Intelligent management system of medical information data based on blockchain

Abstract

The present application provides an intelligent management system for medical information data based on blockchain, which relates to the field of medical information management technology. The system includes: a medical information download module for downloading medical information; a tracking track introduction module for introducing multiple medical resource tracking tracks; a digital certificate addition module for adding non-homogeneous digital certificates; an access authorization opening module for creating an access permission list reserved for the user terminal corresponding to the target user; a model building module for establishing a medical over-analysis model; and a data collaborative management module for collaborative data management of medical information. This application can solve the technical problems of increased bacterial resistance and waste of medical resources due to the abuse and insufficient monitoring of key drugs such as antibiotics in medical resource management, and achieve the technical effect of improving the rationality of medical resource allocation and reducing the risk of drug resistance by establishing a data-driven medical over-analysis model.

Description

Technical Field

[0001] The present application relates to the field of medical information management technology, and in particular to an intelligent medical information data management system based on blockchain. Background Art

[0002] With the rapid development of medical technology and the growing demand for medical care, the field of medical resource management is facing unprecedented challenges. Among them, the irrational abuse of key drugs such as antibiotics has become a major technical problem that restricts the healthy development of the medical industry. As an important treatment tool, antibiotics play an important role in treating patients. However, due to their frequent overuse or improper use in clinical applications, bacteria gradually develop drug resistance, making the originally effective antibiotics lose their therapeutic effect. The widespread spread of drug resistance not only increases the difficulty of treatment and medical costs for patients, but also threatens public health safety. At the same time, due to insufficient monitoring, it is difficult to fully and accurately grasp the use of antibiotics, and it is impossible to detect and correct abuse in a timely manner, which further leads to the formation and spread of drug resistance. Summary of the invention

[0003] The purpose of this application is to provide an intelligent management system for medical information data based on blockchain to solve the technical problems of increased bacterial resistance and waste of medical resources due to the abuse and insufficient monitoring of key drugs such as antibiotics in medical resource management.

[0004] In view of the above problems, this application provides an intelligent medical information data management system based on blockchain.

[0005] The present application provides an intelligent management system for medical information data based on blockchain, the system comprising: a medical information download module, used to connect to a data storage platform and download medical information, the medical information including basic patient information, medical examination information, medical record information, and treatment information; a tracking track introduction module, used to introduce multiple medical resource tracking tracks based on the treatment information in the medical information, the medical resource tracking tracks are obtained by tracing the source of medical supplies; a digital certificate adding module, used to add non-homogeneous digital certificates based on the basic patient information, medical examination information, and medical record information in the medical information using blockchain technology; an access authorization opening module, used to add non-homogeneous digital certificates based on the non-homogeneous A digital certificate is used to open access authorization to the medical staff corresponding to the registration application after the target user completes the registration application, and create an access permission list to be retained in the user terminal corresponding to the target user; a model building module is used to establish a medical over-analysis model based on the medical supplies supply contract triggered by the medical staff's medical supplies usage rights, combined with the multiple medical resource tracking tracks; a data collaborative management module is used to mark high-risk groups based on the medical over-analysis model, set up a dynamic feedback loop, optimize with the goal of minimizing medical risks and maximizing adaptation accuracy, obtain medical resource allocation strategies, and bind with the target user to perform data collaborative management of the medical information.

[0006] The technical solution provided in this application has at least the following technical effects or advantages:

[0007] The above-mentioned blockchain-based intelligent management system for medical information data downloads various medical information of patients from the data storage platform, including basic information, examinations, medical records and treatment conditions. Subsequently, the traceability information of medical supplies is used to track the flow of medical resources. After that, blockchain technology is used to add a unique digital certificate to the patient's medical information to ensure the authenticity and non-tamperability of the information. When the patient needs to register, the non-homogeneous digital certificate on the blockchain is used to provide access authorization for medical staff to ensure that only relevant medical staff can view the patient's medical information. At the same time, these access rights are recorded so that patients can view them at any time. Then, based on the medical staff's medical supplies usage rights and the tracking trajectory of medical resources, a medical overuse analysis model is established to analyze whether there is medical overuse. Through this model, high-risk groups are identified, that is, patients who may not benefit much from excessive medical treatment or have potential risks. In order to optimize the allocation of medical resources, a dynamic feedback loop is set up to continuously adjust and optimize the allocation strategy to minimize medical risks and maximize adaptation accuracy. Finally, this optimized medical resource allocation strategy will be bound to the patient to achieve collaborative management of medical information and ensure that patients receive the most appropriate medical resources and services.

[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0010] Figure 1 This is a structural diagram of the blockchain-based intelligent management system for medical information data in this application.

[0011] Figure 2 This is a flowchart of the open access authorization process for the blockchain-based medical information data intelligent management system for this application.

