Self-management intervention system for glaucoma patient based on HAPA theory

Abstract

The invention discloses a glaucoma patient self-management intervention system based on the HAPA theory, and belongs to the technical field of glaucoma, and the system comprises a patient data collection and processing module which is used for collecting and processing real-time data of a glaucoma patient; the disease progression risk assessment module is used for performing risk assessment on disease progression of the glaucoma patient; the self-management multi-stage intervention module is used for carrying out self-management multi-stage intervention on the glaucoma patient; and the regular evaluation wake-up intervention module is used for regularly evaluating the self-management state of the glaucoma patient and timely providing wake-up intervention. The problem that the self-management intervention effect of the glaucoma patient is poor due to the fact that self-management intervention cannot be performed on the glaucoma patient based on the HAPA theory in the prior art is solved. Self-management intervention is carried out on the glaucoma patient based on the HAPA theory, the disease cognition, treatment compliance and life quality of the patient can be effectively improved, and the self-management intervention effect of the glaucoma patient can be improved.

Description

Technical Field

[0001] This invention relates to the field of glaucoma technology, specifically to a glaucoma patient self-management intervention system based on the HAPA theory. Background Technology

[0002] Glaucoma is a blinding eye disease primarily caused by increased intraocular pressure leading to damage to the optic nerve. It is the second leading cause of blindness worldwide, after cataracts, and the leading cause of irreversible blindness. Therefore, self-management interventions for glaucoma patients are particularly important.

[0003] Chinese patent application CN120147224A discloses a multimodal intelligent glaucoma identification method and system based on transfer learning. This method simulates retinal changes in glaucoma patients at multiple stages of disease progression, captures visual features of pathological characteristics at these stages, extracts and compares visual features from the patient's fundus images, assesses the stage of disease progression, optimizes the feature recognition process using transfer learning, improves the model's generalization ability and diagnostic accuracy, and achieves accurate assessment of visual impairment by combining intraocular pressure measurement and prediction. However, this patent has the following drawbacks: Existing technologies cannot provide self-management interventions for glaucoma patients based on the HAPA theory, and cannot effectively improve patients' disease awareness, treatment adherence, and quality of life, resulting in poor self-management intervention outcomes for glaucoma patients. Summary of the Invention

[0004] The purpose of this invention is to provide a glaucoma patient self-management intervention system based on the HAPA theory. Self-management intervention for glaucoma patients based on the HAPA theory can effectively improve patients' disease awareness, treatment compliance, and quality of life, thereby enhancing the effectiveness of glaucoma patient self-management intervention and solving the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: A glaucoma patient self-management intervention system based on the HAPA theory includes: The patient data acquisition and processing module is used to collect real-time data of glaucoma patients and process the real-time data of glaucoma patients to determine the characteristic data of glaucoma patients. The disease progression risk assessment module is used to assess the risk of disease progression in glaucoma patients and generate a glaucoma patient disease progression risk assessment report. The self-management multi-stage intervention module is used to conduct multi-stage self-management intervention for glaucoma patients based on the HAPA theory. The periodic assessment and awakening intervention module is used to periodically assess the self-management status of glaucoma patients and provide awakening intervention as appropriate.

[0006] Preferably, a risk assessment of disease progression in glaucoma patients is performed, a glaucoma patient disease progression risk assessment report is generated, and the following operations are performed: A risk assessment model for glaucoma patient disease progression was constructed using machine learning algorithms and combined with historical data of glaucoma patients. Deploy a risk assessment model for glaucoma patient disease progression, and place the model in a real-world glaucoma patient disease progression risk assessment environment. The characteristic data of glaucoma patients are input into the glaucoma patient disease progression risk assessment model. The model analyzes the characteristic data of glaucoma patients and automatically assesses the risk of disease progression, thereby generating a glaucoma patient disease progression risk assessment report.

[0007] Preferably, a multi-stage intervention for glaucoma patients' self-management based on the HAPA theory is implemented by performing the following operations: The glaucoma patient disease progression risk assessment report helps glaucoma patients understand the possible consequences of disease progression, enhances their willingness to engage in healthy behaviors, and vividly explains the principles, dangers, and consequences of not treating glaucoma through text, short videos, or animations, emphasizing the importance of self-management to glaucoma patients. Based on the HAPA theory, we can identify glaucoma patients' misconceptions or denials about the disease, clarify the stage of glaucoma, and help them identify specific obstacles that may hinder the implementation of their treatment plan. According to the cognitive, belief, and behavioral stages of glaucoma patients, we can provide self-management interventions suitable for their condition and lifestyle. Based on these self-management interventions, we can help glaucoma patients manage their poor treatment adherence and emotional fluctuations.

[0008] Preferably, glaucoma patients undergo self-management intervention based on self-management intervention measures, and the following operations are performed: Through app push notifications, smart pillboxes, and wearable devices, glaucoma patients are reminded to take their medication and have follow-up examinations. Their behavior is recorded, and positive behaviors are immediately acknowledged and rewarded with points to create positive feedback. Frequently asked questions are quickly searched and answered, and psychological counseling and support are provided in a timely manner to address negative emotions in glaucoma patients.

[0009] Preferably, the self-management status of glaucoma patients is regularly assessed and timely awakening interventions are provided, including the following: Set up an online consultation portal and connect with doctors or health consultants to provide timely emotional support and psychological intervention for glaucoma patients; Real-time monitoring of glaucoma patients' self-management intervention is conducted, and their self-management status is regularly assessed. Negligence or behavioral deviations in glaucoma patients are identified, and timely reminders and suggestions are provided to awaken their awareness of treatment.

