Remote medical monitoring management system based on block chain

Abstract

The invention discloses a remote medical monitoring management system based on a block chain, which belongs to the field of medical monitoring management systems and comprises a data acquisition module, a processing analysis module, a monitoring index calculation module, an early warning generation module, a block chain module, a user interface module and a communication module. Real-time data streams are received from various health monitoring devices, the data are preprocessed, a patient information table is created according to patient types, health training data of different types of patients are obtained, a neural network model is trained, and a patient health condition evaluation model is trained by using the CNN neural network model; calculating a suitable monitoring index based on the health data and the health condition statistical data of the patient; according to the health data of the patient, the suitable monitoring index and the patient information table, generating early warning time for the patient, and based on the early warning time, initiating health deterioration early warning to a guardian; and the blockchain ensures the security in the data transmission process.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical monitoring management, and specifically relates to a remote medical monitoring management system based on blockchain. Background Art

[0002] With the rapid development of science and technology and the popularization of Internet medicine, telemedicine, as an innovative medical model, is gradually changing the way people seek medical treatment. It can not only effectively alleviate the problem of uneven distribution of medical resources, but also improve the accessibility and efficiency of medical services. However, while developing rapidly, telemedicine is also facing many challenges, especially in terms of data security, identity authentication, drug traceability and data sharing.

[0003] In the traditional telemedicine system, patients' personal health data is usually stored in various medical institutions and equipment. This decentralized storage method not only increases the complexity of data management, but also easily leads to data silos, reducing data connectivity and availability. In addition, the lack of unified data exchange standards between different medical systems makes it difficult to effectively ensure the security and integrity of data, and there is a risk of tampering or leakage. Summary of the invention

[0004] The purpose of the present invention is to provide a remote medical monitoring management system based on blockchain to solve existing technical problems.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions: A remote medical monitoring management system based on blockchain, comprising a data acquisition module, a processing and analysis module, a monitoring index calculation module, an early warning generation module, a blockchain module, a user interface module and a communication module; The data acquisition module is used to receive real-time data streams from various health monitoring devices and pass the collected data to the data processing module; The processing and analysis module is used to pre-process the collected data, create a patient information table according to the patient type, obtain health training data of different types of patients, and train the neural network model. The CNN neural network model is used to train the patient health status assessment model; The monitoring indicator calculation module calculates appropriate monitoring indicators based on the patient's health data and health status statistics; The warning generation module generates a warning time for the patient based on the patient's health data, appropriate monitoring indicators, and patient information form, and based on the warning time, issues a warning of health deterioration to the guardian; The blockchain module is responsible for creating and managing smart contracts to achieve data access control, data encryption and decryption to ensure the security of data transmission, and the implementation of the consensus algorithm in the blockchain network to ensure data consistency and immutability. The user interface module is a user interaction interface used to remotely monitor and manage the health status, monitoring indicators, and early warning information of management users.

[0006] The communication module is responsible for the communication between modules within the system, as well as the communication between the system and external devices including health monitoring devices and smart wearable devices.

[0007] As a preferred method, the system workflow is as follows: Step 1: Obtain patient information form and patient health training data; Step 2: Train a neural network model to assess the health status of each type of patient based on the patient health training data; Step 3: Collect health data of patients to be monitored, and use a neural network model to obtain health status statistics of each patient to be monitored; Step 4: based on the health data of the patient to be monitored and the assessed health status statistics of each patient, calculate the appropriate monitoring index of the monitoring system, and set the monitoring index when the monitoring system monitors the patient to be monitored as the appropriate monitoring index; Step 5: Based on the health data, appropriate monitoring indicators and patient information table of the patient to be monitored, a warning time is generated for each patient to be monitored. During the monitoring process, a health deterioration warning is initiated based on the warning time.