[0012] Description of reference numerals:

[0013] Medical information download module 1, tracking trajectory introduction module 2, digital certificate adding module 3, access authorization opening module 4, model building module 5, data collaborative management module 6. DETAILED DESCRIPTION

[0014] This application solves the technical problems of increased bacterial resistance and waste of medical resources due to the abuse and insufficient monitoring of key drugs such as antibiotics in medical resource management by providing an intelligent management system for medical information data based on blockchain. It achieves the technical effect of improving the rationality of medical resource allocation and reducing the risk of drug resistance by establishing a data-driven medical over-analysis model.

[0015] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0016] For examples, please see the attached Figure 1 , this application provides a blockchain-based medical information data intelligent management system, the system specifically includes the following modules:

[0017] The medical information download module 1 is used to connect to the data storage platform and download medical information, which includes basic patient information, medical examination information, medical record information, and treatment information.

[0018] Specifically, in the medical information download module 1, the system terminal establishes a communication connection with the data storage platform, which stores a large number of medical records. By downloading these medical records, the system terminal obtains multiple medical information. Each medical information includes basic patient information, medical examination information, medical record information, treatment information, etc. Among them, the basic patient information includes the personal identification data of the target user, such as name, gender, age, contact information, home address, etc., and also includes the insurance information, emergency contact, etc. of the target user. This information is the starting point of medical services, helping the system terminal to quickly understand the basic situation of the target user and serve as an important basis for verifying the identity of the target user. Medical examination information refers to the result data obtained from various examinations conducted by the target user during the process of receiving medical services. These examinations include blood tests, imaging examinations, electrocardiograms, ultrasounds, etc. Medical examination information provides the system terminal with direct evidence of the target user's physiological condition, disease progression or treatment effect. Medical record information is a detailed record of the entire process of the target user receiving medical services, including the target user's chief complaint, the doctor's consultation record, physical examination results, preliminary diagnosis, treatment process, changes in condition, nursing records, etc. Medical record information reflects the target user's health status and treatment process. Treatment information refers to the data on various treatment measures received by the target user and their effects. This includes drug treatment (drug name, dosage, usage, course of treatment, etc.), surgical treatment (surgery name, surgery time, postoperative recovery, etc.), physical therapy, psychotherapy, etc.

[0019] The tracking track introduction module 2 is used to introduce multiple medical resource tracking tracks based on the treatment information in the medical information, and the medical resource tracking tracks are obtained by tracing the source of medical supplies.

[0020] Specifically, in the tracking track introduction module 2, the system terminal introduces multiple medical resource tracking tracks based on treatment information. These tracks are obtained through the medical resource traceability system, and these medical resource tracking tracks record in detail the entire process of medical supplies from production, circulation to final use. The purpose of this is to ensure that the use of each medical resource can be clearly and accurately tracked, especially the use of antibiotics, so as to improve the utilization efficiency of medical resources, reduce waste, and ensure that the target users receive appropriate and effective treatment, slowing down the development of bacterial resistance.

[0021] Furthermore, this application provides a medical resource tracking track, including:

[0022] The multiple medical resource tracking tracks include multiple drug resource tracking tracks and multiple medical equipment resource tracking tracks; connected to a medical resource tracing system, the medical resource tracing system is used to trace the source of medical supplies, and in combination with the drugs corresponding to the medical supply contract, multiple drug resource tracking tracks are obtained; connected to the medical resource tracing system, in combination with the medical equipment corresponding to the medical supply contract, multiple medical equipment resource tracking tracks are obtained.

[0023] In an optional implementation, the system terminal introduces multiple medical resource tracking tracks through the medical resource traceability system, covering two aspects: drug resources and medical equipment resources, including multiple drug resource tracking tracks and multiple medical equipment resource tracking tracks. In order to obtain these tracks, the system terminal is connected to the medical resource traceability system. This medical resource traceability system is specifically used for source tracking of medical supplies to ensure that the source, circulation and use of each material can be clearly recorded. Specifically, when it is necessary to track drug resources, the system terminal obtains the tracking track of the entire process of drugs from production, transportation to final use through the medical resource traceability system, combined with the drug information involved in the medical material supply contract. These tracks not only allow the system terminal to understand the circulation of drugs, but also help monitor whether the use of drugs is reasonable and whether there is abuse, thereby effectively preventing the occurrence of problems such as antibiotic resistance. Similarly, for medical equipment resources, the system terminal also tracks them through the medical resource traceability system. Combined with the equipment information in the medical material supply contract, the complete track of the equipment from procurement, warehousing, distribution to use can be obtained. This not only helps manage the life cycle of the equipment and ensure its effective use and maintenance, but also enables quick location of the cause when equipment problems occur, thus ensuring the continuity and safety of medical services.

[0024] Furthermore, the present application provides for optimizing inventory management of drugs corresponding to the medical supplies supply contract, including:

[0025] The medicines corresponding to the medical supplies supply contract are managed in optimized inventory, and the optimized inventory management is performed by integrating the inventory forecasting algorithm with the demand forecasting algorithm.

