Peripheral artery disease patient rehabilitation management system based on whole process

Abstract

The invention provides a peripheral artery disease patient rehabilitation management system based on a whole process, and relates to the technical field of peripheral artery disease patient rehabilitation management. The system comprises a patient screening and risk grading module, a rehabilitation evaluation module, an exercise prescription generation and dynamic adjustment module, an intelligent propaganda and education content pushing module and a quality control closed-loop management module. PAD patients are accurately screened through a medical data interface and an NLP technology, and the risk levels of the patients are dynamically evaluated in combination with an intelligent risk grading system; generating a personalized exercise prescription according to the evaluation report, complication and biological monitoring data, and guaranteeing the exercise safety through a dynamic threshold model and collaborative early warning; dynamic matching and timeliness pushing of propaganda and education contents are realized by using an improved KL divergence algorithm; and full-process quality closed-loop management is realized through the quality control closed-loop management module. The precision and safety of rehabilitation management of the PAD patient can be improved, medical resource configuration is optimized, and rehabilitation practice driven by full-process data is assisted.

Description

Technical Field

[0001] The present invention relates to the technical fields of medical informatization and rehabilitation management. Specifically, it relates to a rehabilitation management system for patients with peripheral arterial diseases based on the whole process. Background Art

[0002] Peripheral arterial diseases (PAD) are chronic diseases caused by atherosclerosis that lead to stenosis or occlusion of peripheral arteries. Its incidence is on the rise globally, especially among the elderly population. PAD not only seriously affects the quality of life of patients but may also lead to serious complications such as amputation and even death. Research shows that regular exercise therapy can effectively improve the walking ability, physical function, and quality of life of PAD patients, and reduce the incidence and all-cause cardiovascular mortality. Therefore, it is recommended as the first-line treatment plan by domestic and foreign guidelines.

[0003] However, the current rehabilitation management of PAD patients still faces many challenges. The traditional rehabilitation management mode mainly relies on manual operations, including patient assessment, exercise prescription formulation, data recording and analysis, etc. This method is not only inefficient but also prone to errors due to human factors and is difficult to meet the needs of long-term follow-up and precise management. At the same time, although the existing information systems have realized the automation of some functions to a certain extent, there are still obvious deficiencies. For example, the patient screening mechanism mostly relies on structured diagnostic codes and has limited recognition ability for fuzzy diagnoses such as "suspected PAD", resulting in potential high-risk patients being missed; the risk grading system generally adopts a static determination mode based on a single clinical indicator and fails to achieve multi-dimensional dynamic fusion analysis, unable to capture the changes in the patient's risk level in a timely manner; the personalized degree of the education and promotion module is insufficient, only matching content based on disease diagnosis labels and lacking the ability to adaptively adjust to real-time scenarios such as postoperative changes and decreased behavioral compliance; the quality control management level also mostly stays at the data statistics level, lacking a closed-loop quality control system based on multi-dimensional indicators and unable to automatically identify process loopholes and trigger improvement measures. In addition, there are barriers to the integration of real-time biometric data monitored by IoT devices and the medical system, and the data collected by the devices cannot be effectively integrated into the exercise prescription generation and adjustment algorithm, resulting in a lack of individualized adaptation accuracy in calculating exercise intensity. These problems directly affect the timeliness and safety of rehabilitation management, and there is an urgent need for a whole-process rehabilitation management system that can cover intelligent data analysis, dynamic risk prediction, and multi-modal collaborative analysis to improve the rehabilitation effect and management efficiency of PAD patients.

[0004] In view of this, the present application is specifically proposed. Summary of the Invention

[0005] The present invention aims to provide a rehabilitation management system for patients with peripheral artery disease based on the whole process, so as to solve the defects existing in the existing methods, such as low data management efficiency, insufficient intelligence of exercise prescriptions, low personalization degree of education push, and imperfect quality control system.

[0006] To solve the above technical problems, the present invention is realized through the following technical solutions: A rehabilitation management system for patients with peripheral artery disease based on the whole process, comprising: a patient screening and risk grading module, a rehabilitation assessment module, a motion prescription generation and dynamic adjustment module, an intelligent push module for education content, and a quality control closed-loop management module; Among them, the patient screening and risk grading module is used to connect with the hospital information system through a medical data interface, obtain and analyze the basic data of patients with peripheral artery disease in real time, and construct an intelligent risk grading system based on the Fontaine stage, ankle-brachial index and contraindications, so as to automatically update the patient risk level and trigger an alarm; The rehabilitation assessment module is used to generate an assessment report with time as the axis according to the patient's basic data and the biometric monitoring data obtained in real time; The motion prescription generation and dynamic adjustment module is used to generate a motion prescription based on the assessment report, comorbidities and the biometric monitoring data obtained in real time according to the combined applicable items and safety principles, and perform dynamic optimization and adjustment according to the intelligent risk grading system; The intelligent push module for education content is used to collect multi-dimensional features of patients to construct a patient feature portrait, establish an education knowledge base, generate initial education content, and perform dynamic adjustment and personalized adaptive push on the initial education content; The quality control closed-loop management module is used to construct a standardized quality control index system according to the processing and feedback of the rehabilitation assessment module, the motion prescription generation and dynamic adjustment module, and the intelligent push module for education content, generate quality control data and perform warning and improvement.

[0007] Preferably, the patient's basic data includes the patient's basic information, diagnosis code and test report; If the diagnosis code is a fuzzy diagnosis of suspected peripheral artery disease, the key disease features are analyzed and extracted according to the patient's basic data by using NLP technology, and combined with the patient's test report, the patient screening result is dynamically corrected.

[0008] Preferably, the biological monitoring data includes exercise time, distance, steps, real-time speed, metabolic equivalent, dynamic heart rate, blood oxygen, plantar pressure distribution, and blood pressure; the content of the evaluation report includes: evaluating the patient, evaluation date, height, weight, BMI, medications used, blood glucose, blood lipids, blood pressure, whether smoking, whether drinking alcohol, exercise habits, wound conditions, pain visual analogue scale VAS, lower limb muscle strength, short physical performance battery SPPB, 6-minute walk distance 6MWD and steps, claudication distance, maximum walking distance, ankle-brachial index ABI, leg circumference, quality of life scale, walking impairment questionnaire, hope scale, and subjective exertion score; wherein, BMI = weight / height 2 ; The types of 6MWD are divided into male and female. For male, 6MWD = 1140 (meters) - 5.61×BMI - 6.94×age; for female, 6MWD = 1017 (meters) - 6.24×BMI - 5.83×age, and age is in years.

[0009] Preferably, the exercise prescription includes the patient's exercise basic parameters and simultaneously displays the comorbidity adaptation suggestions; the patient's exercise basic parameters include exercise frequency, exercise intensity, exercise duration, exercise mode, and exercise volume; The exercise intensity is calculated by the following method: ; wherein, I represents the exercise intensity; 6MWD represents the 6-minute walk distance.

[0010] The quantification model of the exercise volume is: ; wherein, represents the exercise volume; I represents the exercise intensity; represents the total exercise duration; represents the actual number of steps in the 6-minute walk test; SafetyFactor represents the safety adjustment coefficient.

