Acupuncture treatment planning system for ischemia with non-obstructive coronary artery disease

Abstract

The invention discloses an acupuncture treatment planning system for ischemia with non-obstructive coronary artery diseases, and relates to the technical field of medical health. The acupuncture treatment planning system for ischemia with non-obstructive coronary artery diseases can dynamically adjust a treatment scheme according to the actual health state and real-time feedback of a patient, and ensures that the treatment effect is exerted to the maximum extent; according to the scheme, the treatment scheme is ensured to be balanced among multiple targets through a multi-target optimization algorithm, and the comprehensive treatment effect is further improved through real-time feedback and dynamic adjustment; the defects of a traditional medical system in the aspect of combining the modern information technology and acupuncture treatment are effectively overcome, and the accuracy, individuation and real-time performance of a treatment scheme are ensured.

Description

Technical Field

[0001] The present invention relates to the field of medical health technology, and in particular to an acupuncture treatment planning system for ischemic non-obstructive coronary artery disease. Background Art

[0002] Currently, ischemia with non-obstructive coronary artery disease (INOCA) is difficult to diagnose and treat clinically. Traditional drugs, interventional and surgical treatments have disadvantages such as large side effects, high risks or strong trauma. At the same time, acupuncture therapy, as a traditional Chinese medicine therapy, shows certain potential in regulating blood flow and alleviating symptoms, but its therapeutic effect is highly dependent on the location, depth and timing of acupuncture, and often relies on the experience of doctors, lacking scientific and personalized guidance. Although the existing intelligent medical system can provide data analysis and auxiliary decision-making for some diseases, it has not yet organically combined traditional acupuncture therapy with modern information technology, and cannot make full use of the patient's electrocardiogram and imaging real-time health data for precise treatment planning. This makes it difficult to form dynamic adjustment and optimization plans based on individual differences in the treatment of ischemia with non-obstructive coronary artery disease. Summary of the invention

[0003] 1. Technical issues to be resolved

[0004] In view of the shortcomings of the existing technology, the present invention provides an acupuncture treatment planning system for ischemic non-obstructive coronary artery disease, which solves the defects of the traditional medical system in combining modern information technology and acupuncture treatment, and ensures the accuracy, personalization and real-time nature of the treatment plan.

[0005] (II) Technical solution

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: an acupuncture treatment planning system for ischemic coronary artery disease with non-obstructive coronary artery disease, the system comprising:

[0007] The multi-dimensional health data collection module integrates a variety of physiological monitoring methods. Through wireless sensors, portable devices or hospital monitoring systems, it collects patients' electrocardiograms, coronary artery imaging data, hemodynamic parameters, biomarkers and related physiological parameters in real time, and combines them with patients' clinical medical records for analysis;

[0008] Heterogeneous data fusion and adaptive algorithm engine, based on the collected health data, uses hybrid data fusion technology, including rule-based, model-driven and data-driven multi-layer fusion strategies to process heterogeneous data and generate accurate and real-time patient health portraits; the engine optimizes data fusion strategies by applying multimodal feature fusion algorithms, and extracts the most relevant diagnostic and treatment features for ischemic non-obstructive coronary artery disease based on big data analysis and deep learning models;

[0009] The treatment plan generation module analyzes the patient's health data, combines traditional acupuncture treatment theory, and uses intelligent algorithms to automatically generate personalized acupuncture treatment plans, including treatment location, depth, and time;

[0010] The real-time feedback and adjustment module is used to dynamically adjust the treatment plan according to the real-time monitoring data during the treatment process to achieve personalized and continuously optimized treatment effects.

[0011] Preferably, the data acquisition module includes:

[0012] A multi-type sensor network, including portable electrocardiogram devices, blood flow velocity monitors, and ultrasound probes, tracks microscopic changes in coronary blood flow in real time, and combines the patient's real-time exercise, rest, and emotional data to further enrich the understanding and dynamic analysis of symptoms, forming a continuous health data stream;

[0013] Integrate data storage and data transmission protocols, adopt distributed database architecture and efficient data transmission protocols to ensure real-time transmission of patient health data to the central processing module or cloud platform, and protect data security, integrity and privacy.

[0014] Preferably, the heterogeneous data fusion and adaptive algorithm engine includes:

[0015] Adaptive model selection and optimization unit, which dynamically selects the most suitable analysis model according to the patient's personalized health status, including convolutional neural network, graph neural network, decision tree, support vector machine, and optimizes model parameters through feedback loop, automatically adjusting the calculation strategy to respond to clinical changes;

[0016] Personalized data weighting algorithm, based on historical treatment data and real-time patient data, automatically assigns weights to different types of health data by learning the physiological and pathological change trends of patients, ensuring that key health information receives adequate attention, thereby providing support for the generation of acupuncture treatment plans;

[0017] In the early stage of heterogeneous data fusion, based on known medical rules and expert knowledge base, rule-based fusion methods are used to preliminarily fuse data from different sensors and data sources; after rule-based fusion, machine learning models are used to further optimize data fusion; through model-driven methods, different types of data are weighted and correlated; through data-driven methods, deep learning algorithms are applied to fuse all multimodal data; data-driven fusion strategies automatically discover potential relationships between different health data by learning complex patterns from big data; for example, through deep neural networks, imaging data and physiological monitoring data are fused to extract important features related to coronary artery disease, and the processing flow is optimized through learning to improve the accuracy of data fusion; after completing multi-level data fusion, all data will be analyzed and processed to generate an accurate and real-time patient health portrait; the health portrait is a comprehensive and vivid description of the patient's status based on the fused heterogeneous data, covering the patient's physiological status, disease progression, and pathological changes.

