CN116319817A - Medical data processing method and system based on edge calculation and blockchain - Google Patents

Abstract

The invention provides a medical data processing method and a system based on edge calculation and blockchain, wherein the method mainly comprises the following steps: collecting data of different patients; feature extraction, identifying features related to the patient state from the obtained data; patient state monitoring, detecting main changes of the patient state by using the identified characteristics, and determining data shared with the blockchain network; the data sender uploads the data to the nearby blockchain manager in the form of a transaction; the block chain manager allocates different priorities and channels to the collected transactions according to the emergency degree of the transactions; the blockchain manager acts as a manager of the validators, distributing unverified blocks to selected validators; the validators perform validation, trigger a consensus process between the validators, and insert the validated blocks into the blockchain. The invention can effectively realize large-scale medical data processing, lighten network load and quickly respond to emergency events.

Description

Medical data processing method and system based on edge computing and blockchain

technical field

The invention relates to a medical data processing method and system based on edge computing and blockchain, and belongs to the technical field of edge computing and blockchain.

Background technique

With the continuous development of the medical field and the acceleration of digitalization, efficient medical data processing across different entities has become a global focus. Modern healthcare involves data covering everything from patient health status to medical records, diagnosis, treatment and prognosis. These data come from different entities such as hospitals, clinics, laboratories, insurance companies, etc., so efficient medical data processing across different entities becomes crucial. By automating most of the medical functions and providing efficient medical services, it can make a key contribution to the development of smart healthcare. Emerging technologies such as edge computing and blockchain can turn this vision into reality. These technologies can efficiently collect, process and exchange medical data.

However, the amount of information at the edge is huge, how to reduce the network load and significantly reduce the amount of information that needs to be shared on the blockchain is a huge challenge. Second, in an emergency, how to activate quick alerts and notifications to facilitate effective analysis without wasting doctors' time is also an important issue.

In view of this, it is necessary to propose a medical data processing method and system based on edge computing and blockchain to solve the above problems.

Contents of the invention

The purpose of the present invention is to provide a medical data processing method and system based on edge computing and blockchain, which can improve the efficiency of large-scale medical data processing.

In order to achieve the above object, the present invention provides a medical data processing method based on edge computing and blockchain, which mainly includes the following steps:

S1. Data collection, collecting data of different patients;

S2. Feature extraction, identifying features related to the patient's state from the obtained data;

S3. Patient status monitoring, using identified features to detect major changes in patient status, and determine the data shared with the blockchain network;

S4. The data sender uploads the data to the nearby blockchain manager in the form of transactions;

S5. The blockchain manager assigns different priorities and channels to the collected transactions according to the urgency of the transactions;

S6. The blockchain manager, as the manager of the verifier, distributes unverified blocks to the selected verifiers;

S7. The verifier performs verification, triggers the consensus process among the verifiers, and inserts the verified block into the blockchain.

As a further improvement of the present invention, in S1, the patient's information includes the patient's brain wave, body temperature, and blood pressure.

最小值/>

平均值/>

方差/>

均方根R_i以及峭度K_i作为特征，记脑电图通道数为n(i∈{1,2,…,n})，样本数为M(m∈{1,2,…,M})，其中As a further improvement of the present invention, in S2, the maximum value of each channel of the collected patient data

min/>

Average />

Variance />

Root mean square R _i and kurtosis K _i are used as features, remember that the number of EEG channels is n(i∈{1,2,…,n}), and the number of samples is M(m∈{1,2,…,M }),in

average value:

variance:

RMS:

Kurtosis:

As a further improvement of the present invention, in S3, the index _θi is defined to obtain clear classification rules:

As a further improvement of the present invention, the definition index quantitative β={β ₁ ,β ₂ ,…,β _i ,…,β _n },

in,

As a further improvement of the present invention, α is defined as the threshold for assessing major changes, and a γ is defined as the final result state,

Among them, [α] ⁺ ＝max(0,α), ∥p‖ ₀ means 0 norm.

As a further improvement of the present invention, in S3, when γ=(1), that is, when a major change is detected, the blockchain network will share emergency notifications through the blockchain, as well as raw data that requires further investigation; When γ=(2), ie slight or no changes are detected, the blockchain network will only share the acquired features.

In order to achieve the above object, the present invention also provides a medical data processing system based on edge computing and block chain, applying the above-mentioned edge computing and block chain based medical data processing method.

As a further improvement of the present invention, the medical data processing system based on edge computing and blockchain includes a local network and a blockchain network, wherein the local network includes: IoT devices connected to patients, professional public health Internet of Things devices connected to patients in institutions, hospitals, primary medical and health institutions, other medical and health institutions, and local networks.