[0011] Preferably, when performing dynamic optimization and adjustment according to the intelligent risk grading system, the intelligent judgment of the matching degree of the exercise prescription is carried out, and the threshold conflict of the data parameters of the exercise prescription is automatically checked and adjusted.

[0012] Preferably, the patient characteristic portrait includes disease diagnosis results, clinical data, medication list, surgical records, exercise prescription, and patient living habits; When generating the initial education content, each content in the education knowledge base is marked with multi-dimensional labels, and then based on the KL divergence for content matching, the education content with the highest matching degree at the current time point is screened out; the calculation formula of the matching degree is: ; Among them, represents the matching degree; represents the timeliness of knowledge at the current time point t, , is the attenuation rate, represents the interval between the knowledge release date and the current time point; represents the total number of feature dimensions of the patient feature portrait; represents the feature dimension variable; represents the weight coefficient of the current feature dimension; represents the patient feature vector; represents the i-th knowledge entry; represents the patient feature vector of the feature dimension; represents the knowledge entry of the feature dimension; represents the intersection; represents the union; represents taking a numerical value; When the matching degrees of the selected education content are equal, the content with a higher reading completion rate is preferentially selected as the initial education content.

[0013] Preferably, the initial education content is dynamically adjusted and personalized adaptively pushed, specifically: Multidimensional features of the patient are collected in real time, and the education knowledge base is updated; According to the updated education knowledge base, the knowledge weights of the initial education content are dynamically adjusted by using a time decay mechanism, and the expression is: ; Among them, is the knowledge weight of the updated initial education content; is the knowledge weight of the initial education content before update; n is the number of push cycles; is the number of days since the last effective reading; represents periodic decay; represents continuous decay; is the forgetting factor; is the event correlation degree of the i-th push cycle indicator function.

[0014] Analyze the real-time reading behavior data of the patient for the initial education content, calculate the reading behavior similarity of the patient, and generate a patient recommendation list, and the expression is: ; ; Among them, represents the reading behavior similarity between patient u and patient v; represents the number of common push cycles of patient u and patient v Indicates the reading status of patient u on the educational content of the i-th push cycle. A value of 1 indicates that the reading time is ≥ 30 seconds, indicating in-depth reading; a value of 0.5 indicates that the reading time is < 30 seconds, indicating quick reading; a value of 0 indicates that the content is not opened; Indicates the reading status of patient v on the educational content of the i-th push cycle; It represents the average reading time of the educational content of patient u in all push cycles; It represents the average reading time of patient v in all push cycles; Indicates patient Recommended list of represents the set of patients with similar reading behaviors to patient u; Indicates the reading status of patient v on the educational content of the jth push cycle; According to the multi-dimensional characteristics of the patient collected in real time, when the patient's indicators are detected to be abnormal, the content related to the abnormal indicators is searched from the education knowledge base, inserted to the first place in the patient recommendation list, and an early warning is sent to the medical care end.

[0015] Preferably, it also includes: when generating an exercise prescription, according to the biological monitoring data acquired in real time, establishing a dynamic threshold model and performing real-time feedback training; the dynamic threshold model includes a maximum heart rate threshold, which is expressed as: Maximum heart rate threshold = 220-patient age ± blood pressure fluctuation value of the day.

[0016] Preferably, it also includes: during the execution of the exercise prescription, according to the exercise prescription and the biological monitoring data obtained in real time, a dynamic target-reaching algorithm is used to calculate the daily exercise target-reaching rate, and the patient's exercise results are fed back in real time; wherein the calculation formula of the daily exercise target-reaching rate is: Daily exercise target achievement rate = Σ (completion amount on the day × time decay coefficient) / exercise prescription requirement; Σ represents the sum of all exercise completion amounts on the day; Time decay coefficient = 1 / (1+0.1×delay days); The exercise results are fed back through the vascular health index VHI score, and the calculation formula is: VHI=0.3×6MWD improvement rate+0.2×gait symmetry improvement+0.5×prescription compliance; Among them, the 6MWD progress rate represents the results of the six-minute walk distance tests of the patient before and after treatment, that is, (6MWD after treatment - 6MWD before treatment) / 6MWD before treatment × 100%; the improvement degree of gait symmetry represents the degree of improvement of the patient's gait symmetry, which is obtained by comparing the gait differences between the left and right sides of the patient before and after treatment; the prescription compliance degree represents the degree of compliance of the patient to exercise according to the exercise prescription issued by the doctor, that is, (the actual number of exercise times / the number of exercise times specified in the prescription) × 100%.

[0017] Preferably, the standardized quality control index system includes the rehabilitation assessment timeliness rate, the patient enrollment timeliness rate, the exercise prescription matching degree, the patient exercise effectiveness rate, the implementation rate of publicity and education push, the publicity and education notice timeliness rate, the health education reading rate and the effective reading rate; Among them, the calculation method of the rehabilitation assessment timeliness rate is: (the number of patients who completed the assessment on time / the number of patients who should be assessed) × 100%, and the definition of completing on time is: the assessment date ≤ the preset date + 1 working day; The calculation method of the patient enrollment timeliness rate is: (the number of patients whose system enrollment time ≤ 24 hours after admission / the total number of newly enrolled patients) × 100%; The calculation method of the exercise prescription matching degree is: (the passing rate × 80% - 120% × the number of patients / the number of patients enrolled in the system) × 100%; the passing rate = (the actual amount of exercise completed by the patient / the required amount of exercise in the exercise prescription) × 100%; The calculation method of the patient exercise effectiveness rate is: the main index improvement rate = (the current 6MWD - the baseline 6MWD) / the baseline 6MWD × 100%; The calculation method of the implementation rate of publicity and education push is: (the number of patients who actually received the publicity and education content / the total number of patients who should be pushed) × 100%; The calculation method of the publicity and education notice timeliness rate is: (the number of patients who received the publicity and education content notice within 3 days / the total number of unread patients) × 100%; The calculation method of the health education reading rate is: (the number of patients who read the health education ≥ 1 time / the total number of patients who received it) × 100%; The calculation method of the effective reading rate is: (the number of patients with in-depth reading / the total number of reading patients) × 100%, and the definition of in-depth reading is: the single stay ≥ 120s and the knowledge test is completed.

[0018] To sum up, compared with the prior art, the present invention has the following beneficial effects: First, the system of the present invention intelligently integrates multi-source patient data and dynamic risk control, significantly improving the recognition and response speed of PAD patients. Specifically, based on the FHIR standard and NLP unstructured text parsing technology, the system of the present invention extracts PAD patient information from the hospital information system in real time, breaks through the limitations of traditional structured coding, and accurately identifies patients with fuzzy diagnoses. By dynamically fusing multi-dimensional parameters such as Fontaine stage, ABI index, and contraindications through a four-color risk matrix, a minute-level risk scanning mechanism is established, greatly reducing the missed screening rate of high-risk patients and the false omission rate of early warnings. Second, the intelligent generation and dynamic adjustment module of exercise prescriptions effectively reduces the occurrence of exercise-related adverse events. This module adopts a three-layer architecture of "multi-modal data input - labeled action library matching - conflict detection", combines a dynamic threshold model and a collaborative early warning network, and monitors the physiological indicators of patients during exercise in real time to ensure exercise safety.