[0018] Preferably, the adaptive model selection and optimization unit selects a suitable analysis model according to the patient's personalized health status, and optimizes the model parameters through a feedback loop to adjust the calculation strategy:

[0019] Collect and preprocess multi-source health data, including electrocardiogram, blood flow parameters, imaging data, and biomarkers; generate personalized health profiles of patients through heterogeneous data fusion, including data in multiple dimensions such as physiology and pathology; these data are used as input to the adaptive model selection and optimization unit;

[0020] Based on the patient's personalized health portrait, the system evaluates changes in their physiological and pathological states, determines the severity, progression, and potential risks of the disease, and selects the most suitable analysis model based on the patient's current health status. Common models include: Convolutional Neural Network (CNN): suitable for extracting features from imaging data and evaluating coronary artery imaging changes; Graph Neural Network (GNN): suitable for processing complex associated data, such as blood flow changes and electrocardiogram time series data; Decision Tree (DT) and Support Vector Machine (SVM): suitable for processing structured data, such as clinical history data and real-time physiological data;

[0021] Through adaptive mechanisms, the most appropriate model is dynamically selected and adjusted. For different patient conditions, the system automatically selects models and adjusts model parameters to ensure the accuracy of diagnosis or treatment planning. For example, for patients with obvious coronary artery lesions, convolutional neural networks (CNNs) may be used to analyze imaging data, while for patients with more complex clinical data, support vector machines (SVMs) may be used to analyze multi-dimensional physiological parameters.

[0022] By collecting patient feedback data in real time (such as physiological responses and blood flow changes after treatment), the currently selected analysis model is optimized; model parameters (such as convolution kernels and learning rates) are dynamically adjusted according to changes in clinical data to improve the accuracy of model predictions; through continuous clinical feedback and data learning, the model's predictive and adaptable capabilities are optimized to ensure that the algorithm can cope with changes in different clinical scenarios; whenever the patient's physiological or pathological state changes significantly, the model will automatically re-evaluate and update the strategy to minimize errors and maintain the accuracy of the treatment effect.

[0023] Preferably, the treatment plan generating module comprises:

[0024] An integrated intelligent decision support system generates a treatment plan for each patient by integrating medical literature, treatment guidelines, and real-time health data. The system uses a combination of reinforcement learning and adaptive algorithms to continuously correct and optimize decisions during the treatment process, ensuring that the plan can be dynamically adjusted based on the patient's response;

[0025] Multi-objective optimization treatment generation algorithm, which considers multiple treatment goals at the same time, and generates a comprehensive treatment plan through multi-objective optimization technology, including acupuncture site, depth, treatment timing and acupuncture frequency, to maximize the treatment effect and reduce side effects.

[0026] Preferably, the multi-objective optimization treatment generation algorithm is based on a reinforcement learning model, and the treatment plan is adjusted through continuous feedback to ensure that the treatment plan can be quickly adapted when the patient's health status changes, thereby ensuring the efficiency and personalization of the treatment;

[0027] The process of generating personalized acupuncture treatment plans by the treatment plan generation module includes: fusing all collected health data and using a multimodal feature fusion algorithm to generate a personalized health profile of the patient. The health profile includes the patient's physiological state, pathological state and other key health information, providing basic data for the generation of personalized treatment plans; combining traditional Chinese medicine acupuncture treatment theory to build a knowledge base that includes acupuncture treatment principles, acupuncture site selection, acupuncture depth and treatment timing; through deep learning, machine learning, and reinforcement learning in intelligent algorithms, the patient's health profile and information in the acupuncture treatment knowledge base are processed. According to the patient's specific symptoms and condition, the system will set clear treatment goals, such as improving blood flow, relieving symptoms, and reducing inflammation. The algorithm will optimize each treatment goal and generate the optimal treatment plan. Combined with the patient's specific health status, the optimal treatment location, depth and treatment duration are automatically evaluated to achieve the best treatment effect and automatically generate a personalized treatment plan;

[0028] A multi-objective optimization algorithm is used to consider multiple treatment goals at the same time to generate a comprehensive treatment plan. This optimization process will not only adjust the acupuncture site and depth, but also comprehensively consider the timing and frequency of treatment to minimize side effects and maximize the treatment effect. The treatment plan will be dynamically adjusted according to the patient's real-time health data. Through reinforcement learning, the treatment process is continuously optimized. The system will monitor the patient's physiological feedback data in real time and make corrections based on the treatment effect to ensure that every link in the treatment process can accurately adapt to the patient's changes. After each treatment cycle, the treatment plan will be reviewed based on the patient's response, and the subsequent treatment process will be optimized to ensure continuous improvement in long-term treatment effects. Based on intelligent algorithms and clinical feedback, a detailed personalized treatment plan is finally generated to clarify the acupuncture site, depth, and treatment time, and the plan is output to the treatment device or doctor through the interface. Once the treatment plan is determined, the treatment device or operator performs acupuncture treatment according to the plan. At the same time, the real-time monitoring system will continue to track the patient's physiological response and treatment effect so that necessary adjustments can be made at any time.

[0029] Preferably, the real-time feedback and adjustment module includes:

[0030] Real-time health monitoring and feedback interface, integrating physiological monitoring equipment with acupuncture treatment equipment, to achieve real-time monitoring during acupuncture treatment and provide instant feedback on the patient's physiological response;

[0031] Multi-dimensional treatment parameter feedback and adjustment strategy, using real-time data streams to adjust treatment parameters, including acupuncture site, depth, and treatment duration, combined with machine learning algorithms to optimize treatment effects and timing;

[0032] The feedback adjustment strategy adopts adaptive time series analysis technology to timely adjust the treatment plan based on dynamically collected data and key feedback information during the treatment process, and re-evaluate the effectiveness of treatment parameters when necessary.

[0033] Preferably, the multi-dimensional treatment parameter feedback and adjustment strategy uses real-time data streams to adjust treatment parameters, combined with machine learning algorithms, to optimize the process of treatment effect and treatment timing:

[0034] Through integrated physiological monitoring equipment, the patient's physiological feedback data, such as heart rate, blood flow changes, and local skin temperature, are collected in real time. The parameters during acupuncture treatment, including acupuncture site, acupuncture depth, and treatment duration, are collected in real time. These data are recorded in real time by dedicated sensors or treatment equipment; all collected real-time data are sent to the data processing module through a high-speed transmission protocol, and combined with the patient's clinical medical records and background information, including medical history, age, and gender. The data is encrypted during transmission to ensure the security, privacy, and integrity of the patient's data; the transmitted real-time data is pre-processed by the data cleaning module, including denoising, standardization, and normalization, to ensure the consistency and accuracy of the data in subsequent analysis. The feature extraction algorithm extracts key indicators from the collected physiological data and treatment data, such as the impact of acupuncture depth on local blood flow, acupuncture duration, and changes in heart rate.

