Rheumatism prediction system based on neural network

Abstract

The invention relates to a rheumatism prediction system based on a neural network, and the system is characterized in that the system comprises a data obtaining module which is used for obtaining the health data, the current geographic position and the occupation of a target patient; the first label construction module is used for obtaining a health label based on the health data; the second label construction module is used for obtaining an environment label based on the current geographic position; the third label construction module is used for obtaining an occupation label based on the occupation; and the prediction module is used for inputting the health label, the environment label and the occupational label into a neural network model to obtain a rheumatism prediction result. Therefore, timely and accurate management and early warning are provided for the health condition of the patient.

Description

Technical Field

[0001] The invention relates to the field of medical technology, and in particular to a rheumatism prediction system based on a neural network. Background Art

[0002] Rheumatism is a chronic systemic disease, and its incidence is usually closely related to factors such as genetics, living environment, and hormonal changes in the body.

[0003] However, the existing technology does not fully consider the causes of the patient's illness, resulting in poor prediction accuracy and failure to achieve good prediction results. Summary of the invention

[0004] The present invention aims at solving the technical problems in the prior art and provides a rheumatism prediction system based on a neural network.

[0005] The technical solution of the present invention to solve the above technical problems is as follows: A rheumatism prediction system based on a neural network, the system comprising: A data acquisition module is used to obtain the health data, current geographic location and occupation of the target patient; A first label building module, used to obtain a health label based on the health data; A second label building module, used to obtain an environment label based on the current geographical location; A third label building module is used to obtain an occupation label based on the occupation; The prediction module is used to input the health label, the environmental label and the occupation label into a neural network model to obtain a rheumatism prediction result.

[0006] Optionally, obtaining a health label based on the health data includes: Based on the health data, construct a feature sequence; The feature sequence is input into the first transformer model and a health label is output.

[0007] Optionally, constructing a feature sequence based on the health data includes: constructing a weighted undirected graph based on the health data; Screening important nodes in the weighted undirected graph; Using the health data corresponding to the important nodes as key health data; A feature sequence is constructed based on the key health data.

[0008] Optionally, screening the important nodes in the weighted undirected graph includes: The importance of node i in the weighted undirected graph is calculated by the following formula : ; in, represents the set of neighbor nodes of node i, represents the weight of the undirected edge between node i and node j; The importance levels are sorted, and a preset number of nodes are selected as important nodes based on the sorted results.

[0009] Optionally, obtaining an environment tag based on the current geographical location includes: The current geographic location is input into a second transformer model, and an environment label is output.

[0010] Optionally, obtaining an occupation label based on the occupation includes: Classifying the occupations to obtain occupational categories; Get the occupation label corresponding to the occupation category.

[0011] Optionally, the neural network model is an MLP model.

[0012] Optionally, the step of inputting the health label, the environmental label and the occupation label into a neural network model to obtain a rheumatism prediction result includes: The health label, the environmental label and the occupational label are input into the MLP model to obtain a rheumatism prediction result.

[0013] Optionally, the system further includes an output module for outputting the rheumatism prediction result to a doctor terminal after the rheumatism prediction result is obtained.

[0014] Optionally, after the rheumatism prediction result is output to the doctor terminal, the doctor analyzes the rheumatism prediction result and generates a rheumatism prediction report.

[0015] In addition, to achieve the above-mentioned purpose, the present invention also proposes an electronic device, comprising: a memory for storing a computer software program; a processor for reading and executing the computer software program, thereby realizing a rheumatism prediction system based on a neural network as described above.

[0016] In addition, to achieve the above-mentioned purpose, the present invention also proposes a non-transitory computer-readable storage medium, in which a computer software program is stored. When the computer software program is executed by a processor, a rheumatism prediction system based on a neural network as described above is implemented.

[0017] The beneficial effects of the present invention are: (1) According to the pathogenesis of rheumatism, the present invention introduces three factors, namely health, location and occupation, and combines neural network to predict rheumatism, thus providing timely and accurate management and early warning for the patient's health status.