As a further improvement of the present invention, the block chain network includes: a data transmitter, a block chain manager, a verifier and a multi-channel block chain, and the multi-channel block chain includes a first channel, a second channel and The third channel, where the first channel is used for urgent data, the second channel is used for non-urgent but high-security data; the third channel is normal data;

Define α as the threshold for evaluating major changes, define a γ as the final result state,

Among them, [α] ⁺ ＝max(0,α), ‖p‖ ₀ means 0 norm, β is the quantitative index, when γ=(1), that is, when detecting major changes, the data will go first Channel, when γ=(2), that is, when a slight or no change is detected, if the data is data with a high security level, the second channel is used; otherwise, the third channel is used.

The beneficial effects of the invention are: the invention can effectively realize large-scale medical data processing, reduce network load and respond quickly to emergency events.

Description of drawings

Fig. 1 is a system architecture diagram of the medical data processing system based on edge computing and block chain of the present invention.

Fig. 2 is a schematic flow chart of the medical data processing method based on edge computing and blockchain in the present invention.

Detailed ways

In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

Here, it should be noted that, in order to avoid obscuring the present invention due to unnecessary details, only the structures and/or processing steps closely related to the solution of the present invention are shown in the drawings, and the steps related to the present invention are omitted. Other details that don't really matter.

Additionally, it should be noted that the term "comprises", "comprises" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article or apparatus comprising a set of elements includes not only those elements, but also Other elements not expressly listed, or inherent to the process, method, article, or apparatus are also included.

As shown in Figures 1 and 2, the present invention discloses a medical data processing method and system based on edge computing and blockchain. The medical data processing system is composed of various electronic medical entities, and its basic functions are monitoring, Promote and maintain people's health.

The system architecture is shown in Figure 1, which is divided into two main networks: local network and blockchain network. For scalability reasons, e-health entities are used to collect medical-related data from local networks, process these data, and share important information through blockchain networks. Shared data is verified and stored locally by individual entities in the blockchain, which is a trusted entity with large storage and computing capabilities.

The local network extends from data sources located on or around the patient to local healthcare delivery systems, such as primary healthcare facilities. The local network includes the following main components: Internet of Things devices connected to patients, professional public health institutions, hospitals, primary medical and health institutions, other medical and health institutions, and Internet of Things devices connected to patients in the local network.

IoT devices connected to the patient to monitor health and activity in an intelligently assisted environment. For example: body area sensor networks (i.e. implantable or wearable sensors that measure different biosignals and vital signs), smartphones, IP cameras, and external medical and non-medical devices.

Professional public health institutions, specifically including disease prevention and control system, maternal and child health care system, pre-hospital first aid system, blood collection and supply system, occupational disease prevention and control system, etc. Its main role is to monitor the quality and effectiveness of health care services through coordination with different health entities, and to strengthen the operational guidance and work coordination of higher-level disease control agencies to lower-level disease control agencies.

Hospitals, divided into public hospitals and private hospitals, are an important part of the medical data exchange system.

Primary medical and health institutions refer to township health centers, community health service centers, village clinics, infirmaries, outpatient departments and clinics, etc. It mainly undertakes basic health services such as prevention, health care, and disease management, diagnosis and treatment of common diseases and frequently-occurring diseases, rehabilitation, nursing, and palliative care services for some diseases, and receiving patients referred by hospitals.

Other medical and health institutions, including mental health institutions and other medical institutions, set up independent medical examination, pathological diagnosis, medical imaging, hemodialysis, health examination and other institutions, establish cooperative relations with hospitals and primary medical and health service institutions, and realize regional resources shared.

The Internet of Things devices connected to the patient in the local network play an important role in monitoring the status of the patient; the local medical and health service system can provide the necessary medical services for local patients, record the status of the patient, and provide timely of emergency services. The local network can be responsible for data storage, apply complex data analysis techniques, and enable various medical and health service entities to share important health-related information. Therefore, utilizing the power of edge computing, each entity can verify the authenticity and integrity of medical data in the local network, and then share the data in the blockchain.

As far as the blockchain network is concerned, its core is a blockchain-based multi-channel data sharing architecture that can securely access, process and share medical data among different electronic medical entities. Blockchain is indeed particularly well-suited for secure medical data exchange because of its immutable and decentralized properties.

The blockchain network mainly includes: 1. Data transmitter; 2. Blockchain manager (BM: blockchainmanager); 3. Validator.

First, data senders upload their data in the form of "transactions" to nearby BMs. Then, BM acts as the manager of validators: distributes unverified blocks to validators for verification, triggers the consensus process among validators, and inserts verified blocks into the blockchain. Therefore, BM acts as the leader, and the verifier acts as the follower to complete the block verification task collaboratively.

