CN116543909A - Medical monitoring system, method, device and storage medium - Google Patents

Abstract

The invention relates to a medical monitoring system, a method, a device and a storage medium. The medical monitoring system comprises a processing module, a transmission module and a monitoring module, wherein: the processing module is used for clustering the detection nodes according to the received node information of the detection nodes, determining cluster head nodes in the detection nodes, and forwarding medical data detected by the detection nodes to the transmission module based on the cluster head nodes; the transmission module is used for transmitting the received medical data to the monitoring module through a wireless communication network; the monitoring module is used for inputting the medical data into the neural network model to obtain detection results of the medical data, and feeding back the detection results to the corresponding detection nodes. The system provided by the invention can monitor the health condition of the user in real time and feed the health condition back to related personnel, thereby ensuring the safety of the user to the maximum extent.

Description

Medical monitoring system, method, device and storage medium

technical field

The invention relates to the technical field of disease monitoring, in particular to a medical monitoring system, method, equipment and storage medium.

Background technique

Cardiovascular disease is a sudden disease with extremely high disability and mortality rates, which hinders the development of my country's public medical and health services and seriously threatens the health of users. Therefore, there is an urgent need to provide a medical monitoring system, so as to be able to monitor the user's health status in real time, detect the disease in time and give an alarm.

Contents of the invention

In order to solve the above technical problems, the present invention provides a medical monitoring system, method, equipment and storage medium, which can monitor the health status of users in real time and feed back to relevant personnel, so as to ensure the safety of users to the greatest extent.

In the first aspect, an embodiment of the present invention provides a medical monitoring system, the medical monitoring system includes a processing module, a transmission module and a monitoring module, wherein:

The processing module is configured to cluster the detection nodes according to the received node information of the detection nodes, determine a cluster head node among the detection nodes, and cluster the detection nodes based on the cluster head node The detected medical data is forwarded to the transmission module;

The transmission module is used to transmit the received medical data to the monitoring module through the wireless communication network;

The monitoring module is used to input the medical data into the neural network model, obtain the detection results of the medical data, and feed back the detection results to the corresponding detection nodes.

In a second aspect, an embodiment of the present invention provides a medical monitoring method, which is applied to the above-mentioned medical monitoring system, and the method includes:

Clustering the detection nodes according to the received node information of the detection nodes, determining a cluster head node among the detection nodes, and forwarding the medical data detected by the detection nodes based on the cluster head node to the transmission module;

Transmitting the received medical data to the monitoring module through the wireless communication network;

Input the medical data into the neural network model to obtain the detection results of the medical data, and feed back the detection results to the corresponding detection nodes.

In a third aspect, an embodiment of the present invention provides an electronic device, including:

memory;

processor; and

Computer program;

Wherein, the computer program is stored in the memory and is configured to be executed by the processor to implement the medical monitoring method.

In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the medical monitoring method are implemented.

An embodiment of the present invention provides a medical monitoring system including a processing module, a transmission module, and a monitoring module, wherein: the processing module is used to cluster the detection nodes according to the received node information of each detection node, and in the Determine the cluster head node among the detection nodes, and forward the medical data detected by the detection nodes to the transmission module based on the cluster head node; the transmission module is used to transmit the received medical data through wireless The communication network is transmitted to the monitoring module; the monitoring module is used to input the medical data into the neural network model, obtain the detection results of the medical data, and feed back the detection results to the corresponding detection nodes. The system provided by the invention can monitor the user's health status in real time, and feed back to relevant personnel, so as to ensure the safety of the user to the greatest extent.

Description of drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description serve to explain the principles of the invention.

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, In other words, other drawings can also be obtained from these drawings without paying creative labor.

Fig. 1 is a schematic structural diagram of a medical monitoring system provided by an embodiment of the present invention;

FIG. 2 is a schematic diagram of a scene of a medical monitoring system provided by an embodiment of the present invention;

FIG. 3 is a schematic diagram of a detection node provided by an embodiment of the present invention;

FIG. 4 is a schematic flow diagram of a medical monitoring method provided by an embodiment of the present invention;

FIG. 5 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention.

Detailed ways

In order to understand the above-mentioned purpose, features and advantages of the present invention more clearly, the solutions of the present invention will be further described below. It should be noted that, in the case of no conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other.

In the following description, many specific details have been set forth in order to fully understand the present invention, but the present invention can also be implemented in other ways different from those described here; obviously, the embodiments in the description are only some embodiments of the present invention, and Not all examples.

With the development of computer technology and modern communication technology, it brings new opportunities for remote medical monitoring services. Telemedicine monitoring service is to transmit remote physiological signals and medical signals to the medical monitoring center and analyze them through the application of computer technology and modern communication, so as to realize the remote transmission and monitoring of medical information between individuals and hospitals, hospitals and hospitals, Remote consultation, medical emergency, distance education and communication.

The portable cardiovascular disease medical monitoring system based on the wireless sensor network is a modern telemedicine monitoring system, which uses medical sensors as the medical data acquisition interface to collect patients' diastolic blood pressure, systolic blood pressure, blood sugar, cholesterol, etc. factor. Using wireless communication technology, the collected medical data is transmitted to the gateway, and then transmitted to the remote monitoring center. Doctors analyze and diagnose the collected medical data in the remote monitoring center, thereby realizing remote monitoring and telemedicine.

