Chronic disease risk early warning method and system based on big data

Abstract

The invention relates to a chronic disease risk early warning method and system based on big data. A data acquisition module is connected with a data processing module, the data processing module is connected with an early warning evaluation model, the early warning evaluation model is connected with an early warning analysis module, and the early warning analysis module is connected with a terminal early warning module; the acquisition mode of the data acquisition module is active uploading and data mining; the data preprocessing module comprises a data validity analysis module and a data processing correction module; the early warning evaluation model obtains an evaluation result through data feature identification, data coding, risk evaluation operation and data decoding output; the early warning analysis module is provided with a preset range value, and after the preset range value is exceeded, early warning information is transmitted to the terminal early warning equipment through the Internet module, so that the chronic disease distribution state, the real-time monitoring information, the chronic disease development situation and the like in the region are subjected to efficient and scientific statistics, and the formulation and implementation of further supervision measures are facilitated.

Description

Technical Field

[0001] The present invention relates to the technical field of chronic disease management, and in particular to a chronic disease risk early warning method and system based on big data. Background Art

[0002] Chronic diseases are a general term for illnesses with a long course, complex etiology, non-infectious properties, and requiring long-term management. They encompass cardiovascular and cerebrovascular diseases, metabolic diseases, tumors, and respiratory diseases. Examples include hypertension, coronary heart disease, stroke, diabetes, hyperlipidemia, hyperuricemia, chronic obstructive pulmonary disease, asthma, tumors, mental illness, and autoimmune diseases. Chronic diseases have high mortality rates and increase the financial burden on patients. They are long-lasting, costly, and can easily lead to disability, impacting work ability and quality of life.

[0003] The traditional chronic disease risk warning system has drawbacks, which are mainly reflected in the following aspects: First, in terms of data collection, the traditional data collection method has defects such as incomplete data and single and one-sided collection method, which has a negative impact on the stability and stability of the data, resulting in deviations and errors in the warning results; second, in terms of data processing, the traditional warning system has correction deficiencies in the data processing process, and a large amount of invalid and erroneous data will affect the data processing operation, resulting in reduced authenticity of the output data; third, in terms of the warning processing model, the traditional warning system cannot accurately and precisely identify the identification features in the module. In the process of implementing model-based operation and processing, the data lacks multi-gradient fusion operations, resulting in deviations in the warning data and the disappearance of gradients of some data, seriously affecting the final warning effect; in addition, the traditional warning system has a single terminal method in the warning analysis process, which is prone to lags. At the same time, there are drawbacks in the query and retrieval of warning red line location information in historical data, resulting in a reduction in overall statistical efficiency.

[0004] Therefore, providing a chronic disease risk warning method and system based on big data that can improve the accuracy of chronic disease risk warning, provide accurate decision-making for chronic disease supervision and control, provide evaluation plans through calculations, and provide technical support for scientific monitoring and prevention and control of chronic diseases, with a simple and easy-to-operate method, has broad market prospects. Summary of the Invention

[0005] In response to the shortcomings of the existing technology, the present invention provides a chronic disease risk warning method and system based on big data that can improve the accuracy of chronic disease risk warning, provide accurate decision-making for chronic disease supervision and control, provide evaluation plans through calculations, and provide technical support for scientific monitoring and prevention and control of chronic diseases. The method is simple and easy to operate, which is used to overcome the defects in the existing technology.

[0006] The technical solution of the present invention is implemented as follows: a chronic disease risk early warning system based on big data, comprising a data acquisition module, the data acquisition module is connected to a data processing module, the data processing module is connected to an early warning assessment model, the early warning assessment model is connected to an early warning analysis module, and the early warning analysis module is connected to a terminal early warning module;

[0007] The data collection module collects data in the form of active uploading and data mining;

[0008] The data preprocessing module includes a data validity analysis module and a data processing correction module;

[0009] The early warning assessment model obtains the assessment results through data feature identification, data coding, risk assessment calculation and data decoding output;

[0010] The warning analysis module is set with a preset range value. When the preset range value is exceeded, the warning information is transmitted to the terminal warning device through the Internet module.

[0011] Furthermore, the data collection module collects medical data, personal health data and public data in real time.

[0012] Furthermore, the signals collected by the data acquisition module are transmitted to the early warning assessment model after optimization processing.

[0013] Furthermore, the data validity analysis module and the data processing correction module are connected to the processing conversion module, and the processing conversion module is connected to the output data module.

[0014] Furthermore, the risk assessment operation uses three algorithms, Logistic, XGBoost and Random Forest, to implement multiple operations on coded features.

[0015] Furthermore, the early warning analysis module also includes a data storage module and a data export module.

[0016] An early warning method for a chronic disease risk early warning system based on big data as described above comprises the following steps:

[0017] S1. The data acquisition module collects medical data, personal health data, and public data in real time through active uploading and data mining. The collected signals are optimized and processed before being transmitted to the early warning assessment model.

