A community health medical data cockpit and a method for creating the same

Abstract

This invention discloses a community health and medical data dashboard and its creation method. It collects updated medical data from a server and performs two-layer data processing. One layer integrates and displays all medical data and performs feature labeling. The labeled medical data is then integrated into corresponding data display nodes, providing a comprehensive view of the integrated and categorized information, while also classifying personalized medical data. The other layer of data processing performs normalization and reduction preprocessing on the collected data. After feature extraction, a decision algorithm model and optimization iterative formula are used to quantitatively display the trends in the development of medical data over time, clarifying the development direction of the community's medical status.

Description

Technical Field

[0001] This invention relates to the technical field of medical and health data integration, and in particular to a community health and medical data dashboard and its creation method. Background Technology

[0002] With the continuous development of the digital internet, the digital community health strategy has been further developed, comprehensively promoting the entry of medical information into communities and households, and gradually building a digital and intelligent platform for information.

[0003] Building a community health and medical data dashboard refers to comprehensively utilizing technologies such as artificial intelligence, big data, blockchain, cloud computing, and the Internet of Things to construct a community health and medical data infrastructure represented by a community digital operating system.

[0004] Currently, the integration and summarization of community health and medical data mainly focuses on directly incorporating household information into routine data systems. Subsequent statistics still rely heavily on periodic data collection by community personnel. The construction of relevant digital platforms has not yet achieved mature integration. Among existing technologies, there are methods for building rural digital infrastructure, which focus on the overall construction of SaaS platforms, but the specific aspects of smart healthcare have not been further demonstrated. Specifically: 1. While the integration and classification of community information under the support of the Internet of Things platform are comprehensive, personalized classification has not been addressed; 2. The trends in the status of community healthcare have not been quantitatively demonstrated, making it difficult to clarify the development direction of community healthcare. Summary of the Invention

[0005] The purpose of this section is to outline some aspects of embodiments of the present invention and to briefly describe some preferred embodiments. Simplifications or omissions may be made in this section, as well as in the abstract and title of this application, to avoid obscuring the purpose of these documents; however, such simplifications or omissions should not be construed as limiting the scope of the invention.

[0006] In view of the problems existing in the above-mentioned community health and medical data integration systems, this invention is proposed.

[0007] Therefore, the technical problem solved by this invention is to address the issues that existing smart healthcare IoT support platforms have failed to address, namely, the lack of personalized information classification and the failure to quantify trends in community healthcare status, thus hindering a clear understanding of the future direction of community healthcare development.

[0008] To address the aforementioned technical problems, this invention provides the following technical solution: a community health and medical data dashboard, comprising an application for creating an independent interface display, a server for integrating and analyzing data, and a touchscreen display client for operating the application; wherein, the signal input terminal of the application is electrically connected to the signal output terminal of the touchscreen display client, and sends a trigger command during signal transmission; the server receives the trigger command, integrates the data, and displays the integrated data interface in a data display node within the application; wherein, the server specifically includes: a data acquisition and storage module for acquiring and storing updated medical data; a feature classification module connected to the data acquisition and storage module for acquiring updated medical data and performing feature labeling on it; and an integration module connected to the feature classification module for integrating the feature-labeled medical data into the corresponding data display node.

[0009] In a preferred embodiment of the community health and medical data cockpit described in this invention, the touchscreen display client and the application are connected via an integrated ultrasonic directional wireless connection. The touchscreen display client includes a server, an FPGA controller, and an active ultrasonic signal transmitting unit. The application embeds a receiving chip, which in turn embeds a multi-channel synchronous receiving unit. The server is connected to the FPGA controller, the output of which is connected to the active ultrasonic signal transmitting unit, and the input of which is connected to the multi-channel synchronous receiving unit. The active ultrasonic signal transmitting unit includes a D / A converter, a power amplifier, an impedance matching circuit, and a transmitting transducer. The FPGA controller is connected to the transmitting transducer sequentially via the D / A converter, power amplifier, and impedance matching circuit. The multi-channel synchronous receiving unit includes an A / D converter, a preamplifier, an impedance transformer, and a receiving transducer. The receiving transducer is connected to the FPGA controller sequentially via the impedance transformer, preamplifier, and A / D converter. The server and the FPGA controller are directly connected via USB 3.0.