[0019] The intelligent push module of education content is based on the improved KL divergence algorithm. The system constructs a deep matching model between the patient feature vector and the knowledge base, realizing the time-decaying push of education content and event-triggered updates. During the execution of exercise prescriptions, biometric data such as foot pressure and gait symmetry are collected in real time through Internet of Things devices to dynamically optimize the compliance rate and achieve precise adaptation of exercise intensity and physiological state. The quality control closed-loop management module drives management upgrades, realizes automatic problem identification and embedding of standardized improvement processes, and reduces the labor cost of quality control management.

[0020] Through the automated risk grading and early warning freezing mechanism, the system of the present invention preferentially allocates medical staff resources to high-risk patients, improving the efficiency of handling critical rehabilitation values. The construction of the whole-process management system retains a traceable data chain for all operations from prescription generation to quality control improvement, providing a high-value data set for clinical research and facilitating the dynamic optimization of PAD patient rehabilitation and precision medicine practice.

[0021] In summary, through multi-modal data fusion, intelligent algorithm collaboration, and closed-loop quality control mechanisms, the present invention solves the pain points of existing PAD patient rehabilitation management systems in aspects such as data management, exercise prescription intelligence, personalized education push, and quality control system improvement, significantly improving the accuracy and safety of rehabilitation management. Brief Description of the Drawings

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the embodiments. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0023] Figure 1Schematic diagram of a rehabilitation management system for peripheral artery disease patients based on the whole process provided for Embodiment 1.

[0024] Figure 2 Schematic diagram of the compliance exception handling process provided for Embodiment 1.

[0025] Figure 3 Schematic diagram of the three - level response mechanism provided for Embodiment 1.

[0026] Figure 4 Schematic diagram of the structure of the education knowledge base provided for Embodiment 1.

[0027] Figure 5 Schematic diagram of the three - level response process for heart rate abnormality handling provided for Embodiment 1.

[0028] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. Specific Embodiments

[0029] To make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present invention. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the present invention to be protected, but merely represents the selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present invention.

[0030] Embodiment 1 Embodiment 1 of the present invention provides a rehabilitation management system for peripheral artery disease patients based on the whole process, which can be implemented by a rehabilitation management device for peripheral artery disease patients based on the whole process (hereinafter referred to as the management device), and in particular, is executed by one or more processors in the management device.

[0031] In this embodiment, the management device can be an electronic device equipped with a processor, and the processor has a computer program of this rehabilitation management system for peripheral artery disease patients based on the whole process and the computer program can be executed, such as a computer, a smart phone, a smart tablet, a workstation, etc., which is not limited here.

[0032] In this embodiment, the implementation of the rehabilitation management system for patients with peripheral arterial disease based on the whole process is divided into two parts: PC and APP. The PC is mainly used by rehabilitation administrators, while the APP is used by patients and their families. The PC includes modules such as patient management, rehabilitation assessment, exercise prescription generation, exercise data recording, education, quality control, etc.; the APP includes intelligent rehabilitation module, adaptive education module and intelligent safety monitoring module. The system adopts a dual-channel encrypted transmission architecture to realize efficient synchronization of medical data and IoT device data respectively, and supports real-time push of vital signs data, daily batch synchronization of assessment reports, and instant forced synchronization of exercise prescription adjustments, ensuring that the data update frequency is flexibly configured and both real-time and accuracy are achieved.

[0033] like Figure 1 As shown, a full-process peripheral arterial disease patient rehabilitation management system includes a patient screening and risk grading module, a rehabilitation assessment module, an exercise prescription generation and dynamic adjustment module, an education content intelligent push module, and a quality control closed-loop management module.

[0034] In the patient screening and risk stratification module, administrators can use the new function to filter out patients diagnosed with PAD in the hospital information HIS system and import them into this system. This function is based on the FHIR medical data interface and NLP text parsing technology to extract key disease features from unstructured text, such as intermittent claudication or ABI values.

[0035] The basic data of patients include basic information of patients, diagnostic codes (e.g., ICD-1: PAD) and test reports. If the diagnostic code is a vague diagnosis of suspected PAD, the NLP technology is used to analyze and extract key disease features based on the basic data of the patients, and the screening results of patients are dynamically revised in combination with the test reports of the patients.

[0036] After the screening is completed, the system automatically marks the patient's name, gender, age, diagnosis, time of joining rehabilitation, contact information, closed / unclosed cases and other basic patient data information. Click the patient's name to enter the patient interface to view their general information, which is automatically imported from the HIS system, including height, weight, disease diagnosis, surgery, medical records, rehabilitation assessment, exercise prescription and exercise records. In the patient interface, the administrator can also set filtering conditions to view the list of closed or unclosed patients, and click to view the specific information of each patient.

[0037] Then, on this basis, an intelligent risk grading system is constructed based on Fontaine staging (a commonly used clinical staging method for lower extremity arteriosclerosis obliterans), ankle-brachial index, and contraindications to automatically update the patient's risk level and trigger warnings. As shown in the four-color risk matrix in Table 1, different risk groups are automatically marked with colors, and the risk status is automatically scanned and updated every morning. When the patient's risk level is upgraded, a warning is sent to the administrator's terminal. When an extremely high risk occurs, the generation of the exercise prescription is immediately frozen and a warning is sent to the administrator's terminal to achieve automatic identification and dynamic monitoring of high-risk patients.

[0038] Table 1. Four-color risk level classification for PAD patients

[0039] The rehabilitation assessment module takes time as the axis. By default, the assessment date for each patient is once at the time of joining rehabilitation, once a week during hospitalization, at the time of discharge, and once a month after discharge. The administrator can view the list of patients to be assessed today, patients whose assessment date has not yet arrived, and patients who have not been assessed beyond the assessment date through the screening function. Click on the patient's name to enter the specific assessment interface. The assessment content includes height, weight, BMI, medication status, blood sugar, blood lipids, blood pressure, whether smoking, whether drinking, exercise habits, wound conditions, VAS score, lower limb muscle strength, SPPB, 6MWD and steps, claudication distance, maximum walking distance, ABI, leg circumference, quality of life scale, walking impairment questionnaire, hope scale, and Borg scale, etc. Among them, BMI is automatically calculated by the system, and the formula is: BMI = weight / height 2 , and the ideal value of 6MWD is also automatically generated according to the formula. The types are divided into male and female. For male, 6MWD = 1140 - 5.61×BMI - 6.94×age; for female, 6MWD = 1017 - 6.24×BMI - 5.83×age, with age in years, which is convenient for the administrator to evaluate the patient's actual performance. After the assessment is completed, the system will automatically generate an assessment report and prompt whether to generate an exercise prescription. If generating is selected, it will jump to the exercise prescription generation interface; if not selected, it will stay on the current interface.

