CN112562862A - Epidemic situation information identification method, device and equipment - Google Patents
Epidemic situation information identification method, device and equipment Download PDFInfo
- Publication number
- CN112562862A CN112562862A CN202011478200.XA CN202011478200A CN112562862A CN 112562862 A CN112562862 A CN 112562862A CN 202011478200 A CN202011478200 A CN 202011478200A CN 112562862 A CN112562862 A CN 112562862A
- Authority
- CN
- China
- Prior art keywords
- epidemic situation
- epidemic
- information
- situation
- probability
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/80—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for detecting, monitoring or modelling epidemics or pandemics, e.g. flu
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Abstract
The application provides an epidemic situation information identification method, device and equipment, and the method comprises the following steps: acquiring epidemic situation basic data and affiliated region information of an epidemic situation object; generating an epidemic situation characteristic set of the epidemic situation object according to the epidemic situation basic data; and identifying epidemic situation state information of the epidemic situation object according to the epidemic situation feature set and the region information. According to the epidemic situation basic data and the affiliated regional information of the epidemic situation object, the epidemic situation state information of the epidemic situation object is identified. The accuracy of epidemic situation information identification is improved, the occurrence state of the epidemic situation is found in advance, and the epidemic situation monitoring efficiency is improved.
Description
Technical Field
The application relates to the technical field of information processing, in particular to an epidemic situation information identification method, device and equipment.
Background
The disease monitoring information system is an interoperation information system used for capturing and analyzing disease data in real time, realizing seamless connection of multiple monitoring information systems, monitoring and evaluating disease development trends, determining public health emergencies, and guiding prevention, monitoring and treatment of diseases. The system mainly comprises an infectious disease network report information system and an emergent public health incident report and management information system. Monitoring is widely applied in a plurality of fields of social science and natural science as a scientific research method for continuously and systematically collecting, analyzing and feeding back data.
The occurrence, development and distribution of diseases are closely related to geographical environment, climate and human environment. The general disease monitoring information system adopts a single-factor, static and qualitative monitoring and analyzing method to monitor and analyze the disease information, which is often not timely and comprehensive enough.
Disclosure of Invention
An object of the embodiments of the present application is to provide a method, an apparatus, and a device for identifying epidemic situation information, which are used to identify epidemic situation state information of an epidemic situation object according to epidemic situation basic data and affiliated regional information of the epidemic situation object.
A first aspect of an embodiment of the present application provides an epidemic situation information identification method, including: acquiring epidemic situation basic data and affiliated region information of an epidemic situation object; generating an epidemic situation characteristic set of the epidemic situation object according to the epidemic situation basic data; and identifying epidemic situation state information of the epidemic situation object according to the epidemic situation feature set and the region information.
In an embodiment, the generating the epidemic situation feature set of the epidemic situation object according to the epidemic situation basic data includes: analyzing the epidemic situation basic data according to a preset parameter type; generating an epidemic situation characteristic set of the epidemic situation object according to the analysis result, wherein the epidemic situation characteristic set comprises: one or more of epidemiological characteristic data, symptom characteristic data, and laboratory test result data.
In an embodiment, the identifying epidemic situation state information of the epidemic situation object according to the epidemic situation feature set and the regional information includes: inquiring at least one epidemic type with the epidemic characteristic set in a first database; counting the conditional probability of each epidemic situation feature in the epidemic situation feature set in each epidemic situation type; and identifying epidemic situation state information of the epidemic situation object according to the conditional probability and the region information.
In an embodiment, the identifying the epidemic situation state information of the epidemic situation object according to the conditional probability and the regional information includes: respectively inquiring the prior probability of each epidemic situation type in a second database according to the region information; calculating the posterior probability of each epidemic type of the epidemic object according to the conditional probability and the prior probability; and generating the epidemic situation state information according to the posterior probability.
In an embodiment, the generating the epidemic situation state information according to the posterior probability includes: sequencing all the epidemic types in turn according to the sequence of the posterior probability from large to small; and outputting the sequencing result of each epidemic situation type as epidemic situation state information of the epidemic situation object.