[0010] As a preferred embodiment of the community health and medical data dashboard described in this invention, the acquisition and storage module specifically includes: an acquisition input unit, which acquires medical data after each update and inputs it into a preprocessing unit; a preprocessing unit, which is data-connected to the acquisition input unit, receives the medical data and performs normalization preprocessing; a feature extraction unit, which is data-connected to the preprocessing unit, and extracts features from the preprocessed medical data; a decision display unit, which is data-connected to the feature extraction unit, synchronously constructs a decision algorithm model, substitutes the feature-extracted medical data into the decision algorithm model, and seeks the decision value when the algorithm value is maximized through an optimization iteration formula; and a trend display unit, which is data-connected to the decision display unit, obtains the decision value of the medical data after each update in real time, displays the decision values ​​of each time period in a basic coordinate system, obtains the trend measurement change of the medical data, and defines that the higher the decision value, the higher the optimism of the medical data.

[0011] As a preferred embodiment of the community health and medical data dashboard described in this invention, receiving medical data and performing normalization preprocessing includes: acquiring various medical data under different features; performing reduction preprocessing sequentially based on the selected feature values ​​corresponding to each medical data to acquire the reduced medical data; and performing normalization processing sequentially on the reduced medical data.

[0012] In a preferred embodiment of the community health and medical data dashboard described in this invention, medical data is preprocessed to reduce its size according to the following formula to obtain the reduced medical data.

[0013]

[0014] Where t represents the acquired medical data, t' represents the reduced medical data for each item, and δ represents the selected feature value corresponding to each medical data t.

[0015] In a preferred embodiment of the community health and medical data dashboard described in this invention, the reference quantity for feature extraction when extracting features from the preprocessed medical data is:

[0016]

[0017] Where δ' is the extraction reference value when performing feature extraction, and δ is the selected feature value corresponding to each medical data t.

[0018] As a preferred embodiment of the community health and medical data dashboard described in this invention, the decision algorithm model constructed is specifically as follows:

[0019] Objective function J(y):

[0020] J(y)=[E[g(y}-E{g(y)}) guass )}] 2

[0021] Where J is the decision value output function, y is the output feature extraction value function, E{} is the expectation function, defined as the extraction reference function for different data items, and g() is a nonlinear function, wherein the nonlinear function is g=tanh(1.5y).

[0022] Constraint: E{}∈{0,1}.

[0023] To address the aforementioned technical problems, the present invention also provides the following technical solution: a method for creating a community health and medical data dashboard, comprising the following steps: creating an application with an independent interface, a server for integrating and analyzing data, and a touch screen display client for operating the application; the server receiving a trigger command from the application to complete two-dimensional data layering processing; and displaying the data interfaces after data layering processing in the corresponding data display nodes of the application.

[0024] As a preferred embodiment of the community health and medical data dashboard creation method described in this invention, the server-side data layering process includes: collecting and storing updated medical data; obtaining updated medical data and performing feature labeling on it; and integrating the feature-labeled medical data into the corresponding data display nodes.

[0025] As a preferred embodiment of the community health and medical data dashboard creation method described in this invention, the server-side data layering process includes: collecting medical data after each update and inputting it into a preprocessing unit for normalization preprocessing; extracting features from the preprocessed medical data; constructing a decision algorithm model, substituting the feature-extracted medical data into the decision algorithm model, and seeking the decision value when the algorithm value is maximized through an optimization iterative formula; acquiring the decision value of the medical data after each update in real time, and displaying the decision values ​​for each time period in a basic coordinate system to obtain the trend measurement changes of the medical data.

[0026] The beneficial effects of this invention are as follows: This invention provides a community health and medical data dashboard and its creation method. It collects updated medical data from the server and completes two-dimensional data layering processing. One layer integrates and displays all medical data and performs feature labeling. The labeled medical data is then integrated into the corresponding data display nodes, providing a comprehensive view of the integrated and categorized information, while also classifying personalized medical data. The other layer of data processing performs normalization and reduction preprocessing on the collected data. After feature extraction, a decision algorithm model and optimization iterative formula are used to quantitatively display the trends in the development of medical data over time, clarifying the development direction of the community's medical status. Attached Figure Description

[0027] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein:

[0028] Figure 1 This is a schematic diagram of the server-side module involved in the community health and medical data cockpit provided by the present invention.