[0035] Based on real-time collected data, reinforcement learning and deep learning in the machine learning algorithm continuously adjust the treatment strategy through feedback loops. The machine learning model is trained based on historical treatment data and real-time data to optimize the treatment effect. The algorithm can identify deviations or adverse reactions that occur during the treatment process and automatically adjust the acupuncture parameters to ensure the personalization and efficiency of the treatment.

[0036] Combined with the analysis results of the machine learning model, the treatment parameters: acupuncture site, depth, and duration are dynamically adjusted to generate a set of real-time adjustment strategies. These strategies may include fine-tuning the acupuncture site, increasing or decreasing the treatment depth, and extending or shortening the treatment duration. These adjustments will be based on real-time monitoring data and the prediction results of the machine learning model to optimize the treatment effect. After each treatment cycle, the system will evaluate the treatment effect, analyze the real-time data feedback, and determine whether the current treatment plan has achieved the expected treatment goals, including blood flow restoration and symptom relief. According to the feedback results after treatment, the system will further adjust the optimization strategy to ensure that in subsequent treatment cycles, the treatment plan can quickly adapt and adjust according to the changes in the patient's health status. Comprehensive adjustment of multi-dimensional parameters: Multi-dimensional adjustment is not limited to a single treatment parameter, but combines multiple physiological and treatment feedback dimensions, such as combining the patient's electrocardiogram changes, local blood flow parameters, and the influence of acupuncture depth and duration to comprehensively evaluate the treatment effect and adjust the treatment plan. This comprehensive adjustment process enables the treatment plan to respond to the patient's physiological changes at any time to ensure the optimization of treatment timing and effect.

[0037] Preferably, the method comprises:

[0038] Step 1: Collect the patient's electrocardiogram, coronary artery imaging data, hemodynamic parameters, biomarkers and related physiological parameters in real time through wireless sensors, portable devices or hospital monitoring systems, and analyze them in combination with the patient's clinical medical records;

[0039] Step 2: Based on the collected health data, hybrid data fusion technology is used to process heterogeneous data and generate a patient health profile;

[0040] Step 3: Analyze the patient's health data, combine it with traditional acupuncture treatment theory, and use intelligent algorithms to automatically generate personalized acupuncture treatment plans;

[0041] Step 4: Dynamically adjust the treatment plan based on real-time monitoring data during the treatment process;

[0042] The deep learning algorithm is based on multimodal data, uses convolutional neural networks (CNNs) to extract features from image data, combines them with physiological data, and generates optimized treatment plans through multi-task learning.

[0043] An electronic device, comprising:

[0044] one or more processors and storage devices for storing programs and data and executing the treatment planning method;

[0045] The display device is used to display the generation and dynamic adjustment process of the treatment plan, and provide feedback information to the treatment staff in real time to ensure that the patient's treatment process is visualized and operational.

[0046] (III) Beneficial effects

[0047] The present invention provides an acupuncture treatment planning system for ischemic non-obstructive coronary artery disease. It has the following beneficial effects:

[0048] The acupuncture treatment planning system for ischemic non-obstructive coronary artery disease generates a treatment plan based on deep learning. Unlike existing fixed treatment plans, the present invention can dynamically adjust the treatment plan according to the patient's actual health status and real-time feedback through a combination of reinforcement learning and deep neural network models to ensure that the treatment effect is maximized. This plan ensures that the treatment plan strikes a balance between multiple goals through a multi-objective optimization algorithm, and further improves the overall effect of the treatment through real-time feedback and dynamic adjustment. It effectively solves the defects of the traditional medical system in combining modern information technology and acupuncture treatment, and ensures the accuracy, personalization and real-time nature of the treatment plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 A schematic diagram of the framework of an acupuncture treatment planning system for ischemic coronary artery disease with non-obstructive coronary artery disease according to the present invention;

[0050] Figure 2 The present invention is a flowchart of an acupuncture treatment planning method for ischemic non-obstructive coronary artery disease. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] See also Figure 1 and Figure 2 The present invention provides a technical solution: an acupuncture treatment planning system for ischemic non-obstructive coronary artery disease, the system comprising:

[0053] The multi-dimensional health data collection module integrates a variety of physiological monitoring methods. Through wireless sensors, portable devices or hospital monitoring systems, it collects patients' electrocardiograms, coronary artery imaging data, hemodynamic parameters (such as blood flow velocity and blood flow resistance), biomarkers (such as inflammatory indicators) and related physiological parameters (such as body temperature and respiratory rate) in real time, and combines them with patients' clinical medical records (such as age and medical history) for analysis;

[0054] Heterogeneous data fusion and adaptive algorithm engine, based on the collected health data, uses hybrid data fusion technology, including rule-based, model-driven and data-driven multi-layer fusion strategies to process heterogeneous data and generate accurate and real-time patient health portraits; the engine optimizes data fusion strategies by applying multimodal feature fusion algorithms, and extracts the most relevant diagnostic and treatment features for ischemic non-obstructive coronary artery disease based on big data analysis and deep learning models;

[0055] The treatment plan generation module analyzes the patient's health data, combines traditional acupuncture treatment theory, and uses intelligent algorithms to automatically generate personalized acupuncture treatment plans, including treatment location, depth, and time;

[0056] The real-time feedback and adjustment module is used to dynamically adjust the treatment plan according to the real-time monitoring data during the treatment process to achieve personalized and continuously optimized treatment effects.

[0057] The data acquisition module includes:

[0058] A multi-type sensor network, including portable electrocardiogram devices, blood flow velocity monitors, and ultrasound probes, tracks microscopic changes in coronary blood flow in real time, and combines the patient's real-time exercise, rest, and emotional data to further enrich the understanding and dynamic analysis of symptoms, forming a continuous health data stream;

[0059] Integrate data storage and data transmission protocols, adopt distributed database architecture and efficient data transmission protocols to ensure real-time transmission of patient health data to the central processing module or cloud platform, and protect data security, integrity and privacy.