Telemedicine is a new model for the normalization of epidemic prevention and control and the construction of urban and rural medical institutions in the post-epidemic era. The telemedicine monitoring system based on wireless sensor networks gives patients greater freedom of movement, and each patient can stay at home without leaving home. You can get the supervision of the hospital monitoring center anytime and anywhere. It not only solves the problem of personnel flow and gathering, but also meets the needs of patients for real-time monitoring.

However, the monitoring environment of the medical monitoring system is complex, and there will be a large number of medical sensors that need to perform telemedicine, resulting in the imbalance of energy consumption of each medical sensor node, which in turn leads to obvious differences in energy consumption in each area where the medical sensor is located, seriously affecting each medical system. The transmission efficiency of the sensor.

In view of the above technical problems, an embodiment of the present invention provides a medical monitoring system, which is mainly divided into a processing module, a transmission module and a monitoring module. The processing module can also be regarded as the sensor node layer, which is composed of a large number of medical sensors (such as the user's portable wireless sensor), and the medical sensors are used to measure the user's diastolic blood pressure, systolic blood pressure, blood sugar, cholesterol and other medical data that affect cardiovascular diseases. The sensor node layer is used to detect, receive and process medical data. After the cluster head node is determined in each medical sensor, the acquired user data (medical data) is uploaded to the monitoring module through the wireless communication network of the transmission module. The monitoring module according to The medical data determines whether the user has a sudden cardiovascular disease. If the system detects that the patient has an emergency, it will trigger an emergency alarm function, and notify the patient's family and emergency center, and send it to the hospital for treatment in time. Specifically, the following one or more embodiments are described in detail.

FIG. 1 is a schematic structural diagram of a medical monitoring system provided by an embodiment of the present invention. The medical monitoring system 100 includes a processing module 110, a transmission module 120 and a monitoring module 130, wherein:

The processing module 110 is configured to cluster the detection nodes according to the received node information of the detection nodes, determine a cluster head node among the detection nodes, and cluster the detection nodes based on the cluster head node. The medical data detected by the node is forwarded to the transmission module.

Wherein, the processing module is connected to at least one first base station, the first base station is connected to a plurality of detection nodes, and the first base station is configured to receive node information of the plurality of detection nodes.

Understandably, the processing module can be regarded as a sensor node layer. Considering the complexity of the monitoring environment, the sensor node layer is usually composed of a large number of detection nodes. The detection nodes and the first base station constitute the basis of the entire medical monitoring system, that is, the processing The module communicates with a large number of detection nodes through the first base station, for example, the processing module communicates with 5 first base stations, and each first base station communicates with 50 detection nodes. Among them, the detection node can also be understood as a heterogeneous node. The detection node can be a medical sensor. The medical sensor can be a small portable detection device configured by the patient at home according to his own needs, and has an abnormal or dangerous situation alarm function. The detection device It can detect the patient's medical data. The medical data mainly include body temperature, pulse, heart rate, blood oxygen saturation, blood pressure (diastolic blood pressure, systolic blood pressure), blood sugar, cholesterol, etc. After the first base station receives the node information of all the detection nodes within the range, it clusters the detection nodes through the IAP (Improved Affinity propagation) clustering algorithm, and divides all the detection nodes into different clusters. After the clustering of all the detection nodes is completed, for each According to the adaptive cluster head round robin (ACRR) method, a cluster head node is elected among multiple detection nodes in the cluster, and the cluster head node organizes, fuses and forwards the medical data sent by each detection node in the cluster to the transfer module.

The transmission module 120 is used to transmit the received medical data to the monitoring module through the wireless communication network.

Wherein, the transmission module 120 includes a second base station and a system gateway, the second base station is used to receive the medical data forwarded by the corresponding cluster head node in the processing module through bus communication, and the system gateway is used to Protocol conversion is performed on each of the above medical data, and it is packaged into a preset data format and transmitted to the monitoring module through a wireless communication network.

Understandably, corresponding to the sensor node layer, the transmission module can be regarded as a data transmission layer, and the transmission module includes a second base station and a system gateway, that is, the data transmission layer includes a community base station node layer and a system gateway layer, and the second base station It can be regarded as a community base station. The workload of the second base station is relatively large. It needs to receive data from each cluster head node and communicate with the external network. Therefore, the second base station adopts a field bus communication method with strong anti-interference ability and long communication distance. The specific work of the second base station includes: protocol conversion, communication with external networks, sending user instructions, and data fusion. As the core of the medical monitoring system, the second base station uses power supply to ensure its long-term operation. The system gateway mainly realizes the exchange of information between the body area network and the monitoring module. After receiving the medical data transmitted by the second base station, the system gateway performs protocol conversion on the medical data, and then attaches the current time to it, and encapsulates it into the data format of the application layer. , to the monitoring module, and the system gateway also receives warnings from the monitoring module. The system gateway is a bridge for the user to interact with the medical monitoring system. Users can operate the wireless sensor network through this bridge, so in fact the system gateway It can be regarded as the human-machine interface of the medical monitoring system.

The monitoring module 130 is used to input the medical data into the neural network model, obtain the detection results of the medical data, and feed back the detection results to the corresponding detection nodes.