[0029] Figure 2 This is a schematic diagram of the structure of the touch screen display client and application wirelessly connected in the community health and medical data cockpit provided by the present invention.

[0030] Figure 3 A schematic diagram of the data acquisition and storage module involved in the community health and medical data cockpit provided by the present invention.

[0031] Figure 4 The flowchart illustrates the method for receiving and normalizing preprocessing medical data in the community health and medical data cockpit provided by this invention.

[0032] Figure 5 A flowchart illustrating the method for creating a community health and medical data dashboard provided by this invention.

[0033] Figure 6 The flowchart illustrates the method for server-side data layering processing with two dimensions provided by this invention.

[0034] Figure 7 This is a flowchart illustrating another method for server-side data layering processing to achieve two-dimensional data layering, as provided by the present invention.

[0035] Figure 8 This is a schematic diagram of the code interface during the database deletion operation of this invention.

[0036] Figure 9 This is one of the schematic diagrams of the sparse coding linear model provided by the present invention. Detailed Implementation

[0037] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0038] Currently, the integration and summarization of community health and medical data mainly focuses on directly incorporating household information into routine data systems. Subsequent statistics still rely heavily on periodic data collection by community personnel. The construction of relevant digital platforms has not yet achieved mature integration. Among existing technologies, there are methods for building rural digital infrastructure, which focus on the overall construction of SaaS platforms, but the specific aspects of smart healthcare have not been further demonstrated. Specifically: 1. While the integration and classification of community information under the support of the Internet of Things platform are comprehensive, personalized classification has not been addressed; 2. The trends in the status of community healthcare have not been quantitatively demonstrated, making it difficult to clarify the development direction of community healthcare.

[0039] Therefore, please refer to Figure 1 The present invention provides a community health and medical data cockpit, including an application for creating an independent interface display, a server for integrating and analyzing data, and a touch screen display client for operating the application;

[0040] The application's signal input terminal is electrically connected to the touch screen display client's signal output terminal, and sends a trigger command during signal transmission. The server receives the trigger command, integrates the data, and displays the integrated data interface in the application's data display node.

[0041] It should be noted that the trigger command sent by the touch screen display client is a conventional signal trigger command, and the data interface displayed in the data display node of the application is also a conventional data display method, which does not need to be elaborated further here.

[0042] Specifically, the server side includes:

[0043] The data acquisition and storage module 100 is used to acquire and store the medical data after each update.

[0044] The feature classification module 200 is connected to the acquisition and storage module 100 to acquire updated medical data and perform feature labeling on it.

[0045] The integration module 300 is connected to the feature classification module 200 to integrate the feature-labeled medical data into the corresponding data display node.

[0046] Integrating the feature-labeled medical data into the corresponding data display nodes is a conventional data display method, which will not be elaborated further here.

[0047] It should be noted that: Please refer to Figure 2 The touchscreen display client and application are connected via an integrated ultrasonic directional wireless connection.

[0048] The touch screen display client includes a server, an FPGA controller, an active ultrasonic signal transmitting unit, a receiving chip embedded in the application, a multi-channel synchronous receiving unit embedded in the receiving chip, a server connected to the FPGA controller, an output of the FPGA controller connected to the active ultrasonic signal transmitting unit, and an input of the FPGA controller connected to the multi-channel synchronous receiving unit.

[0049] The ultrasonic signal active transmission unit includes a D / A converter, a power amplifier, an impedance matching device, and a transmitting transducer. The FPGA controller is connected to the transmitting transducer in sequence via the D / A converter, the power amplifier, and the impedance matching device.

[0050] The multi-channel synchronous receiving unit includes an A / D converter, a preamplifier, an impedance transformer, and a receiving transducer. The receiving transducer is connected to the FPGA controller in sequence via the impedance transformer, the preamplifier, and the A / D converter.