[0026] In an optional implementation, in order to more effectively manage the drug inventory involved in the medical supplies supply contract, the system terminal adopts an inventory optimization management strategy that integrates the inventory prediction algorithm and the demand prediction algorithm. The inventory prediction algorithm is based on the long short-term memory network, and is determined by training historical inventory data, historical outbound data, historical seasonal factors, and historical disease epidemic trends. It is used to predict the demand for antibiotics and similar drugs in the future based on the current inventory data, outbound data, seasonal factors, and disease epidemic trends. The demand prediction algorithm is also constructed based on the long short-term memory network, but it further refines the prediction of the demand for antibiotics and similar drugs. It not only considers the direct demand for antibiotics and similar drugs, but also integrates the changes in the needs of target users and the prescription habits of doctors to obtain a prediction result that is closer to the actual demand. By integrating and optimizing the management of these two prediction algorithms, the inventory status of antibiotics and similar drugs can be more accurately grasped, avoiding the occupation of funds and the waste of expired drugs caused by excessive inventory, and at the same time ensuring that drugs can be supplied in time when needed to meet the treatment needs of target users. This inventory optimization management method not only improves the management efficiency of medical supplies, but also helps to reduce operating costs and improve the quality of medical services.

[0027] The digital certificate adding module 3 is used to add non-homogeneous digital certificates based on the patient's basic information, medical examination information, and medical record information in the medical information using blockchain technology.

[0028] Specifically, in the digital certificate adding module 3, the system terminal uses blockchain technology to add non-homogeneous digital certificates (NFTs) to the patient's basic information, medical examination information, and medical record information. This approach aims to improve the security, transparency, and credibility of medical data, while providing target users with a more convenient and secure way to manage medical records. As a decentralized, distributed ledger technology, blockchain is very suitable for the storage and verification of medical data due to its tamper-proof and highly transparent characteristics. The system terminal writes the medical information of each target user through a smart contract, and casts the medical information into a unique NFT through the written smart contract. This NFT not only contains the specific content of the medical information, but also comes with meta-information such as an identity identifier and a timestamp to prove the reliability of its source and the accuracy of the timestamp. By converting the target user's medical information into NFT, it can be ensured that this information is permanently stored on the blockchain, and every access, modification, or transmission will be recorded in detail to form a complete and traceable data chain.

[0029] The access authorization opening module 4 is used to open access authorization to the medical staff corresponding to the registration application based on the non-homogeneous digital certificate after the target user completes the registration application, and create an access permission list to be retained in the user terminal corresponding to the target user.

[0030] Specifically, in the access authorization opening module 4, when the target user completes the registration application, the system terminal will automatically generate the corresponding access authorization for this registration application. This access authorization is based on the uniqueness of NFT, ensuring that only specific medical staff can access the medical information related to the target user's registration application. The system terminal identifies the registration application of the target user and searches for the corresponding NFT on the blockchain based on the information in this application, such as the target user ID, registration department, appointment time, etc. Subsequently, an access control list is created for the medical staff responsible for the consultation. This access control list is directly associated with the NFT, allowing medical staff to access the relevant medical information of the target user when needed. This access control list will be recorded in the target user's access rights list, which exists on the blockchain to ensure its non-tamperability and transparency, and will also be synchronized to the user terminal corresponding to the target user, such as mobile APP, hospital self-service terminal, etc., so that the target user can check his or her medical information access at any time.

[0031] Further, if Figure 2 As shown, this application provides an open access authorization for the medical staff corresponding to the registration application based on the non-homogeneous digital certificate after the target user completes the registration application, and also includes:

[0032] Based on the use of hash functions, blockchain technology is used to add non-homogeneous digital certificates, and the non-homogeneous digital certificates contain encrypted personal identity identifiers; through Hyperledger Fabric, attribute-based encryption is adopted to set access control lists corresponding to medical staff with specific attributes, and the specific attributes are associated and mapped with the medical supplies use rights; based on the access control lists corresponding to medical staff with specific attributes, access records are updated in the access rights list.