Understandably, corresponding to the above data transmission layer, the monitoring module can be regarded as the monitoring management layer. The functions of the monitoring module include: storing the medical data transmitted by the wireless communication network into the medical big data platform, and simultaneously storing the medical data transmitted by the wireless communication network. The acquired medical data is input into the pre-trained cardiovascular and cerebrovascular neural network model based on the back propagation neural network (Back Propagation Neural Network, BP), and the current health status of the user is diagnosed and the detection results are obtained. The neural network model can be understood as two Classification model, that is, whether a sudden cardiovascular disease occurs. If the detection result is a sudden vascular disease, the user and the emergency center will be notified, and the user will be sent to the hospital for treatment in time. If the detection result is not a sudden vascular disease, continue to monitor.

For example, refer to FIG. 2. FIG. 2 is a schematic diagram of a scene of a medical monitoring system provided by an embodiment of the present invention. FIG. 2 includes a processing module, a transmission module and a monitoring module. As shown in FIG. 2, the processing module includes a plurality of first A base station, each first base station includes multiple retrieval nodes, multiple users using different detection nodes may live in different residential buildings, a possible scenario, in all retrieval nodes within the range of each first base station After at least one cluster head node is elected, each cluster head node within the range of the first base station will directly receive the medical data sent by other member nodes. The member nodes do not need to send medical data to the first base station, and the cluster head node directly forwarded to the second base station, or directly sent by the cluster head node to the first base station, and then forwarded to the second base station by the first base station. The transmission module includes a plurality of second base stations and a system gateway. The plurality of second base stations communicate with the monitoring module through the system gateway. Each first base station has a one-to-one correspondence with the second base station. In a feasible scenario, the processing module only includes Multiple search nodes, excluding the first base station, multiple search nodes communicate directly with the second base station, another possible scenario, for each second base station, at least one is elected from all search nodes within the range of the second base station After the cluster head node, each cluster head node within the scope of the second base station will directly receive the medical data sent by other member nodes, and the cluster head node will directly forward it to the second base station, that is, each cluster head node has a corresponding the second base station. The monitoring module includes a medical big data platform, a neural network model and an online doctor. After the system gateway stores the medical data into the medical big data platform, it inputs the medical data into the neural network model for diagnosis, obtains the test results of the medical data, and sends the test results to Give it to your doctor for review and testing.

It is understandable that the bottom layer of the portable cardiovascular disease telemedicine monitoring system is composed of wireless sensors (detection nodes), and the detection nodes obtain medical data of users' diastolic blood pressure, systolic blood pressure, blood sugar, cholesterol and other factors that affect cardiovascular diseases. The medical data obtained by the detection node is detected by the user, and uploaded and authorized to the medical monitoring system for telemedicine. Specifically, the calculation sub-module clusters the detection nodes within the range of each first base station through the IAP clustering algorithm, and selects a cluster head node from all detection nodes within the range to forward the collected medical information, which is beneficial to Reduce node energy consumption and prolong the life of wireless sensor network. The most critical core issues in the working process of the clustering routing protocol are how to reasonably elect cluster-head nodes, how to quickly and effectively build a clustering structure, how to save energy and prolong the network life cycle. The data subject randomization algorithm (Energy Efficient Multi-hop Routing, EEMR) of the class is used to solve the problem of uneven distribution of node energy in each detection node, which leads to network instability. At the same time, an adaptive cluster head round robin method is used to select A suitable cluster head node.

Optionally, the processing module 110 includes a computing submodule and a forwarding submodule.

Wherein, the calculation submodule is used to calculate the first distance between the plurality of detection nodes according to the node information, and cluster the plurality of detection nodes according to the first distance to obtain at least one clustering area , and select the target detection node as the cluster head node among the multiple detection nodes included in the clustering area, and at the same time select the remaining detection nodes except the target detection node among the multiple detection nodes included in the clustering area node as a member node.

Understandably, after the calculation submodule acquires the node information of each detection node, it calculates the first distance between any two detection nodes among the plurality of detection nodes according to the node information of each detection node. Subsequently, the calculation sub-module performs clustering according to the first distance between multiple detection nodes, and divides multiple detection nodes into different clustering areas, which can be understood as clusters or clusters. The following embodiments include processing modules Multiple first base stations are taken as an example for illustration, each first base station is divided into multiple clustering areas, and each clustering area includes multiple detection nodes. After the division of the clustering area is completed, for each clustering area, a target detection node is selected from the multiple detection nodes included in the clustering area, and the target detection node is used as the cluster head node in the clustering area , the number of cluster head nodes included in each clustering area can be determined according to user requirements, for example, another cluster head node can be elected as a candidate node. After the calculation sub-module determines the cluster head node of the cluster area, other detection nodes except the target detection node in the multiple detection nodes included in the cluster area are used as member nodes, thus, the cluster area includes multiple member nodes and a cluster head node.