[0051] The server connects directly to the FPGA controller via USB 3.0, an interface that provides 3Gbps of bandwidth.

[0052] The transmitting and receiving transducers are standard configurations for acoustic signal platforms. The server and FPGA controller are commercially available. The D / A converter, power amplifier, impedance matching circuit, impedance transformer, preamplifier, and A / D converter are all conventional electrical components. The specific circuit structures are all existing technologies and will not be described in detail here.

[0053] The server serves as the control center for the touchscreen display client, providing a user-friendly interface. Users can edit transmitted signals, set sampling rates, and initiate transmission and reception through the server. It also offers functions such as time-domain filtering and frequency-domain analysis of transmitted and received waveforms. Waveform editing and other functions are built into the acoustic signal platform. After the system starts operating, the server transmits the preset transmitted signal to the FPGA controller in real time, which then drives the D / A converter to output the signal while simultaneously acquiring the received data from the A / D converter.

[0054] The FPGA controller is the control unit of the entire hardware system. It connects to the server via USB 3.0, and all A / D and D / A data are transferred through the FPGA. Upon receiving the start command from the server, the FPGA controller simultaneously activates both the A / D and D / A units, ensuring synchronous startup. Furthermore, the A / D and D / A units use the same clock source, so they are completely synchronized during operation. The FPGA's system clock operates at 50MHz, thus the synchronization accuracy of each A / D and D / A channel can be controlled within 20ns.

[0055] The power amplifier amplifies the output signal to the required sound source level for the system. The impedance matching circuit is a conventional impedance matching circuit, primarily used to improve the efficiency of driving the transmitting transducer and minimize energy reflection. The impedance transformer is a conventional impedance transformer circuit, designed to effectively improve the system's response at low frequencies, taking into account the low-frequency, high-impedance characteristics of the receiving transducer. The preamplifier is a small-signal amplification circuit that amplifies the effective signal while minimizing the signal floor.

[0056] The touchscreen display client and application provided by this invention integrate an acoustic signal active transmission unit and a multi-channel synchronous receiving unit through an ultrasonic directional wireless integrated connection method, realizing adjustable delay between transmission and reception, with the adjustment step within one sample point, thereby ensuring a high degree of synchronization of the entire system in all aspects.

[0057] For further details, please refer to [link / reference]. Figure 3 The data acquisition and storage module 100 specifically includes:

[0058] The data acquisition and input unit collects the updated medical data and inputs it into the preprocessing unit.

[0059] The preprocessing unit is connected to the data acquisition and input unit, receives medical data and performs normalization preprocessing;

[0060] The feature extraction unit is connected to the preprocessing unit to extract features from the preprocessed medical data.

[0061] The decision display unit is connected to the feature extraction unit to synchronously build a decision algorithm model. The medical data after feature extraction is substituted into the decision algorithm model, and the decision value when the algorithm value is maximized is sought through the optimization iterative formula.

[0062] The trend display unit is connected to the decision display unit to obtain the decision value of the medical data after each update in real time, and displays the decision value of each time period in the basic coordinate system to obtain the trend measurement change of the medical data. It is defined that the higher the decision value, the higher the tendency of the medical data to become better.

[0063] The data acquisition and input unit uses a conventional data input device to collect medical data and then input it into the MCU preprocessing unit for subsequent data processing.

[0064] Furthermore, see Figure 4 Receiving medical data and performing normalization preprocessing includes:

[0065] S1: Acquire various medical data under different characteristics;

[0066] S2: Based on the selected feature values ​​corresponding to each medical data, perform reduction preprocessing in sequence to obtain the reduced medical data.

[0067] S3: Normalize each of the reduced medical data in sequence.

[0068] It should be noted that each piece of medical data has its own characteristics. In this invention, feature values ​​are assigned to each piece of medical data based on important characteristics, such as feature values ​​for key diseases (Class A), feature values ​​for non-key diseases (Class B and below), feature values ​​for medical equipment reserve levels, and feature values ​​for physician resource reserve levels.