[0060] Heterogeneous data fusion and adaptive algorithm engine includes:

[0061] The adaptive model selection and optimization unit dynamically selects the most suitable analysis model, i.e., one of the convolutional neural network, graph neural network, decision tree, support vector machine, according to the patient's personalized health status, and optimizes the model parameters through a feedback loop, automatically adjusting the calculation strategy to cope with clinical changes;

[0062] Personalized data weighting algorithm, based on historical treatment data and real-time patient data, automatically assigns weights to different types of health data by learning the physiological and pathological change trends of patients, ensuring that key health information receives adequate attention, thereby providing support for the generation of acupuncture treatment plans;

[0063] The process of heterogeneous data fusion and adaptive algorithm engine: Through the multi-dimensional health data collection module, multi-source data of patients are obtained from different sensors and devices. The data sources include electrocardiogram (ECG), blood flow velocity, blood flow resistance, coronary artery imaging, inflammatory indicators, age, and medical history. In order to ensure the real-time and consistency of the data, the collected heterogeneous data streams are sent to the data processing module through an efficient data transmission protocol; all collected heterogeneous data are first denoised to remove irrelevant noise signals and improve data quality; then, the data is standardized and normalized to ensure that data from different sources can be subsequently analyzed with unified standards; interpolation and filling are used for missing health data to ensure data integrity;

[0064] In the early stage of heterogeneous data fusion, based on known medical rules and expert knowledge base, rule-based fusion methods are used to preliminarily fuse data from different sensors and data sources; for example, through rule-based logical judgment, imaging data and electrocardiogram data are combined to verify the patient's cardiovascular status; the goal of this stage is to preliminarily integrate and screen data based on the existing knowledge system; after rule-based fusion, the decision tree in the machine learning model is used to further optimize data fusion; different types of data are weighted and correlated through model-driven methods; for example, electrocardiogram data and hemodynamic data are combined to generate a patient's blood flow status and cardiac function assessment model; model-driven methods help improve the accuracy and effectiveness of data fusion and deal with those that rely on The data is related to more complex patterns; through data-driven methods, convolutional neural networks in deep learning algorithms are applied to fuse all multimodal data; data-driven fusion strategies automatically discover potential relationships between different health data by learning complex patterns from big data; for example, through deep neural networks, imaging data and physiological monitoring data are fused to extract important features related to coronary artery disease, and the accuracy of data fusion is improved through learning and optimizing the processing flow; after completing multi-level data fusion, all data will be analyzed and processed to generate an accurate and real-time patient health portrait; the health portrait is a comprehensive and vivid description of the patient's status based on the fused heterogeneous data, covering the patient's physiological status, disease progression, pathological changes and other information;

[0065] The health profile will be dynamically updated as the patient's real-time data changes, ensuring that the health profile can reflect the patient's current physical condition in real time; for example, as new electrocardiogram and blood flow data are input, the health profile will update the patient's cardiovascular condition and provide the latest health assessment;

[0066] Through adaptive algorithms, the system can automatically adjust the analysis model according to the patient's health profile and real-time data; adaptive algorithms include dynamic optimization of deep learning models, machine learning models and fusion algorithms to better process the personalized data of different patients; for example, for patients with different pathological characteristics, the system will adaptively select different analysis models: convolutional neural networks or graph neural networks, to ensure that the generation process of health profiles can be optimized for individualized data;

[0067] Adaptive algorithms can also continuously optimize data fusion strategies through continuous feedback loops. When new data is input into the system, the algorithm will adjust the calculation model and processing method to ensure the accuracy of the fusion results. The system is optimized based on real-time data streams, historical treatment data and feedback information to continuously improve the accuracy of data fusion. Ultimately, the generated patient health portrait contains health information in multiple dimensions, accurately describing the patient's physiology, pathology, treatment response and other information. The portrait will be used for subsequent treatment plan generation and optimization, providing data support for personalized treatment decisions. The health portrait will be displayed in a visual way, making it easier for doctors, treatment staff or patients themselves to quickly understand the patient's health status. The system can provide a display of the health portrait through charts, dynamic reports, etc., and provide corresponding explanations and suggestions.

[0068] The process of heterogeneous data fusion and adaptive algorithm engine includes the collection and preprocessing of multi-source data, the integration of heterogeneous data through hybrid data fusion technology, and multi-layer fusion strategies based on rule-based, model-driven and data-driven, and then the generation of accurate and real-time patient health portraits based on the fused data; in this process, the adaptive algorithm dynamically optimizes the data fusion and health portrait generation strategies to adapt to the personalized needs of patients; finally, the health portraits generated by the system provide accurate and real-time support for the subsequent generation and adjustment of treatment plans.

[0069] The adaptive model selection and optimization unit selects the appropriate analysis model according to the patient's personalized health status, and optimizes the model parameters through a feedback loop to adjust the calculation strategy:

[0070] Collect and preprocess multi-source health data, including electrocardiogram, blood flow parameters, imaging data, and biomarkers; generate personalized health profiles of patients through heterogeneous data fusion, including data in multiple dimensions such as physiology and pathology; these data are used as input to the adaptive model selection and optimization unit;

[0071] Based on the patient's personalized health portrait, the system evaluates changes in their physiological and pathological states, determines the severity, progression, and potential risks of the disease, and selects the most suitable analysis model based on the patient's current health status. Common models include: Convolutional Neural Network (CNN): suitable for extracting features from imaging data and evaluating coronary artery imaging changes; Graph Neural Network (GNN): suitable for processing complex associated data, such as blood flow changes and electrocardiogram time series data; Decision Tree (DT) and Support Vector Machine (SVM): suitable for processing structured data, such as clinical history data and real-time physiological data;

[0072] Through adaptive mechanisms, the most appropriate model is dynamically selected and adjusted. For different patient conditions, the system automatically selects the model and adjusts the model parameters to ensure the accuracy of diagnosis or treatment planning. For example, for patients with obvious coronary artery lesions, convolutional neural networks (CNN) may be used to analyze imaging data, while for patients with more complex clinical data, support vector machines (SVM) may be used to analyze multi-dimensional physiological parameters.