[0040] The assessment data statistics interface can also view the trend charts and data of various assessment data according to the time of day, week, month / year (1. Select the assessment date range (such as "2024 / 07 / 01 - 2024 / 07 / 31"); 2. The system automatically captures: electronic medical record data (ABI value, medication records, etc.), bracelet data (daily average step change curve), video assessment results (wound healing progress analysis); 3. Generate a PDF assessment report (including a risk trend radar chart)), so as to judge the rehabilitation effectiveness rate of the patient.

[0041] The exercise prescription generation and dynamic adjustment module is designed based on a three-layer architecture of "multimodal data input - labeled action library matching - conflict detection". At the bottom layer, the results of the multimodal patient data integration assessment report, comorbidities, and real-time physical signs are integrated. At the middle layer, the basic prescription is generated using the principle of combined applicability. At the top layer, the final exercise prescription is output by combining safety rules and doctor confirmation. The exercise prescription includes the basic exercise parameters of the patient and also displays comorbidity adaptation suggestions; the basic exercise parameters of the patient include exercise frequency, exercise intensity, exercise duration, exercise mode, and exercise volume. Specifically, the exercise intensity calculation algorithm first quantifies the exercise volume based on the actual number of steps in the 6-minute walk test and the safety adjustment coefficient, and then combines the patient's comorbidities to adapt to a specific exercise mode, such as adding resistance training when combined with diabetes.

[0042] The exercise intensity is calculated by the following method: ; where I represents the exercise intensity; 6MWD represents the 6-minute walk distance; The quantification model of the exercise volume is: ; where represents the exercise volume; represents the exercise intensity; represents the total exercise duration; represents the actual number of steps in the 6-minute walk test; SafetyFactor represents the safety adjustment coefficient, such as 0.8 - 1.2, which can be set according to the patient's age or complication level.

[0043] In addition, the system also has a motion safety conflict detection mechanism with static priority rules. When dynamically optimizing and adjusting according to the intelligent risk classification system, it intelligently judges the matching degree of the exercise prescription and automatically checks and adjusts the threshold conflicts of the data parameters of the exercise prescription. For example, when the exercise intensity requirement conflicts with the heart rate limit, the heart rate upper limit is given priority. When the heart rate exceeds the safety threshold during the real-time connection to the bracelet to monitor the exercise process, a three-level warning is triggered: the first level is a pop-up reminder on the APP, the second level is to automatically reduce the intensity, and the third level is to urgently pause and notify the doctor. The adjustment of the exercise prescription parameters in stages is set according to Table 2, and the administrator can dynamically optimize the prescription content according to the actual exercise situation of the patient.

[0044] Table 2. Adjustment of exercise prescription parameters

[0045] During the execution of the exercise prescription, according to the exercise prescription and the biometric monitoring data obtained in real time, a dynamic compliance algorithm is used to calculate the daily exercise compliance rate and real-time feedback on the patient's exercise results; among them, the calculation formula for the daily exercise compliance rate is: Daily exercise compliance rate = Σ (daily completion amount × time decay coefficient) / exercise prescription requirement amount; Σ represents the sum of all daily exercise completion amounts; Time decay coefficient = 1 / (1 + 0.1 × number of delayed days); The exercise results are fed back through the vascular health index VHI score, and the calculation formula is: VHI = 0.3 × 6MWD progress rate + 0.2 × gait symmetry improvement degree + 0.5 × prescription compliance degree; Among them, the 6MWD progress rate represents the test results of the 6-minute walking distance of the patient before and after treatment, that is, (6MWD after treatment - 6MWD before treatment) / 6MWD before treatment × 100%; the gait symmetry improvement degree represents the improvement degree of the patient's gait symmetry, which is obtained by comparing the differences in the gait of the patient's left and right sides before and after treatment; the prescription compliance degree represents the degree of compliance of the patient to exercise according to the exercise prescription issued by the doctor, that is, (actual number of exercise times / prescribed number of exercise times) × 100%.

[0046] The principle of combining applicable items means that when a patient has multiple diseases and special conditions, the completely identical items in multiple exercise rehabilitation guidance programs applicable to different diseases and special conditions of the patient are combined, and different items appear side by side; that is, all items in all exercise rehabilitation guidance programs are retained, the completely identical items only appear once, and different items appear side by side.

[0047] The safety principle means that when different exercise rehabilitation guidance programs for different health conditions have different regulations for the same item, and a certain disease has clear safety regulations for this item, safety is given priority.

[0048] In addition, the real-time exercise execution situation of the patient is displayed through the intelligent exercise record dashboard, the prescription matching degree is judged and disposal suggestions are provided. The length of the progress bar represents the weekly exercise times required by the prescription. The color rule is that all green means 100% completion and the intensity meets the standard, yellow and green alternating means ≥ 80% completion but the intensity fluctuates, and a red frame warning means non-compliance for 3 consecutive days.

[0049] The present invention also includes a mechanism for handling abnormal compliance, and the specific process is shown in Figure 2Schematic diagram of the process for handling non-compliance exceptions. When the weekly exercise compliance rate of a patient is abnormal, such as below 80% or above 120%, the system will analyze the reasons (such as judging the type of exceeding the standard, analyzing the distribution of exercise time periods, retrieving heart rate and blood oxygen data, etc.) and pop up a floating prompt box for the administrator to choose to contact the patient, adjust the prescription, or continue to observe. For example, when the weekly compliance rate of patient Zhang San shows 72%, clicking on the "Prescription?" icon will pop up an analysis window showing indicators such as exercise volume, exercise frequency, and average intensity. After the system recommends increasing the exercise volume, the administrator can choose to adjust the prescription. The system will also automatically generate optimization options for selection, such as video communication with the patient, one-click adjustment of the prescription, marking for observation, etc.

[0050] In addition, a data management system can be constructed through exercise prescriptions and real-time collected patient exercise data to form a patient exercise file and interface with the hospital information system. The patient exercise file includes: (1) Generate a dynamic data dashboard. The data includes: 1) Cumulative exercise days: circular progress chart (current exercise progress / target exercise progress); 2) Exercise volume heat map: showing exercise distribution by hour; 3) 3D trajectory map: integrating GPS data to generate the exercise path (for inpatients, showing the in-hospital exercise area); 4) Historical comparison module: slide to select the time axis, showing the change curve of exercise volume (the red line is the prescription value), heart rate-blood oxygen correlation scatter plot, and the system automatically marks abnormal points (such as when the heart rate > 180, it is marked in red).

[0051] (2) Generate an intelligent exercise log: Combine the bracelet and manual input to form a dual-channel log entry mechanism, automatically generate a standardized medical document, and synchronize the medical record and nursing record. The specific steps are as follows: 1) Real-time collect the following data: Basic data (through the bracelet): exercise time, distance, steps; Intensity indicators (through the bracelet): real-time speed, metabolic equivalent; Physiological parameters: dynamic heart rate (bracelet), blood oxygen (bracelet), plantar pressure distribution (intelligent insole), blood pressure (Internet of Things sphygmomanometer) (recorded every 5 minutes).

[0052] 2) Manually supplement item data: Pain site marking: Visual Analogue Scale (VAS) score for pain; Subjective exertion grading: Subjective Borg score for exertion.