In one embodiment, the method further comprises: calculating the epidemic situation grade of the epidemic situation object according to the epidemic situation state information; and when the epidemic situation level exceeds a safety threshold value, sending out alarm information.
A second aspect of the embodiments of the present application provides an epidemic situation information identification apparatus, including: the acquisition module is used for acquiring epidemic situation basic data and affiliated region information of the epidemic situation object; the generating module is used for generating an epidemic situation characteristic set of the epidemic situation object according to the epidemic situation basic data; and the identification module is used for identifying the epidemic situation state information of the epidemic situation object according to the epidemic situation feature set and the region information.
In one embodiment, the generating module is configured to: analyzing the epidemic situation basic data according to a preset parameter type; generating an epidemic situation characteristic set of the epidemic situation object according to the analysis result, wherein the epidemic situation characteristic set comprises: one or more of epidemiological characteristic data, symptom characteristic data, and laboratory test result data.
In one embodiment, the identification module is configured to: inquiring at least one epidemic type with the epidemic characteristic set in a first database; counting the conditional probability of each epidemic situation feature in the epidemic situation feature set in each epidemic situation type; and identifying epidemic situation state information of the epidemic situation object according to the conditional probability and the region information.
In an embodiment, the identifying the epidemic situation state information of the epidemic situation object according to the conditional probability and the regional information includes: respectively inquiring the prior probability of each epidemic situation type in a second database according to the region information; calculating the posterior probability of each epidemic type of the epidemic object according to the conditional probability and the prior probability; and generating the epidemic situation state information according to the posterior probability.
In an embodiment, the generating the epidemic situation state information according to the posterior probability includes: sequencing all the epidemic types in turn according to the sequence of the posterior probability from large to small; and outputting the sequencing result of each epidemic situation type as epidemic situation state information of the epidemic situation object.
In one embodiment, the apparatus further comprises: the computing module is used for computing the epidemic situation grade of the epidemic situation object according to the epidemic situation state information; and the alarm module is used for sending out alarm information when the epidemic situation grade exceeds a safety threshold value.
A third aspect of embodiments of the present application provides an electronic device, including: a memory to store a computer program; a processor configured to execute the method of the first aspect and any embodiment thereof of the embodiments of the present application to identify epidemic status information of an epidemic object.
The application provides an epidemic situation information identification method, device and equipment, collect the epidemic situation basic information of epidemic situation object at first, and the regional information that the epidemic situation object belongs to, then through carrying out data analysis to epidemic situation basic information, obtain the epidemic situation characteristic set of epidemic situation object from it, the contact between epidemic situation characteristic set and the regional information is considered comprehensively, and then the epidemic situation state information of this epidemic situation object is discerned, the rate of accuracy of epidemic situation information identification has been improved, help discovering the emergence state of epidemic situation in advance, the epidemic situation monitoring efficiency is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and that those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.
Fig. 1 is a schematic structural diagram of an electronic device according to an embodiment of the present application;
fig. 2 is a schematic view of an epidemic situation information monitoring scenario according to an embodiment of the present application;
fig. 3 is a schematic flow chart illustrating an epidemic situation information identification method according to an embodiment of the present application;
fig. 4A is a schematic flowchart of an epidemic situation information identification method according to an embodiment of the present application;
FIG. 4B is a schematic view of a Bayesian classification model according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an epidemic situation information identification apparatus according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application. In the description of the present application, the terms "first," "second," and the like are used solely to distinguish one from another and are not to be construed as indicating or implying relative importance.
As shown in fig. 1, the present embodiment provides an electronic apparatus 1 including: at least one processor 11 and a memory 12, one processor being exemplified in fig. 1. The processor 11 and the memory 12 are connected through the bus 10, and the memory 12 stores instructions executable by the processor 11, and the instructions are executed by the processor 11, so that the electronic device 1 can execute all or part of the flow of the method in the embodiments described below, so as to identify the epidemic situation information of the epidemic situation object according to the epidemic situation basic data and the affiliated area information of the epidemic situation object.