[0073] By collecting patient feedback data in real time: physiological responses and blood flow changes after treatment, the currently selected analysis model is optimized; model parameters: convolution kernel, learning rate, are dynamically adjusted according to changes in clinical data, thereby improving the accuracy of model predictions; through continuous clinical feedback and data learning, the model's predictive and adaptive capabilities are optimized to ensure that the algorithm can cope with changes in different clinical scenarios; whenever a patient's physiological or pathological state changes significantly, the model will automatically re-evaluate and update the strategy to minimize errors and maintain the accuracy of treatment effects;

[0074] The process of personalized data weight allocation algorithm: The system collects the patient's physiological, pathological and treatment data in real time through the health data collection module, including electrocardiogram, hemodynamic parameters, imaging data, and historical treatment records; multi-source heterogeneous data are fused and processed to generate a comprehensive health portrait of the patient, forming a multi-dimensional information set including individual characteristics, treatment history, real-time health data, etc.; based on historical treatment data and real-time data of patients, the system uses time series analysis and LSTM to analyze the physiological and pathological change trends of patients; this analysis helps identify the patient's health development trajectory and capture possible changes in disease progression or treatment effects;

[0075] Through trend prediction, the system can automatically detect potential anomalies in health data, such as reduced blood flow or abnormal electrocardiogram, so as to adjust treatment strategies in time; according to the patient's health data and disease progression, the system automatically assigns weights to different types of health data; including: for blood flow velocity and blood flow resistance in hemodynamic data, higher weights may be given in patients with cardiovascular diseases; for imaging data, if the patient's coronary artery lesions are more obvious, the weight of imaging data will be automatically increased; for historical treatment data, if a certain treatment plan has shown good efficacy in past treatments, the system will assign a higher weight to the treatment parameter based on historical results; as the treatment progresses and new data is input, the system will continuously update the weight allocation strategy; including: if the patient's treatment response is not as expected, the data weight of a certain treatment parameter may be reduced, and other key data sources may be emphasized instead: physiological feedback data on the treatment plan impact; based on the weighted data, the system generates a personalized treatment plan for each patient; in the process of generating acupuncture treatment plans, the most critical health data will be given priority to ensure the accuracy and personalization of the treatment plan; the system further optimizes the treatment plan by continuously learning and updating the weight allocation strategy of the patient's health status to ensure that the patient's treatment needs are fully met; through the adaptive model selection and optimization unit, the system can select and optimize the most suitable analysis model according to the patient's personalized health status, and optimize the model parameters through feedback loops to ensure that it can respond to changes in clinical status; and the personalized data weight allocation algorithm dynamically assigns weights to different types of health data by learning the patient's physiological, pathological and treatment history data, thereby ensuring that critical health information is fully considered when generating treatment plans; the combination of the two provides strong data support and optimization capabilities for the generation of personalized acupuncture treatment plans.

[0076] The treatment plan generation module includes: an integrated intelligent decision support system that generates a treatment plan for each patient by integrating medical literature, treatment guidelines, and real-time health data. The system uses a combination of reinforcement learning and adaptive algorithms to continuously correct and optimize decisions during the treatment process to ensure that the plan can be dynamically adjusted based on the patient's response;

[0077] A multi-objective optimization treatment generation algorithm considers multiple treatment goals at the same time: blood flow restoration, symptom relief, and generates a comprehensive treatment plan through multi-objective optimization technology, including acupuncture site, depth, treatment timing and acupuncture frequency, to maximize the treatment effect and reduce side effects.

[0078] The multi-objective optimization treatment generation algorithm is based on a reinforcement learning model. It adjusts the treatment plan through continuous feedback to ensure that the treatment plan can be quickly adapted when the patient's health status changes, ensuring the efficiency and personalization of the treatment;

[0079] The process of generating personalized acupuncture treatment plans by the treatment plan generation module includes: integrating all collected health data and using a multimodal feature fusion algorithm to generate a personalized health profile of the patient, which includes the patient's physiological state, pathological state and other key health information, providing basic data for the generation of personalized treatment plans; combining traditional Chinese medicine acupuncture treatment theory to build a knowledge base that includes acupuncture treatment principles, acupuncture site selection, acupuncture depth and treatment timing; this knowledge base is based on classic acupuncture therapy and combines existing clinical experience and literature to cover the key points of acupuncture treatment for different diseases and symptoms; combining traditional acupuncture treatment theory with traditional Chinese medicine acupuncture treatment theory to build a knowledge base that includes acupuncture treatment principles, acupuncture site selection, acupuncture depth and treatment timing; this knowledge base is based on classic acupuncture therapy and combines existing clinical experience and literature to cover the key points of acupuncture treatment for different diseases and symptoms; Mapping with the patient's health profile, the appropriate acupuncture site, depth and treatment timing are determined based on the patient's specific symptoms, clinical manifestations and physiological status; through deep learning, machine learning and reinforcement learning in intelligent algorithms, the patient's health profile and information in the acupuncture treatment knowledge base are processed. According to the patient's specific symptoms and condition, the system will set clear treatment goals, such as improving blood flow, relieving symptoms and reducing inflammation. The algorithm will optimize each treatment goal and generate the best treatment plan. Combined with the patient's specific health status, the optimal acupuncture site, depth and treatment duration are automatically evaluated to achieve the best treatment effect and automatically generate a personalized treatment plan;

[0080] A multi-objective optimization algorithm is used to consider multiple treatment goals at the same time: blood flow restoration, symptom relief, and generate a comprehensive treatment plan. This optimization process will not only adjust the acupuncture site and depth, but also comprehensively consider the treatment timing and frequency to minimize side effects and maximize the treatment effect; the treatment plan will be dynamically adjusted according to the patient's real-time health data: physiological changes and feedback during the treatment process; for example, if the feedback result of a certain treatment goal is poor, the system will adjust the acupuncture depth or treatment duration, or even change the treatment site during the treatment process; through reinforcement learning, the treatment process is continuously optimized, and the system will monitor the patient's physiological feedback data in real time: heart rate, blood flow, local feedback, etc. The treatment plan will be reviewed and modified according to the treatment effect to ensure that each link in the treatment process can accurately adapt to the changes of the patient; after each treatment cycle, the treatment plan will be reviewed according to the patient's response, and the subsequent treatment process will be optimized to ensure the continuous improvement of the long-term treatment effect; based on the intelligent algorithm and clinical feedback, a detailed personalized treatment plan will be finally generated to specify the acupuncture site, depth, and treatment time, and the plan will be output to the treatment device or doctor through the interface; once the treatment plan is determined, the treatment device or operator will perform acupuncture treatment according to the plan. At the same time, the real-time monitoring system will continue to track the patient's physiological response and treatment effect so that necessary adjustments can be made at any time;

[0081] The treatment plan generation module automatically generates personalized treatment plans suitable for patients through the collection and analysis of multi-dimensional health data, combined with traditional acupuncture treatment theory and intelligent algorithms; the process includes the collection and preprocessing of health data, the generation of personalized health portraits, the optimization and dynamic adjustment of treatment plans, and real-time monitoring and correction during the treatment process, ultimately ensuring that the treatment plan is accurate, efficient and personalized; this module enables acupuncture treatment to be precisely adjusted according to the individual differences of patients, thereby optimizing the treatment effect and maximizing its clinical efficacy.