[0053] Standardized medical documents: For inpatients, standard medical records are automatically generated, such as "The patient completed x sets of walking training today, with an average heart rate of xx bpm, blood pressure fluctuating between xx-xx / xx-xx mmHg, and blood oxygen fluctuating between xx-xx%." When critical values occur during exercise, treatment measures and records are prompted, such as: when the blood oxygen < 90%, "Oxygen inhalation for observation" is automatically added. For discharged patients, a home rehabilitation report and suggestions are generated: "The compliance rate this week is 82%. It is recommended to increase resistance training", and abnormal values are marked: the exceeding data is highlighted in yellow.

[0054] Through the real-time biological monitoring - prescription dynamic optimization - multi-terminal collaboration mechanism, this module forms a three-layer security protection system to monitor the exercise health of patients. Specifically as follows: (1)Real-time biological monitoring 1) Dynamic threshold monitoring: The basic threshold is automatically generated according to the patient's file (such as heart rate max = 220 - age); The threshold is adjusted in real time: It floats up and down by 5% according to the blood pressure of the day.

[0055] 2) When data abnormalities occur in inpatients, a three-level response mechanism is activated, with the interface flashing for reminder, video and voice warnings paused, and the responsible nurse automatically called. For the process details, see Figure 3 。

[0056] (2)Prescription dynamic optimization: 1) Generate a "Prescription Adaptation Report" every month: such as retention rate analysis, and statistics on the implementation of prescription terms; Progress curve: such as showing the improvement trend of the main indicators; Intelligent suggestions: such as significant improvement / stagnant improvement: It is recommended to advance to the next stage / recommend changing the training mode.

[0057] 2) Prescription confirmation process: Major adjustments require double review (doctor + rehabilitation therapist / nurse); Historical versions can be traced and compared.

[0058] (3)When data abnormalities occur during exercise and exceed the threshold, a multi-terminal collaborative warning is activated. Specifically as follows: 1) Patient side: The sports bracelet vibrates + voice broadcasts, such as "The current heart rate is too fast. Please slow down immediately"; 2) Administrator side: The pop-up window shows the patient's real-time exercise path, and automatically associates the electronic medical record to display key information such as the allergy history; 3) Family member side: The APP side pushes a concise warning, such as "Zhang San's current blood pressure is 165 / 100 mmHg".

[0059] The intelligent push module for health education content includes two parts: a health education knowledge base and a personalized health education path.

[0060] Collect multi-dimensional features of patients, organize the educational content related to PAD-related diseases, diet, medications, exercise, lifestyle habits, and surgeries, and upload it to the knowledge base. Administrators can manage this content through functions such as uploading, adding, editing, and deleting.

[0061] A personalized educational path generation method constructs a patient feature portrait based on the collected multi-dimensional features. The patient feature portrait includes disease diagnosis results, clinical data, medication lists, surgical records, exercise prescriptions, and patient lifestyle habits. When generating the initial educational content, the system performs multi-dimensional label annotation on each piece of content in the educational knowledge base and establishes a knowledge vector matrix, and filters out the educational content with the highest matching degree at the current time point through an improved KL divergence algorithm.

[0062] The calculation formula for the matching degree is: ; Where, represents the matching degree; represents the knowledge timeliness at the current time point t, , is the decay rate, represents the interval between the knowledge release date and the current time point; represents the total number of feature dimensions of the patient feature portrait; represents the feature dimension variable, such as , corresponding to the disease diagnosis result in the patient feature portrait; represents the weight coefficient of the current feature dimension; represents the patient feature vector; represents the i-th knowledge item; represents the patient feature vector of the feature dimension; represents the knowledge item of the feature dimension; represents the intersection; represents the union; represents taking the numerical value.

[0063] The initial path generation executes a priority sorting algorithm. If the KL distances of multiple pieces of content are similar, the content with a high reading completion rate is preferred. For example, the educational content adopts mandatory association items: content directly related to diagnosis / surgery (such as "PAD nursing points"); for example, high-risk items: content related to current abnormal indicators (such as pushing a low-fat diet guide when blood lipid-related indicators increase); for example, behavior intervention items: content matching bad lifestyle habits (such as automatically adding a "module on the damage of tobacco to blood vessels" for smoking patients).

[0064] For example Figure 4 as shown, a tree-like push path is generated.

[0065] In addition, the system also sets key monitoring node triggers, such as time nodes like the preoperative preparation period, the postoperative acute period, the in-hospital rehabilitation period, and the home rehabilitation period, as well as event nodes like a decrease in the number of steps, abnormal blood sugar, and a decrease in ABI, to dynamically adjust the content knowledge weight and optimize the push strategy. A time decay mechanism is used to dynamically adjust the knowledge weight of the initial education content, and the expression is: ; Wherein, is the knowledge weight of the updated initial education content; is the knowledge weight of the initial education content before update; n is the number of push cycles; represents periodic decay; represents continuous decay; is the number of days since the last effective reading; is the forgetting factor, such as set to 0.05; is the event correlation degree of the i-th push cycle is the indicator function of, for example, when an event (ABI value decrease > 0.15) is detected, otherwise it is 0.

[0066] Analyze the real-time reading behavior data of patients for the initial education content, calculate the reading behavior similarity of patients, and generate a patient recommendation list. The expression is: ; ; Wherein, represents the reading behavior similarity between patient u and patient v; represents the set of the number of common push cycles between patient u and patient v; represents the reading situation of patient u for the education content of the i-th push cycle. A value of 1 indicates that the reading duration ≥ 30s, representing in-depth reading; a value of 0.5 indicates that the reading duration < 30s, representing fast reading; a value of 0 indicates that the content is not opened; represents the reading situation of patient v for the education content of the i-th push cycle; represents the average reading duration of patient u for the education content in all push cycles; represents the average reading duration of patient v for the education content in all push cycles; represents patient 's recommendation list; represents the set of patients with similar reading behaviors to patient u; represents the reading situation of patient v for the education content of the j-th push cycle; According to the multi-dimensional features of patients collected in real time, when abnormal indicators of a patient are detected, relevant content matching the abnormal indicators is searched from the education knowledge base, inserted at the top of the patient recommendation list, and a warning is sent to the medical staff side.

[0067] For the processing of unread content, the system has a hierarchical reminder mechanism. When the number of unread items of a certain patient is greater than 2 and the unread days are between 1 and 3 days, a first-level reminder is triggered, that is, the APP in-site message is automatically pushed at 09:00 every day; a text message reminder template is sent on the 3rd day of unread; the intelligent outbound call system is started on the 7th day of unread. After the status is updated to confirmed after a phone call, it is marked as read. If not answered, it is added to the next call queue. If the recipient refuses to receive, it is transferred to manual follow-up.

[0068] The quality control closed-loop management module constructs a standardized quality control index system based on the processing and feedback of the rehabilitation evaluation module, the exercise prescription generation and dynamic adjustment module, and the intelligent push module of education content, generates quality control data, and conducts early warning and improvement.