[0008] As a preferred method, in step 1, the patient information table and the patient health training data are obtained as follows: S101, create a patient information form; Create a database table with patient type as the primary key, various health indicators as attributes, and the average health maintenance time under each health indicator as the attribute value, and mark it as a patient information table; The average health maintenance time is obtained by pre-calculating the average health maintenance time of each type of patient in each health indicator; the average health maintenance time is the average time from health to symptom onset for each patient in each health indicator; S102, obtaining patient health training data; The patient health data includes health status data of each type of patient in different time periods and the health status level corresponding to each set of data.

[0009] Preferably, in step 2, a neural network model for evaluating the health status of each type of patient is trained based on the patient health training data, as follows: For the i-th patient type, each health status data of the patient type in the patient health training data is used as the input of the neural network model, and the neural network model uses the health status level of each data as the output, and the health status level corresponding to each data in the patient health training data as the evaluation target, and minimizing the sum of the evaluation errors of all data as the training target; The neural network model is trained until the sum of the evaluation errors reaches convergence, and the training is stopped, and a neural network model is trained to output an evaluation health status level according to the patient health status data, wherein the neural network model is a CNN neural network model; The calculation formula of the evaluation error is as follows: ; in, To assess the error; For the The assessed health status level corresponding to the health status data of each patient; For the The actual health status level of a patient, that is, the baseline value.

[0010] As a preference, step three is specifically as follows: S301, collecting health data of patients to be monitored, including health indicators of each patient to be monitored, standard price series, and health data collected for each patient to be monitored before the patient to be monitored is included in the monitoring system; wherein the standard price series is the medical expenses of each health maintenance time of each patient to be monitored under the standard health indicators; S302, obtaining health status statistical data; Identify and segment the health data of individual patients to be monitored from the health data of the patients to be monitored; obtain health status statistics of each patient to be monitored based on each piece of health data of the individual patient to be monitored and the neural network model; The specific method for obtaining health status statistical data is as follows: for the i-th patient type, the number of health data of the corresponding individual patient to be monitored is marked as Ni; each piece of health data of the individual patient to be monitored is input into the neural network model, and the health status level of each individual patient to be monitored output by the neural network model is obtained.

[0011] Preferably, the appropriate monitoring index in step 4 is a monitoring index that is most beneficial to the patient's health calculated based on the statistical data of the health status of the patient to be monitored.

[0012] As a preference, step five is specifically as follows: Mark the appropriate monitoring index of the monitoring system as t1; obtain the average health maintenance time Ht1i corresponding to the i-th patient to be monitored from the patient information table; for the i-th patient to be monitored with the x-th health status level, calculate its warning time Fix; Method for initiating health deterioration warning: During the monitoring process, the monitoring system control background determines at regular intervals whether the total monitoring time is greater than or equal to the corresponding warning time Fix for the i-th patient to be monitored with the x-th health status level. If it is greater than the warning time Fix, a warning is initiated to the monitoring personnel.

[0013] Preferably, the patient information form is stored on the blockchain to ensure the security and non-tamperability of the data.

[0014] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are: 1. The present invention realizes personalized modeling of the patient's health status by creating a patient information table with the patient type as the primary key and introducing the average health maintenance time as the key attribute value. This modeling method not only takes into account the patient's type, but also combines the average health maintenance time.

[0015] 2. The present invention uses a convolutional neural network model to learn a large amount of patient health training data, thereby realizing automatic and rapid assessment of the patient's health status. The model can accurately output the patient's health status level, with higher accuracy and efficiency than traditional methods.

[0016] 3. The present invention dynamically calculates and sets appropriate monitoring indicators of the monitoring system based on the actual health data and health status statistics of the patient to be monitored, ensuring the pertinence and effectiveness of monitoring, and better meeting the personalized needs of different patients; combining the average health maintenance time in the patient information table, appropriate monitoring indicators, and the health status level output by the neural network model to generate an early warning time. At the same time, through the regular judgment and early warning mechanism of the monitoring system control background, timely early warning of health deterioration is achieved, improving the timeliness and effectiveness of monitoring.

