Public health epidemic early warning method, system, terminal and medium based on big data

Abstract

The application discloses a public health epidemic early warning method and system based on big data, a terminal and a medium, and relates to the technical field of public health.The technical scheme is as follows: a patient data set containing personal information and medication information is acquired;trajectory information of the corresponding patient in a preset time period is retrieved according to the personal information, and a trajectory point correlation graph is constructed by fusion;trajectory points with trajectory density greater than a density threshold value in the trajectory point correlation graph are selected as target analysis points;trajectory information of all patients corresponding to the target analysis points is divided into trajectory groups under different space-time;the corresponding indication feature set is extracted according to the medication information of the patients, and the disease accumulation value of the corresponding trajectory points under the corresponding space-time is analyzed;when the disease accumulation value exceeds a similarity threshold value, a public health epidemic early warning signal of the corresponding trajectory points under the corresponding space-time is output.The application can timely and accurately warn and dispose of trajectory points and related personnel with public health epidemics.

Description

Technical Field

[0001] This invention relates to the field of public health technology, and more specifically, to a public health epidemic early warning method, system, terminal, and medium based on big data. Background Technology

[0002] Public health outbreaks mainly refer to events that affect public safety caused by infectious diseases, outbreaks of unexplained illnesses, etc. These events are characterized by their suddenness and unpredictability, but they also generally present with the same or similar symptoms, such as the novel coronavirus.

[0003] Currently, public health outbreaks are primarily identified by hospital doctors based on a surge in patient numbers and pathological analysis. After initial confirmation of an outbreak, tracing the source based on the travel history of similar patients can effectively curb its further spread to some extent. However, because patients may visit hospitals in dispersed locations, limitations in data sharing and the influence of different medical teams make it difficult to detect large numbers of patients or similar symptoms in a timely manner. Furthermore, once patients develop symptoms, they generally seek treatment at the nearest medical institution, such as community hospitals, clinics, and pharmacies. Limited access to medical resources can further hinder the timely detection of public health outbreaks.

[0004] Therefore, how to research and design a public health epidemic early warning method, system, terminal and medium based on big data that can overcome the above-mentioned defects is an urgent problem that we need to solve. Summary of the Invention

[0005] To address the shortcomings of existing technologies, the purpose of this invention is to provide a public health epidemic early warning method, system, terminal, and medium based on big data, which can provide timely and accurate early warning and handling of trajectory points and related personnel involved in public health epidemics.

[0006] The above-mentioned technical objective of the present invention is achieved through the following technical solution:

[0007] Firstly, it provides a public health epidemic early warning method based on big data, including the following steps:

[0008] Obtain a patient database containing personal and medication information recorded by at least one medical institution within the target area;

[0009] Based on personal information, retrieve the trajectory information of the corresponding patients within a preset time period, and merge the trajectory information of all patients to construct a trajectory point association map;

[0010] Trajectory points with a trajectory density greater than a density threshold in the trajectory point association graph are selected as target analysis points;

[0011] The trajectory information of all patients corresponding to the target analysis point is divided into trajectory groups under different time and space conditions;

[0012] Extract the corresponding indication feature set based on the patient's medication information, and analyze the cumulative symptom value of the corresponding trajectory point in the corresponding time and space based on the indication feature set of all patients in the trajectory group;

[0013] When the cumulative value of symptoms exceeds a similar threshold, a public health epidemic early warning signal is output for the corresponding trajectory point in the corresponding time and space.

[0014] Furthermore, each drug in the medication information corresponds to an indication feature set, and the feature value of each indication feature in the indication feature set is the reciprocal of the number of indications.

[0015] Furthermore, the specific process for obtaining the cumulative value of the symptoms is as follows:

[0016] The number of patients with the same indication in the statistical trajectory group is counted, and the indication feature with more than the preset number of patients is selected as the early warning analysis feature;

[0017] Calculate the patient characteristic values ​​for the same indication for different patients;

[0018] The total characteristic value of all patients for the same indication is calculated by summing the patient characteristic values.

[0019] The cumulative symptom value is calculated by summing the feature values ​​of all early warning analysis features.

[0020] Furthermore, the formula for calculating the cumulative value of the symptoms is as follows:

[0021]

[0022] in, express The cumulative value of symptoms corresponding to each early warning analysis feature; Indicates the first The patient belongs to the first Among the drugs, for the first The characteristic values ​​of each early warning analysis feature; Indicates the first The number of drugs containing early warning analysis features per patient; This indicates the number of patients in the trajectory group who share the same indication characteristics.

