[0105] The degree prediction unit is used to predict the degree of mild cognitive impairment in glaucoma patients.

[0106] Specifically, the data collection unit includes:

[0107] A historical data extraction module is used to extract the collected historical data of mild cognitive impairment in glaucoma patients;

[0108] A garbled data screening module is used to check whether there is garbled data in the historical data of mild cognitive impairment of the glaucoma patient;

[0109] A garbled code element information extraction module is used to obtain the number of garbled code data when there is garbled code data in the historical data of mild cognitive impairment of glaucoma patients, mark the number of garbled code data as the number of observations, and extract the weight value and garbled code character corresponding to each garbled code data;

[0110] A garbled code influence factor acquisition module is used to obtain the garbled code influence factor by using the weight value and garbled code character corresponding to each garbled code data;

[0111] The garbled code impact factor is obtained by the following formula:

[0112]

[0113] Among them, L represents the garbled code impact factor; n represents the number of garbled code data; U mi Indicates the number of characters corresponding to the i-th garbled data; U ci Indicates the number of characters of normal data corresponding to the i-th garbled data; i Indicates the weight value corresponding to the i-th garbled data; λ b Indicates the standard deviation of the weight values ​​corresponding to n garbled data; min Indicates the minimum weight value corresponding to n garbled data; U b Indicates the standard deviation of the number of characters corresponding to n garbled data; U min Indicates the minimum number of characters corresponding to n garbled data;

[0114] A factor value comparison module, used for comparing the garbled code influence factor with a preset garbled code factor threshold;

[0115] The secondary quality determination module is used to re-retrieve the garbled data when the garbled code influence factor exceeds a preset garbled code factor threshold, and to perform a secondary quality determination on the re-retrieved historical data of mild cognitive impairment in glaucoma patients.

[0116] The technical effect of the above technical solution is: through the historical data extraction module, the historical data of mild cognitive impairment of glaucoma patients can be efficiently collected and extracted, providing a basis for subsequent analysis. The garbled data screening module can timely discover and identify garbled problems in the data, which is an important step in data cleaning and helps to improve the accuracy and reliability of the data. The garbled element information extraction module not only counts the number of garbled data, but also extracts the weight value and garbled characters corresponding to each garbled data, which provides detailed information for the subsequent analysis of garbled problems. By calculating the garbled impact factor L, the technical solution can comprehensively consider multiple dimensions such as the number of garbled data, the number of characters, and the weight value to achieve accurate quantification of the garbled problem. This quantification method helps to more objectively evaluate the impact of garbled on the overall data quality. The factor value comparison module compares the garbled impact factor with the preset garbled factor threshold, which provides a basis for the intelligent determination of data quality. When the garbled impact factor exceeds the threshold, the secondary quality determination module can trigger the process of re-retrieving data and performing secondary quality determination, which helps to timely discover and correct errors in the data and ensure the accuracy and reliability of subsequent analysis. This technical solution achieves effective cleaning and quality control of historical data on mild cognitive impairment in glaucoma patients through a series of modular processing procedures. This not only helps to improve the accuracy of data analysis and research, but also provides higher quality data support for scientific research in related fields.

[0117] In summary, this technical solution effectively improved the quality and analysis accuracy of historical data on mild cognitive impairment in glaucoma patients through refined data processing procedures, intelligent decision support and quantitative garbled code evaluation methods, providing strong support for research and application in related fields.

[0118] Specifically, the secondary quality determination module includes:

[0119] A garbled data retrieval module, used for re-retrieving the garbled data to obtain the garbled data when the garbled influence factor exceeds a preset garbled factor threshold;

[0120] A first number comparison module is used to compare the number of the garbled data with a preset data number threshold;

[0121] A first abnormal alarm module is used to issue an abnormal alarm for historical data quality when the number of garbled data exceeds a preset data number threshold;

[0122] A second number comparison module is used to compare the number of the garbled data with the observed number;

[0123] A second abnormal alarm module is used to issue an abnormal alarm for historical data quality when the number of garbled data exceeds the observed number;