[0010] Preferably, a glaucoma patient disease progression risk assessment model is constructed using machine learning algorithms and combined with historical data of glaucoma patients, and the following operations are performed: Collect and segment historical data of glaucoma patients, dividing the historical data of glaucoma patients into training set and test set; Machine learning algorithms are used to train a machine learning model using a training set. The machine learning model learns autonomously from the training set the risk assessment behavior of glaucoma patients' disease progression and performs risk assessment of glaucoma patients' disease progression, thus determining the risk assessment model for glaucoma patients' disease progression. The model for assessing the risk of glaucoma disease progression was tested using a test set to evaluate whether it could achieve the expected effect of assessing the risk of glaucoma disease progression and to determine the model test evaluation results. When the risk assessment model for glaucoma disease progression fails to achieve the expected results in assessing the risk of glaucoma disease progression, the parameters of the risk assessment model for glaucoma disease progression are adjusted and optimized until the risk assessment model for glaucoma disease progression achieves the expected results in assessing the risk of glaucoma disease progression, thereby determining the optimal risk assessment model for glaucoma disease progression.

[0011] Preferably, real-time data from glaucoma patients is collected, and the following operations are performed: By connecting to the hospital's HIS system, we can obtain the medical records, intraocular pressure curves, and visual field examination results of glaucoma patients in real time and collect clinical data of glaucoma patients. We collected real-time data on the family history, eye habits, and daily activities of glaucoma patients through questionnaires. Real-time data for glaucoma patients was determined based on their clinical and lifestyle data.

[0012] Preferably, the real-time data of glaucoma patients is processed by performing the following operations: The real-time data of glaucoma patients was cleaned to remove noise unrelated to the self-management intervention of glaucoma patients, and missing and outlier values ​​related to the self-management intervention of glaucoma patients were processed. The real-time data of glaucoma patients is transformed to remove the dimensional differences in the real-time data of glaucoma patients and form standardized real-time data of glaucoma patients. Feature extraction was performed on real-time data of glaucoma patients to extract features related to self-management intervention of glaucoma patients and to determine the characteristic data of glaucoma patients.

[0013] Preferred self-management multi-stage intervention modules include: The first intervention submodule of the motivation activation phase is used to conduct an initial assessment of the glaucoma knowledge level of glaucoma patients based on a glaucoma knowledge questionnaire, determine the initial assessment results, obtain the baseline data of glaucoma patients, and transform the initial assessment results and the baseline data of glaucoma patients into personalized risk reports based on the risk perception elements in the HAPA theory. The second intervention submodule of the motivation activation phase is used to match glaucoma patients with successful management experiences of glaucoma patients with similar conditions based on personalized risk reports and collaborative filtering recommendation algorithms, and to enhance glaucoma patients' self-management awareness based on the successful management experiences. The first intervention submodule in the action execution phase is used to generate a daily self-management plan after glaucoma patients have developed self-management awareness. Based on glaucoma diagnosis and treatment guidelines and combined with individual differences among glaucoma patients, a multi-dimensional objective function is constructed, and multi-dimensional constraints are integrated to generate the plan. The daily self-management plan includes a physiological indicator monitoring plan and a behavior execution plan. The second intervention submodule in the action execution phase is used to acquire real-time execution data of the physiological indicator monitoring plan and behavior execution plan, and generate behavior execution record data; construct an intraocular pressure prediction LSTM network, with the input layer including historical intraocular pressure sequences, environmental variables and behavioral variables, outputting the predicted intraocular pressure value for the future time period, and calculating the prediction deviation range. The deviation range threshold for glaucoma patients is dynamically adjusted based on the intraocular pressure fluctuation cycle of glaucoma patients; when it is determined that the deviation between the actual measured intraocular pressure of a glaucoma patient and the preset target value exceeds the acceptable range, the system immediately triggers an early warning intervention mechanism. The first intervention submodule in the maintenance and optimization phase is used to acquire and analyze behavioral execution records of glaucoma patients within a preset time period to identify weaknesses in their self-management process. Using the K-means clustering algorithm, glaucoma patients with similar weaknesses are grouped into a weak group. Common characteristics within this group are extracted to generate a targeted group-based intervention template. This template is then combined with the specific data of individual glaucoma patients to generate personalized intervention templates. Based on these personalized intervention templates, the self-management process of glaucoma patients is dynamically adjusted and intervened. The second intervention submodule in the maintenance and optimization phase is used to introduce a penalty indicator when glaucoma patients fail to perform self-management behaviors as planned. The system calculates the penalty indicator for deviations in self-management behaviors. When the penalty indicator for deviations exceeds a preset deviation threshold, the system pushes targeted educational content to glaucoma patients to strengthen their behavioral awareness.

[0014] Preferably, the periodic evaluation of the awakening intervention module includes: The first acquisition submodule is used to acquire the core daily self-management behavior types of glaucoma patients within a preset time period; the core daily self-management behavior types include intraocular pressure monitoring, medication adherence, and rest management. The judgment submodule is used to judge the information on intraocular pressure monitoring, medication adherence and rest management, and to determine the number of non-standard behaviors in the information on intraocular pressure monitoring, medication adherence and rest management; The assessment submodule is used to evaluate glaucoma patients from the dimensions of basic management and key event management based on intraocular pressure monitoring, medication adherence, rest and activity management information, and information on the number of non-standard behaviors, and to determine the self-management status score of glaucoma patients. in, This indicates the self-management status score of glaucoma patients; This indicates the number of irregularities in the i-th category of daily self-management behavior; This represents the total number of times the i-th type of daily self-management behavior was performed; Indicates the weighting coefficients for the basic management dimensions; Indicates the weighting coefficient for the critical incident management dimension; This represents the weight of the difficulty and importance of self-management in the t-th critical event; This represents the effectiveness value of self-management during the t-th critical event; This indicates the total number of times a critical incident was self-managed; The wake-up submodule is used to compare the self-management status score with a preset score threshold. When the self-management status score is determined to be less than the preset score threshold, a wake-up prompt is issued to promptly awaken the glaucoma patient's awareness of treatment.

[0015] Compared with the prior art, the beneficial effects of the present invention are: 1. This invention collects and processes real-time data from glaucoma patients to determine their characteristic data. It then uses machine learning algorithms and combines them with historical data to construct a risk assessment model for glaucoma patient disease progression. Based on this model, the invention analyzes the characteristic data of glaucoma patients and automatically assesses the risk of disease progression, thereby generating a risk assessment report for glaucoma patient disease progression.