[0069] In this embodiment, a standardized quality control index system is constructed through 8 dimensions to comprehensively ensure the timeliness, effectiveness, accuracy, and scientificity of the rehabilitation of PAD patients. As shown in Table 3, the standardized quality control index system of 8 dimensions includes: the timely rate of rehabilitation evaluation, the timely rate of patient enrollment, the matching degree of exercise prescription, the effective rate of patient exercise, the implementation rate of education push, the timely rate of education notice, the health education reading rate, and the effective reading rate.

[0070] Table 3. 8-Dimension Quality Control Index Model

[0071] The quality control data is also visually displayed through a heat matrix chart, a trend comparison chart, and a quality control analysis and improvement report. The heat matrix chart shows the completion degree of 8 indicators and forms a three-color warning of red-yellow-green, as shown in Table 4. The trend comparison chart supports the comparison of historical data. The quality control analysis report is generated monthly and supports screening by indicator classification.

[0072] Table 4. Quality Control Three-Color Warning Processing Flow Chart

[0073] In terms of quality improvement, a closed-loop built-in PDCA cycle processing mechanism is adopted. The system automatically generates a "Quality Control Analysis Report" to recommend a standardized improvement process and track the implementation progress. When indicators deviate for multiple consecutive cycles, the system automatically calls the improvement measure knowledge base to recommend solutions and track the effect verification. The PDCA cycle processing mechanism process is as follows: 1) Problem discovery: The system automatically generates a "Quality Control Analysis Report" (including a fishbone diagram of the root cause).

[0074] 2) Improvement plan: Build a knowledge base of improvement measures (including more than 50 standardized improvement processes).

[0075] 3) Execution tracking: Establish an improvement task tracking dashboard (showing progress in Gantt chart mode).

[0076] 4) Effect verification: Automatically trigger the effect evaluation algorithm after the improvement cycle ends.

[0077] The initial interface of the APP adopts a hierarchical progressive architecture, mainly including an intelligent rehabilitation module, an adaptive education module, and an intelligent safety monitoring module. The intelligent rehabilitation module uses an intelligent prescription engine of "hierarchical progressive - dynamic optimization". The exercise plan is dynamically demonstrated with a 3D human body model. The activation degree of key muscle groups is displayed with a heat map, and each action is marked with multi-dimensional labels such as indications, metabolic equivalents, and contraindication reminders. Real-time biofeedback training collects data from bracelets and intelligent insoles through the linkage of Internet of Things devices, establishes a dynamic threshold model, and triggers a three-level response when abnormal, as Figure 5 shown. Intelligent progress management uses a dynamic compliance algorithm to calculate the compliance rate and sets up a vascular health index integral system to encourage patient compliance. The multi-modal exercise log constructs a three-in-one recording system of "device collection - manual supplement - intelligent analysis". The automated collection layer integrates GPS and indoor positioning data to mark the exercise hot spots. The dynamic curve of physiological parameters records the changes in heart rate - blood oxygen - foot pressure every 5 seconds. The manually supplemented data includes the marking of pain locations and the manual filling of the daily blood pressure. The intelligent analysis report generates a "Exercise Health Brief" every day and associates the exercise data of the previous 24 hours to generate an inducement analysis tree.

[0078] The adaptive education module uses a recommendation algorithm of "feature clustering - dynamic optimization" to establish a six-dimensional feature vector to construct a patient portrait, and the real-time update mechanism triggers portrait reconstruction when the change in ABI value is greater than 0.15. The content matching algorithm applies the improved KL divergence for knowledge matching. The interactive learning system improves the learning effect of patients through scenario simulation tests and knowledge mastery evaluations. The multi-channel reminder system constructs a three-level intelligent reminder strategy. When the number of unread items is greater than 2 and the unread duration is less than 3 days, it triggers an APP push for unread reminders. When the unread duration is 3 to 7 days, it triggers a text message reminder. When the unread duration is greater than 7 days, it triggers an intelligent outbound call + family member linkage. Emergency content is preferentially pushed. For example, when the system detects that the systolic blood pressure is greater than 180 mmHg, it automatically pushes the content of "Treatment of hypertensive emergencies". The AI image recognition system analyzes the wound photos uploaded by patients and automatically matches the wound care guidelines.

[0079] The intelligent security monitoring module constructs a three - level protection network of "device - algorithm - human". The dynamic threshold system adjusts the upper limit of heart rate according to the morning blood pressure value of the day. The foot pressure feedback system generates a plantar pressure cloud map in real - time and triggers a gait correction suggestion when the unilateral pressure difference is greater than 15%. The multi - parameter correlation early warning establishes a blood pressure - blood oxygen - gait correlation matrix, and triggers a red fall warning when "blood pressure drops + blood oxygen drops + gait symmetry drops", and uses the LSTM model to predict the trend of fall risk and issue a warning 30 minutes in advance. Remote rehabilitation monitoring supports voice interaction to query exercise data through a virtual rehabilitation assistant, and the intelligent Q&A system analyzes common rehabilitation problems based on a medical knowledge graph. Family - hospital collaboration establishes a family member monitoring dashboard, automatically pushes a concise report when key indicators are abnormal, and artificial consultation is used as a supplementary means to answer complex questions.

[0080] After testing, after using the system of the present invention, the incidence rate of adverse exercise events in orange - risk patients decreased from 12.7% to 4.3%; the recognition response time of high - risk patients was shortened from an average of 4.2 hours to 11 minutes.

[0081] In summary, compared with the prior art, the full - process PAD patient rehabilitation management system proposed by the present invention realizes the innovation of the PAD patient rehabilitation management mode through multi - modal data fusion and an intelligent decision - making engine, and its beneficial effects are reflected in the following aspects: (1)Intelligent integration of multi - source data and dynamic risk control 1) In - depth analysis of cross - system data: Based on the FHIR standard and NLP unstructured text parsing technology, it realizes the real - time integration of HIS / NIS system data, breaks through the limitations of traditional structured coding, and accurately identifies patients with fuzzy diagnoses such as "suspected PAD". Through an intelligent risk grading system, it dynamically fuses multi - dimensional parameters such as Fontaine stage, ABI index, and contraindications, establishes a minute - level risk scanning mechanism, improves the recognition response speed of extremely high - risk patients, and reduces the false alarm and missed alarm rate of early warnings.

[0082] 2) Intelligent generation of exercise prescriptions and safety protection: Adopting a three - layer architecture of "multi - modal data input - labeled action library matching - conflict detection", it realizes the accurate calculation of exercise prescription parameters, combines a dynamic threshold model and a three - level collaborative early warning network, and reduces the incidence rate of exercise - related adverse events.

[0083] (2)Intelligent decision - making and full - process quality control closed - loop 1) Adaptive rehabilitation path optimization: Based on the improved KL divergence algorithm, a deep matching model of patient feature vectors and education knowledge bases is constructed to achieve time-limited decay push of education content and event-triggered updates (such as automatic triggering of nursing guide push for newly developed wounds), improving the reading completion rate. During the execution of the exercise prescription, biometric data such as foot pressure and gait symmetry are collected in real time through Internet of Things devices, and the pass rate algorithm is dynamically optimized to achieve precise adaptation of exercise intensity and physiological state.