[0124] A secondary garbled element extraction module is used to retrieve the weight value and garbled character corresponding to each garbled data when the number of garbled data is lower than the number of observations and lower than a preset data number threshold;

[0125] A module for retrieving the influence factor of random characters is used to retrieve the influence factor of random characters;

[0126] A secondary garbled code factor acquisition module is used to obtain the secondary garbled code factor by using the garbled code influence factor and the weight value and garbled code character corresponding to each current garbled code data;

[0127] The secondary garbled factor is obtained by the following formula:

[0128]

[0129] Among them, L x represents the secondary garbled factor; m represents the number of garbled codes corresponding to the secondary garbled code; λ ei Indicates the weight value corresponding to the i-th garbled data of the secondary garbled code; 01max Indicates the maximum weight value corresponding to n garbled data; λ 02max Indicates the maximum weight value of the m garbled data corresponding to the secondary garbled code; U mei Indicates the length of the number of characters corresponding to the i-th garbled data of the secondary garbled code; b Indicates the standard deviation of the weight values ​​corresponding to n garbled data; U cei The length of the number of characters of the normal data corresponding to the i-th garbled data of the secondary garbled code; P x Indicates the ratio of garbled codes that occur for the first time and are repeated for the second time; L indicates the garbled code impact factor; L0 indicates the preset garbled code factor threshold;

[0130] a third number comparison module, used for comparing the secondary garbled code factor with a preset secondary garbled code factor threshold;

[0131] The third abnormal alarm module is used to issue an abnormal alarm for the quality of historical data when the secondary garbled code factor exceeds a preset secondary garbled code factor threshold.

[0132] The technical effect of the above technical solution is: through the garbled data retrieval module, when the garbled impact factor exceeds the preset threshold, the garbled data can be accurately retrieved, providing a basis for subsequent analysis and processing. The first number comparison module and the first abnormal alarm module can perform a preliminary quality assessment based on the number of garbled data. When there are too many garbled data, a quality abnormality alarm is issued in time, which helps to timely discover and deal with serious problems in the data. The second number comparison module and the second abnormal alarm module further refine the logic of abnormal detection by comparing the number of garbled data with the number of observations. When the number of re-retrieved garbled data is still too high, the alarm is triggered again, which enhances the reliability of data quality. When the number of garbled data is at a low level, the garbled data is analyzed and processed more deeply through the secondary garbled element extraction module and the secondary garbled factor acquisition module, and the secondary garbled factor formula is used to comprehensively consider multiple factors, including the number of characters, weight values, and the proportion of repeated garbled data, etc., to achieve a comprehensive assessment of the garbled problem. Through the third number comparison module and the third abnormal alarm module, the secondary garbled factor is compared with the preset secondary garbled factor threshold, realizing intelligent data quality judgment. When the secondary garbled factor exceeds the threshold, an alarm is issued in time, which helps to timely discover and correct potential problems in the data. This technical solution significantly improves the quality and accuracy of historical data through refined garbled data processing, multi-level anomaly detection mechanism and intelligent data quality judgment. This not only helps to reduce errors and uncertainties in data analysis and research, but also provides more reliable data support for scientific research in related fields, and promotes the development and progress of related fields.

[0133] In summary, this technical solution achieves comprehensive control and optimization of historical data quality through a series of modular processing flows and multi-level anomaly detection mechanisms, providing higher quality data support for data analysis and research.

[0134] In this embodiment, as a preferred technical solution of the present invention, the degree of mild cognitive impairment of glaucoma patients is predicted, including:

[0135] Acquire real-time data of mild cognitive impairment in glaucoma patients, including real-time behavioral data and cognitive data of mild cognitive impairment in glaucoma patients;

[0136] Input the real-time data of mild cognitive impairment in glaucoma patients into the optimal prediction model of mild cognitive impairment in glaucoma patients;

[0137] Based on the optimal prediction model for the degree of mild cognitive impairment in glaucoma patients, the real-time data of mild cognitive impairment in glaucoma patients are analyzed and predicted, the degree of mild cognitive impairment in glaucoma patients is judged, and the prediction results of the degree of mild cognitive impairment in glaucoma patients are determined.