[0016] 2. This invention vividly explains the principles, dangers, and consequences of not treating glaucoma through text, short videos, or animations. It emphasizes the importance of self-management to glaucoma patients, identifies glaucoma patients' misconceptions or denials about the disease based on the HAPA theory, clarifies the stage of glaucoma patients, helps glaucoma patients identify specific obstacles that may hinder the implementation of their plans, and provides self-management interventions suitable for the glaucoma patients' condition and lifestyle based on their cognitive, belief, and behavioral stages.

[0017] 3. This invention reminds glaucoma patients of medication and follow-up examinations through APP push notifications, smart pillboxes, and wearable devices, and records the behavior of glaucoma patients. Positive behaviors are immediately acknowledged and rewarded with points, creating positive feedback. It also provides quick access to answers to frequently asked questions, offers timely psychological counseling and support for negative emotions, and provides timely emotional support and psychological intervention by setting up online consultation portals and connecting with doctors or health consultants. Furthermore, it regularly assesses the self-management status of glaucoma patients, identifies apathetic or behavioral deviations, and provides timely alerting interventions through push notifications and suggestions, promptly awakening patients' treatment awareness. Based on the HAPA theory, this invention can effectively improve patients' disease awareness, treatment adherence, and quality of life, thus enhancing the effectiveness of self-management interventions for glaucoma patients. Attached Figure Description

[0018] Figure 1 This is a flowchart of the module of the glaucoma patient self-management intervention system based on HAPA theory of the present invention. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] To address the current limitations of HAPA (Hyper-Hyper-Age Patient Self-Management) interventions for glaucoma patients, which fail to effectively improve patient disease awareness, treatment adherence, and quality of life, resulting in poor outcomes from glaucoma patient self-management interventions, please refer to [link to relevant documentation]. Figure 1 This embodiment provides the following technical solution: A glaucoma patient self-management intervention system based on the HAPA theory includes: The patient data acquisition and processing module is used to collect real-time data of glaucoma patients and process the real-time data of glaucoma patients to determine the characteristic data of glaucoma patients.

[0021] In this embodiment, real-time data from glaucoma patients is collected, and the following operations are performed: By connecting to the hospital's HIS system, we can obtain the medical records, intraocular pressure curves, and visual field examination results of glaucoma patients in real time and collect clinical data of glaucoma patients. We collected real-time data on the family history, eye habits, and daily activities of glaucoma patients through questionnaires. Based on clinical and lifestyle data of glaucoma patients, real-time data of glaucoma patients is determined to provide a data foundation for subsequent risk assessment of disease progression.

[0022] In this embodiment, real-time data of glaucoma patients is processed by performing the following operations: Cleaning real-time data of glaucoma patients to remove noise unrelated to their self-management interventions, and processing missing and outlier values ​​related to their self-management interventions, can improve the data quality of real-time data of glaucoma patients. The real-time data of glaucoma patients is transformed to remove the dimensional differences in the real-time data of glaucoma patients and form standardized real-time data of glaucoma patients. Feature extraction was performed on real-time data of glaucoma patients to extract features related to self-management intervention of glaucoma patients and to determine the characteristic data of glaucoma patients.

[0023] It should be noted that by cleaning, transforming and extracting features from real-time data of glaucoma patients, the characteristic data of glaucoma patients can be further identified, which facilitates better analysis of the characteristic data of glaucoma patients in the future. This will enable automatic risk assessment of disease progression in glaucoma patients and generate a risk assessment report on disease progression in glaucoma patients.

[0024] The disease progression risk assessment module is used to assess the risk of disease progression in glaucoma patients and generate a glaucoma patient disease progression risk assessment report.

[0025] In this embodiment, a glaucoma patient disease progression risk assessment model is constructed using machine learning algorithms and combined with historical data of glaucoma patients, and the following operations are performed: Collect and segment historical data of glaucoma patients, dividing the historical data of glaucoma patients into training set and test set; Machine learning algorithms are used to train a machine learning model using a training set. The machine learning model learns autonomously from the training set the risk assessment behavior of glaucoma patients' disease progression and performs risk assessment of glaucoma patients' disease progression, thus determining the risk assessment model for glaucoma patients' disease progression. The model for assessing the risk of glaucoma disease progression was tested using a test set to evaluate whether it could achieve the expected effect of assessing the risk of glaucoma disease progression and to determine the model test evaluation results. When the risk assessment model for glaucoma disease progression fails to achieve the expected results in assessing the risk of glaucoma disease progression, the parameters of the risk assessment model for glaucoma disease progression are adjusted and optimized until the risk assessment model for glaucoma disease progression achieves the expected results in assessing the risk of glaucoma disease progression, thereby determining the optimal risk assessment model for glaucoma disease progression.

[0026] In this embodiment, a risk assessment of disease progression in glaucoma patients is performed, and a glaucoma patient disease progression risk assessment report is generated. The following operations are performed: Deploy a risk assessment model for glaucoma patient disease progression, and place the model in a real-world glaucoma patient disease progression risk assessment environment. The characteristic data of glaucoma patients are input into the glaucoma patient disease progression risk assessment model. The model analyzes the characteristic data of glaucoma patients and automatically assesses the risk of disease progression, thereby generating a glaucoma patient disease progression risk assessment report.

[0027] The self-management multi-stage intervention module is used to conduct multi-stage self-management intervention for glaucoma patients based on the HAPA theory.

[0028] In this embodiment, a multi-stage intervention for glaucoma patients' self-management based on the HAPA theory is implemented, and the following operations are performed: The glaucoma patient disease progression risk assessment report helps glaucoma patients understand the possible consequences of disease progression, enhances their willingness to engage in healthy behaviors, and vividly explains the principles, dangers, and consequences of not treating glaucoma through text, short videos, or animations, emphasizing the importance of self-management to glaucoma patients. Based on the HAPA theory, identify glaucoma patients' misconceptions or denials about the disease, clarify the stage of glaucoma patients, and help glaucoma patients identify specific obstacles that may hinder the implementation of the plan.