[0018] (2) Considering the large amount of health data, the variety of types, the differences between patients, and the correlation between information such as living habits and physiological indicators, the present invention uses health data as nodes, establishes undirected edges based on the correlation between health data, and weights the undirected edges between any two nodes according to the co-occurrence probability to construct a weighted undirected graph; calculates the importance of any node in the graph, screens out important nodes, and uses the health data corresponding to the important nodes as key health data; constructs a feature sequence based on the key health data. In this way, health data that meets the physiological characteristics of different patients can be screened out to improve the accuracy of prediction.

[0019] (3) Output the health data as health labels, the location data as environment labels, and the occupation labels as occupation labels, input the health labels, environment labels, and occupation labels into the MLP model to obtain prediction results; further, input the health labels and environment labels into the MLP model to obtain first prediction data; input the health labels and occupation labels into the MLP model to obtain second prediction data; input the health labels, environment labels, and occupation labels into the MLP model to obtain third prediction data; combine the first prediction data, the second prediction data, and the third prediction data into a rheumatism prediction result. Through multi-level analysis of labels and neural networks, doctors can be helped to analyze, manage, and warn more accurately. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A scene diagram of a rheumatism prediction system based on a neural network provided by the present invention; Figure 2 A schematic diagram of the structure of a rheumatism prediction system based on a neural network provided by the present invention; Figure 3 A schematic flow chart of the steps executed by the first label building module provided by the present invention; Figure 4 A schematic flow chart of the steps performed by the prediction module provided by the present invention; Figure 5 A schematic diagram of the hardware structure of a possible electronic device provided by the present invention; Figure 6 A schematic diagram of the hardware structure of a possible computer-readable storage medium provided by the present invention. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0022] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0023] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0024] See also Figure 1 , Figure 1 This is a scene diagram of a rheumatism prediction system based on a neural network provided by the present invention. Figure 1 As shown, the terminal and the server are connected via a network, such as a wired or wireless network connection. The terminal may include but is not limited to portable terminals such as mobile phones and tablets installed with various network platform applications, as well as fixed terminals such as computers, query machines, and advertising machines. The server provides users with various business services, including service push servers, user recommendation servers, etc.

[0025] It should be noted that Figure 1The scene diagram of a neural network-based rheumatism prediction system shown is only an example. The terminal, server and application scenario described in the embodiment of the present invention are intended to more clearly illustrate the technical solution of the embodiment of the present invention, and do not generate limitations on the technical solution provided by the embodiment of the present invention. Ordinary technicians in this field can know that with the evolution of the system and the emergence of new business scenarios, the technical solution provided by the embodiment of the present invention is also applicable to similar technical problems.

[0026] Among them, the terminal can be used for: Obtain target patient’s health data, current geographic location, and occupation; Based on the health data, a health label is obtained; Based on the current geographical location, obtain an environmental label; Based on the occupation, an occupation label is obtained; The health label, the environmental label and the occupational label are input into a neural network model to obtain a rheumatism prediction result.

[0027] See also Figure 2 , Figure 2 A schematic diagram of the structure of a rheumatism prediction system based on a neural network provided by the present invention.

[0028] like Figure 2 As shown, a rheumatism prediction system based on a neural network proposed in an embodiment of the present invention includes: The data acquisition module 201 is used to acquire the health data, current geographical location and occupation of the target patient.

[0029] Among them, the health data in the target patient's health report (such as age 30, smoking, blood sugar 7.8) can be collected through a data collection device, and standardized (such as standardizing blood sugar 7.8 as high blood sugar) for subsequent construction of a weighted undirected graph; the current geographic location of the target patient is collected through a GPS positioning system; and the target patient manually enters his / her occupation in the system, such as high-altitude workers.

[0030] The first label building module 202 is used to obtain a health label based on the health data.

[0031] In one embodiment, Figure 3 As shown, the first label construction module 202 can be further used to perform the following steps: Step 2021: construct a weighted undirected graph based on the health data.

[0032] Optionally, health data (or standardized data corresponding to health data) is used as a node, and undirected edges are established based on the association relationship between health data. The step of weighting the undirected edges between any two nodes includes: obtaining the health data corresponding to the two nodes; counting the number of co-occurrences of the health data in historical patients, and calculating the co-occurrence frequency.