Understandably, within the monitoring range of the medical monitoring system, different patients in different communities in the city use miniature wireless medical sensors to detect their diastolic blood pressure, systolic blood pressure, blood sugar, cholesterol and other medical data that affect cardiovascular disease factors. Different communities It can be regarded as a first base station. All the medical sensor nodes (detection nodes) in the community, as member nodes, pass the collected data to the cluster head node after multi-hop routing through the self-organizing network, and the cluster head node performs fusion processing on the data and forwards it to the second base station. Due to the stability requirements of the telemedicine wireless sensor network, the medical sensor nodes in the network form a cluster (clustering area) according to certain rules. The cluster includes a cluster head node and multiple member nodes, and data transmission is performed between the clusters through base station nodes. Communication, in which the clustering protocol clusters the medical sensor nodes of users in each community according to certain rules, and selects the cluster head node of each cluster for data transmission, and the medical sensor nodes reach the cluster head after multi-hop routing The node communicates with the base station node through the cluster head node, which is beneficial to reduce the energy loss of the node. In addition, due to the overall flexibility of the cluster routing protocol network, the size of the routing table is reduced to a certain extent, energy consumption is saved, and the life cycle of the network is extended.

For example, refer to FIG. 3 . FIG. 3 is a schematic diagram of a detection node provided by an embodiment of the present invention. The community monitoring range shown in FIG. After the detection nodes are clustered by IAP, they are divided into multiple clustering areas (clusters). The clustering area is the area formed by the dotted circle in Figure 3, and then the cluster head node is elected in each clustering area to complete the election Finally, each clustering area includes a cluster head node and multiple member nodes. The cluster head node is represented by a circle filled with a black background, and the member nodes are represented by a circle filled with a white background. Each member node will detect The medical data is transmitted to the cluster head node, and then each cluster head node directly performs data transmission with the corresponding second base station in the transmission module, and sends the medical data detected by each member node to the second base station.

Wherein, the node information includes average energy, remaining energy, position information and initial energy.

Wherein, the calculation submodule is used to calculate the second distance between the plurality of detection nodes according to the position information, calculate the first energy of the detection nodes according to the average energy and the remaining energy, and calculate the first energy of the detection nodes according to the The second distance and the first energy are calculated to obtain the first distance.

Understandably, in order to further solve the problem of unbalanced node energy consumption in the clustering data collection algorithm, the calculation sub-module uses distance and energy factors as the cluster head election strategy, that is, the data subject randomization algorithm based on neighbor dynamic clustering (EEMR ) as a cluster head election strategy, the clustering method in this algorithm is an improved affinity propagation (IAP) algorithm. Specifically, the calculation sub-module calculates the second distance between any two detection nodes according to the position information. Taking one of the above-mentioned arbitrary two detection nodes as an example, the detection node is calculated according to the average energy and residual energy of the detection node The first energy of the second distance, the product of the first energy and the preset adjustment factor is calculated to obtain the first distance of the detection node, wherein the adjustment factor can specifically be the adjustment factor of the number of cluster heads, and the adjustment factor of other detection nodes The first distance can be calculated by the same method, which will not be repeated here. After the first distance of each detection node is obtained, clustering is performed based on the first distance of each detection node, and all detection nodes in the community are divided into different clustering regions. Specifically, the calculation formula of the second distance is shown in formula (1), and the calculation formula of the first distance is shown in formula (2).

Formula 1)

In the formula, dist(i, j) represents the second distance between detection node i and detection node j, which can be understood as the distance between detection nodes is close to the "intimacy", Indicates the location information of the detection node i, /> Indicates the location information of the detection node j.

Formula (2)

In the formula, Indicates the first distance between detection node i and detection node j, /> Indicates the average energy of all detection nodes in the processing module at the beginning of operation, /> Indicates the remaining energy of the detection node j, and the remaining energy refers to the remaining energy level of the detection node j after performing the task, /> Indicates the first energy of the detection node j, the first energy refers to the "intimacy" of energy attraction between detection nodes, and β represents the adjustment factor of the number of cluster heads.

Among them, after the calculation sub-module completes the clustering area division, it is also used to elect the cluster head node in each clustering area, where:

For each detection node, calculate the ratio of the residual energy to the initial energy to obtain the absolute energy ratio of the detection node; determine the sum of the residual energy of multiple detection nodes included in the clustering area, and calculate the residual energy The ratio of the energy to the sum value is used to obtain the relative energy ratio of the detection node; the relative distance ratio of the detection node is calculated according to the position information and the position information of the first base station corresponding to the clustering area; and the relative distance ratio of the detection node is determined; The first number of detection nodes included in the clustering area, and calculating the ratio of the number of nodes that do not continuously serve as cluster head nodes in the clustering area to the first number to obtain a relative node ratio; according to the absolute energy ratio, the The relative energy ratio, the relative distance ratio and the relative node ratio are calculated to obtain the cluster head ratio of the detection node; according to the cluster head ratio, the target detection is selected from a plurality of detection nodes included in the clustering area node as the cluster head node.

Understandably, in the EEMR algorithm, after the first base station receives the node information of all detection nodes, the calculation submodule runs the IAP clustering algorithm for network clustering. In addition, the EEMR algorithm proposes the ACRR (Adaptive cluster -headRound Robin) method It is used for local dynamic election of cluster heads, where ACRR is a cluster head polling strategy based on node adaptability, and the relevant formulas of the cluster head node election strategy are shown in the following formulas (3) to (7):

Formula (3)

Formula (4)

Formula (5)

Formula (6)

Formula (7)

In the formula, H(j) represents the cluster head ratio of detection node j, H ₁ represents the absolute energy ratio (absolute proportion) of detection node j, Indicates the remaining energy of the detection node j, that is, the remaining energy of the detection node j after the r-th round of medical data collection, E ₀ represents the initial energy of the detection node j, that is, the energy of the initial configuration of the detection node j, H ₂ represents the detection Relative energy ratio (relative proportion) of node j, /> Indicates the sum of the remaining energies of multiple detection nodes included in the clustering area to which detection node j belongs, _that is, the energy of the cluster to which detection node j belongs. The relative distance ratio of the distance between a base station, dist(i, sink) indicates the distance between the detection node j and the first base station, /> Indicates the farthest distance from the first base station in the cluster to which the detection node j belongs, H ₄ represents the relative node ratio, that is, the ratio of the nodes that the detection node j does not serve as the cluster head continuously in the cluster to which the detection node j belongs, once the detection node j acts as the cluster head _rm is set to 0.