[0084] 2) Eight-dimensional quality control engine-driven management upgrade: A quality control heat map covering indicators such as evaluation timeliness rate, prescription matching degree, and reading completion rate is constructed. Combining with the PDCA cycle, automatic problem identification (such as continuous abnormal pass triggering root cause analysis of fishbone diagrams) and embedding of standardized improvement processes are realized, improving the scientific nature of rehabilitation plan adjustment and reducing the labor cost of quality control management.

[0085] (3) Multimodal interaction and positive incentive for patient behavior 1) Scenario-based intelligent reminder system: Breaking through the traditional time-series reminder mode, multi-dimensional event triggers such as abnormal physiological indicators and decreased behavior compliance are established to achieve priority push of emergency education content and linkage warning for the family member side. Through the three-dimensional motion visualization model and VHI integral feedback, the patient's understanding of rehabilitation goals is improved.

[0086] 2) Improvement of rehabilitation efficacy throughout the cycle: Based on real-time data such as foot pressure cloud maps of intelligent insoles and physiological curves of bracelets, a motion-physiology correlation analysis model is constructed to improve the individual adaptation accuracy of exercise prescriptions. Through closed-loop quality control and multi-terminal collaboration, the patient's disease state is improved, the incidence of postoperative complications is reduced, and the overall rehabilitation cycle is shortened.

[0087] (4) Optimization of medical resources and evidence-based decision-making support 1) Data-driven resource reallocation: Through an automated risk grading and warning freezing mechanism, medical staff resources are tilted towards high-risk patients to improve the efficiency of handling critical values in rehabilitation.

[0088] 2) Construction of a full-process management system: From prescription generation (algorithm formula floating prompt) to quality control improvement (automatic generation of standardized medical documents), all operations retain a traceable data chain, providing a high-value data set for clinical research and assisting in the dynamic optimization and precision medical practice of PAD patient rehabilitation.

[0089] In summary, the present invention constructs a management system covering the entire rehabilitation process of PAD patients through multimodal data fusion and intelligent algorithm collaboration, significantly improving the accuracy and safety of rehabilitation management, and solving the pain points of the existing technology in aspects such as low data management efficiency, insufficient intelligence of exercise prescriptions, low personalization degree of education push, and imperfect quality control systems.

[0090] In several embodiments provided by the embodiments of the present invention, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device and method embodiments described above are merely illustrative. For example, the flowcharts in the accompanying drawings show the possible architectures, functions, and operations of devices, methods, and computer program products according to multiple embodiments of the present invention. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code, and the module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0091] In addition, the functional modules in each embodiment of the present invention can be integrated together to form an independent part, or each module can exist separately, or two or more modules can be integrated to form an independent part.

[0092] If the function is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, an electronic device, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes. It should be noted that in this article, the term "including", "comprising", or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article, or device including a series of elements not only includes those elements, but also includes other elements that are not explicitly listed, or also includes elements inherent to this process, method, article, or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article, or device including the said element.

[0093] The terms used in the embodiments of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The singular forms "a", "the", and "said" used in the embodiments of the present invention and the appended claims are also intended to include the plural forms unless the context clearly dictates otherwise.

[0094] It should be understood that the term "and / or" used herein is merely a description of an association relationship between associated objects, indicating that three relationships may exist. For example, A and / or B may represent: the sole existence of A, the simultaneous existence of A and B, and the sole existence of B. Additionally, the character " / " herein generally represents an "or" relationship between the associated objects before and after.

[0095] Depending on the context, the word "if" as used herein can be interpreted as "when" or "while" or "in response to determining" or "in response to detecting". Similarly, depending on the context, the phrase "if determined" or "if detected (stated condition or event)" can be interpreted as "when determined" or "in response to determining" or "when detected (stated condition or event)" or "in response to detecting (stated condition or event)".

[0096] The "first / second" mentioned in the embodiments is merely to distinguish similar objects and does not represent a specific order for the objects. It can be understood that the "first / second" can be interchanged in their specific order or sequence when permitted. It should be understood that the objects distinguished by the "first / second" can be interchanged appropriately so that the embodiments described herein can be implemented in an order other than those illustrated or described herein.

[0097] The foregoing is only a preferred embodiment of the present invention and is not used to limit the present invention. For those skilled in the art, various modifications and variations can be made to the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A rehabilitation management system for patients with peripheral artery disease based on the whole process, characterized in that, Including: A patient screening and risk grading module, a rehabilitation assessment module, a sports prescription generation and dynamic adjustment module, an intelligent push module for education content, and a quality control closed-loop management module; Among them, the patient screening and risk grading module is used to connect with the hospital information system through a medical data interface, obtain and analyze the basic data of patients with peripheral artery disease in real time, and construct an intelligent risk grading system based on the Fontaine stage, ankle-brachial index, and contraindications to automatically update the patient risk level and trigger an alarm; The rehabilitation assessment module is used to generate an assessment report with time as the axis according to the patient's basic data and the biologically monitored data obtained in real time; The sports prescription generation and dynamic adjustment module is used to generate a sports prescription based on the assessment report, comorbidities, and biologically monitored data obtained in real time according to the combined applicable items and safety principles, and perform dynamic optimization and adjustment according to the intelligent risk grading system; The intelligent push module for education content is used to collect multi-dimensional features of patients to construct a patient feature portrait, establish an education knowledge base, generate initial education content, and perform dynamic adjustment and personalized adaptive push on the initial education content; The quality control closed-loop management module is used to construct a standardized quality control index system, generate quality control data, and give an alarm and make improvements according to the processing and feedback of the rehabilitation assessment module, the sports prescription generation and dynamic adjustment module, and the intelligent push module for education content.

2. The rehabilitation management system for peripheral artery disease patients based on the whole process according to claim 1, wherein , The patient's basic data includes the patient's basic information, diagnosis code, and test report; If the diagnosis code is a fuzzy diagnosis of suspected peripheral artery disease, the key disease features are analyzed and extracted using NLP technology based on the patient's basic data, and combined with the patient's test report to dynamically correct the patient screening result.

3. The rehabilitation management system for peripheral artery disease patients based on the whole process according to claim 1, characterized in that , The biologically monitored data includes exercise time, distance, steps, real-time speed, metabolic equivalent, dynamic heart rate, blood oxygen, plantar pressure distribution, and blood pressure; the content of the assessment report includes: patient assessment, assessment date, height, weight, BMI, medications used, blood glucose, blood lipids, blood pressure, whether smoking, whether drinking, exercise habits, wound conditions, pain visual analogue scale VAS, lower limb muscle strength, short physical performance battery SPPB, 6-minute walk distance 6MWD and steps, claudication distance, maximum walking distance, ankle-brachial index ABI, leg circumference, quality of life scale, walking impairment questionnaire, hope scale, and subjective fatigue score; Among them, BMI = weight / height 2 ; The types of 6MWD are divided into male and female. For male, 6MWD = 1140 - 5.61×BMI - 6.94×age; for female, 6MWD = 1017 - 6.24×BMI - 5.83×age, and age is in years.