In our blockchain network, a multi-channel blockchain is also included, where each channel corresponds to a separate transaction chain, which can be used to support data access and private communication between channel users. Using this architecture can effectively handle different levels of medical events.

There are three channels in the blockchain, where the first channel (channel 1) is used for urgent data (such as emergency notifications), the second channel (channel 2) is used for data that is not urgent but requires a high level of security; the third channel The channel (channel 3) is normal data.

In the work, the proposed multi-channel blockchain architecture is motivated by the fact that when there is minimal trust between participating entities (or when the generated transactions are not urgent), it takes more time to verify And protection affairs would be ideal. On the other hand, when the participating entities share a high level of trust, or when the nature of the generated transactions is urgent, enforcing high security will unnecessarily reduce transaction throughput. This is especially evident in healthcare applications, where supporting rapid response in emergency situations is a primary goal of urgent care.

Therefore, urgent data (i.e. requiring minimal latency) should be given the highest priority and will be processed for less constrained blockchains, i.e. with a minimum number of validators.

The medical data processing method includes the following steps:

S1: Data collection, collecting data of different patients;

Use electronic medical entities to collect medical-related data from the local network. The collected patient data includes routine observation data such as brain waves, body temperature, and blood pressure. Brain wave is the overall activity of brain nerve cells, including ion exchange, metabolism and other comprehensive external manifestations. In-depth study of the characteristics of brain wave will promote the exploration and research process of people's own brain and enhance its ability to diagnose diseases. From the initial EEG recording device that can only record 1 or 2 channels, 6-lead and 8-lead EEG machines gradually appeared. EEG machines commonly used in clinical practice now have 16 leads, 32 leads and 64 leads.

S2: Feature extraction, identifying specific features from the acquired data that are informative and relevant to the state of the patient;

最小值/>

平均值/>

方差/>

均方根R_i以及峭度K_i作为特征，记脑电图通道数为n(i∈{1,2,…,n})，样本数为M(m∈{1,2,…,M})，其中For the collected EEG data, it is difficult for doctors to distinguish and detect changes. The maximum value of each channel of the collected patient data

min/>

Average />

Variance />

Root mean square R _i and kurtosis K _i are used as features, remember that the number of EEG channels is n(i∈{1,2,…,n}), and the number of samples is M(m∈{1,2,…,M }),in

average value:

variance:

RMS:

Kurtosis:

S3: Patient status monitoring, using identified features to detect major changes in patient status, and determine data shared with the blockchain network;

Using the features generated above to define an index _θi to obtain clear classification rules, thereby revealing the main changes in the obtained data, the index integration features are as follows:

Define an index quantitative β={β ₁ ,β ₂ ,…,β _i ,…,β _n }

其中，/>

定义一个α为评估主要变化的阈值，可根据实际情况动态调整(比如α＝20％或α＝30％等)。另外定义一个γ为最终结果状态，

where, />

An α is defined as a threshold for assessing major changes, which can be dynamically adjusted according to actual conditions (such as α=20% or α=30%, etc.). In addition, define a γ as the final result state,

Among them, [α] ⁺ ＝max(0,α), ∥p‖ ₀ means 0 norm.

The identified features are used to detect major changes in patient status. Based on the detected changes, edge nodes can optimize shared content on the blockchain network. When γ = (1), that is, in the case of detecting major changes (i.e. emergencies) , it will share emergency notifications via the blockchain, as well as raw data that may require further investigation; when γ = (2), i.e., where slight or no changes are detected, it will only share the acquired features.

Further, in S3, major changes in patient status are detected with the identified features, and based on the detected changes, edge nodes can optimize the shared content on the blockchain network. In the case of detecting major changes (i.e., emergencies), It will share emergency notifications via the blockchain, as well as raw data that may require further investigation; where minor or no changes are detected, it will only share the characteristics obtained.

S4: Data senders upload their data to nearby BMs in the form of "transactions"

S5: BM assigns different priorities and notifications to the collected transactions according to the urgency of the transactions.

BM assigns different priorities and channels to the collected transactions according to the urgency of the transactions. Data obtained from different entities should be handled differently depending on its urgency and level of security. For example, urgent data (i.e. requiring minimal latency) should be given the highest priority and processed using a less restrictive blockchain, i.e. using the smallest number of validators. However, for higher security requirements, a fully restricted blockchain should be used. For normal data, that is, data that requires both latency and security, the blockchain configuration can be further optimized. When γ=(1), that is, when major changes are detected, the data will go through the first channel. When γ=(2), that is, when slight or no changes are detected, if the data is of high security level data, it goes through the second channel, otherwise it goes through the third channel.