Wherein, the clustering area includes the cluster head node and multiple member nodes.

Wherein, the calculation sub-module is used for:

For each member node, calculate the member node according to the remaining energy of the cluster head node, the initial energy of the cluster head node, the distance from the member node to the cluster head node, and the preset data transmission deflection angle The node capability; according to the node capability, determine the target member node among the plurality of member nodes as a relay node, and the relay node is used to forward the medical data detected by the member node to the cluster head node .

It is understandable that the core of the EEMR algorithm is to avoid the control energy consumption caused by frequent clustering, so the calculation sub-module adopts a hierarchical multi-hop data forwarding strategy based on the detection node capability, that is, after determining the cluster head node, according to each member node The node capability selects the relay node among them. The relay node can be understood as a forwarding node, which is used to forward the medical data of other member nodes to the cluster head node, that is, the relay node for data multi-hop transmission is composed of member nodes If the capability is determined, for example, a member node with a higher capability can be used as a relay node to undertake the jumping task of other member nodes. For example, as shown in Figure 3, the cluster head node 310, the relay node 320 and a plurality of detection nodes are included in the clustering area 300, and the detection node 330 in the plurality of detection nodes transmits the medical data to the relay node 320, and then the The relay node 320 transmits the medical data to the cluster head node 310, that is, the transmission direction shown by the arrow in FIG. The node energy consumption caused by frequent clustering can further reduce the energy consumption of member nodes when jumping. The calculation method of node capability is shown in formula (8):

Formula (8)

In the formula, f(j) represents the node capability of the detection node j, Represents the remaining energy of the cluster head node s, E _init represents the initial energy of the cluster head node s, dist(j, s) represents the distance between the cluster head node s and the detection node j, R _h is the communication radius, θ is the data transmission The deflection angle, λ _i (j=1,2) represents the weight coefficient of each competency factor.

Wherein, the forwarding submodule is configured to forward the medical data detected by the member nodes to the transmission module after fusion processing based on the cluster head node.

Understandably, the forwarding sub-module in the processing module is applied to the medical data received by the cluster head node and detected by the member nodes in the same clustering area as the cluster head node, and the cluster head node will perform fusion processing on each medical data, and then Send the fused medical data to the corresponding second base station.

Wherein, the monitoring module includes a training submodule, and the training submodule is used to train the constructed neural network to obtain the neural network model.

Wherein, the training sub-module is specifically used for:

Inputting the obtained learning samples into the neural network to obtain prediction results; calculating gradient squares based on the learning samples and the prediction results, and calculating the mean value according to the gradient squares and first preset parameters, and calculating the mean value according to the gradient square sums Calculate the variance of the second preset parameter; calculate the parameter difference according to the preset learning rate, the mean value and the variance, and train the neural network according to the parameter difference to obtain the neural network model.

Specifically, cardiovascular disease is a chronic disease with a high disability rate and mortality rate, which has hindered the development of my country's public medical and health services. Nowadays, most research focuses on the treatment of diseases, while ignoring the work on disease prevention . In addition, with the rapid development of big data analysis, machine learning methods can obtain higher accuracy when processing complex data. Therefore, the medical monitoring system conducts cardiovascular disease prediction research on the basis of machine learning, from age, gender, Systolic blood pressure, diastolic blood pressure, height, weight, smoking, exercise, alcohol consumption, cholesterol, and blood sugar, which are 11 factors that affect cardiovascular diseases, can predict cardiovascular diseases and help doctors make judgments on whether users have cardiovascular diseases , can provide effective auxiliary decision-making support for doctors in medical data processing, and realize real-time and effective monitoring of users' health status.

Understandably, the monitoring module includes a training sub-module and a prediction module, the training sub-module is used to train the constructed neural network based on the above 11 factors to obtain a neural network model, and the prediction module is used to use the trained neural network model based on medical data Diagnose the user's health status. Specifically, in order to increase the speed of neural network training and improve the accuracy of training results, the training sub-module uses the BP neural network of the optimal gradient adaptive optimization algorithm as the deep learning system, and the BP neural network is a back propagation neural network (Back Propagation The abbreviation of Neural Network), the front part of the BP neural network is an input layer, the middle contains several hidden layers, and the rear part is an output layer. The full connection method is used between each layer. If the neurons are in the same layer, then There is no connection between them, and the neurons of each layer can only output activation signals to the neurons of the next layer, and reversely transmit the correction error to the upper layer.

Understandably, the training sub-module first initializes the BP neural network, then inputs the learning samples into the BP neural network, and calculates the input and output of each layer of neurons. Preferably, the BP neural network input layer node is 11, and the output layer node is 2. Then calculate the output error according to the prediction results of the learning samples and network output, perform backpropagation according to the output error, re-update the weight of the BP neural network, and finally calculate the global error, and judge whether to stop learning according to the accuracy requirements. If the accuracy is met, Obtain the trained neural network model.