[0023] Furthermore, the formula for calculating the cumulative value of the symptoms is as follows:

[0024]

[0025] in, express The cumulative value of symptoms corresponding to each early warning analysis feature; Indicates the first The patient belongs to the first Among the drugs, for the first The characteristic values ​​of each early warning analysis feature; Indicates the first The number of drugs containing early warning analysis features per patient; This indicates the number of patients in the trajectory group who exhibit the same indication characteristics; Represents trajectory points In space and time The number of people in circulation.

[0026] Furthermore, the medical institutions include hospitals, clinics, and pharmacies.

[0027] Furthermore, the trajectory density is the overlap frequency of corresponding trajectory points in the trajectory point association graph.

[0028] Secondly, it provides a public health epidemic early warning system based on big data, including:

[0029] The information collection module is used to acquire patient data sets containing personal and medication information recorded by at least one medical institution within the target area;

[0030] The trajectory fusion module is used to retrieve the trajectory information of the corresponding patient within a preset time period based on personal information, and to merge the trajectory information of all patients to construct a trajectory point association map.

[0031] The trajectory filtering module is used to filter out trajectory points in the trajectory point association graph whose trajectory density is greater than the density threshold as target analysis points.

[0032] The trajectory segmentation module is used to divide the trajectory information of all patients corresponding to the target analysis point into trajectory groups under different time and space conditions;

[0033] The symptom analysis module is used to extract the corresponding indication feature set based on the patient's medication information, and to analyze the cumulative symptom value of the corresponding trajectory point in the corresponding time and space based on the indication feature set of all patients in the trajectory group.

[0034] The early warning judgment module is used to output a public health epidemic early warning signal for the corresponding trajectory point in the corresponding time and space when the cumulative value of symptoms exceeds the similar threshold.

[0035] Thirdly, a computer terminal is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the big data-based public health epidemic early warning method as described in any one of the first aspects.

[0036] Fourthly, a computer-readable medium is provided having a computer program stored thereon, the computer program being executed by a processor to implement the big data-based public health epidemic early warning method as described in any one of the first aspects.

[0037] Compared with the prior art, the present invention has the following beneficial effects:

[0038] 1. The public health epidemic early warning method based on big data proposed in this invention establishes a patient data set for each patient's drug purchases and analyzes the correlation between patients' drug purchases based on patients' trajectory information and drug indications. It can quickly analyze and obtain the cumulative value of symptoms that characterizes the possibility of different patients being affected by public health epidemics at the same trajectory point and in the same time and space. At the same time, it filters some trajectory points based on density thresholds, which effectively reduces the workload of public health epidemic early warning analysis and enables timely and accurate early warning and handling of trajectory points and related personnel with public health epidemics.

[0039] 2. The cumulative symptom value calculation of this invention without considering the basic number of people in circulation is applicable to large-scale, high-density public health epidemic early warning analysis;

[0040] 3. This invention calculates the cumulative symptom value corresponding to the basic number of people in circulation, making it applicable to small-scale, low-density public health epidemic early warning analysis, and has a wide range of applications. Attached Figure Description

[0041] The accompanying drawings, which are included to provide a further understanding of embodiments of the invention and form part of this application, do not constitute a limitation thereof. In the drawings:

[0042] Figure 1 This is a flowchart from an embodiment of the present invention;

[0043] Figure 2 This is a system block diagram in an embodiment of the present invention. Detailed Implementation

[0044] To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the embodiments and accompanying drawings. The illustrative embodiments and descriptions of the present invention are only used to explain the present invention and are not intended to limit the present invention.

[0045] Example 1: A public health epidemic early warning method based on big data, such as Figure 1 As shown, it includes the following steps:

[0046] S1: Obtain a patient data set containing personal and medication information recorded by at least one medical institution within the target area; medical institutions include, but are not limited to, hospitals, clinics, and pharmacies;

[0047] S2: Retrieve the trajectory information of the corresponding patient within a preset time period based on personal information, and merge the trajectory information of all patients to construct a trajectory point association map; the trajectory information can be obtained through mobile network communication system positioning;

[0048] S3: Select trajectory points in the trajectory point association graph whose trajectory density is greater than the density threshold as target analysis points; the trajectory density can be determined by the overlap frequency of the corresponding trajectory points in the trajectory point association graph.