[0029] It should be noted that the main obstacles faced by glaucoma patients include: 1) Cognitive impairment: Misconception: Some patients believe that glaucoma does not require long-term treatment or will not cause blindness.

[0030] Denial: Patients may ignore early symptoms due to the insidious nature of the disease.

[0031] 2) Psychological barriers: Negative emotions, such as anxiety and depression, may affect treatment adherence.

[0032] Fear: worry about vision loss or disease progression.

[0033] 3) Behavioral disorders: Poor medication adherence: such as stopping medication without authorization or not taking medication as prescribed.

[0034] Lifestyle issues: such as staying up late, excessive screen time, and other bad habits.

[0035] Furthermore, based on the cognitive, belief, and behavioral stages of glaucoma patients, self-management intervention measures suitable for their condition and lifestyle are provided. These measures help glaucoma patients manage their condition and cope with poor treatment adherence and emotional fluctuations.

[0036] It should be noted that the HAPA theory divides the change of health behaviors into three stages, each with its key elements. The three stages are as follows: Pre-concept stage: The patient's perception of the importance of the disease (such as risk perception) and attitude.

[0037] Intention phase: Patients develop an action plan and assess their ability to execute it (e.g., self-efficacy).

[0038] Action phase: Patients implement healthy behaviors while addressing potential obstacles.

[0039] In this embodiment, the application of the HAPA theory in glaucoma patients is mainly reflected as shown in Table 1:

[0040] Therefore, self-management interventions for glaucoma patients based on the HAPA theory can effectively improve patients' disease awareness, treatment adherence, and quality of life, thereby enhancing the effectiveness of self-management interventions for glaucoma patients.

[0041] In this embodiment, glaucoma patients undergo self-management intervention based on self-management intervention measures, and the following operations are performed: Through APP push notifications, smart pillboxes, and wearable devices, glaucoma patients are reminded to take their medication and have follow-up examinations. Their behavior is recorded, and positive behaviors are immediately recognized and rewarded with points to create positive feedback. The system also provides quick access to answers to common questions (such as medication side effects and what to do if medication is forgotten). In response to negative emotions, the system provides timely psychological counseling and support.

[0042] The periodic assessment and awakening intervention module is used to periodically assess the self-management status of glaucoma patients and provide awakening intervention as appropriate.

[0043] In this embodiment, the self-management status of glaucoma patients is regularly assessed and timely awakening interventions are provided, including the following operations: Set up an online consultation portal and connect with doctors or health consultants to provide timely emotional support and psychological intervention for glaucoma patients; Real-time monitoring of glaucoma patients' self-management intervention is conducted, and their self-management status is regularly assessed. Negligence or behavioral deviations in glaucoma patients are identified, and timely reminders and suggestions are provided to awaken their awareness of treatment.

[0044] In summary, self-management interventions for glaucoma patients based on the HAPA theory can effectively improve patients' disease awareness, treatment adherence, and quality of life, thereby enhancing the effectiveness of self-management interventions for glaucoma patients.

[0045] In this embodiment, the self-management multi-stage intervention module includes: The first intervention submodule of the motivation activation phase is used to conduct an initial assessment of the glaucoma knowledge level of glaucoma patients based on a glaucoma knowledge questionnaire, determine the initial assessment results, obtain the baseline data of glaucoma patients, and transform the initial assessment results and the baseline data of glaucoma patients into personalized risk reports based on the risk perception elements in the HAPA theory. The second intervention submodule of the motivation activation phase is used to match glaucoma patients with successful management experiences of glaucoma patients with similar conditions based on personalized risk reports and collaborative filtering recommendation algorithms, and to enhance glaucoma patients' self-management awareness based on the successful management experiences. The first intervention submodule in the action execution phase is used to generate a daily self-management plan after glaucoma patients have developed self-management awareness. Based on glaucoma diagnosis and treatment guidelines and combined with individual differences among glaucoma patients, a multi-dimensional objective function is constructed, and multi-dimensional constraints are integrated to generate the plan. The daily self-management plan includes a physiological indicator monitoring plan and a behavior execution plan. The second intervention submodule in the action execution phase is used to acquire real-time execution data of the physiological indicator monitoring plan and behavior execution plan, and generate behavior execution record data; construct an intraocular pressure prediction LSTM network, with the input layer including historical intraocular pressure sequences, environmental variables and behavioral variables, outputting the predicted intraocular pressure value for the future time period, and calculating the prediction deviation range. The deviation range threshold for glaucoma patients is dynamically adjusted based on the intraocular pressure fluctuation cycle of glaucoma patients; when it is determined that the deviation between the actual measured intraocular pressure of a glaucoma patient and the preset target value exceeds the acceptable range, the system immediately triggers an early warning intervention mechanism. The first intervention submodule in the maintenance and optimization phase is used to acquire and analyze behavioral execution records of glaucoma patients within a preset time period to identify weaknesses in their self-management process. Using the K-means clustering algorithm, glaucoma patients with similar weaknesses are grouped into a weak group. Common characteristics within this group are extracted to generate a targeted group-based intervention template. This template is then combined with the specific data of individual glaucoma patients to generate personalized intervention templates. Based on these personalized intervention templates, the self-management process of glaucoma patients is dynamically adjusted and intervened. The second intervention submodule in the maintenance and optimization phase is used to introduce a penalty indicator when glaucoma patients fail to perform self-management behaviors as planned. The system calculates the penalty indicator for deviations in self-management behaviors. When the penalty indicator for deviations exceeds a preset deviation threshold, the system pushes targeted educational content to glaucoma patients to strengthen their behavioral awareness.