[0082] The real-time feedback and adjustment module includes:

[0083] Real-time health monitoring and feedback interface, integrating physiological monitoring equipment and acupuncture treatment equipment, is used to achieve real-time monitoring of acupuncture depth and time during acupuncture treatment, and to provide instant feedback on the patient's physiological responses, such as heart rate changes, local blood flow changes, and skin temperature, to ensure real-time adjustments during treatment;

[0084] Multi-dimensional treatment parameter feedback and adjustment strategy, using real-time data streams to adjust treatment parameters: acupuncture site, depth, treatment duration, in real time, combined with machine learning algorithms to optimize treatment effects and treatment timing;

[0085] The feedback adjustment strategy uses adaptive time series analysis technology to adjust the treatment plan in a timely manner based on dynamically collected data and key feedback information during the treatment process, and re-evaluate the effectiveness of treatment parameters when necessary.

[0086] Multi-dimensional treatment parameter feedback and adjustment strategy uses real-time data streams to adjust treatment parameters, combined with machine learning algorithms to optimize the treatment effect and treatment timing process: through integrated physiological monitoring equipment, the patient's physiological feedback data, such as heart rate, blood flow changes, local skin temperature, and real-time collection of acupuncture treatment parameters, including acupuncture site, acupuncture depth, and treatment duration, are collected in real time. These data are recorded in real time by dedicated sensors or treatment equipment; all collected real-time data are sent to the data processing module through a high-speed transmission protocol, and combined with the patient's clinical medical records and background information, including medical history, age, and gender. The data is encrypted during transmission to ensure the security of the patient's data. The system ensures the integrity, privacy and completeness of the data. The real-time data transmitted is pre-processed through the data cleaning module, including denoising, standardization and normalization, to ensure the consistency and accuracy of the data in subsequent analysis. The feature extraction algorithm extracts key indicators from the collected physiological data and treatment data, such as the effect of acupuncture depth on local blood flow, acupuncture duration and changes in heart rate. Deep learning based on real-time data continuously adjusts the treatment strategy through a feedback loop. The machine learning model is trained based on historical treatment data and real-time data to optimize the treatment effect. The algorithm can identify deviations or adverse reactions that occur during the treatment process and automatically adjust the acupuncture parameters to ensure the personalization and efficiency of the treatment.

[0087] Combined with the analysis results of the machine learning model, the acupuncture site, depth, and duration of the treatment parameters are dynamically adjusted. For example, if the patient's local blood flow velocity is monitored to be below the expected level during treatment, the system will automatically adjust the acupuncture depth or increase the treatment duration. If the patient's heart rate is too fast, the system may adjust the timing of treatment or the severity of acupuncture and generate a set of real-time adjustment strategies. These strategies may include fine-tuning the acupuncture site, increasing or decreasing the treatment depth, and extending or shortening the treatment duration. These adjustments will be based on real-time monitoring data and the predicted results of the machine learning model to optimize the treatment effect. After each treatment cycle, the system will evaluate the treatment effect, analyze real-time data feedback, and determine whether the current treatment plan has achieved the expected treatment goals: blood flow recovery and symptom relief. Based on the feedback results after treatment, the system will further adjust the optimization strategy to ensure that in subsequent treatment cycles, the treatment plan can be quickly adapted and adjusted according to changes in the patient's health status.

[0088] Comprehensive adjustment of multi-dimensional parameters: Multi-dimensional adjustment is not limited to a single treatment parameter, but combines multiple physiological and treatment feedback dimensions, such as the patient's electrocardiogram changes, local blood flow parameters, the influence of acupuncture depth and duration, to comprehensively evaluate the treatment effect and adjust the treatment plan; this comprehensive adjustment process enables the treatment plan to respond to the patient's physiological changes at any time, ensuring the optimization of treatment timing and effect;

[0089] This process continuously optimizes the treatment plan by collecting the patient's health data in real time and combining it with machine learning algorithms. During the entire treatment process, the system can automatically adjust the location, depth, and duration of acupuncture parameters to ensure the accuracy and effectiveness of the treatment, maximize the patient's treatment effect and reduce treatment risks. At the same time, the system can continuously adjust the treatment strategy based on real-time data and feedback to achieve personalized and continuously optimized treatment effects.

[0090] By integrating multiple monitoring devices, the present invention proposes an innovative heterogeneous data fusion and optimization algorithm that can process complex health data and generate accurate treatment plans; the depth and diversity of data fusion make the treatment plan more personalized and accurate; by adopting reinforcement learning and adaptive adjustment strategies, the present invention can continuously optimize the treatment plan during the treatment process, especially when traditional methods cannot dynamically respond to the health fluctuations of patients, thus ensuring the personalization and real-time nature of the treatment;

[0091] The treatment plan generation based on deep learning is different from the existing fixed treatment plan. The present invention can dynamically adjust the treatment plan according to the patient's actual health status and real-time feedback through the combination of reinforcement learning and deep neural network models to ensure the maximum treatment effect. This plan uses a multi-objective optimization algorithm to ensure that the treatment plan strikes a balance between multiple goals, including maximizing the treatment effect, minimizing side effects, and optimizing the treatment time, and further improves the comprehensive effect of the treatment through real-time feedback and dynamic adjustment.

[0092] These innovative technical solutions effectively address the shortcomings of the traditional medical system in combining modern information technology and acupuncture treatment, and ensure the accuracy, personalization and real-time nature of treatment plans.