[0138] It should be noted that, based on deep learning technology, a prediction model for the degree of mild cognitive impairment in glaucoma patients is trained, and the real-time data of mild cognitive impairment in glaucoma patients is analyzed and predicted based on the prediction model for the degree of mild cognitive impairment in glaucoma patients, so as to judge the degree of mild cognitive impairment in glaucoma patients and determine the prediction results of the degree of mild cognitive impairment in glaucoma patients, thereby realizing the prediction of the degree of mild cognitive impairment in glaucoma patients.

[0139] In this embodiment, as a preferred technical solution of the present invention, personalized treatment and control of mild cognitive impairment in glaucoma patients is performed; including:

[0140] To obtain the prediction results of mild cognitive impairment in patients with glaucoma;

[0141] Based on the prediction results of the degree of mild cognitive impairment in glaucoma patients, develop a personalized treatment and control plan for mild cognitive impairment in glaucoma patients;

[0142] Among them, for mild glaucoma patients with mild cognitive impairment, psychological therapy and cognitive training are used to treat and control the mild cognitive impairment of glaucoma patients;

[0143] Among them, for severe glaucoma patients with mild cognitive impairment, psychological therapy, cognitive training and drug therapy are used to treat and control the mild cognitive impairment of glaucoma patients;

[0144] When conducting treatment and control on mild cognitive impairment in glaucoma patients, the treatment and control effects of mild cognitive impairment in glaucoma patients are monitored and tracked in real time, and the treatment and control plan is adjusted in real time based on the treatment and control effects.

[0145] It should be noted that by using a treatment control plan to control and treat mild cognitive impairment in glaucoma patients, and by monitoring and tracking the treatment control effects of mild cognitive impairment in glaucoma patients in real time, and adjusting the treatment control plan in real time based on the treatment control effects, the progression of the disease can be effectively prevented and controlled, and the treatment control effects of mild cognitive impairment in glaucoma patients can be improved.

[0146] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0147] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A screening and prediction system for mild cognitive impairment in glaucoma patients, characterized in that: include: Data collection module, used to collect real-time data of glaucoma patients; Analysis and screening module, used to analyze real-time data of glaucoma patients and screen for mild cognitive impairment; A degree prediction module is used to predict the degree of mild cognitive impairment of glaucoma patients and determine the prediction result of the degree of mild cognitive impairment of glaucoma patients; The treatment control module is used to provide personalized treatment control for mild cognitive impairment in glaucoma patients.

2. The system for screening and predicting mild cognitive impairment in glaucoma patients according to claim 1, characterized in that: The real-time data of glaucoma patients include: Real-time data of ophthalmological examination: Using virtual reality and computer vision technology, the eyes of glaucoma patients are examined based on an eye tracker to obtain the eye movement trajectory characteristics of glaucoma patients when processing visual information, record the reverse saccade reaction time and reverse saccade error rate, and determine the real-time data of ophthalmological examination; Real-time data of imaging examinations: Based on computer tomography or magnetic resonance imaging technology, the brain of glaucoma patients is examined to evaluate the brain structure and function of glaucoma patients, to check whether there are pathological changes related to mild cognitive impairment, and to determine the real-time data of imaging examinations; Biomarker Identification Real-Time Data: Biomarker identification real-time data is determined by analyzing blood, saliva or tear samples from glaucoma patients to identify the presence of biomarkers associated with mild cognitive impairment in the samples.