[0018] S2, the data processing module processes the data transmitted in S1 and performs data validity analysis. When the data processing mark is valid, it directly enters the processing conversion module and outputs the data. When the data processing mark is invalid, the data is repeated filled or repeatedly collected through the data processing correction module, and then enters the processing conversion module and outputs the data.

[0019] S3, receives the data output in S2 through the early warning assessment model, then performs feature identification on the received data and encodes the feature identification data. Then, three algorithms, Logistic, XGBoost, and Random Forest, are used to perform multiple operations on the encoded features to perform risk assessment operations on the data. The final assessment structure is output after data decoding.

[0020] S4. The decoded data is transmitted to the early warning analysis module. When the evaluation result exceeds the preset range value, the early warning information is transmitted to the terminal early warning device through the Internet module to implement an alarm. At the same time, the data exceeding the set range value is synchronously stored in the data storage module. When the evaluation result does not exceed the preset range value, the data is directly synchronously stored in the data storage module. The data in the data storage module is exported through the data export module to obtain a warning analysis report.

[0021] The present invention has the following positive effects:

[0022] 1. The present invention collects medical data, personal health data and public data in real time through active uploading and data mining. The collection method is comprehensive, the data is stable and stable, and the early warning results are accurate and effective, avoiding defects such as data anomalies, deficiencies or losses, and ensuring that the early warning results will not have deviations and errors.

[0023] 2. In the data processing process of the present invention, the effectiveness implementation analysis module and the data processing correction module are adopted to correct the missing of acute data, avoid the transmission of a large amount of invalid and erroneous data, reduce the result deviation caused by invalid processing, and ensure that the data entering the early warning evaluation model is true and valid.

[0024] 3. The present invention uses data feature identification to accurately add identification features. During the modeling operation and processing of data, the feature identification data is accurately identified through data encoding, and then multi-gradient and multi-dimensional data operations are performed through multiple operation methods to accurately obtain risk assessment results, thereby ensuring the integrity and accuracy of the early warning data, avoiding defects caused by data deviations and anomalies, and improving the early warning capability.

[0025] 4. The present invention uses an early warning analysis module to judge the evaluation results. When the evaluation results exceed the preset range value, the early warning signal is transmitted to multi-terminal early warning devices through the Internet. The terminal alarm mode is diverse. Even if the alarm preset value is not reached, the data information will be exported through the data storage module to obtain a comprehensive early warning analysis report, and long-term monitoring will be carried out. Efficient and scientific statistics will be conducted on the distribution status of chronic diseases in the region, real-time monitoring information, and development trends of chronic diseases, which will help to formulate and implement further regulatory measures. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 Schematic diagram of the system layered structure of the present invention.

[0027] Figure 2 Schematic diagram of the hierarchical structure of the data acquisition module of the present invention.

[0028] Figure 3 It is a schematic diagram of the hierarchical structure of the data processing model of the present invention.

[0029] Figure 4 It is a schematic diagram of the hierarchical structure of the early warning assessment model of the present invention.

[0030] Figure 5 This is a schematic diagram of the hierarchical structure of the early warning analysis module of the present invention. DETAILED DESCRIPTION

[0031] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0032] In the following description of the invention, it should be noted that the terms "upper," "lower," "left," "right," "inner," and "outer," etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings and are intended solely to facilitate and simplify the description of the invention. They are not intended to indicate or imply that the devices or components referred to must have a specific orientation, be constructed, or operate in a specific orientation. The term "connected" simply indicates a connection between devices and does not have any special meaning.

[0033] like Figure 1 、 2As shown in Figures 3, 4, and 5, a chronic disease risk warning system based on big data includes a data acquisition module, the data acquisition module is connected to the data processing module, the data processing module is connected to the warning evaluation model, the warning evaluation model is connected to the warning analysis module, and the warning analysis module is connected to the terminal warning module; the data acquisition module collects data in the form of active uploading and data mining; the data preprocessing module includes a data validity analysis module and a data processing and correction module; the warning evaluation model obtains the evaluation result through data feature identification, data encoding, risk assessment operation and data decoding output; the warning analysis module is set with a preset range value, and when the preset range value is exceeded, the warning information is transmitted to the terminal warning device through the Internet module.

[0034] As another embodiment of the present invention, the data collection module collects medical data, personal health data and public data in real time.

[0035] As another embodiment of the present invention, the signals collected by the data acquisition module are transmitted to the early warning evaluation model after being optimized.

[0036] As another embodiment of the present invention, the data validity analysis module and the data processing and correction module are connected to the processing conversion module, and the processing conversion module is connected to the output data module.

[0037] As another embodiment of the present invention, the risk assessment operation uses three algorithms, Logistic, XGBoost and Random Forest, to implement multiple operations on encoding features.

[0038] As another embodiment of the present invention, the early warning analysis module further includes a data storage module and a data export module.

[0039] A method for early warning of a chronic disease risk early warning system based on big data, comprising the following steps:

[0040] S1. The data acquisition module collects medical data, personal health data, and public data in real time through active uploading and data mining. The collected signals are optimized and processed before being transmitted to the early warning assessment model.