[0049] S4: Divide the trajectory information of all patients corresponding to the target analysis point into trajectory groups under different spatiotemporal conditions; under the same spatiotemporal condition, it means that different patients pass through the same trajectory point in the same time period;

[0050] S5: Extract the corresponding indication feature set based on the patient's medication information, and analyze the cumulative symptom value of the corresponding trajectory point in the corresponding time and space based on the indication feature set of all patients in the trajectory group;

[0051] S6: Output the public health epidemic early warning signal for the corresponding trajectory point in the corresponding time and space when the cumulative value of symptoms exceeds the similarity threshold.

[0052] In this embodiment, each drug in the medication information corresponds to an indication feature set, and the feature value of each indication feature in the indication feature set is the reciprocal of the number of indications.

[0053] The specific process for obtaining the cumulative symptom value analysis is as follows: count the number of patients with the same indication feature in the trajectory group, and select the indication feature with more than the preset number of patients as the early warning analysis feature; calculate the patient feature value for the same indication feature for different patients; sum the patient feature values ​​to obtain the total feature value for the same indication feature for all patients; and calculate the cumulative symptom value based on the sum of the feature values ​​of all early warning analysis features.

[0054] As an optional implementation method, the formula for calculating the cumulative symptom value is as follows:

[0055]

[0056] in, express The cumulative value of symptoms corresponding to each early warning analysis feature; Indicates the first The patient belongs to the first Among the drugs, for the first The characteristic values ​​of each early warning analysis feature; Indicates the first The number of drugs containing early warning analysis features per patient; This indicates the number of patients in the trajectory group who share the same indication characteristics.

[0057] The invention calculates the cumulative symptom value without considering the basic number of people in circulation, making it applicable to large-scale, high-density public health epidemic early warning analysis.

[0058] As another optional implementation method, the formula for calculating the cumulative symptom value is as follows:

[0059]

[0060] in, express The cumulative value of symptoms corresponding to each early warning analysis feature; Indicates the first The patient belongs to the first Among the drugs, for the first The characteristic values ​​of each early warning analysis feature; Indicates the first The number of drugs containing early warning analysis features per patient; This indicates the number of patients in the trajectory group who exhibit the same indication characteristics; Represents trajectory points In space and time The number of people in circulation.

[0061] This invention calculates the cumulative symptom value based on the basic number of people in circulation, making it applicable to small-scale, low-density public health epidemic early warning analysis, and thus has a wide range of applications.

[0062] Example 2: A public health epidemic early warning system based on big data. This public health epidemic early warning system is used to implement the public health epidemic early warning method described in Example 1, such as... Figure 2 As shown, it includes an information collection module, a trajectory fusion module, a trajectory filtering module, a trajectory division module, a symptom analysis module, and an early warning judgment module.

[0063] The system comprises the following modules: Information Collection Module: Acquires patient data sets containing personal and medication information from at least one medical institution within the target area. Trajectory Fusion Module: Retrieves trajectory information of corresponding patients within a preset time period based on personal information and merges the trajectory information of all patients to construct a trajectory point association map. Trajectory Filtering Module: Filters trajectory points in the trajectory point association map with a trajectory density greater than a density threshold as target analysis points. Trajectory Division Module: Divides the trajectory information of all patients corresponding to the target analysis point into trajectory groups under different spatiotemporal conditions. Disease Analysis Module: Extracts corresponding indication feature sets based on patients' medication information and analyzes the cumulative disease value of the corresponding trajectory point in the corresponding spatiotemporal region based on the indication feature sets of all patients in the trajectory group. Early Warning Judgment Module: Outputs a public health epidemic early warning signal for the corresponding trajectory point in the corresponding spatiotemporal region when the cumulative disease value exceeds a similarity threshold.

[0064] Working principle: This invention establishes a patient database for each patient's medication purchases and analyzes the correlation between patients' medication purchases based on their trajectory information and medication indications. This allows for rapid analysis of the cumulative symptom value representing the likelihood of different patients being affected by public health emergencies at the same trajectory point and in the same time and space. Simultaneously, it filters some trajectory points based on density thresholds, effectively reducing the workload of public health emergency early warning analysis. This enables timely and accurate early warning and response to trajectory points and related personnel where public health emergencies exist.

[0065] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied 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.