[0069] Specifically, the present invention preferably uses the following feature values: the feature value δ for key diseases (Class A) is 1.2 to 1.3, with 1.2 generally selected as the optimal feature value in the subsequent normalization model; the feature value δ for non-key diseases (Class B and below) is 0.8 to 1.1, with 0.9 generally selected as the optimal feature value in the subsequent normalization model; the feature value δ for medical equipment reserve level is 0.5 to 0.8, with 0.6 generally selected as the optimal feature value in the subsequent normalization model; the feature value δ for physician resource reserve level is 0.3 to 0.5, with 0.4 generally selected as the optimal feature value in the subsequent normalization model.

[0070] Considering the massive volume of data after continuous updates of various medical data, and that representative data occupies only a portion before and after each update node, to alleviate the computational burden on the database, improve computational efficiency, and increase the accuracy of the results, the medical data is preprocessed and reduced according to the following formula to obtain the reduced medical data:

[0071]

[0072] Where t represents the acquired medical data, t' represents the reduced medical data for each item, and δ represents the selected feature value corresponding to each medical data t.

[0073] The process involves reducing and filtering out the medical data that meets the reduction requirements. Of course, the selection feature values ​​used for the filtered medical data are still the same as those selected in the previous step. This step is merely to complete the data reduction and filtering process.

[0074] For additional information, please refer to [link / reference]. Figure 8 This is a code execution diagram of the database when performing the corresponding deletion operation. The algorithm for database reduction is as follows:

[0075] Spring.datasource.url=jdbc:mysql: / / localhost:3307 / springboot-crud-mysql-vuejs / serverTimezone=UTC&useSSL=false

[0076] Spring.datasource.username=root

[0077] Spring.datasource.password=(δ,δ′)

[0078] Spring.datasource.driver-class-name=com.mysql.jdbc.Driver

[0079] Spring.jpa.hibernate.ddl-auto=create

[0080] Spring.jpa.database-platform=org.hiberate.dialect.MySQL1.2Dialect

[0081] Spring.jpa.database-platform=org.hiberate.dialect.MySQL0.9Dialect

[0082] Spring.jpa.generate-ddl=true

[0083] Spring.jpa.show-sql = true

[0084] Spring.freemarker.suffix=.html

[0085] Additionally, normalizing the reduced medical data is a standard practice in existing technologies, designed to facilitate subsequent value assignment and calculation in the model. The reference standards for normalization are the respective selected feature values ​​used for each piece of medical data.

[0086] Furthermore, autoencoder techniques such as sparse coding are used to extract features from the adjusted data.

[0087] It should be noted that the above steps have already selected and assigned feature values ​​to various medical data, and then reduced them for feature extraction. The assignment of feature values ​​is different from the feature extraction step. These values ​​are then substituted into the sparse coding cost function model to output the extracted feature values.

[0088] For details, please refer to Figure 9 The sparse coding cost function model is as follows:

[0089]

[0090]

[0091]

[0092] Where X represents each medical data point, A represents the selected feature value for each medical data point, y is defined as the output feature extraction value, i and j are the permutation numbers of each medical data point (each representing two data points), m and k are the current permutation numbers of each medical data point (each representing two data points), λ is defined as the unit 1, S is the maximum value function, C is defined as ln2, and α... i and Φ i This is the reference value for extracting the i-th item (representing two data items respectively);

[0093] The detailed algorithm is as follows:

[0094] Input: Signal: f(t), dictionaryD.

[0095] Output: Listofcoefficients:(a n, g rn ).

[0096] initialization:

[0097] R1——f(t);

[0098] n——1;

[0099] repeat:

[0100] findg rn ∈Dwithmaximuminnerproduct∣<R n, g rn > |;

[0101] a n ——<Rn, g rn >;

[0102] R n+1 ——R n -g rn ;

[0103] n——n+1;

[0104] Until the sparsity stopping condition is reached, for example: ||R n ||<threshold.

[0105] Furthermore, the reference values ​​for feature extraction when performing feature extraction on preprocessed medical data are:

[0106]

[0107] Where δ' is the extraction reference value when performing feature extraction, and δ is the selected feature value corresponding to each medical data t.