[0041] S2, the data processing module processes the data transmitted in S1 and performs data validity analysis. When the data processing mark is valid, it directly enters the processing conversion module and outputs the data. When the data processing mark is invalid, the data is repeated filled or repeatedly collected through the data processing correction module, and then enters the processing conversion module and outputs the data.

[0042] S3, receives the data output in S2 through the early warning assessment model, then performs feature identification on the received data and encodes the feature identification data. Then, three algorithms, Logistic, XGBoost, and Random Forest, are used to perform multiple operations on the encoded features to perform risk assessment operations on the data. The final assessment structure is output after data decoding.

[0043] S4. The decoded data is transmitted to the early warning analysis module. When the evaluation result exceeds the preset range value, the early warning information is transmitted to the terminal early warning device through the Internet module to implement an alarm. At the same time, the data exceeding the set range value is synchronously stored in the data storage module. When the evaluation result does not exceed the preset range value, the data is directly synchronously stored in the data storage module. The data in the data storage module is exported through the data export module to obtain a warning analysis report.

[0044] The present invention implements integrated data collection through multiple data collection channels, and then implements deviation, error, authenticity and other detection processing through data processing to ensure that the data source is authentic and valid. The early warning assessment model can evaluate early warning information through multiple calculation methods, and conduct early identification, mid-term monitoring and late auxiliary supervision of high-risk groups for chronic diseases. Compared with traditional manual assessment models, it can achieve more comprehensive and multi-dimensional accurate assessment, as well as objective and accurate identification of risk factors.

[0045] The present invention builds a chronic disease health risk early warning assessment model, utilizes big data mining technology, uses regional medical data, public data and personal health data as the carrier of the model training module, adopts three algorithms, Logistic, XGBoost and Random Forest, to implement model prediction and perform analysis through the analysis module, and issues early warning for data exceeding the preset range. The terminal early warning module is directly targeted at public health management units such as hospitals and community health service centers.

[0046] The present invention helps to promote the detection and assessment of individuals with chronic diseases, thereby reducing the burden of chronic diseases, reducing the disability and mortality rates of chronic diseases, improving the quality of life of patients with chronic diseases, alleviating the economic burden on their families, forming a chronic disease management method within a regional module, and promoting dynamic intelligent monitoring and early warning of regional chronic diseases. Although the embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A chronic disease risk early warning system based on big data, including a data acquisition module, characterized by: The data acquisition module is connected to the data processing module, the data processing module is connected to the early warning assessment model, the early warning assessment model is connected to the early warning analysis module, and the early warning analysis module is connected to the terminal early warning module; The data collection module collects data in the form of active uploading and data mining; The data preprocessing module includes a data validity implementation analysis module and a data processing correction module; The early warning assessment model obtains the assessment results through data feature identification, data coding, risk assessment calculation and data decoding output; The warning analysis module is set with a preset range value. When the preset range value is exceeded, the warning information is transmitted to the terminal warning device through the Internet module.

2. The big data-based chronic disease risk early warning system according to claim 1 is characterized by: The data collection module collects medical data, personal health data and public data in real time.

3. The big data-based chronic disease risk early warning system according to claim 1 or 2, characterized in that: The signals collected by the data acquisition module are transmitted to the early warning evaluation model after optimization processing.

4. The big data-based chronic disease risk early warning system according to claim 1 is characterized by: The data validity analysis module and the data processing correction module are connected to the processing conversion module, and the processing conversion module is connected to the output data module.

5. The chronic disease risk early warning system based on big data according to claim 1 is characterized by: The risk assessment operation uses three algorithms, Logistic, XGBoost and Random Forest, to implement multiple operations on coded features.

6. The big data-based chronic disease risk early warning system according to claim 1 is characterized by: The early warning analysis module also includes a data storage module and a data export module.

7. An early warning method for a chronic disease risk early warning system based on big data according to any one of claims 1 to 6, characterized in that: The method comprises the following steps: S1. The data acquisition module collects medical data, personal health data, and public data in real time through active uploading and data mining. The collected signals are optimized and processed before being transmitted to the early warning assessment model. S2, the data processing module processes the data transmitted in S1 and performs data validity analysis. When the data processing mark is valid, it directly enters the processing conversion module and outputs the data. When the data processing mark is invalid, the data is repeated filled or repeatedly collected through the data processing correction module, and then enters the processing conversion module and outputs the data. S3, receives the data output in S2 through the early warning assessment model, then performs feature identification on the received data and encodes the feature identification data. Then, three algorithms, Logistic, XGBoost, and Random Forest, are used to perform multiple operations on the encoded features to perform risk assessment operations on the data. The final assessment structure is output after data decoding. S4. The decoded data is transmitted to the early warning analysis module. When the evaluation result exceeds the preset range value, the early warning information is transmitted to the terminal early warning device through the Internet module to implement an alarm. At the same time, the data exceeding the set range value is synchronously stored in the data storage module. When the evaluation result does not exceed the preset range value, the data is directly synchronously stored in the data storage module. The data in the data storage module is exported through the data export module to obtain a warning analysis report.

Images