[0066] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0067] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0068] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0069] The above specific embodiments further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A public health epidemic early warning method based on big data, characterized by: Includes the following steps: Obtain a patient database containing personal and medication information recorded by at least one medical institution within the target area; Based on personal information, retrieve the trajectory information of the corresponding patients within a preset time period, and merge the trajectory information of all patients to construct a trajectory point association map; Trajectory points with a trajectory density greater than a density threshold in the trajectory point association graph are selected as target analysis points; The trajectory information of all patients corresponding to the target analysis point is divided into trajectory groups under different time and space conditions; Based on the patient's medication information, the corresponding indication feature set is extracted. Then, based on the indication feature sets of all patients in the trajectory group, the cumulative symptom value of the corresponding trajectory point in the corresponding time and space is analyzed. Each drug in the medication information corresponds to one indication feature set, and the feature value of each indication feature in the indication feature set is the reciprocal of the number of indications. Specifically, the process of obtaining the cumulative symptom value is as follows: The number of patients with the same indication feature in the statistical trajectory group is counted, and the indication feature with more than the preset number of patients is selected as the early warning analysis feature. The feature value of the indication feature is used to calculate the patient feature value of different patients for the same indication feature. The feature value of all patients for the same indication feature is calculated by summing the patient feature values. The cumulative value of the disease is calculated based on the sum of the feature values ​​of all early warning analysis features. When the cumulative value of symptoms exceeds a similar threshold, a public health epidemic early warning signal is output for the corresponding trajectory point in the corresponding time and space.

2. The public health epidemic early warning method based on big data according to claim 1, characterized in that, The specific formula for calculating the cumulative value of the disease is as follows: in, express The cumulative value of symptoms corresponding to each early warning analysis feature; Indicates the first The patient belongs to the first Among the drugs, for the first The characteristic values ​​of each early warning analysis feature; Indicates the first The number of drugs containing early warning analysis features per patient; This indicates the number of patients in the trajectory group who share the same indication characteristics.

3. The public health epidemic early warning method based on big data according to claim 1, characterized in that, The specific formula for calculating the cumulative value of the disease is as follows: in, express The cumulative value of symptoms corresponding to each early warning analysis feature; Indicates the first The patient belongs to the first Among the drugs, for the first The characteristic values ​​of each early warning analysis feature; Indicates the first The number of drugs containing early warning analysis features per patient; This indicates the number of patients in the trajectory group who exhibit the same indication characteristics; Represents trajectory points In space and time The number of people in circulation.

4. The public health epidemic early warning method based on big data according to claim 1, characterized in that, The medical institutions mentioned include hospitals, clinics, and pharmacies.

5. The public health epidemic early warning method based on big data according to claim 1, characterized in that, The trajectory density is the frequency of overlap of corresponding trajectory points in the trajectory point association graph.

6. A public health epidemic early warning system based on big data, characterized by: include: The information collection module is used to acquire patient data sets containing personal and medication information recorded by at least one medical institution within the target area; The trajectory fusion module is used to retrieve the trajectory information of the corresponding patient within a preset time period based on personal information, and to merge the trajectory information of all patients to construct a trajectory point association map. The trajectory filtering module is used to filter out trajectory points in the trajectory point association graph whose trajectory density is greater than the density threshold as target analysis points. The trajectory segmentation module is used to divide the trajectory information of all patients corresponding to the target analysis point into trajectory groups under different time and space conditions; The symptom analysis module is used to extract corresponding indication feature sets based on the patient's medication information, and to analyze the cumulative symptom value of the corresponding trajectory point in the corresponding time and space based on the indication feature sets of all patients in the trajectory group. Each drug in the medication information corresponds to an indication feature set, and the feature value of each indication feature in the indication feature set is the reciprocal of the number of indications. The specific process for obtaining the cumulative symptom value is as follows: The number of patients with the same indication feature in the statistical trajectory group is counted, and the indication feature with more than the preset number of patients is selected as the early warning analysis feature. The feature value of the indication feature is used to calculate the patient feature value of different patients for the same indication feature. The feature value of all patients for the same indication feature is calculated by summing the patient feature values. The cumulative value of the disease is calculated based on the sum of the feature values ​​of all early warning analysis features. The early warning judgment module is used to output a public health epidemic early warning signal for the corresponding trajectory point in the corresponding time and space when the cumulative value of symptoms exceeds the similar threshold.

7. A computer terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the big data-based public health epidemic early warning method as described in any one of claims 1-5.

8. A computer-readable medium having a computer program stored thereon, characterized in that, The computer program, when executed by a processor, can implement the big data-based public health epidemic early warning method as described in any one of claims 1-5.

Images