[0033] In a preferred embodiment, the system terminal uses the basic information of the patient in the medical information as the information in the personal identifier, inputs it into the hash function SHA-256, and generates a fixed-length hash value. This hash value will be used as the encrypted personal identifier in the NFT. Subsequently, the encrypted personal identifier, medical examination information, medical record information, and treatment information are written into smart contracts according to the ERC-721 standard protocol, and the encrypted personal identifier and the remaining medical information are cast into NFTs through smart contracts. The casting process includes storing the hash value and medical information on the blockchain and generating the corresponding NFT, that is, a non-homogeneous digital certificate. Afterwards, in order to more finely control the access rights to medical information, the system terminal uses the blockchain framework Hyperledger Fabric and adopts attribute-based encryption (ABE) technology. In ABE, specific attributes are set for medical staff, which are directly related to their positions, departments, titles, etc. in the hospital, and these specific attributes are associated with the use rights of medical supplies. This means that only medical staff who meet the specific attribute conditions can obtain the corresponding access rights, configure the dosage of antibiotics and similar drugs, and use them. Then, the system terminal creates an access control column on the blockchain based on the specific attributes of the medical staff. This column records in detail which medical staff can access which medical information and medical supplies. Whenever a medical staff attempts to access, the system terminal automatically checks whether its attributes meet the requirements in the access control column. Once the medical staff is verified, their access behavior will be recorded in the access rights list. This list is dynamically updated and can reflect the access status of medical staff in real time. Through such a mechanism, the security of medical information is guaranteed, and the fine management of medical staff's access rights is realized to avoid the abuse of antibiotics and similar drugs. At the same time, since all operations are recorded on the blockchain, these records are tamper-proof and traceable, providing higher transparency and credibility for the management of medical information.

[0034] Furthermore, the present application provides a method for determining a distribution route for emergency medical supplies, including:

[0035] Based on the remote assisted medical platform, after receiving emergency medical rescue assistance, the user terminal corresponding to the target user is connected online; the symptom description of the target user is analyzed using natural language processing technology, and it is determined whether a fast registration channel is open; based on the fast registration channel, a remote diagnosis electronic prescription is sent, and through the sending coordinates of the user terminal, the medical supplies supply terminal corresponding to the medical supplies supply contract is connected to determine the emergency medical supplies distribution route.

[0036] In an optional implementation, when the remote assisted medical platform receives an assistance request for emergency medical rescue, it will immediately establish an online connection with the target user and communicate in real time through the user terminal. The platform uses natural language processing technology to parse the symptoms described by the target user and recognizes the parsed symptoms through a deep learning model. Subsequently, the time required for the emergency medical rescue vehicle to arrive is compared based on the recognition results to determine whether to open a fast registration channel. If it is determined that emergency treatment is required, the system terminal will open a fast registration channel for the target user through the remote assisted medical platform to speed up the medical treatment process. After confirming the opening of the fast registration channel, the system terminal sends a detailed diagnostic prescription to the user terminal of the target user through the remote assisted medical platform based on the diagnosis results of the remote doctor. At the same time, using the geographic location information provided by the user terminal, the distance matching of multiple medical supply terminals in the medical supply supply contract is performed according to the geographic location information system (GIS), and the medical supply terminal closest to the geographic location information provided by the user terminal is found. Afterwards, the system terminal will use the navigation tool to output the route from the nearest medical supplies supply terminal to the geographic location information provided by the user terminal, determine an emergency medical supplies distribution route, and ensure that the medical supplies can be delivered to the target user's location quickly and accurately to support the needs of emergency medical treatment.

[0037] Furthermore, the present application provides a method of using natural language processing technology to parse the symptom description of the target user and determine whether to open a fast registration channel, including:

[0038] A deep learning model is established, and the deep learning model is used to identify disease patterns; based on the disease pattern, the optimal duration of emergency treatment is predicted, and compared with the emergency medical treatment duration corresponding to the emergency medical rescue vehicle connected to the remote assisted medical platform; if the emergency medical treatment duration corresponding to the emergency medical rescue vehicle is greater than the optimal duration of emergency treatment, the fast registration channel is opened.

[0039] In an optional implementation, in order to improve the efficiency and accuracy of medical services, the system terminal collects a large amount of historical symptom description information and corresponding historical disease patterns. Subsequently, the named entity recognition algorithm in natural language processing technology (NLP) is used to extract historical key symptom information from the symptom description, such as pain location, symptom type, severity, etc., and then the sentence structure in the symptom description is analyzed to understand the logical relationship between each historical key symptom information, such as causal relationship, parallel relationship, etc., to obtain historical logical symptom information. In this process, taking the long short-term memory (LSTM) model as an example, the system terminal uses the LSTM model as a deep learning model. Due to its advantages in processing time series data, the LSTM model can effectively capture the implicit temporal dependencies and logical relationships in the symptom description. The output of the LSTM layer will be passed to the fully connected layer, and finally the predicted disease pattern will be output through the Softmax layer. After that, the system terminal divides the historical logical symptom information and the historical disease pattern to obtain a training set and a test set. During the model initialization process, the system terminal uses the Xavier or He initialization method to initialize the weights of the LSTM layer and the fully connected layer to ensure the stability of the model in the early stage of training. The bias term of LSTM can be initialized with zero value or with a small constant according to specific needs. The system terminal then inputs the training set into the deep learning model and calculates the predicted disease pattern through forward propagation. The classification cross entropy loss is used to calculate the difference between the predicted disease pattern and the historical disease pattern. The gradient of the loss function with respect to each parameter of the LSTM model is calculated by the back propagation through time (BPTT) algorithm. The optimization algorithm Adam is used to update the parameters of the LSTM model according to the gradient information. Repeat the above steps for iterative training until the preset number of iterations is reached. Finally, the system terminal uses the test set data to evaluate the performance of the LSTM model and calculates performance indicators such as accuracy and recall. If the calculated performance indicator meets the performance indicator threshold, the current deep learning model is output. Otherwise, the LSTM model is tuned by adjusting the model architecture and adjusting the hyperparameters.