[0046] In this embodiment, baseline data refers to benchmark data that is comprehensively collected and recorded on the research object or system at a specific point in time, and is used for subsequent analysis, comparison and evaluation.

[0047] In this embodiment, based on the risk perception elements in the HAPA theory, natural language generation technology is used to transform the assessment results and baseline data of glaucoma patients into personalized risk reports. For example, the report may state, "Your current intraocular pressure fluctuation risk is high, which is closely related to irregular medication use," thereby enhancing the patient's intuitive understanding of their own disease risk.

[0048] In this embodiment, the collaborative filtering recommendation algorithm is a core technology that achieves personalized recommendations based on user group behavior data by analyzing the preferences of similar users or items.

[0049] In this embodiment, the multi-dimensional constraints include lifestyle constraints, such as the frequency of exercise for patients over 65 years of age, and avoiding strenuous exercise.

[0050] In this embodiment, the physiological indicator monitoring plan includes specifying the exact time for daily intraocular pressure measurement, the frequency of visual field self-examination, and other details.

[0051] In this embodiment, the behavioral execution plan includes specifying the medication time, dietary restrictions (such as strictly reducing the intake of high-salt foods), and suitable types of exercise.

[0052] In this embodiment, the calculation of the self-management behavior deviation penalty index includes:

[0053] in This represents the cumulative value of penalties for deviations in self-management behavior; Indicates the total duration or total number of steps in a time period; This represents the coefficient for measuring the severity of behavioral deviation at time point t; This indicates an indicator function; when a patient exhibits behavior that does not conform to the self-management plan at time t, =1; When the patient strictly adheres to self-management behaviors at time t =0.

[0054] The working principle and beneficial effects of the above technical solution are as follows: First, an initial assessment of the patient's glaucoma knowledge level is conducted using a glaucoma knowledge questionnaire to obtain the initial assessment results; simultaneously, baseline data of the patient is acquired, such as the patient's basic health status and medical history; then, based on the risk perception elements in the HAPA (Health Action Process Orientation Theory), the initial assessment results and baseline data are transformed into a personalized risk report; this process combines the patient's cognitive level, basic situation, and risk perception to provide a basis for subsequent intervention; based on the previously generated personalized risk report, a collaborative filtering recommendation algorithm is used; this algorithm, based on the principle of similarity, matches glaucoma patients with successful management experiences of patients with similar conditions; because the experiences of patients with similar conditions may be more referential, this method enhances the patient's self-management awareness; after the patient has developed self-management awareness, based on glaucoma diagnosis and treatment guidelines, a multi-dimensional objective function is constructed considering individual patient differences. The system generates a daily self-management plan by integrating multiple constraints. This plan includes a physiological indicator monitoring plan (such as intraocular pressure monitoring) and a behavioral execution plan (such as medication and rest arrangements). Real-time execution data of the physiological indicator monitoring plan and behavioral execution plan are acquired to form behavioral execution record data. An intraocular pressure prediction LSTM (Long Short-Term Memory) network is constructed, with its input layer covering historical intraocular pressure sequences, environmental variables (such as weather, air pressure, and other factors that may affect intraocular pressure), and behavioral variables (such as the patient's eye-use behavior). The output is a predicted intraocular pressure value for a future time period, and the prediction deviation range is calculated. The deviation range threshold is dynamically adjusted according to the patient's intraocular pressure fluctuation cycle. When the actual measured intraocular pressure deviates from the preset target value beyond the acceptable range, an early warning intervention mechanism is triggered to ensure that the patient's intraocular pressure remains within a reasonable range. Behavioral execution record data of the patient within a preset time period is acquired, and weaknesses in the patient's self-management process are identified through analysis. K-means... The system employs a clustering algorithm to group patients with similar weaknesses into a weak group, extracts common features within each group, generates a group-based intervention template, and then combines this with individual patient data to create a personalized intervention template. Finally, the system dynamically adjusts the patient's self-management process based on this personalized template to continuously optimize self-management effectiveness. When a patient fails to perform self-management behaviors as planned, a penalty indicator is introduced to calculate a self-management behavior deviation penalty index. When this index exceeds a preset deviation threshold, the system pushes targeted educational content to the patient, thereby strengthening their behavioral awareness and encouraging them to better execute their self-management plan. Throughout the intervention process, from motivation activation to action execution and maintenance optimization, each stage fully considers individual patient differences. Whether it's personalized risk reports, personalized intervention templates, or daily self-management plans built based on individual differences, all these elements make the intervention measures more tailored to the patient's actual situation, improving the effectiveness of the intervention.

[0055] In this embodiment, the wake-up intervention module is periodically evaluated, including: The first acquisition submodule is used to acquire the core daily self-management behavior types of glaucoma patients within a preset time period; the core daily self-management behavior types include intraocular pressure monitoring, medication adherence, and rest management. The judgment submodule is used to judge the information on intraocular pressure monitoring, medication adherence and rest management, and to determine the number of non-standard behaviors in the information on intraocular pressure monitoring, medication adherence and rest management; The assessment submodule is used to evaluate glaucoma patients from the dimensions of basic management and key event management based on intraocular pressure monitoring, medication adherence, rest and activity management information, and information on the number of non-standard behaviors, and to determine the self-management status score of glaucoma patients. in, This indicates the self-management status score of glaucoma patients; This indicates the number of irregularities in the i-th category of daily self-management behavior; This represents the total number of times the i-th type of daily self-management behavior was performed; Indicates the weighting coefficients for the basic management dimensions; Indicates the weighting coefficient for the critical incident management dimension; This represents the weight of the difficulty and importance of self-management in the t-th critical event; This represents the effectiveness value of self-management during the t-th critical event; This indicates the total number of times a critical incident was self-managed; The wake-up submodule is used to compare the self-management status score with a preset score threshold. When the self-management status score is determined to be less than the preset score threshold, a wake-up prompt is issued to promptly awaken the glaucoma patient's awareness of treatment.

[0056] In this embodiment, This represents the score for the basic management dimension.