It is understandable that the choice of learning rate is crucial to the accuracy of the neural network. A higher learning rate will lead to larger errors or irregular dispersion of the network, and a too low learning rate will reduce the efficiency of network training. Compared with the fixed learning rate, the training sub-module chooses Adam as the optimization algorithm to realize the adaptive adjustment of the learning rate, and adopts a new adaptive algorithm TAdam to solve the problem that the accuracy of the model decreases due to the excessive adjustment of the learning rate by Adam.

It is understandable that the medical monitoring system needs extremely high accuracy to predict the health status of the user. The concept of adaptive friction coefficient is introduced into the Adam algorithm to obtain a new adaptive algorithm called TAdam algorithm. Among them, the TAdam algorithm The update rules are shown in formula (9) to formula (12):

Formula (9)

Formula (10)

Formula (11)

Formula (12)

In the formula, Represents the gradient square, m _t represents the mean value, v _t represents the variance, β ₁ represents the first preset parameter, β ₂ represents the second preset parameter, β ₁ and β ₂ are specifically the exponential decay coefficient, and △θ _t represents the parameter difference value, η is the learning rate, generally set to 0.001, and θ _t is the model parameter.

It is understandable that the main update point of the TAdam algorithm lies in the update rule of the second-order momentum of the gradient. The difference between v _t and v _t-1 in the TAdam algorithm only depends on , when v _t-1 is much larger than /> , the TAdam algorithm will increase the effective learning rate in a more gradual manner, and the convergence speed and accuracy of the model can be significantly improved by controlling the growth rate of the learning rate.

It is understandable that the monitoring module takes the prevalence of cardiovascular disease as the dependent variable, conducts detailed descriptive statistical analysis on whether the user has cardiovascular disease, builds a BP neural network model for cardiovascular and cerebrovascular diseases, and establishes a neural network model for In-depth statistical analysis of cardiovascular diseases and prediction of cardiovascular diseases to achieve real-time monitoring.

The embodiment of the present invention provides a medical monitoring system, including a processing module, a transmission module and a monitoring module. Whether the user has a sudden vascular disease, so that the patient can be sent to the hospital for treatment in time. The processing module also includes a calculation sub-module. The calculation sub-module can solve the problem of obvious differences in energy consumption in different communities when the detection nodes are published by clustering and clustering each detection node. At the same time, after all the clusters are formed, all The cluster independently and distributedly executes the adaptive cluster head round-robin mechanism to update the cluster head dynamically. While increasing the transmission rate, it reduces the energy consumption of nodes and prolongs the life of the wireless sensor network.

On the basis of the above-mentioned embodiments, FIG. 4 is a schematic flowchart of a medical monitoring method provided by an embodiment of the present invention, which is applied to the above-mentioned medical monitoring system, and specifically includes the following steps S410 to S430 as shown in FIG. 4:

S410. Cluster the detection nodes according to the received node information of the detection nodes, determine a cluster head node among the detection nodes, and classify the medical values detected by the detection nodes based on the cluster head node The data is forwarded to the transmission module.

S420. Transmit the received medical data to the monitoring module through the wireless communication network.

S430. Input the medical data into the neural network model to obtain detection results of the medical data, and feed back the detection results to corresponding detection nodes.

It can be understood that, for the implementation manners of the foregoing S410 to S430, refer to the foregoing embodiments, and details are not described here.

Optionally, clustering the detection nodes according to the received node information of the detection nodes, and determining a cluster head node among the detection nodes includes:

Calculate a first distance between the plurality of detection nodes according to the node information, cluster the plurality of detection nodes according to the first distance, obtain at least one cluster area, and include in the cluster area The target detection node is selected as the cluster head node from the plurality of detection nodes, and the remaining detection nodes except the target detection node among the plurality of detection nodes included in the clustering area are regarded as member nodes.

Optionally, forwarding the medical data detected by the detection nodes to the transmission module based on the cluster head node includes:

Based on the cluster head node, the medical data detected by the member nodes are fused and then forwarded to the transmission module.

Optionally, the node information includes average energy, remaining energy and location information.

Optionally, calculating the first distance between the plurality of detection nodes according to the node information includes:

Calculate the second distance between the plurality of detection nodes according to the position information, calculate the first energy of the detection node according to the average energy and the remaining energy, and calculate the first energy of the detection node according to the second distance and the first The energy is calculated to obtain the first distance.

Optionally, the node information also includes initial energy.

Optionally, electing a target detection node as a cluster head node from among multiple detection nodes included in the clustering area, including:

For each detection node, calculate the ratio of the residual energy to the initial energy to obtain the absolute energy ratio of the detection node; determine the sum of the residual energy of multiple detection nodes included in the clustering area, and calculate the residual energy The ratio of the energy to the sum value is used to obtain the relative energy ratio of the detection node; the relative distance ratio of the detection node is calculated according to the position information and the position information of the first base station corresponding to the clustering area; and the relative distance ratio of the detection node is determined; The first number of detection nodes included in the clustering area, and calculating the ratio of the number of nodes that do not continuously serve as cluster head nodes in the clustering area to the first number to obtain a relative node ratio; according to the absolute energy ratio, the The relative energy ratio, the relative distance ratio and the relative node ratio are calculated to obtain the cluster head ratio of the detection node; according to the cluster head ratio, the target detection is selected from a plurality of detection nodes included in the clustering area node as the cluster head node.