[0093] Methods include:

[0094] Step 1: Collect the patient's electrocardiogram, coronary artery imaging data, hemodynamic parameters, biomarkers and related physiological parameters in real time through wireless sensors, portable devices or hospital monitoring systems, and analyze them in combination with the patient's clinical medical records;

[0095] Step 2: Based on the collected health data, hybrid data fusion technology is used to process heterogeneous data and generate a patient health profile;

[0096] Step 3: Analyze the patient's health data, combine it with traditional acupuncture treatment theory, and use intelligent algorithms to automatically generate personalized acupuncture treatment plans;

[0097] Step 4: Dynamically adjust the treatment plan based on real-time monitoring data during the treatment process;

[0098] The deep learning algorithm is based on multimodal data, uses convolutional neural networks (CNNs) to extract features from image data, combines them with physiological data, and generates optimized treatment plans through multi-task learning.

[0099] It should be further explained that, in the specific implementation process, a method for planning acupuncture treatment for ischemic non-obstructive coronary artery disease includes the following steps:

[0100] Step 1: Real-time collection of the patient's physiological data, imaging data and clinical medical record data; the collected data include but are not limited to electrocardiogram (ECG), hemodynamic data (such as blood flow velocity, blood flow resistance), coronary artery imaging data, inflammatory markers (such as C-reactive protein) and other physiological parameters (such as body temperature, respiratory rate); the collected health data is transmitted to the data processing platform or cloud system through an efficient transmission protocol to ensure the real-time and integrity of the data; the data will be processed and stored synchronously and prepared for subsequent analysis;

[0101] Step 2: Use hybrid data fusion technology: rule-based, model-driven and data-driven multi-layer fusion strategies to integrate and process heterogeneous data from different data sources; based on the fused data, the system generates an accurate and real-time patient health profile through heterogeneous data fusion and adaptive algorithm engine; the health profile reflects the patient's current physiological state, pathological changes and potential risks, and combines historical treatment data to form a personalized health profile for the patient;

[0102] Step 3: Based on the patient's health profile and in combination with traditional acupuncture treatment theory, the patient's pathology, symptoms, and historical treatment records are analyzed through intelligent algorithms to tailor a treatment plan for the patient; through the personalized treatment plan generation module, intelligent algorithms are used to automatically generate personalized acupuncture treatment plans, including treatment location, acupuncture depth, and treatment duration; the intelligent algorithm combines traditional Chinese medicine theory and modern medical technology to automatically adjust treatment parameters according to the patient's specific needs and health status to achieve the best treatment effect; in the process of generating treatment plans, a multi-objective optimization treatment generation algorithm is used to consider multiple treatment goals at the same time, such as blood flow restoration, symptom relief, and inflammation reduction, and comprehensively optimize treatment parameters, such as acupuncture location, depth, and treatment timing, to maximize treatment effects and minimize side effects;

[0103] Step 4: During the treatment process, the real-time feedback and adjustment module monitors the patient's real-time physiological reactions, such as heart rate changes, local blood flow changes, and skin temperature. Based on the real-time monitoring data, the system dynamically adjusts the treatment plan through the feedback loop. For example, if the patient is monitored to have adverse reactions during the treatment process, such as a fast heart rate or a poor local reaction, the system will automatically adjust the acupuncture depth, position or treatment duration to optimize the treatment effect. The effectiveness of the treatment parameters is evaluated in real time through adaptive time series analysis technology, and the treatment plan is adjusted in time according to key feedback information. During the treatment process, the system can continuously optimize the treatment strategy according to the changes in the data stream.

[0104] Step 5: After each treatment, the system will monitor the patient's feedback data and physiological changes, evaluate the effectiveness of the current treatment plan, and record the treatment data; based on the data feedback and historical effects during the treatment process, the system will optimize the treatment plan again; in the subsequent treatment process, the plan will be further adjusted and optimized based on the new health data; through continuous learning and feedback, the treatment plan will be continuously adjusted in multiple treatment cycles, so that each treatment can maximize the adaptation to the patient's health changes, ensuring that the treatment plan always meets the patient's personalized needs;

[0105] Step 6: After each treatment cycle, the system will evaluate the treatment effect, such as blood flow recovery, symptom relief, and patient comfort; if the current treatment plan fails to achieve the expected effect, the system will automatically modify the treatment plan, such as adjusting the acupuncture site, depth, and duration, and re-optimize it; after multiple cycles of optimization and adjustment, the system will generate a final personalized treatment plan to ensure that the treatment goals are achieved and side effects are minimized.

[0106] This method generates a personalized patient health portrait through dynamic health data collection and analysis, and combines traditional acupuncture treatment theory with intelligent algorithms to generate a personalized acupuncture treatment plan; during the treatment process, real-time feedback and dynamic adjustment modules ensure that the treatment plan can be flexibly adjusted according to the patient's physiological changes to achieve continuous optimization of the treatment effect; through multi-objective optimization and adaptive adjustment mechanisms, the treatment plan can more accurately meet the patient's health needs, thereby improving the treatment effect and patient comfort.

[0107] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0108] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An acupuncture treatment planning system for ischemic and non-obstructive coronary artery disease, characterized in that: The system comprises: The multi-dimensional health data collection module collects the patient's electrocardiogram, coronary artery imaging data, hemodynamic parameters, biomarkers and related physiological parameters in real time through wireless sensors, portable devices or hospital monitoring systems, and combines them with the patient's clinical medical record data for analysis; Heterogeneous data fusion and adaptive algorithm engine, based on the collected health data, uses hybrid data fusion technology to process heterogeneous data and generate patient health portraits; The treatment plan generation module analyzes the patient's health data, combines traditional acupuncture treatment theory, and uses intelligent algorithms to automatically generate personalized acupuncture treatment plans, including treatment location, depth, and time; The real-time feedback and adjustment module is used to dynamically adjust the treatment plan based on the real-time monitoring data during the treatment process.