[0057] In this embodiment, This represents the score for the critical incident management dimension.

[0058] In this embodiment, the number 200 is the full score base for the basic management dimension, representing the total score of daily self-management under ideal conditions.

[0059] In this embodiment, the number 4 represents the baseline threshold in the exponential calculation, used to define the upper limit of the impact of non-compliant behavior. The number 10 represents the amplification coefficient of a single type of intervention deduction item, used to enhance the weight of non-compliant behavior on the base score.

[0060] In this embodiment, the self-management ability of glaucoma patients is comprehensively evaluated from two dimensions: basic daily management and critical event response. The core logic is to focus on both the standardization of daily core behaviors (basic dimension) and the effectiveness of coping with sudden / important events (critical event dimension). Finally, the weighted summary reflects the patient's overall treatment compliance and risk control ability.

[0061] In this embodiment, common situations of non-standard self-management behavior and core daily self-management behaviors include "intraocular pressure monitoring, medication adherence, and daily routine management." The three types of non-standard behaviors are as follows: 1) Incorrect intraocular pressure monitoring; monitoring frequency not in accordance with the instructions: for example, the doctor requires monitoring once every 8 am, but monitoring is actually done once every 3 days; incorrect monitoring conditions: such as not fasting (some tonometers require fasting), or strenuous exercise before monitoring (affecting the results); missing data records: the values ​​and time were not recorded after monitoring or were not synchronized with the doctor; incorrect equipment use: such as the tonometer not being calibrated, or incorrect operating posture leading to data distortion.

[0062] 2) Incorrect medication adherence: Missed / incorrect doses: such as forgetting to instill intraocular pressure-lowering eye drops, or mistakenly taking "1 drop / time" as "2 drops / time"; Unauthorized discontinuation / change of medication: such as stopping medication when symptoms are relieved, or switching to other brands on one's own; Incorrect timing: such as not spacing out when there is a conflict with other medications (e.g., antihypertensive drugs and intraocular pressure-lowering drugs should be spaced 1 hour apart); Failure to follow special requirements: such as not following the requirement to "press the inner corner of the eye for 5 minutes after instilling" for certain eye drops.

[0063] 3) Irregular work and rest management; insufficient sleep: such as doctors recommending "7-8 hours of sleep per day", but actually staying up late for a long time (only sleeping 5 hours per day); excessive use of eyes: such as looking at mobile phones / computers for more than 4 hours continuously (doctors recommend taking a 10-minute break every hour); dietary violations: such as excessive intake of high-salt foods (affecting intraocular pressure), excessive drinking (worsening eye congestion); inappropriate emotions / exercises: such as long-term anxiety (which easily increases intraocular pressure), strenuous exercise (such as weightlifting, which may affect intraocular pressure).

[0064] In this embodiment, This indicates the total number of times the i-th type of daily self-management behavior is performed; the "total number of performances" refers to the number of times the patient should theoretically or actually performs the core daily behaviors within a preset time period (e.g., 1 month), specifically corresponding to three types of behaviors: intraocular pressure monitoring: if the doctor requires "once a day", the total number of performances in 1 month (30 days) is 30 times; medication adherence: if "eye drops are instilled 3 times a day", the total number of performances in 1 month is 3 × 30 = 90 times; rest management: if "the duration of eye use is controlled every day (rest once every hour)", it needs to be performed 6-8 times a day (based on 12 hours of wakefulness), about 200 times a month.

[0065] In this embodiment, critical events refer to sudden, non-routine events in glaucoma management that may significantly affect the condition. These events usually require timely intervention, otherwise they may lead to risks such as a sudden increase in intraocular pressure and deterioration of vision. For example: a sudden increase in intraocular pressure: sudden eye pain, headache, blurred vision (may be a precursor to an acute angle-closure glaucoma attack); adverse drug reactions: eye redness, swelling, itching, or systemic symptoms (such as nausea, rash) after instilling eye drops; eye trauma: such as accidental impact to the eye or foreign objects entering the eye (may cause inflammation or fluctuations in intraocular pressure); coexisting diseases: such as a sudden cold and fever (elevated body temperature may affect intraocular pressure), or the need for long-term use of steroid medications (steroids may increase intraocular pressure); special scenarios: such as long-distance travel (disruption of sleep schedule + environmental changes may affect intraocular pressure), or severe emotional fluctuations (such as increased intraocular pressure after an argument).

[0066] In this embodiment, critical event self-management refers to the coping measures that patients take independently when critical events occur (rather than relying entirely on doctors), with the aim of controlling risks and reducing harm; for example: when intraocular pressure rises suddenly: immediately measure intraocular pressure, administer emergency intraocular pressure-lowering medication according to the backup plan, and contact the doctor to schedule an emergency appointment; when experiencing an allergic reaction to medication: immediately stop taking the medication, rinse the eyes with clean water, record the symptoms and take photos, and call the doctor for consultation; when experiencing eye trauma: avoid rubbing the eyes, apply a clean gauze gently, and go to the ophthalmology department as soon as possible.

[0067] In this embodiment, the effectiveness of critical event self-management is typically assessed by combining "behavioral norms" and "actual results," scored by a doctor or system-preset standards. For example: Sudden increase in intraocular pressure (critical event t=1) Patient behavior: Immediately measure intraocular pressure (record the value) → Instill emergency eye drops as prescribed → Remeasure after 1 hour → Contact a doctor and seek medical attention within 2 hours; Result: At the time of medical attention, intraocular pressure has decreased from 35 mmHg to 22 mmHg (normal range 10-21 mmHg), and no visual impairment has occurred; Effectiveness : 0.9 (standardized measures + significant results); For example: drug allergy (critical event t=2) Patient behavior: did not stop medication (continued to use drops) → only took antihistamines on their own → informed the doctor only 2 days later; Effect: worsened eye redness and swelling, corneal damage occurred; Effectiveness : 0.2 (Incorrect measures + poor results); Weight The values ​​are set according to the importance and difficulty of the event. For example, "acute increase in intraocular pressure" may endanger vision, so ω=0.8; "mild discomfort from medication" so ω=0.3.