Optionally, the clustering area includes the cluster head node and multiple member nodes, and after the cluster head node and member nodes are determined, the method further includes:

For each member node, calculate the member node according to the remaining energy of the cluster head node, the initial energy of the cluster head node, the distance from the member node to the cluster head node, and the preset data transmission deflection angle The node capability; according to the node capability, determine the target member node among the plurality of member nodes as a relay node, and the relay node is used to forward the medical data detected by the member node to the cluster head node .

Optionally, the training process of the neural network model in S430 is as follows:

Inputting the obtained learning samples into the neural network to obtain prediction results; calculating gradient squares based on the learning samples and the prediction results, and calculating the mean value according to the gradient squares and first preset parameters, and calculating the mean value according to the gradient square sums Calculate the variance of the second preset parameter; calculate the parameter difference according to the preset learning rate, the mean value and the variance, and train the neural network according to the parameter difference to obtain the neural network model.

It can be understood that, for the specific implementation steps of the above medical monitoring method, refer to the above embodiments, and details are not repeated here.

The medical monitoring method provided by the embodiment of the present invention can quickly and accurately diagnose the user's health status. If the diagnosis result is a sudden vascular disease, the patient's family and emergency center will be notified, and the patient will be sent to the hospital for treatment in time.

FIG. 5 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. Referring to FIG. 5 in detail below, it shows a schematic structural diagram of an electronic device 500 suitable for implementing an embodiment of the present invention. The electronic device 500 in the embodiment of the present invention may include but not limited to such as mobile phone, notebook computer, digital broadcast receiver, PDA (personal digital assistant), PAD (tablet computer), PMP (portable multimedia player), vehicle terminal ( Mobile terminals such as car navigation terminals), wearable electronic devices, etc., and fixed terminals such as digital TVs, desktop computers, smart home devices, etc. The electronic device shown in FIG. 5 is only an example, and should not limit the functions and scope of use of this embodiment of the present invention.

As shown in FIG. 5 , an electronic device 500 may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 501 that can be randomly accessed according to a program stored in a read-only memory (ROM) 502 or loaded from a storage device 508 The program in the memory (RAM) 503 executes various appropriate actions and processes to realize the medical monitoring method according to the embodiment of the present invention. In the RAM 503, various programs and data necessary for the operation of the electronic device 500 are also stored. The processing device 501 , ROM 502 and RAM 503 are connected to each other through a bus 504 . An input/output (I/O) interface 505 is also connected to the bus 504 .

Typically, the following devices can be connected to the I/O interface 505: input devices 506 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; including, for example, a liquid crystal display (LCD), speaker, vibration an output device 507 such as a computer; a storage device 508 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 509. The communication means 509 may allow the electronic device 500 to perform wireless or wired communication with other devices to exchange data. While FIG. 5 shows electronic device 500 having various means, it is to be understood that implementing or having all of the means shown is not a requirement. More or fewer means may alternatively be implemented or provided.

In particular, according to an embodiment of the present invention, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, the embodiments of the present invention include a computer program product, which includes a computer program carried on a non-transitory computer readable medium, and the computer program includes program code for executing the method shown in the flow chart, thereby realizing the above The medical monitoring method described. In such an embodiment, the computer program may be downloaded and installed from a network via communication means 509 , or from storage means 508 , or from ROM 502 . When the computer program is executed by the processing device 501, the above-mentioned functions defined in the method of the embodiment of the present invention are performed.

It should be noted that the computer-readable medium mentioned above in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable Programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present invention, however, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program codes therein. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can transmit, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device . Program code embodied on a computer readable medium may be transmitted by any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

In some embodiments, the client and the server can communicate using any currently known or future-developed network protocols such as HTTP (HyperText Transfer Protocol), and can communicate with digital data in any form or medium (eg, communication network) interconnections. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), internetworks (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network of.

The above-mentioned computer-readable medium may be included in the above-mentioned electronic device, or may exist independently without being incorporated into the electronic device.

Optionally, when the above one or more programs are executed by the electronic device, the electronic device may also perform other steps described in the above embodiments.

Computer program code for carrying out operations of the present invention may be written in one or more programming languages, or combinations thereof, including but not limited to object-oriented programming languages—such as Java, Smalltalk, C++, and Includes conventional procedural programming languages - such as the "C" language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In cases involving a remote computer, the remote computer can be connected to the user computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (such as through an Internet service provider). Internet connection).

The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, program segment, or portion of code that contains one or more logical functions for implementing specified executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved. It should also be noted that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented by a dedicated hardware-based system that performs the specified functions or operations , or may be implemented by a combination of dedicated hardware and computer instructions.

The units involved in the description in the embodiments of the present invention may be implemented by means of software or by means of hardware. Wherein, the name of a unit does not constitute a limitation of the unit itself under certain circumstances.

The functions described herein above may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), System on Chips (SOCs), Complex Programmable Logical device (CPLD) and so on.