[0040] After building a deep learning model, the system terminal uses natural language processing technology to extract key symptom information from the target user's symptom description, and inputs the extracted key symptom information into the deep learning model to identify the disease pattern. Subsequently, the system terminal transmits the identified disease pattern to the remote doctor through the remote auxiliary medical platform. The remote doctor analyzes the disease pattern based on professional knowledge and predicts the optimal duration of emergency treatment and the required antibiotics or similar drugs. After that, the system terminal generates a remote diagnosis electronic prescription based on the required antibiotics or similar drugs, and then judges the emergency medical time of the emergency medical rescue vehicle connected to the remote auxiliary medical platform based on the optimal duration of emergency treatment to determine whether the emergency medical rescue vehicle can arrive within the optimal duration of emergency treatment. If the emergency medical rescue vehicle's emergency medical time is longer than the optimal duration of emergency treatment, it means that the emergency medical rescue vehicle may miss the best time for rescue. At this time, the system terminal opens a fast registration channel to provide target users with a faster way to seek medical treatment.

[0041] The model building module 5 is used to build a medical over-analysis model based on the medical supplies supply contract triggered by the medical staff's medical supplies usage rights and in combination with the multiple medical resource tracking tracks.

[0042] Specifically, in the model building module 5, the system terminal searches the medical supplies supply contract according to the medical supplies use rights of the medical staff, determines the dosage and drug name of the antibiotics and similar drugs that the medical staff can use, and obtains the historical drug information. Subsequently, the determined drug name is used to determine the historical use of these drugs according to multiple medical resource tracking trajectories, that is, the use of these drugs for different target users, and obtains the historical drug use information. After that, the system terminal uses professional medical knowledge to mark the use of different target users in the historical drug use information to obtain historical marking information. The marking content is divided into overuse and normal use. Overuse means that the dosage of antibiotics and similar drugs is too much, the abuse of antibiotics and similar drugs occurs, and the resistance of antibiotics and similar drugs is prone to occur. Normal use means that the dosage of antibiotics and similar drugs is within the normal range. Then, the system terminal uses the same method as the above-mentioned deep learning model to train a medical over-analysis model based on historical drug information, historical drug use information and historical marking information.

[0043] Furthermore, the present application provides a medical supplies supply contract triggered by the medical staff's medical supplies usage rights, including:

[0044] Collect the equipment status data of the medical equipment corresponding to the medical supplies supply contract, and retain the equipment's entire life cycle recorded by blockchain technology using the Internet of Things protocol, the equipment status data including usage frequency, operating time, and performance parameters; predict the usage trend and potential failures of the medical equipment, and plan a maintenance plan; based on the equipment's entire life cycle and in combination with the maintenance plan, use an event-driven architecture to automatically trigger maintenance tasks.

[0045] In a preferred embodiment, the system terminal extracts the basic information of the recorded medical equipment from the medical supplies supply contract, including the equipment type, equipment name, and the department where the equipment is located. Subsequently, the status data of these equipment are collected to obtain the equipment status data of these medical equipment, including the frequency of use, operating time, and key performance parameters of the equipment. After that, the system terminal transmits these equipment status data in real time through the Internet of Things protocol, and uses blockchain technology to record these transmitted data on the blockchain, and uses the immutability and transparency of the blockchain to provide reliable records for the full life cycle management of the equipment. Then, the system terminal inputs the equipment status data related to the full life cycle recorded on the blockchain into the pre-built operation and maintenance prediction model to predict the usage trend and potential failure of the medical equipment. After obtaining the prediction results of the usage trend and potential failure, the system terminal analyzes the usage trend of the medical equipment, including the future usage frequency and load changes of the equipment. Identify which medical equipment may have high load or high frequency use in the future, and which equipment may have a decreased usage rate. Then analyze the predicted potential failure type, time, and severity. Determine which equipment may fail and the impact that the failure may have on medical services. For the analysis results, the system terminal combines expert advice and historical experience to plan a maintenance plan and make targeted adjustments to these devices according to the maintenance plan. This maintenance plan aims to extend the service life of the equipment and improve the reliability and safety of the equipment through regular maintenance, inspection and necessary repairs. For example, for high-frequency medical equipment, the medical equipment is sorted in ascending order based on the frequency of use, the use priority of the medical equipment is determined, and then a specific inspection and maintenance time is arranged for each medical equipment to ensure that the maintenance is carried out before the medical equipment fails or the performance deteriorates. Finally, the system terminal uses an event-driven architecture to automatically trigger maintenance tasks. This means that when the medical equipment reaches the predetermined maintenance conditions (such as the frequency of use is higher than the frequency threshold) or predicts an imminent failure, the system terminal will automatically generate and send maintenance tasks to the corresponding maintenance personnel. This approach greatly improves the efficiency and response speed of maintenance and reduces downtime and safety risks caused by medical equipment failures.