[0017] 4. The present invention uses blockchain technology to ensure the security and privacy of data, implements data access control through smart contracts, and ensures data consistency through a consensus mechanism. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in 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 described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 A module diagram of a blockchain-based remote medical monitoring management system of the present invention is shown.

[0020] Figure 2 A workflow diagram of the present invention is shown. DETAILED DESCRIPTION

[0021] 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.

[0022] Example 1

[0023] See also Figure 1 As shown, a blockchain-based remote medical monitoring management system provided by the present invention includes a data acquisition module, a processing and analysis module, a monitoring index calculation module, an early warning generation module, a blockchain module, a user interface module and a communication module.

[0024] Data acquisition module: responsible for receiving real-time data streams from various health monitoring devices and passing the collected data to the data processing module.

[0025] Processing and analysis module: pre-process the collected data, create a patient information table according to the patient type, obtain health training data of different types of patients, and train the neural network model. Use the CNN neural network model to train the patient health status assessment model.

[0026] Monitoring indicator calculation module: calculates appropriate monitoring indicators based on the patient's health data and health status statistics.

[0027] Early warning generation module: Generates early warning time for patients based on their health data, appropriate monitoring indicators and patient information form, and issues early warning of health deterioration to guardians based on the early warning time.

[0028] Blockchain module: responsible for creating and managing smart contracts to achieve data access control; responsible for data encryption and decryption to ensure the security of data transmission; responsible for implementing the consensus algorithm in the blockchain network to ensure the consistency and immutability of data.

[0029] User interface module: It is a user interaction interface used to remotely monitor and manage the health status, monitoring indicators, and early warning information of management users.

[0030] Communication module: responsible for the communication between modules within the system, as well as the communication between the system and external devices including health monitoring devices and smart wearable devices.

[0031] Beneficial effects of this embodiment: Through the design of these modules, a complete blockchain-based remote medical monitoring management system is realized, which can not only monitor the patient's health status in real time, but also ensure the security and privacy of the data.

[0032] Example 2

[0033] See also Figure 2 As shown, the present invention provides a blockchain-based remote medical monitoring management system, and the workflow is as follows: Step 1: Obtain patient information form and patient health training data.

[0034] S101. Create a patient information table.

[0035] Create a database table with patient type (such as diabetic patients, hypertensive patients, etc.) as the primary key, various health indicators as attributes, and the average health maintenance time under each health indicator as the attribute value, and mark it as a patient information table.

[0036] The average health maintenance time is obtained by pre-classifying patients of various types in various health indicators and then counting the average health maintenance time of each type of patient; the average health maintenance time is the average time from health to symptom onset for each patient in each health indicator.

[0037] S102. Obtain patient health training data.

[0038] Among them, the patient health data includes health status data of each type of patient in different time periods (such as blood sugar values, blood pressure values, etc.) and the health status level corresponding to each set of data.

[0039] Step 2: Train a neural network model to assess the health status of each type of patient based on the patient health training data.

[0040] Specifically, for the i-th patient type, each health status data of the patient type in the patient health training data is used as the input of the neural network model, and the neural network model uses the health status level of each data as the output, and the health status level corresponding to each data in the patient health training data as the evaluation target, and minimizes the sum of the evaluation errors of all data as the training target; the neural network model is trained until the sum of the evaluation errors reaches convergence, and the training is stopped, and a neural network model that outputs the evaluation health status level according to the patient health status data is trained. Wherein, the neural network model is a CNN neural network model.

[0041] The calculation formula of the evaluation error is as follows: ; in, To assess the error; For the The assessed health status level corresponding to the health status data of each patient; For the The actual health status level of a patient, that is, the baseline value.

[0042] Step 3: Collect health data of patients to be monitored, and use the neural network model to obtain health status statistics of each patient to be monitored.