2. The acupuncture treatment planning system for ischemic non-obstructive coronary artery disease according to claim 1, characterized in that: The data acquisition module comprises: A multi-type sensor network, including portable electrocardiogram devices, blood flow velocity monitors, and ultrasound probes, tracks microscopic changes in coronary blood flow in real time and combines the patient's real-time exercise, rest, and emotional data to form a continuous health data stream; Integrate data storage and data transmission protocols, adopt distributed database architecture and data transmission protocols, and transmit patients' health data to the central processing module or cloud platform in real time.

3. The acupuncture treatment planning system for ischemic non-obstructive coronary artery disease according to claim 2, characterized in that: The heterogeneous data fusion and adaptive algorithm engine includes: The adaptive model selection and optimization unit selects the appropriate analysis model according to the patient's personalized health status, optimizes the model parameters and adjusts the calculation strategy through feedback loops; Personalized data weighting algorithm, based on historical treatment data and real-time patient data, assigns weights to different types of health data by learning the physiological and pathological change trends of patients; In the initial stage of heterogeneous data fusion, based on known medical rules and expert knowledge base, rule-based fusion methods are used to initially fuse data from different sensors and data sources; after rule-based fusion, machine learning models are used to optimize data fusion; through model-driven methods, different types of data are weighted and analyzed for association; through data-driven methods, deep learning algorithms are applied to fuse multimodal data; data-driven fusion strategies discover potential relationships between different health data by learning complex patterns from big data; after completing multi-level data fusion, the data will be analyzed and processed to generate a patient health profile.

4. The acupuncture treatment planning system for ischemic non-obstructive coronary artery disease according to claim 3, characterized in that: The adaptive model selection and optimization unit selects a suitable analysis model according to the patient's personalized health status, and optimizes the model parameters through a feedback loop to adjust the calculation strategy: collect and preprocess multi-source health data, generate a personalized health profile of the patient through heterogeneous data fusion, and evaluate the changes in the patient's physiological and pathological status based on the personalized health profile of the patient, and judge the severity, progression and potential risks of the disease; Select the appropriate analysis model based on the patient's current health status.

5. The acupuncture treatment planning system for ischemic non-obstructive coronary artery disease according to claim 4, characterized in that: The treatment plan generation module includes: Integrated intelligent decision support system that generates treatment plans for each patient by integrating medical literature, treatment guidelines and real-time health data; Multi-objective optimization treatment generation algorithm, which considers multiple treatment goals at the same time and generates a comprehensive treatment plan through multi-objective optimization technology.

6. The acupuncture treatment planning system for ischemic non-obstructive coronary artery disease according to claim 5, characterized in that: The process of generating a personalized acupuncture treatment plan by the treatment plan generation module includes: fusing the collected health data and generating a personalized health profile of the patient using a multimodal feature fusion algorithm; building a knowledge base in combination with traditional Chinese medicine acupuncture treatment theory; processing the patient's health profile and the information in the acupuncture treatment knowledge base through an intelligent algorithm, setting treatment goals according to the patient's symptoms and condition, and automatically evaluating the treatment location depth and treatment duration in combination with the patient's specific health status to generate a personalized treatment plan; A multi-objective optimization algorithm is used to consider multiple treatment goals at the same time, generate a comprehensive treatment plan, and adjust the acupuncture site and depth during the optimization process. The treatment process is optimized through reinforcement learning, and the patient's physiological feedback data is monitored in real time. Modifications are made based on the treatment effect to ensure that each link in the treatment process can adapt to the patient's changes. Based on intelligent algorithms and clinical feedback, personalized treatment plans are generated and output to the treatment equipment or doctors through the interface.

7. The acupuncture treatment planning system for ischemic non-obstructive coronary artery disease according to claim 6, characterized in that: The real-time feedback and adjustment module includes: Real-time health monitoring and feedback interface, integrating physiological monitoring equipment with acupuncture treatment equipment, for real-time monitoring during acupuncture treatment and feedback of the patient's physiological response; Multi-dimensional treatment parameter feedback and adjustment strategy uses real-time data streams to adjust treatment parameters and combines machine learning algorithms to optimize treatment effects and timing.

8. The acupuncture treatment planning system for ischemic non-obstructive coronary artery disease according to claim 7, characterized in that: The multi-dimensional treatment parameter feedback and adjustment strategy uses real-time data streams to adjust treatment parameters, combined with machine learning algorithms, to optimize the treatment effect and treatment timing process: the integrated physiological monitoring device collects the patient's physiological feedback data in real time, and collects the parameters of the acupuncture treatment process in real time, including acupuncture site, acupuncture depth, and treatment duration; The collected real-time data is sent to the data processing module through the transmission protocol, and combined with the patient's clinical medical history and background information, key indicators are extracted from the collected physiological data and treatment data. Based on the real-time collected data, the machine learning algorithm continuously adjusts the treatment strategy through the feedback loop. The machine learning model is trained according to historical treatment data and real-time data to optimize the treatment effect. Combined with the analysis results of the machine learning model, the treatment parameters are dynamically adjusted to generate an adjustment strategy. After each treatment cycle, the treatment effect is evaluated, and the real-time data feedback is analyzed to determine whether the current treatment plan has achieved the expected treatment goals. According to the feedback results after treatment, the optimization strategy is adjusted to ensure that in subsequent treatment cycles, the treatment plan can be quickly adapted and adjusted according to changes in the patient's health status.

9. A method for planning acupuncture treatment for ischemic non-obstructive coronary artery disease, characterized in that: The method comprises: Step 1: Collect the patient's electrocardiogram, coronary artery imaging data, hemodynamic parameters, biomarkers and related physiological parameters in real time through wireless sensors, portable devices or hospital monitoring systems, and analyze them in combination with the patient's clinical medical records; Step 2: Based on the collected health data, hybrid data fusion technology is used to process heterogeneous data and generate a patient health profile; Step 3: Analyze the patient's health data, combine it with traditional acupuncture treatment theory, and use intelligent algorithms to automatically generate personalized acupuncture treatment plans; Step 4: Dynamically adjust the treatment plan based on real-time monitoring data during the treatment process.

10. An electronic device, characterized in that: The device comprises: One or more processors and storage devices, used to store programs and data and execute the treatment planning method of claim 9; The display device is used to display the generation and dynamic adjustment process of the treatment plan, and provide feedback information to the treatment staff in real time to ensure that the patient's treatment process is visualized and operational.

Images