In the context of the present invention, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media would include one or more wire-based electrical connections, portable computer disks, hard disks, Random Access Memory (RAM), Read Only Memory (ROM), Erasable Programmable Read Only Memory (EPROM or flash memory), fiber optics, compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

It should be noted that in this article, relative terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply these No such actual relationship or order exists between entities or operations. Furthermore, the term "comprises", "comprises" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article, or gateway comprising a set of elements includes not only those elements, but also includes elements not expressly listed other elements of, or also include elements inherent to, such a process, method, article, or gateway. Without further limitations, an element defined by the statement "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article or gateway comprising said element.

The above descriptions are only specific embodiments of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be readily 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 invention. Therefore, the present invention will not be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (10)

1. A medical monitoring system, characterized in that, the medical monitoring system includes a processing module, a transmission module and a monitoring module, wherein: The processing module is configured to cluster the detection nodes according to the received node information of the detection nodes, determine a cluster head node among the detection nodes, and cluster the detection nodes based on the cluster head node The detected medical data is forwarded to the transmission module; The transmission module is used to transmit the received medical data to the monitoring module through the wireless communication network; The monitoring module is used to input the medical data into the neural network model, obtain the detection results of the medical data, and feed back the detection results to the corresponding detection nodes. 2. The system according to claim 1, wherein the processing module includes a calculation submodule and a forwarding submodule, wherein the processing module is connected to at least one first base station, and the first base station is connected to a plurality of detection a node, the first base station is configured to receive node information of the plurality of detection nodes; The calculation submodule is configured to calculate a first distance between the plurality of detection nodes according to the node information, cluster the plurality of detection nodes according to the first distance to obtain at least one clustering area, and Select the target detection node as the cluster head node from the plurality of detection nodes included in the clustering area, and at the same time use the rest of the detection nodes except the target detection node in the plurality of detection nodes included in the clustering area as the cluster head node. member node; The forwarding sub-module is configured to fuse the medical data detected by the member nodes based on the cluster head node and then forward to the transmission module. 3. The system according to claim 2, wherein the node information includes average energy, remaining energy and position information, and the calculation submodule is used to calculate the distance between the plurality of detection nodes according to the position information For the second distance, calculate the first energy of the detection node according to the average energy and the remaining energy, and calculate the first distance according to the second distance and the first energy. 4. The system according to claim 3, wherein the node information also includes initial energy, and the calculation submodule is used for: For each detection node, calculate the ratio of the remaining energy to the initial energy to obtain the absolute energy ratio of the detection node; Determining the sum of the residual energies of multiple detection nodes included in the clustering area, and calculating the ratio of the residual energy to the sum to obtain the relative energy ratio of the detection nodes; calculating the relative distance ratio of the detection nodes according to the location information and the location information of the first base station corresponding to the clustering area; Determining a first number of detection nodes included in the clustering area, and calculating a ratio between the number of nodes in the clustering area that do not continuously serve as cluster head nodes and the first number to obtain a relative node ratio; calculating the cluster head ratio of the detection node according to the absolute energy ratio, the relative energy ratio, the relative distance ratio and the relative node ratio; Electing a target detection node as a cluster head node from the plurality of detection nodes included in the clustering area according to the cluster head ratio. 5. The system according to claim 4, wherein the clustering area includes the cluster head node and a plurality of member nodes, and the calculation submodule is used for: For each member node, calculate the member node according to the remaining energy of the cluster head node, the initial energy of the cluster head node, the distance from the member node to the cluster head node, and the preset data transmission deflection angle node capacity; A target member node is determined among the plurality of member nodes according to the node capability as a relay node, and the relay node is configured to forward the medical data detected by the member node to the cluster head node. 6. The system according to claim 1, wherein the transmission module includes a second base station and a system gateway, and the second base station is used to receive the information forwarded by the corresponding cluster head node in the processing module through bus communication. For each medical data, the system gateway is used to perform protocol conversion on the various medical data, and encapsulate it into a preset data format and transmit it to the monitoring module through a wireless communication network. 7. The system according to claim 1, wherein the monitoring module includes a training submodule, and the training submodule is used to train the constructed neural network to obtain the neural network model; The training sub-module is specifically used for: Inputting the obtained learning samples into the neural network to obtain prediction results; Calculate the gradient square based on the learning sample and the prediction result, calculate the mean value according to the gradient square and a first preset parameter, and calculate the variance according to the gradient square and a second preset parameter; The parameter difference is calculated according to the preset learning rate, the mean value and the variance, and the neural network is trained according to the parameter difference to obtain the neural network model. 8. A medical monitoring method, characterized in that being applied to the medical monitoring system according to any one of claims 1-7, said method comprising: Clustering the detection nodes according to the received node information of the detection nodes, determining a cluster head node among the detection nodes, and forwarding the medical data detected by the detection nodes based on the cluster head node to the transmission module; Transmitting the received medical data to the monitoring module through the wireless communication network; Input the medical data into the neural network model to obtain the detection results of the medical data, and feed back the detection results to the corresponding detection nodes. 9. An electronic device, characterized in that it comprises: memory; processor; and Computer program; Wherein, the computer program is stored in the memory and is configured to be executed by the processor to realize the medical monitoring method as claimed in claim 8 . 10. A computer-readable storage medium, on which a computer program is stored, characterized in that, when the computer program is executed by a processor, the steps of the medical monitoring method as claimed in claim 8 are realized.