[0033] For example, health data includes smoking and high blood sugar, with smoking as node 1 and high blood sugar as node 2. Since there is a correlation between smoking and high blood sugar, an undirected edge is established between node 1 and node 2. The number of co-occurrences of smoking and high blood sugar in historical patients is counted, and the co-occurrence frequency is calculated. The co-occurrence frequency is used as the weight value between node 1 and node 2. Similarly, the connection relationship between other health data (i.e., other nodes) is established and weighted, thereby constructing a weighted undirected graph.

[0034] In addition, each edge may be weighted based on the medical experience of the expert.

[0035] Step 2022: Screen important nodes in the weighted undirected graph.

[0036] Optionally, the importance of node i in the weighted undirected graph is calculated by the following formula: : ; in, represents the set of neighbor nodes of node i, represents the weight of the undirected edge between node i and node j; The importance levels are sorted, and a preset number of nodes are selected as important nodes based on the sorted results.

[0037] The present invention takes into account the differences between patients and the correlation between information such as living habits and physiological indicators, and proposes the above-mentioned graph construction and node screening method to screen out health data that meets the physiological characteristics of different patients and improve prediction accuracy.

[0038] Step 2023: Use the health data corresponding to the important nodes as key health data.

[0039] Step 2024: construct a feature sequence based on the key health data.

[0040] Step 2026: Input the feature sequence into the first transformer model and output a health label.

[0041] Among them, health labels may include health levels (such as excellent, good, poor, etc.).

[0042] The second label building module 203 is used to obtain an environment label based on the current geographical location.

[0043] Optionally, the current geographic location is input into a second transformer model, and an environment label is output.

[0044] Among them, environmental tags may include air quality, temperature, humidity, etc.

[0045] The third label building module 204 is used to obtain an occupation label based on the occupation.

[0046] Optionally, the occupation is classified to obtain an occupational category, and an occupational label corresponding to the occupational category is obtained. The occupational category and the occupational label are stored in a database correspondingly, and after obtaining the occupational category of the target patient, the database is queried to obtain the corresponding occupational label.

[0047] Among them, occupational labels may include workload, working environment (such as indoors, outdoors), etc.

[0048] The prediction module 205 is used to input the health label, the environmental label and the occupation label into the neural network model to obtain a rheumatism prediction result.

[0049] Optionally, the neural network model is an MLP model (multi-layer perceptron), and the health label, the environmental label and the occupational label are input into the MLP model to obtain a rheumatism prediction result. The MLP model includes an input layer, a hidden layer and an output layer; the input layer receives the input label (i.e., the health label, the environmental label and the occupational label); and the output layer outputs a rheumatism probability value, i.e., a rheumatism prediction result, through a softmax activation function.

[0050] In one embodiment, Figure 4 As shown, the prediction module 205 can be further used to perform the following steps: Step 2051: Input the health label and the environmental label into the MLP model to obtain first prediction data.

[0051] Step 2052: Input the health label and the occupation label into the MLP model to obtain second prediction data.

[0052] Step 2053: input the health label, the environmental label and the occupation label into the MLP model to obtain third prediction data.

[0053] Step 2054: combine the first prediction data, the second prediction data and the third prediction data into a rheumatism prediction result.

[0054] For example, if the first prediction data is 0.7, the second prediction data is 1, and the third prediction data is 0.8, they are combined as the rheumatism prediction result, and through comparative analysis, a prompt is generated: "The patient's current health condition is in general state, the current position is in a safe state, and the current occupation is in a risky state."

[0055] This implementation method obtains more accurate rheumatism prediction results through multi-level analysis of labels.

[0056] The output module 206 is used to output the rheumatism prediction result to the doctor terminal after obtaining the rheumatism prediction result.

[0057] Furthermore, after the rheumatism prediction result is output to the doctor's terminal, the doctor analyzes the rheumatism prediction result and generates a rheumatism prediction report.