4. The rehabilitation management system for peripheral artery disease patients based on the whole process according to claim 1, characterized in that , The sports prescription includes the basic exercise parameters of the patient and also shows comorbidity adaptation suggestions; the basic exercise parameters of the patient include exercise frequency, exercise intensity, exercise duration, exercise mode, and exercise volume; The exercise intensity is calculated by the following method: ； Where I represents the exercise intensity; 6MWD represents the 6-minute walk distance; The quantification model of the exercise volume is: ； Among them, represents the amount of exercise; I represents the exercise intensity; represents the total exercise duration; represents the actual number of steps in the 6-minute walk test; SafetyFactor represents the safety adjustment coefficient.

5. A rehabilitation management system for peripheral artery disease patients based on the whole process according to claim 1, characterized in that , When making dynamic optimization and adjustment according to the intelligent risk grading system, the matching degree of the exercise prescription is judged intelligently, and the threshold conflict of the data parameters of the exercise prescription is automatically checked and adjusted.

6. The rehabilitation management system for peripheral artery disease patients based on the whole process according to claim 1, wherein , The patient characteristic portrait includes disease diagnosis results, clinical data, medication lists, surgical records, exercise prescriptions, and patient living habits; When generating the initial education content, after performing multi-dimensional label annotation on each content in the education knowledge base, content matching is performed based on the KL divergence, and the education content with the highest matching degree at the current time point is selected; the calculation formula for the matching degree is: ； Among them, represents the matching degree; represents the knowledge timeliness at the current time point t, , is the attenuation rate, represents the interval between the knowledge release date and the current time point; represents the total number of feature dimensions of the patient feature portrait; represents the feature dimension variable; represents the weight coefficient of the current feature dimension; represents the patient feature vector; represents the i-th knowledge item; represents the patient feature vector of the feature dimension; represents the knowledge item of the feature dimension; represents the intersection; represents the union; represents taking a numerical value; When the matching degrees of the selected education content are equal, the content with a high reading completion rate is preferentially selected as the initial education content.

7. A rehabilitation management system for peripheral artery disease patients based on the whole process according to claim 1, characterized in that , The dynamic adjustment and personalized adaptive push of the initial education content are as follows: Multidimensional characteristics of the patient are collected in real time, and the education knowledge base is updated; According to the updated education knowledge base, the knowledge weight of the initial education content is dynamically adjusted using the time decay mechanism, and the expression is: ； Among them, is the knowledge weight of the updated initial missionary content; is the knowledge weight of the initial missionary content before update; n is the number of push cycles; is the number of days since the last effective reading; represents periodic decay; represents continuous decay; is the forgetting factor; is the event correlation degree of the i-th push cycle indicator function; Analyze the real-time reading behavior data of the patient for the initial education content, calculate the reading behavior similarity of the patient, and generate a patient recommendation list. The expression is: ； ； Among them, represents the reading behavior similarity between patient u and patient v; represents the set of the number of common push cycles between patient u and patient v; represents the reading situation of patient u for the educational content in the i-th push cycle. The value of 1 indicates that the reading duration is ≥ 30s, representing in-depth reading; the value of 0.5 indicates that the reading duration < 30s, representing fast reading; the value of 0 indicates that the content is not opened; represents the reading situation of patient v for the educational content in the i-th push cycle; represents the average reading duration of patient u for the educational content in all push cycles; represents the average reading duration of patient v for the educational content in all push cycles; Represents a patient 's recommended list; Represents the set of patients with similar reading behaviors to patient u; Represents the reading situation of patient v for the educational content in the j-th push cycle; According to the multi-dimensional characteristics of the patient collected in real time, when it is detected that the patient's indicators are abnormal, the content related to the abnormal indicators is searched and matched from the education knowledge base, inserted at the top of the patient recommendation list, and a warning is sent to the medical staff side.

8. A rehabilitation management system for peripheral artery disease patients based on the whole process according to claim 1, characterized in that , It also includes: when generating an exercise prescription, a dynamic threshold model is established and real-time feedback training is performed according to the biometric monitoring data obtained in real time; the dynamic threshold model includes a maximum heart rate threshold, and its expression is: Maximum heart rate threshold = 220 - patient age ± daily blood pressure fluctuation value.

9. The rehabilitation management system for peripheral artery disease patients based on the whole process according to claim 1, characterized in that , It also includes: during the execution of the exercise prescription, according to the exercise prescription and the biometric monitoring data obtained in real time, a dynamic compliance algorithm is used to calculate the daily exercise compliance rate and the patient's exercise results are fed back in real time; among them, the calculation formula for the daily exercise compliance rate is: Daily exercise compliance rate = Σ (daily completed amount × time decay coefficient) / exercise prescription requirement amount; Σ represents the sum of all daily exercise completed amounts; Time decay coefficient = 1 / (1 + 0.1 × delay days); The exercise results are fed back through the vascular health index VHI score, and the calculation formula is: VHI = 0.3 × 6MWD progress rate + 0.2 × gait symmetry improvement degree + 0.5 × prescription compliance degree; Among them, the 6MWD progress rate represents the results of two 6-minute walking distance tests of the patient before and after treatment, that is, (6MWD after treatment - 6MWD before treatment) / 6MWD before treatment × 100%; the gait symmetry improvement degree represents the improvement degree of the patient's gait symmetry, which is obtained by comparing the differences in the patient's left and right gait before and after treatment; the prescription compliance degree represents the degree of compliance of the patient in exercising according to the exercise prescription issued by the doctor, that is, (actual number of exercise times / prescribed number of exercise times) × 100%.

10. The rehabilitation management system for peripheral artery disease patients based on the whole process according to claim 1, wherein , the standardized quality control index system includes the timely rehabilitation assessment rate, the timely patient enrollment rate, the matching degree of exercise prescriptions, the effective patient exercise rate, the implementation rate of education push, the timely education notice rate, the health education reading rate and the effective reading rate; Among them, the calculation method of the timely rehabilitation assessment rate is: (the number of patients who completed the assessment on time / the total number of patients to be assessed) × 100%, and the definition of completing on time is: the assessment date ≤ the preset date + 1 working day; The calculation method of the timely patient enrollment rate is: (the number of patients whose system enrollment time ≤ 24 hours after admission / the total number of newly enrolled patients) × 100%; The calculation method of the matching degree of exercise prescriptions is: (the passing rate × 80% - 120% × the number of patients / the number of patients enrolled in the system) × 100%; the passing rate = (the actual amount of exercise completed by the patient / the amount of exercise required by the exercise prescription) × 100%; The calculation method of the effective patient exercise rate is: the main index improvement rate = (the current 6MWD - the baseline 6MWD) / the baseline 6MWD × 100%; The calculation method of the implementation rate of education push is: (the number of patients who actually received the education content push / the total number of patients to be pushed) × 100%; The calculation method of the timely education notice rate is: (the number of patients who received the education content notice within 3 days / the total number of unread patients) × 100%; The calculation method of the health education reading rate is: (the number of patients who read health education ≥ 1 time / the total number of patients received) × 100%; The calculation method of the effective reading rate is: (the number of patients with in-depth reading / the total number of reading patients) × 100%, and the definition of in-depth reading is: single stay ≥ 120s and complete the knowledge test.

Images