[0046] For the operation and maintenance prediction model, the system terminal designs a multi-task neural network consisting of a shared layer and a specific task layer according to business needs and data characteristics. The shared layer includes an embedding layer and a text convolution layer, which are used to extract common features from the input data. The specific task layer includes a usage trend prediction layer and a potential fault prediction layer. Both prediction layers contain a fully connected layer and an output layer, which are used to make predictions based on the extracted status features. Subsequently, the system terminal uses the same training method as above to train the constructed multi-task neural network using historical equipment status data, historical usage data, and historical maintenance data to obtain the final operation and maintenance prediction model.

[0047] The data collaborative management module 6 is used to mark high-risk groups based on the medical over-analysis model, set up a dynamic feedback loop, optimize with the goal of minimizing medical risks and maximizing adaptation accuracy, obtain medical resource allocation strategies, and bind with the target users to perform data collaborative management of the medical information.

[0048] Specifically, in the data collaborative management module 6, the system terminal analyzes the drug use information of different target users based on the constructed medical over-analysis model, and marks the use status. Subsequently, the drug use information marked as over-use is extracted from the marking results output by the medical over-analysis model, and then the target user is traced back based on this drug use information, and the target user is marked as a high-risk group. The high-risk population includes groups that are prone to or have already developed drug resistance due to excessive use of antibiotics and similar drugs, and groups that frequently undergo medical equipment examinations and suffer physical injuries or complications. For example, multiple films and multiple X-ray exposures in a short period of time will lead to the accumulation of ionizing radiation, resulting in increased radiation exposure, damage to the body's cell DNA, damage to the reproductive system, and an increase in the incidence of leukemia.

[0049] Afterwards, the system terminal sets up a dynamic feedback loop based on the pre-set objective function. The objective function in this dynamic feedback loop strives to reduce medical risks to the lowest level, ensure that high-risk groups can obtain necessary medical interventions in a timely manner, and maximize the adaptation accuracy, that is, to ensure that the antibiotics and similar drugs provided can accurately match the actual needs of patients and avoid waste or improper use of medical resources. Through the objective function, the variables corresponding to the medical resource allocation strategy are continuously optimized, and the system terminal can obtain an optimal medical resource allocation strategy to ensure the maximum benefits of antibiotics and similar drugs to delay the emergence of drug resistance. Then, the system terminal binds this medical resource allocation strategy to the target user, and through data collaborative management, ensures that the target user can easily obtain the required medical information and services. This collaborative management not only improves the efficiency and quality of medical services, but also enhances the sense of control over one's own health in the future and prevents the abuse of antibiotics and similar drugs.

[0050] Furthermore, the present application provides a method for marking high-risk groups, setting a dynamic feedback loop, optimizing with the goal of minimizing medical risks and maximizing adaptation accuracy, and obtaining a medical resource allocation strategy, including:

[0051] Setting the objective function .

[0052] In a preferred embodiment, in order to optimize the medical resource allocation strategy, that is, the dosage, duration, number of usage categories, etc. of antibiotics and similar drugs, the system terminal constructs an objective function, which is as follows: ; Among them, y is used to represent the variable corresponding to the medical resource allocation strategy, which involves how to allocate medical resources to different high-risk groups. Medical resources include doctor time, drug types, medication time, drug dosage, etc. R (y) = Used to characterize the medical risk function under the variable y. This function calculates the medical risk faced by high-risk groups under a given allocation of medical resources. The medical risk score used to characterize the i-th high-risk population is determined based on drug usage and is used to quantify the medical risks they face, namely the risk of developing drug resistance. Used to characterize the amount of medical resources allocated to the i-th high-risk population; A(y) = The adaptation accuracy function used to characterize the variable y measures the degree of match between the allocation of medical resources and the actual medical needs of high-risk groups. The adaptation accuracy coefficient used to characterize the i-th high-risk population reflects the sensitivity and responsiveness of this population to specific medical resources and is used to adjust the importance of different populations in the adaptation accuracy function. Used to characterize the actual medical needs allocated to the i-th high-risk population; and is the weight coefficient, which is used to balance the importance of medical risk and adaptation accuracy in the objective function.

[0053] Furthermore, the present application provides adding constraints based on the objective function, including:

[0054] The total amount of medical resources is constrained to ensure that the total amount of medical resources allocated to all high-risk groups does not exceed the total amount of available medical resources. ,in, It is used to characterize the amount of medical resources allocated to the i-th high-risk population. It is used to characterize the total amount of medical resources available in the system; the upper limit constraint of group medical resources is used to ensure that the amount of medical resources allocated to each high-risk group does not exceed the upper limit of medical resources. ,in, Used to represent the minimum amount of medical resources to meet basic medical needs. is a function that adjusts the upper limit of medical resources based on the actual medical needs of the ith high-risk group and the medical risk score of the ith high-risk group. .