3. The system for screening and predicting mild cognitive impairment in glaucoma patients according to claim 2, characterized in that: Analyze real-time data of glaucoma patients and screen for mild cognitive impairment, including: Standard data for glaucoma patients with mild cognitive impairment were prespecified; Among them, the standard data of glaucoma patients include standard data of ophthalmological examination, standard data of imaging examination and standard data of biomarker identification; Based on the standard data of glaucoma patients, the real-time data of glaucoma patients are analyzed, and mild cognitive impairment is screened to determine the screening results of mild cognitive impairment in glaucoma patients; Among them, when the real-time data of the glaucoma patient is within the standard data range of the glaucoma patient, the screening result of the mild cognitive impairment of the glaucoma patient is that the glaucoma patient has mild cognitive impairment behavior; Among them, when the real-time data of the glaucoma patient is not within the standard data range of the glaucoma patient, the screening result of mild cognitive impairment in the glaucoma patient is that the glaucoma patient does not have mild cognitive impairment behavior.

4. The system for screening and predicting mild cognitive impairment in glaucoma patients according to claim 3, characterized in that: The degree prediction module comprises: A data collection unit for collecting historical data on mild cognitive impairment in glaucoma patients; A model training unit, used to train a prediction model for the degree of mild cognitive impairment in glaucoma patients; The degree prediction unit is used to predict the degree of mild cognitive impairment in glaucoma patients.

5. The system for screening and predicting mild cognitive impairment in glaucoma patients according to claim 4, characterized in that: Data collection unit, including: A historical data extraction module is used to extract the collected historical data of mild cognitive impairment in glaucoma patients; A garbled data screening module is used to check whether there is garbled data in the historical data of mild cognitive impairment of the glaucoma patient; A garbled code element information extraction module is used to obtain the number of garbled code data when there is garbled code data in the historical data of mild cognitive impairment of glaucoma patients, mark the number of garbled code data as the number of observations, and extract the weight value and garbled code character corresponding to each garbled code data; A garbled code influence factor acquisition module is used to obtain the garbled code influence factor by using the weight value and garbled code character corresponding to each garbled code data; The garbled code impact factor is obtained by the following formula: Among them, L represents the garbled code impact factor; n represents the number of garbled code data; U mi Indicates the number of characters corresponding to the i-th garbled data; U ci Indicates the number of characters of normal data corresponding to the i-th garbled data; i Indicates the weight value corresponding to the i-th garbled data; λ b Indicates the standard deviation of the weight values ​​corresponding to n garbled data; min Indicates the minimum weight value corresponding to n garbled data; U b Indicates the standard deviation of the number of characters corresponding to n garbled data; U min Indicates the minimum number of characters corresponding to n garbled data; A factor value comparison module, used for comparing the garbled code influence factor with a preset garbled code factor threshold; The secondary quality determination module is used to re-retrieve the garbled data when the garbled code influence factor exceeds a preset garbled code factor threshold, and to perform a secondary quality determination on the re-retrieved historical data of mild cognitive impairment in glaucoma patients.

6. The system for screening and predicting mild cognitive impairment in glaucoma patients according to claim 5, characterized in that: Secondary quality determination module, including: A garbled data retrieval module, used for re-retrieving the garbled data to obtain the garbled data when the garbled influence factor exceeds a preset garbled factor threshold; A first number comparison module is used to compare the number of the garbled data with a preset data number threshold; A first abnormal alarm module is used to issue an abnormal alarm for historical data quality when the number of garbled data exceeds a preset data number threshold; A second number comparison module is used to compare the number of the garbled data with the observed number; A second abnormal alarm module is used to issue an abnormal alarm for historical data quality when the number of garbled data exceeds the observed number; A secondary garbled element extraction module is used to retrieve the weight value and garbled character corresponding to each garbled data when the number of garbled data is lower than the number of observations and lower than a preset data number threshold; A module for retrieving the influence factor of random characters is used to retrieve the influence factor of random characters; A secondary garbled code factor acquisition module is used to obtain the secondary garbled code factor by using the garbled code influence factor and the weight value and garbled code character corresponding to each current garbled code data; The secondary garbled factor is obtained by the following formula: Among them, L x represents the secondary garbled factor; m represents the number of garbled codes corresponding to the secondary garbled code; λ ei Indicates the weight value corresponding to the i-th garbled data of the secondary garbled code; 01max Indicates the maximum weight value corresponding to n garbled data; λ 02max Indicates the maximum weight value of the m garbled data corresponding to the secondary garbled code; U mei Indicates the length of the number of characters corresponding to the i-th garbled data of the secondary garbled code; b Indicates the standard deviation of the weight values ​​corresponding to n garbled data; U cei The length of the number of characters of the normal data corresponding to the i-th garbled data of the secondary garbled code; P x Indicates the ratio of garbled codes that occur for the first time and are repeated for the second time; L indicates the garbled code impact factor; L0 indicates the preset garbled code factor threshold; a third number comparison module, used for comparing the secondary garbled code factor with a preset secondary garbled code factor threshold; The third abnormal alarm module is used to issue an abnormal alarm for the quality of historical data when the secondary garbled code factor exceeds a preset secondary garbled code factor threshold.