[0043] S301. Collect health data of patients to be monitored, including health indicators of each patient to be monitored (such as blood sugar value, blood pressure value, etc.), standard price series, and health data collected for each patient to be monitored before the patient to be monitored is included in the monitoring system.

[0044] The standard price series is the medical expenses for each health maintenance period of each patient under monitoring under standard health indicators.

[0045] S301. Obtain health status statistics.

[0046] The health data of individual patients to be monitored are identified and segmented from the health data of the patients to be monitored; based on each piece of health data of the individual patients to be monitored and the neural network model, the health status statistics of each patient to be monitored are obtained.

[0047] The specific method for obtaining health status statistical data is as follows: for the i-th patient type, the number of health data of the corresponding individual patient to be monitored is marked as Ni; each piece of health data of the individual patient to be monitored is input into the neural network model, and the health status level of each individual patient to be monitored output by the neural network model is obtained.

[0048] Step 4: Based on the health data of the patient to be monitored and the assessed health status statistics of each patient, calculate the appropriate monitoring index of the monitoring system, and set the monitoring index when the monitoring system monitors the patient to be monitored as the appropriate monitoring index.

[0049] Among them, appropriate monitoring indicators are those that are most beneficial to the health of patients calculated based on statistical data on their health conditions.

[0050] Step 5: Based on the health data, appropriate monitoring indicators and patient information table of the patient to be monitored, a warning time is generated for each patient to be monitored. During the monitoring process, a health deterioration warning is initiated based on the warning time.

[0051] Specifically, the method of generating the warning time is as follows: mark the appropriate monitoring index of the monitoring system as t1; obtain the average health maintenance time Ht1i corresponding to the i-th patient to be monitored from the patient information table; for the i-th patient to be monitored with the x-th health status level, calculate its warning time Fix.

[0052] Method for initiating health deterioration warning: During the monitoring process, the monitoring system control background determines at regular intervals whether the total monitoring time is greater than or equal to the corresponding warning time Fix for the i-th patient to be monitored with the x-th health status level. If it is greater than the warning time Fix, a warning is initiated to the monitoring personnel.

[0053] The beneficial effects of this embodiment are as follows: generating warning time, and combining regular judgment with warning mechanism, achieving timely warning of health deterioration, helping patients to take timely intervention measures to avoid worsening of the disease.

[0054] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

[0055] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A remote medical monitoring management system based on blockchain, characterized in that: It includes data acquisition module, processing and analysis module, monitoring index calculation module, warning generation module, blockchain module, user interface module and communication module; The data acquisition module is used to receive real-time data streams from various health monitoring devices and pass the collected data to the data processing module; The processing and analysis module is used to pre-process the collected data, create a patient information table according to the patient type, obtain health training data of different types of patients, and train the neural network model. The CNN neural network model is used to train the patient health status assessment model; The monitoring indicator calculation module calculates appropriate monitoring indicators based on the patient's health data and health status statistics; The warning generation module generates a warning time for the patient based on the patient's health data, appropriate monitoring indicators, and patient information form, and issues a warning of health deterioration to the guardian based on the warning time; The blockchain module is responsible for creating and managing smart contracts to achieve data access control, encrypting and decrypting data to ensure the security of data transmission, and implementing the consensus algorithm in the blockchain network to ensure data consistency and immutability; The user interface module is a user interaction interface used to remotely monitor the health status, monitoring indicators, and early warning information of supervisory users; The communication module is responsible for the communication between modules within the system, as well as the communication between the system and external devices including health monitoring devices and smart wearable devices.