[0055] In an optional implementation, in order to ensure the reasonable allocation and utilization of medical resources, the system terminal adds two constraints, namely, the total amount of medical resources constraint and the upper limit constraint of group medical resources. Among them, the total amount of medical resources constraint is to ensure that the total amount of medical resources allocated to all high-risk groups does not exceed the total amount of existing and available medical resources, that is, .in, It is used to characterize the amount of medical resources allocated to the i-th high-risk population. It is used to characterize the total amount of medical resources available in the system. It is a fixed value that reflects the maximum resource support that the current medical system can provide in a specific period of time. It prevents excessive consumption or waste of medical resources and avoids the emergence of drug resistance. The upper limit constraint of group medical resources is to ensure that the amount of medical resources allocated to each high-risk group does not exceed a reasonable upper limit, that is, .in, It represents the minimum amount of medical resources to meet basic medical needs. It is a benchmark value used to ensure that each high-risk group has at least the resources needed to meet their basic medical needs. is a function that adjusts the upper limit of medical resources based on the actual medical needs of the ith high-risk group and the medical risk score of the ith high-risk group, where i is a random number, that is, This upper limit function of medical resources will dynamically adjust the upper limit of the resources that each high-risk group deserves according to their specific circumstances and needs, ensuring that there is neither over-allocation nor over-restriction. At the same time, this upper limit will also be subject to a maximum resource amount. This means that even if a high-risk group has a very high need and risk score, the resources allocated to it will not exceed this absolute upper limit. This constraint helps avoid excessive concentration of medical resources in certain high-risk groups.

[0056] In summary, the blockchain-based intelligent medical information data management system provided by this application has the following technical effects:

[0057] This application connects to the data storage platform through the medical information download module 1 to download the patient's basic information, medical examination information, medical record information and treatment information. Subsequently, the tracking trajectory introduction module 2 introduces the medical material traceability trajectory based on the treatment information. The digital certificate addition module 3 uses blockchain technology to add non-homogeneous digital certificates based on patient information. After the target user completes the registration application, the access authorization opening module 4 opens the access authorization to the corresponding medical staff and creates an access permission list. The model building module 5 establishes a medical over-analysis model based on the material use rights of the medical staff and the medical material supply contract, combined with the medical resource tracking trajectory. The data collaborative management module 6 marks high-risk groups based on the model, sets up a dynamic feedback loop, optimizes with the goal of minimizing medical risks and maximizing adaptation accuracy, obtains medical resource allocation strategies, and binds with the target user for data collaborative management. In addition, it also includes connecting the target user terminal through the remote auxiliary medical platform, using natural language processing technology to parse symptom descriptions, judging whether to open a fast registration channel, sending remote diagnosis electronic prescriptions, and determining the emergency medical material delivery route. Deep learning models are then used to identify disease patterns, predict the optimal duration of emergency treatment, compare it with the duration of medical treatment by emergency medical rescue vehicles, and open a fast registration channel when necessary. Equipment status data is also collected based on the material usage permissions of medical staff to conduct full life cycle management, predict equipment usage trends and potential failures, plan maintenance plans, and automatically trigger maintenance tasks. These technical effects jointly solve the technical problems of increased bacterial resistance and waste of medical resources due to the abuse and insufficient monitoring of key drugs such as antibiotics in medical resource management, and achieve the technical effect of improving the rationality of medical resource allocation and reducing the risk of drug resistance by establishing a data-driven medical over-analysis model.