7. The system for screening and predicting mild cognitive impairment in glaucoma patients according to claim 4, characterized in that: The historical data of mild cognitive impairment in glaucoma patients include: Behavioral data of mild cognitive impairment in glaucoma patients: Conduct behavioral surveys on the daily living habits, social interactions, and emotional regulation of glaucoma patients to understand their cognitive behavioral characteristics and obtain behavioral data of mild cognitive impairment in glaucoma patients; Cognitive data of mild cognitive impairment in glaucoma patients: The Montreal Cognitive Function Scale was used to test the cognitive function of glaucoma patients to evaluate their memory, attention, language, executive function, recall and orientation, arithmetic, visual memory, processing speed, delayed recall and grammar to determine the cognitive data of mild cognitive impairment in glaucoma patients.

8. The system for screening and predicting mild cognitive impairment in glaucoma patients according to claim 7, characterized in that: Training a model to predict the degree of mild cognitive impairment in glaucoma patients, including: Data division: The collected historical data of mild cognitive impairment in glaucoma patients were divided into training set and test set according to the ratio of 7:3; Model training: Based on deep learning technology, the deep learning model is trained using a training set to determine the prediction model for the degree of mild cognitive impairment in glaucoma patients; Model testing: Use the test set to perform performance testing on the mild cognitive impairment prediction model for glaucoma patients to determine whether the mild cognitive impairment prediction model for glaucoma patients can achieve the expected effect and to determine the optimal mild cognitive impairment prediction model for glaucoma patients.

9. The system for screening and predicting mild cognitive impairment in glaucoma patients according to claim 8, characterized in that: Prediction of the degree of mild cognitive impairment in patients with glaucoma, including: Acquire real-time data of mild cognitive impairment in glaucoma patients, including real-time behavioral data and cognitive data of mild cognitive impairment in glaucoma patients; Input the real-time data of mild cognitive impairment in glaucoma patients into the optimal prediction model of mild cognitive impairment in glaucoma patients; Based on the optimal prediction model for the degree of mild cognitive impairment in glaucoma patients, the real-time data of mild cognitive impairment in glaucoma patients are analyzed and predicted, the degree of mild cognitive impairment in glaucoma patients is judged, and the prediction results of the degree of mild cognitive impairment in glaucoma patients are determined.

10. The system for screening and predicting mild cognitive impairment in glaucoma patients according to claim 9, characterized in that: Personalized treatment management for mild cognitive impairment in glaucoma patients; including: To obtain the prediction results of mild cognitive impairment in patients with glaucoma; Based on the prediction results of the degree of mild cognitive impairment in glaucoma patients, develop a personalized treatment and control plan for mild cognitive impairment in glaucoma patients; Among them, for mild glaucoma patients with mild cognitive impairment, psychological therapy and cognitive training are used to treat and control the mild cognitive impairment of glaucoma patients; Among them, for severe glaucoma patients with mild cognitive impairment, psychological therapy, cognitive training and drug therapy are used to treat and control the mild cognitive impairment of glaucoma patients; When conducting treatment and control on mild cognitive impairment in glaucoma patients, the treatment and control effects of mild cognitive impairment in glaucoma patients are monitored and tracked in real time, and the treatment and control plan is adjusted in real time based on the treatment and control effects.

Images