[0068] In this embodiment, the daily management of glaucoma is a process of "quantitative change leading to qualitative change": occasional standardization is meaningless, but long-term, high-frequency and standardized execution is necessary to stabilize intraocular pressure. The combination of the two parameters, the number of non-standardizations and the total number of executions, is precisely to avoid "false compliance." The core logic is: not to look at "whether it was done or not," but to look at "how well it was done" and "how much was done." The risks of glaucoma mainly come from two aspects: (1) the slow deterioration of the condition caused by long-term laxity in daily management, and (2) acute blindness caused by improper handling of sudden critical events. In order to balance the importance of the two, a weight value is proposed. The purpose of introducing these parameters is to transform glaucoma self-management from a vague qualitative description into a quantifiable and accurate assessment.

[0069] The working principle and beneficial effects of the above technical solution are as follows: First, the core daily self-management behaviors of glaucoma patients within a preset time period are acquired. These behaviors include intraocular pressure monitoring, medication adherence, and daily routine management. This is the basic data source for the entire assessment. By collecting this data, a comprehensive understanding of the patient's self-management in daily life can be achieved. Each patient has different characteristics in their self-management behaviors. Through the calculation of these parameters, a self-management status score that matches the patient's individual characteristics can be obtained based on the patient's actual situation. By comparing this score with a preset score threshold, deficiencies in the patient's self-management can be identified in a timely manner. When the patient's self-management status score falls below the threshold, a wake-up prompt is issued, which can promptly awaken the patient's awareness of treatment, prevent the patient's glaucoma condition from worsening due to poor self-management, improve the treatment effect of glaucoma, and protect the patient's visual health.

[0070] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0071] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A glaucoma patient self-management intervention system based on the HAPA theory, characterized in that, include: The patient data acquisition and processing module is used to collect real-time data of glaucoma patients and process the real-time data of glaucoma patients to determine the characteristic data of glaucoma patients. The disease progression risk assessment module is used to assess the risk of disease progression in glaucoma patients and generate a glaucoma patient disease progression risk assessment report. The self-management multi-stage intervention module is used to conduct multi-stage self-management intervention for glaucoma patients based on the HAPA theory. The periodic assessment and awakening intervention module is used to periodically assess the self-management status of glaucoma patients and provide awakening intervention as needed. Among them, glaucoma patients were evaluated from the basic management dimension and the critical event management dimension based on intraocular pressure monitoring, medication adherence, rest and activity management information and information on the number of non-standard behaviors, and the self-management status score of glaucoma patients was determined. When the self-management status score is lower than the preset score threshold, a wake-up prompt is issued to promptly awaken the glaucoma patient's awareness of treatment.

2. The glaucoma patient self-management intervention system based on HAPA theory according to claim 1, characterized in that, Regularly evaluate the arousal intervention module, including: The first acquisition submodule is used to acquire the core daily self-management behavior types of glaucoma patients within a preset time period; the core daily self-management behavior types include intraocular pressure monitoring, medication adherence, and rest management. The judgment submodule is used to judge the information on intraocular pressure monitoring, medication adherence and rest management, and to determine the number of non-standard behaviors in the information on intraocular pressure monitoring, medication adherence and rest management; The assessment submodule is used to evaluate glaucoma patients from the dimensions of basic management and key event management based on intraocular pressure monitoring, medication adherence, rest and activity management information, and information on the number of non-standard behaviors, and to determine the self-management status score of glaucoma patients. in, This indicates the self-management status score of glaucoma patients; This indicates the number of irregularities in the i-th category of daily self-management behavior; This represents the total number of times the i-th type of daily self-management behavior was performed; Indicates the weighting coefficients for the basic management dimensions; Indicates the weighting coefficient for the critical incident management dimension; This represents the weight of the difficulty and importance of self-management in the t-th critical event; This represents the effectiveness value of self-management during the t-th critical event; This indicates the total number of times a critical incident was self-managed; The wake-up submodule is used to compare the self-management status score with a preset score threshold. When the self-management status score is determined to be less than the preset score threshold, a wake-up prompt is issued to promptly awaken the glaucoma patient's awareness of treatment.

3. A glaucoma patient self-management intervention system based on HAPA theory according to claim 2, characterized in that, The self-management multi-stage intervention module includes: The first intervention submodule of the motivation activation phase is used to conduct an initial assessment of the glaucoma knowledge level of glaucoma patients based on a glaucoma knowledge questionnaire, determine the initial assessment results, obtain the baseline data of glaucoma patients, and transform the initial assessment results and the baseline data of glaucoma patients into personalized risk reports based on the risk perception elements in the HAPA theory. The second intervention submodule of the motivation activation phase is used to match glaucoma patients with successful management experiences of glaucoma patients with similar conditions based on personalized risk reports and collaborative filtering recommendation algorithms, and to enhance glaucoma patients' self-management awareness based on the successful management experiences. The first intervention submodule in the action execution phase is used to generate a daily self-management plan after glaucoma patients have developed self-management awareness. Based on glaucoma diagnosis and treatment guidelines and combined with individual differences among glaucoma patients, a multi-dimensional objective function is constructed, and multi-dimensional constraints are integrated to generate the plan. The daily self-management plan includes a physiological indicator monitoring plan and a behavior execution plan. The second intervention submodule in the action execution phase is used to acquire real-time execution data of the physiological indicator monitoring plan and behavior execution plan, and generate behavior execution record data; construct an intraocular pressure prediction LSTM network, with the input layer including historical intraocular pressure sequences, environmental variables and behavioral variables, outputting the predicted intraocular pressure value for the future time period, and calculating the prediction deviation range. The deviation range threshold for glaucoma patients is dynamically adjusted based on the intraocular pressure fluctuation cycle of glaucoma patients; when it is determined that the deviation between the actual measured intraocular pressure of a glaucoma patient and the preset target value exceeds the acceptable range, the system immediately triggers an early warning intervention mechanism. The first intervention submodule in the maintenance and optimization phase is used to acquire and analyze behavioral execution records of glaucoma patients within a preset time period to identify weaknesses in their self-management process. Using the K-means clustering algorithm, glaucoma patients with similar weaknesses are grouped into a weak group. Common characteristics within this group are extracted to generate a targeted group-based intervention template. This template is then combined with the specific data of individual glaucoma patients to generate personalized intervention templates. Based on these personalized intervention templates, the self-management process of glaucoma patients is dynamically adjusted and intervened. The second intervention submodule in the maintenance and optimization phase is used to introduce a penalty indicator when glaucoma patients fail to perform self-management behaviors as planned. The system calculates the penalty indicator for deviations in self-management behaviors. When the penalty indicator for deviations exceeds a preset deviation threshold, the system pushes targeted educational content to glaucoma patients to strengthen their behavioral awareness.