[0058] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0059] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. Blockchain-based intelligent management system for medical information data, characterized by: include: A medical information download module, used to connect to the data storage platform and download medical information, including basic patient information, medical examination information, medical record information, and treatment information; A tracking track introduction module is used to introduce multiple medical resource tracking tracks based on the treatment information in the medical information, and the medical resource tracking tracks are obtained by tracing the source of medical supplies; A digital certificate adding module, used to add a non-homogeneous digital certificate using blockchain technology based on the patient's basic information, medical examination information, and medical record information in the medical information; An access authorization opening module is used to open access authorization to the medical staff corresponding to the registration application based on the non-homogeneous digital certificate after the target user completes the registration application, and create an access permission list to be reserved for the user terminal corresponding to the target user; A model building module, for training a medical overanalysis model based on the medical supplies supply contract triggered by the medical staff's medical supplies use rights, combining the plurality of medical resource tracking tracks, and according to historical drug information, historical drug use information, and historical annotation information, thereby building a medical overanalysis model; A data collaborative management module is used to mark high-risk groups based on the medical over-analysis model, set a dynamic feedback loop, optimize with the goal of minimizing medical risks and maximizing adaptation accuracy, obtain a medical resource allocation strategy, and bind with the target user to perform data collaborative management of the medical information, wherein the drug usage information marked as over-use is extracted from the labeling results output by the medical over-analysis model, and then the target user is traced back based on the drug usage information, and the target user is marked as a high-risk group, wherein the high-risk group includes a group that is prone to or has already developed drug resistance due to excessive use of antibiotics and similar drugs, and a group that suffers physical injuries or complications due to frequent medical equipment inspections; Wherein, based on the non-homogeneous digital certificate, after the target user completes the registration application, the medical staff corresponding to the registration application is given access authorization, which also includes: Based on the use of hash functions, blockchain technology is used to add a non-fungible digital certificate, wherein the non-fungible digital certificate contains an encrypted personal identity identifier; Through Hyperledger Fabric, attribute-based encryption is used to set access control columns corresponding to medical staff with specific attributes, and the specific attributes are associated and mapped with the medical supplies use rights; Based on the access control list corresponding to the medical staff with specific attributes, the access record is updated in the access permission list; The plurality of medical resource tracking tracks include a plurality of drug resource tracking tracks and a plurality of medical equipment resource tracking tracks; Connecting to a medical resource tracing system, the medical resource tracing system is used to trace the source of medical supplies, and combining the drugs corresponding to the medical supply contract to obtain multiple drug resource tracking tracks; Connecting to the medical resource tracing system, combining with the medical equipment corresponding to the medical supplies supply contract, to obtain multiple medical equipment resource tracking tracks; Among them, high-risk groups are marked, dynamic feedback loops are set up, and optimization is performed with the goal of minimizing medical risks and maximizing adaptation accuracy to obtain medical resource allocation strategies, including: Setting the objective function ; Among them, y is used to represent the variable corresponding to the medical resource allocation strategy, R (y) = It is used to characterize the medical risk function under the variable y. The medical risk score used to characterize the i-th high-risk population, It is used to characterize the amount of medical resources allocated to the i-th high-risk population; A(y) = It is used to characterize the adaptation accuracy function under the variable y. The adaptation accuracy coefficient used to characterize the i-th high-risk population, Used to characterize the actual medical needs allocated to the i-th high-risk population; and is the weight coefficient, which is used to balance the importance of medical risk and adaptation accuracy in the objective function; Wherein, based on the objective function, adding constraints includes: The total amount of medical resources is constrained to ensure that the total amount of medical resources allocated to all high-risk groups does not exceed the total amount of available medical resources. ,in, It is used to characterize the amount of medical resources allocated to the i-th high-risk population. Used to characterize the total amount of medical resources available in the system; The upper limit constraint of group medical resources is used to ensure that the amount of medical resources allocated to each high-risk group does not exceed the upper limit of medical resources. ,in, Used to represent the minimum amount of medical resources to meet basic medical needs. is a function that adjusts the upper limit of medical resources based on the actual medical needs of the ith high-risk group and the medical risk score of the ith high-risk group. .

2. The blockchain-based intelligent medical information data management system according to claim 1, characterized in that: include: Based on the remote medical assistance platform, after receiving emergency medical rescue assistance, connect online to the user terminal corresponding to the target user; Use natural language processing technology to parse the target user's symptom description and determine whether to open a fast registration channel; Based on the fast registration channel, a remote diagnosis electronic prescription is sent, and through the sending coordinates of the user terminal, the medical supplies supply terminal corresponding to the medical supplies supply contract is connected to determine the emergency medical supplies distribution route.

3. The blockchain-based intelligent medical information data management system according to claim 2, characterized in that: Use natural language processing technology to parse the target user's symptom description and determine whether to open a fast registration channel, including: Establishing a deep learning model, the deep learning model is used to identify disease patterns; Based on the disease pattern, predict the optimal duration of emergency treatment, and compare it with the emergency medical rescue time corresponding to the emergency medical rescue vehicle connected to the remote auxiliary medical platform; If the emergency medical treatment time corresponding to the emergency medical rescue vehicle is longer than the optimal emergency treatment time, the fast registration channel will be opened.

4. The blockchain-based intelligent medical information data management system according to claim 1, characterized in that: The medical supplies supply contract triggered by the medical staff's right to use medical supplies includes: Collect the equipment status data of the medical equipment corresponding to the medical supplies supply contract, and retain the equipment's entire life cycle recorded by blockchain technology using the Internet of Things protocol, wherein the equipment status data includes usage frequency, operating time, and performance parameters; Predict usage trends and potential failures of the medical equipment and plan maintenance schedules; Based on the entire life cycle of the equipment and in combination with the maintenance plan, maintenance tasks are automatically triggered using an event-driven architecture.

5. The blockchain-based intelligent medical information data management system according to claim 1, characterized in that: The medicines corresponding to the medical supplies supply contract are managed in optimized inventory, and the optimized inventory management is performed by integrating the inventory forecasting algorithm with the demand forecasting algorithm.

Images