2. According to claim 1, a blockchain-based remote medical monitoring management system is characterized in that: The system workflow is as follows: Step 1: Obtain patient information form and patient health training data; Step 2: Train a neural network model to assess the health status of each type of patient based on the patient health training data; Step 3: Collect health data of patients to be monitored, and use a neural network model to obtain health status statistics of each patient to be monitored; Step 4: based on the health data of the patient to be monitored and the assessed health status statistics of each patient, calculate the appropriate monitoring index of the monitoring system, and set the monitoring index when the monitoring system monitors the patient to be monitored as the appropriate monitoring index; Step 5: Based on the health data, appropriate monitoring indicators and patient information table of the patient to be monitored, a warning time is generated for each patient to be monitored. During the monitoring process, a health deterioration warning is initiated based on the warning time.

3. According to a blockchain-based remote medical monitoring management system according to claim 2, it is characterized in that: The patient information table and patient health training data are obtained in step 1, as follows: S101, create a patient information form; Create a database table with patient type as the primary key, various health indicators as attributes, and the average health maintenance time under each health indicator as the attribute value, and mark it as a patient information table; The average health maintenance time is obtained by pre-calculating the average health maintenance time of each type of patient in each health indicator; the average health maintenance time is the average time from health to symptom onset of each patient in each health indicator; S102, obtaining patient health training data; The patient health data includes health status data of each type of patient in different time periods and the health status level corresponding to each set of data.

4. According to claim 2, a blockchain-based remote medical monitoring management system is characterized in that: In step 2, a neural network model for evaluating the health status of each type of patient is trained based on the patient health training data, as follows: For the i-th patient type, each health status data of the patient type in the patient health training data is used as the input of the neural network model, and the neural network model uses the health status level of each data as the output, and the health status level corresponding to each data in the patient health training data as the evaluation target, and minimizing the sum of the evaluation errors of all data as the training target; The neural network model is trained until the sum of the evaluation errors reaches convergence, and the training is stopped, so as to train a neural network model that outputs an evaluation health status level according to the patient health status data, wherein the neural network model is a CNN neural network model; The calculation formula of the evaluation error is as follows: ； in, To assess the error; For the The assessed health status level corresponding to the health status data of each patient; For the The actual health status level of a patient, that is, the baseline value.

5. According to a blockchain-based remote medical monitoring management system as described in claim 2, it is characterized in that: The step three is as follows: S301, collecting health data of patients to be monitored, including health indicators of each patient to be monitored, standard price series, and health data collected for each patient to be monitored before the patient to be monitored is included in the monitoring system; wherein the standard price series is the medical expenses of each health maintenance time of each patient to be monitored under the standard health indicators; S302, obtaining health status statistical data; Identify and segment the health data of individual patients to be monitored from the health data of the patients to be monitored; obtain health status statistics of each patient to be monitored based on each piece of health data of the individual patient to be monitored and the neural network model; The specific method for obtaining health status statistical data is as follows: for the i-th patient type, the number of health data of the corresponding individual patient to be monitored is marked as Ni; each piece of health data of the individual patient to be monitored is input into the neural network model, and the health status level of each individual patient to be monitored output by the neural network model is obtained.

6. A blockchain-based remote medical monitoring management system according to claim 2, characterized in that: In the step 4, the appropriate monitoring index is calculated based on the statistical data of the health status of the patient to be monitored to find the monitoring index that is most beneficial to the patient's health.

7. A blockchain-based remote medical monitoring management system according to claim 2, characterized in that: The step five is specifically as follows: Mark the appropriate monitoring index of the monitoring system as t1; obtain the average health maintenance time Ht1i corresponding to the i-th patient to be monitored from the patient information table; for the i-th patient to be monitored with the x-th health status level, calculate its warning time Fix; Method for initiating health deterioration warning: During the monitoring process, the monitoring system control background determines at regular intervals whether the total monitoring time is greater than or equal to the corresponding warning time Fix for the i-th patient to be monitored with the x-th health status level. If it is greater than the warning time Fix, a warning is initiated to the monitoring personnel.

8. According to claim 2, a blockchain-based remote medical monitoring management system is characterized in that: The patient information form is stored on the blockchain to ensure the security and immutability of the data.

Images