S6: Then, BM acts as the validator's manager: distributes unverified blocks to selected validators (such as hospitals, etc., which have sufficient computing and storage resources)

S7: The validator performs verification, triggers the consensus process among the validators, and inserts the verified block into the blockchain. BM acts as the leader, and the verifier acts as the follower to complete the block verification task collaboratively.

To sum up, the present invention proposes a set of medical data processing system and method relying on edge computing technology and blockchain technology to effectively realize large-scale medical data processing. On the premise of ensuring the safe transmission of medical data, on the one hand, at the edge, the amount of information that needs to be shared on the blockchain is significantly reduced by detecting changes in the collected data, thereby reducing network load and quickly responding to emergencies. On the other hand, in the blockchain network, consider a multi-channel blockchain that assigns different priorities and channels to the collected transactions according to the urgency of the transactions, thereby facilitating effective analysis without wasting doctors and patients time.

The above embodiments are only used to illustrate the technical solutions of the present invention without limitation. Although the present invention has been described in detail with reference to preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced. Without departing from the spirit and scope of the technical solution of the present invention.

Claims (10)

1. A medical data processing method based on edge calculation and blockchain, which is characterized by mainly comprising the following steps:

s1, data acquisition, namely collecting data of different patients;

s2, extracting features, and identifying features related to the state of the patient from the obtained data;

s3, monitoring the state of the patient, detecting main changes of the state of the patient by using the identified characteristics, and determining data shared with a blockchain network;

s4, uploading the data to a nearby blockchain manager by a data sender in a transaction mode;

s5, the block chain manager distributes different priorities and channels to the collected transactions according to the emergency degree of the transactions;

s6, the block chain manager serves as a manager of the verifier, and unverified blocks are distributed to the selected verifier;

and S7, verifying by the verifiers, triggering a consensus process among the verifiers, and inserting the verified blocks into the blockchain.

2. The edge computing and blockchain based medical data processing method of claim 1, wherein: in S1, the data of the patient comprise brain waves, body temperature and blood pressure of the patient.

3. The edge computing and blockchain based medical data processing method of claim 1, wherein: s2, maximum value of each channel of the acquired patient data

Minimum->

Average value->

Variance->

Root mean square R _i Kurtosis K _i As a characteristic, record electroencephalogramThe number of lanes is n (i.e {1,2, …, n }) and the number of samples is M (m.e {1,2, …, M }), where

Average value:

variance:

root mean square:

kurtosis:

4. the edge computing and blockchain based medical data processing method of claim 3, wherein: s3, defining an index theta _i To obtain an explicit classification rule:

5. the edge computing and blockchain based medical data processing method of claim 4, wherein: definition index quantitative beta= { beta ₁ ,β ₂ ,…,β _i ,…,β _n }，

wherein ,

6. the edge computing and blockchain based medical data processing method of claim 5, wherein: defining alpha as the threshold for evaluating the main change, defining a gamma as the final result state,

wherein ,[α]⁺ ＝max(0,α)，‖p‖ ₀ Representing a 0 norm.

7. The edge computing and blockchain based medical data processing method of claim 6, wherein: in S3, when γ= (1), i.e. in case of a significant change detected, the blockchain network will share emergency notification by blockchain, as well as the raw data that needs further investigation; in the case of γ= (2), i.e. in the case of a slight or no change detected, the blockchain network will only share the obtained characteristics.

8. A medical data processing system based on edge computing and blockchain, characterized by: use of the edge computing and blockchain based medical data processing method of any of claims 1-7.

9. The edge computing and blockchain based medical data processing system of claim 8, wherein: the edge computing and blockchain based medical data processing system includes a local network and a blockchain network, wherein the local network includes: the system comprises Internet of things equipment connected to the patient, professional public health institutions, hospitals, basic medical health institutions, other medical health institutions and Internet of things equipment connected to the patient in a local network.

10. The edge computing and blockchain based medical data processing system of claim 9, wherein: the blockchain network includes: a data transmitter, a blockchain manager, a verifier, and a multi-channel blockchain, the multi-channel blockchain including a first channel, a second channel, and a third channel, wherein the first channel is for urgent data, and the second channel is for data that is not urgent but requires a high level of security; the third channel is normal data;

defining alpha as the threshold for evaluating the main change, defining a gamma as the final result state,

wherein ,[α]⁺ ＝max(0,α)，‖p‖ ₀ And (2) indicating 0 norm, wherein beta is the index quantification, when gamma= (1), namely, in the case of detecting a major change, the data can travel through a first channel, when gamma= (2), namely, in the case of detecting a slight or no change, if the data is data with high security level, the data can travel through a second channel, and otherwise, the data can travel through a third channel.

Images