[0108] Specifically, the constructed decision-making algorithm model is as follows:

[0109] Objective function J(y):

[0110] J(y)=[E{g(y}-E{g(y)} guass )}] 2

[0111] Where J is the decision value output function, y is the output feature extraction value function, E{} is the expectation function, defined as the extraction reference function for different data items, and g() is a nonlinear function, and the nonlinear function is g=tanh(1.5y).

[0112] Constraint: E{}∈{0,1}.

[0113] The optimization iterative formula is as follows:

[0114]

[0115] In the formula, X is the data matrix, Z is the data matrix after centering and whitening, W(i) and W(i+1) are the separation matrices before and after iteration, E{} is the expectation, g() is a nonlinear function, and the nonlinear function is g=tanh(1.5y), g'() is the derivative function of the nonlinear function, and T is the iteration exponent.

[0116] It should be noted that, preferably, the iteration efficiency can be accelerated by constructing a Newton's method with a fifth-order convergence rate, substituting it into the modified Newton's method, and improving the iteration formula.

[0117] The Newton's method for fifth-order convergence speed is as follows:

[0118]

[0119] Substituting the modified Newton's method, the improved iterative formula is as follows:

[0120]

[0121] For additional information, please refer to [link / reference]. Figure 5 The present invention also provides a community health and medical data dashboard, a method for creating which includes the following steps:

[0122] The application creates an independent interface, a server integrates and analyzes the data, and a touchscreen client for operating the application.

[0123] The server receives the trigger command from the application and completes the two-dimensional data layering process;

[0124] The data interfaces, after being processed into layers, are displayed in the data display nodes of the corresponding applications.

[0125] For further details, please refer to [link / reference]. Figure 6 The server-side data stratification process, which involves two dimensions, includes:

[0126] Collect and store medical data after each update;

[0127] Acquire updated medical data and perform feature labeling on it;

[0128] The medical data after feature labeling is integrated into the corresponding data display nodes.

[0129] Furthermore, see Figure 7 The server-side data stratification process, which involves two dimensions, also includes:

[0130] Collect the updated medical data each time and input it into the preprocessing unit for normalization preprocessing;

[0131] Feature extraction is performed on the preprocessed medical data;

[0132] A decision algorithm model is constructed, the medical data after feature extraction is substituted into the decision algorithm model, and the decision value when the algorithm value is maximized is sought through the optimization iterative formula;

[0133] The system acquires decision values ​​from each updated medical data in real time and displays these decision values ​​across different time periods on a basic coordinate system to measure the trend changes in the medical data.

[0134] This invention provides a community health and medical data dashboard and its creation method. It collects updated medical data from a server and performs two-layer data processing. One layer integrates and displays all medical data and performs feature labeling. The labeled medical data is then integrated into corresponding data display nodes, providing a comprehensive view of the integrated and categorized information, while also classifying personalized medical data. The other layer of data processing performs normalization and reduction preprocessing on the collected data. After feature extraction, a decision algorithm model and optimization iterative formula are used to quantitatively display the trends in the development of medical data over time, clarifying the development direction of the community's medical status.

[0135] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A community health and medical data dashboard, characterized in that: It includes an application for creating a standalone interface, a server for integrating and analyzing data, and a touchscreen client for operating the application; The touchscreen display client and the application are connected via an integrated ultrasonic directional wireless connection. The touchscreen display client includes a server, an FPGA controller, and an ultrasonic signal active transmission unit. The application embeds a receiving chip, which in turn embeds a multi-channel synchronous receiving unit. The server is connected to the FPGA controller, the output of which is connected to the ultrasonic signal active transmission unit, and the input of which is connected to the multi-channel synchronous receiving unit. The ultrasonic signal active transmission unit includes a D / A converter, a power amplifier, an impedance matching circuit, and a transmitting transducer. The FPGA controller is connected to the transmitting transducer sequentially via the D / A converter, power amplifier, and impedance matching circuit. The multi-channel synchronous receiving unit includes an A / D converter, a preamplifier, an impedance transformer, and a receiving transducer. The receiving transducer is connected to the FPGA controller sequentially via the impedance transformer, preamplifier, and A / D converter. The server and the FPGA controller are directly connected via USB 3.