[0058] Optionally, the doctor can assist in generating a rheumatism prediction report based on the rheumatism prediction results and system prompts.

[0059] Therefore, according to the pathogenesis of rheumatism, the three factors of health, location and occupation are introduced, and rheumatism prediction is carried out in combination with neural networks to provide timely and accurate management and early warning of patients' health conditions.

[0060] See also Figure 5 , Figure 5 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 5 As shown, an embodiment of the present invention provides an electronic device 400, including a memory 410, a processor 420, and a computer program 411 stored in the memory 410 and executable on the processor 420. When the processor 420 executes the computer program 411, the following steps are implemented: Obtain target patient’s health data, current geographic location, and occupation; Based on the health data, a health label is obtained; Based on the current geographical location, obtain an environmental label; Based on the occupation, an occupation label is obtained; The health label, the environmental label and the occupational label are input into a neural network model to obtain a rheumatism prediction result.

[0061] See also Figure 6 , Figure 6 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 6 As shown, this embodiment provides a computer-readable storage medium 500, on which a computer program 411 is stored. When the computer program 411 is executed by a processor, the following steps are implemented: Obtain target patient’s health data, current geographic location, and occupation; Based on the health data, a health label is obtained; Based on the current geographical location, obtain an environmental label; Based on the occupation, an occupation label is obtained; The health label, the environmental label and the occupational label are input into a neural network model to obtain a rheumatism prediction result.

[0062] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0063] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0064] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A system that specifies the functions of a box or multiple boxes.

[0065] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction system, which is implemented in the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0066] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0067] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0068] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A rheumatism prediction system based on neural network, characterized in that: The system comprises: A data acquisition module is used to obtain the health data, current geographic location and occupation of the target patient; A first label building module, used to obtain a health label based on the health data; A second label building module, used to obtain an environment label based on the current geographical location; A third label building module is used to obtain an occupation label based on the occupation; The prediction module is used to input the health label, the environmental label and the occupation label into a neural network model to obtain a rheumatism prediction result.

2. The rheumatism prediction system based on neural network according to claim 1, characterized in that: The obtaining of a health label based on the health data includes: Based on the health data, construct a feature sequence; The feature sequence is input into the first transformer model and a health label is output.

3. The rheumatism prediction system based on neural network according to claim 2, characterized in that: The constructing a feature sequence based on the health data includes: constructing a weighted undirected graph based on the health data; Screening important nodes in the weighted undirected graph; Using the health data corresponding to the important nodes as key health data; A feature sequence is constructed based on the key health data.

4. The rheumatism prediction system based on neural network according to claim 3, characterized in that: The screening of important nodes in the weighted undirected graph includes: The importance of node i in the weighted undirected graph is calculated by the following formula : ； in, represents the set of neighbor nodes of node i, represents the weight of the undirected edge between node i and node j; The importance levels are sorted, and a preset number of nodes are selected as important nodes based on the sorted results.

5. The rheumatism prediction system based on neural network according to claim 1, characterized in that: The obtaining of an environment tag based on the current geographical location includes: The current geographic location is input into a second transformer model, and an environment label is output.

6. The rheumatism prediction system based on neural network according to claim 1, characterized in that: Based on the occupation, an occupation label is obtained, including: Classifying the occupations to obtain occupational categories; Get the occupation label corresponding to the occupation category.

7. The rheumatism prediction system based on neural network according to claim 1, characterized in that: The neural network model is an MLP model.

8. The rheumatism prediction system based on neural network according to claim 7, characterized in that: The step of inputting the health label, the environmental label and the occupation label into a neural network model to obtain a rheumatism prediction result includes: The health label, the environmental label and the occupational label are input into the MLP model to obtain a rheumatism prediction result.

9. The rheumatism prediction system based on neural network according to claim 8, characterized in that: The system also includes an output module for outputting the rheumatism prediction result to a doctor terminal after the rheumatism prediction result is obtained.

10. The neural network-based rheumatism prediction system according to claim 9, characterized in that: After the rheumatism prediction result is output to the doctor terminal, the doctor analyzes the rheumatism prediction result and generates a rheumatism prediction report.

Images