4. A glaucoma patient self-management intervention system based on HAPA theory according to claim 3, characterized in that, To assess the risk of disease progression in glaucoma patients and generate a glaucoma patient disease progression risk assessment report, the following operations are performed: A risk assessment model for glaucoma patient disease progression was constructed using machine learning algorithms and combined with historical data of glaucoma patients. Deploy a risk assessment model for glaucoma patient disease progression, and place the model in a real-world glaucoma patient disease progression risk assessment environment. The characteristic data of glaucoma patients are input into the glaucoma patient disease progression risk assessment model. The model analyzes the characteristic data of glaucoma patients and automatically assesses the risk of disease progression, generating a glaucoma patient disease progression risk assessment report.

5. A glaucoma patient self-management intervention system based on HAPA theory according to claim 4, characterized in that, Based on the HAPA theory, a multi-stage intervention for self-management of glaucoma patients is performed, including the following steps: The glaucoma patient disease progression risk assessment report helps glaucoma patients understand the possible consequences of disease progression, enhances their willingness to engage in healthy behaviors, and vividly explains the principles, dangers, and consequences of not treating glaucoma through text, short videos, or animations, emphasizing the importance of self-management to glaucoma patients. Based on the HAPA theory, we can identify glaucoma patients' misconceptions or denials about the disease, clarify the stage of glaucoma, and help them identify specific obstacles that may hinder the implementation of their treatment plan. According to the cognitive, belief, and behavioral stages of glaucoma patients, we can provide self-management interventions suitable for their condition and lifestyle. Based on these self-management interventions, we can help glaucoma patients manage their poor treatment adherence and emotional fluctuations.

6. A glaucoma patient self-management intervention system based on HAPA theory according to claim 5, characterized in that, To implement self-management interventions for glaucoma patients, the following steps should be taken: Through app push notifications, smart pillboxes, and wearable devices, glaucoma patients are reminded to take their medication and have follow-up examinations. Their behavior is recorded, and positive behaviors are immediately acknowledged and rewarded with points to create positive feedback. Frequently asked questions are quickly searched and answered, and psychological counseling and support are provided in a timely manner to address negative emotions in glaucoma patients.

7. A glaucoma patient self-management intervention system based on HAPA theory according to claim 6, characterized in that, Regularly assess the self-management status of glaucoma patients and provide timely awakening interventions, and perform the following actions: Set up an online consultation portal and connect with doctors or health consultants to provide timely emotional support and psychological intervention for glaucoma patients; Real-time monitoring of glaucoma patients' self-management intervention is conducted, and their self-management status is regularly assessed. Negligence or behavioral deviations in glaucoma patients are identified, and timely reminders and suggestions are provided to awaken their awareness of treatment.

8. A glaucoma patient self-management intervention system based on HAPA theory according to claim 7, characterized in that, A glaucoma patient disease progression risk assessment model was constructed using machine learning algorithms and combined with historical data from glaucoma patients. The following operations were performed: Collect and segment historical data of glaucoma patients into training and testing sets. Machine learning algorithms are used to train a machine learning model using a training set. The machine learning model learns autonomously from the training set the risk assessment behavior of glaucoma patients' disease progression and performs risk assessment of glaucoma patients' disease progression, thus determining the risk assessment model for glaucoma patients' disease progression. The model for assessing the risk of glaucoma disease progression was tested using a test set to evaluate whether it could achieve the expected effect of assessing the risk of glaucoma disease progression and to determine the model test evaluation results. When the risk assessment model for glaucoma patient disease progression fails to achieve the expected effect of assessing the risk of glaucoma patient disease progression, the parameters of the risk assessment model for glaucoma patient disease progression are adjusted and optimized until the risk assessment model for glaucoma patient disease progression achieves the expected effect of assessing the risk of glaucoma patient disease progression, and the optimal risk assessment model for glaucoma patient disease progression is determined.

9. A glaucoma patient self-management intervention system based on HAPA theory according to claim 8, characterized in that, Collect real-time data from glaucoma patients and perform the following operations: By connecting to the hospital's HIS system, we can obtain the medical records, intraocular pressure curves, and visual field examination results of glaucoma patients in real time and collect clinical data of glaucoma patients. We collected real-time data on the family history, eye habits, and daily activities of glaucoma patients through questionnaires. Real-time data for glaucoma patients was determined based on their clinical and lifestyle data.

10. A glaucoma patient self-management intervention system based on HAPA theory according to claim 9, characterized in that, The real-time data of glaucoma patients is processed, and the following operations are performed: The real-time data of glaucoma patients was cleaned to remove noise unrelated to the self-management intervention of glaucoma patients, and missing and outlier values ​​related to the self-management intervention of glaucoma patients were processed. The real-time data of glaucoma patients is transformed to remove the dimensional differences in the real-time data of glaucoma patients and form standardized real-time data of glaucoma patients. Feature extraction was performed on real-time data of glaucoma patients to extract features related to self-management intervention of glaucoma patients and to determine the characteristic data of glaucoma patients.

Images