0. The signal input terminal of the application is electrically connected to the signal output terminal of the touchscreen display client, and a trigger command is sent during signal transmission. The server receives the trigger command, integrates the data, and displays the integrated data interface in the data display node of the application. Specifically, the server includes: The acquisition and storage module is used to acquire and store the updated medical data; the acquisition and storage module specifically includes, The data acquisition and input unit collects the updated medical data and inputs it into the preprocessing unit. The preprocessing unit is connected to the data acquisition and input unit to receive medical data and perform normalization preprocessing. The feature extraction unit, connected to the preprocessing unit, extracts features from the preprocessed medical data. It employs autoencoder techniques, such as sparse coding, to extract features from the adjusted data. The sparse coding cost function model is as follows: Where X represents each medical data item, A represents the selected feature value of each medical data item, y is defined as the output feature extraction value, i and j are the arrangement numbers of the two medical data items, m and k are the current arrangement numbers of each medical data item, λ is defined as unit 1, S is the maximum value function, C is defined as log2, and αi and Φi are the extraction reference values ​​of the two medical data items in the i-th data item. The decision display unit is connected to the feature extraction unit, synchronously constructs a decision algorithm model, substitutes the medical data after feature extraction into the decision algorithm model, and seeks the decision value when the algorithm value is maximized through an optimization iterative formula; The trend display unit is connected to the decision display unit in real time to obtain the decision value of the medical data after each update, and displays the decision value of each time period in the basic coordinate system to obtain the trend measurement change of the medical data. It is defined that the higher the decision value, the higher the tendency of the medical data to become better. The feature classification module is connected to the acquisition and storage module to obtain updated medical data and perform feature labeling on it. The integration module is connected to the feature classification module to integrate the feature-labeled medical data into the corresponding data display node.

2. The community health and medical data dashboard according to claim 1, characterized in that: Receiving medical data and performing normalization preprocessing includes, Acquire various medical data under different characteristics; Based on the selected feature values ​​corresponding to each medical data point, the data is preprocessed to reduce the data points and obtain the reduced medical data. The reduced medical data were then normalized sequentially.

3. The community health and medical data cockpit according to claim 2, characterized in that: Based on the following formula for medical treatment The data undergoes reduction preprocessing to obtain the reduced medical data. Where t represents the acquired medical data, t' represents the reduced medical data for each item, and δ represents the selected feature value corresponding to each medical data t.

4. The community health and medical data cockpit according to claim 3, characterized in that: The reference value for feature extraction when performing feature extraction on preprocessed medical data is: Where δ' is the extraction reference value when performing feature extraction, and δ is the selected feature value corresponding to each medical data t.

5. The community health and medical data cockpit according to claim 4, characterized in that: The constructed decision algorithm model is specifically as follows: Objective function J(y): Where J is the decision value output function, y is the output feature extraction value function, E{} is the expectation function, defined as the extraction reference function for different data items, and g() is a nonlinear function, wherein the nonlinear function is g=tanh(1.5y). Constraint: E{}∈{0,1}.

6. A method for creating a community health and medical data dashboard according to any one of claims 1 to 5, characterized in that: Includes the following steps, The application creates an independent interface, a server integrates and analyzes the data, and a touchscreen client for operating the application. The server receives the trigger command from the application and completes the two-dimensional data layering process; The data interfaces, after being processed in layers, are displayed in the corresponding data display nodes of the application.

7. The method for creating a community health and medical data dashboard according to claim 6, characterized in that: The server-side data stratification process, which involves two dimensions, includes: Collect and store medical data after each update; Acquire updated medical data and perform feature labeling on it; The medical data after feature labeling is integrated into the corresponding data display nodes.

8. The method for creating a community health and medical data dashboard according to claim 6, characterized in that: The server-side data stratification process, which involves two dimensions, includes: Collect the updated medical data each time and input it into the preprocessing unit for normalization preprocessing; Feature extraction is performed on the preprocessed medical data; A decision algorithm model is constructed, the medical data after feature extraction is substituted into the decision algorithm model, and the decision value when the algorithm value is maximized is sought through the optimization iterative formula; The system acquires decision values ​​from each updated medical data in real time and displays these decision values ​​across different time periods on a basic coordinate system to measure the trend changes in the medical data.

Images