In an embodiment, the electronic device 1 may be a mobile phone, a notebook computer, a desktop computer, or the like.
Please refer to fig. 2, which is a schematic view of an epidemic situation information monitoring scenario according to an embodiment of the present application, including: a data collection platform 210, a monitoring server 220, and a user terminal 230, wherein:
the data collection platform 210 is configured to collect epidemic situation basic data of epidemic situation objects, where the epidemic situation objects may be people or may be special groups in humans, such as students. Taking a student as an example, the data collection platform 210 may establish a data sharing mechanism with a platform associated with the student, for example, the data collection platform 210 may interface a school data platform where the student is located, a disease control data platform to which the student belongs, a hospital data platform where the student attends a doctor, a home data terminal of the student, and the like, so as to obtain epidemic situation basic data of the student from the above platform in real time.
The monitoring server 220 may be implemented by the electronic device 1, and may establish a data sharing mechanism with the data collection platform 210, so as to obtain epidemic situation basic data and affiliated area information of the epidemic situation object from the data collection platform 210 in real time.
The user terminal 230, taking a student as an example, the user terminal 230 may be a mobile phone, a computer, or other devices of a parent of the student, and may send the epidemic situation information of the student to the user terminal 230, so that the parent can find the epidemic situation of the student in time.
In an embodiment, the user terminal 230 may be a mobile phone, an operation interface of the mobile phone is accessed by a preset account of a corresponding regional disease prevention control center (hereinafter, referred to as a disease control center), and when a parent requests for a student to leave and report a symptom by self, the parent needs to open the preset account of the disease control center to log in. Because the preset account number contains rich infectious diseases, especially the disease prevention knowledge of the currently popular or early-warning infectious diseases, parents can passively learn related knowledge in the login process, so that the vast parents obtain a large amount of health disease prevention knowledge through the use process of the monitoring system (the monitoring server 220), and the self prevention consciousness of the infectious diseases of the parents and students is improved. The monitoring system is bound with a preset account and synchronously developed (for example, a district disease prevention control center applies for WeChat 'disease control and micro health' public number, a page link of the monitoring system is accessed in a column in the public number, a user enters the public number and can enter a system login interface by clicking at a corresponding position), and the additional benefit of the system is maximized. Similarly, the benefit coverage of the mode is simultaneously expanded to system users such as office officers, school doctors, community doctors and the like.
In one embodiment, the monitoring system can automatically recognize the user operation, and the system automatically recognizes and judges the health knowledge acquisition requirement of the user by taking the operation action as a recognition condition, such as selection of symptoms, selection of disease names, viewing and browsing of student leave information and the like, and automatically pushes articles or health prompts meeting the requirement to the user through WeChat, so that accurate service of health knowledge propagation is realized.
Please refer to fig. 3, which is a method for identifying epidemic situation information according to an embodiment of the present application, and the method can be executed by the electronic device 1 shown in fig. 1 as the monitoring server 220, and can be applied to the epidemic situation information monitoring scene shown in fig. 2, so as to identify the epidemic situation state information of an epidemic situation object according to the epidemic situation basic data and the belonging area information of the epidemic situation object. The method comprises the following steps:
step 301: acquiring epidemic situation basic data and affiliated area information of the epidemic situation object.
In this step, the epidemic situation basic data can be obtained by interfacing with the data collection platform 210. Taking students as an example, the epidemic situation basic data can be: diagnosis and treatment information of students in hospitals, symptom information of students, lesson absence information of students in schools, information that parents of students ask for students to leave, and the like.
In one embodiment, the epidemic situation object can be divided into regional information according to the geographic location or the administrative location. For example, in the area a, the community health service organization is used as a center, schools scattered in various places are used as unit grids, and epidemic situation basic data of each student and area information to which the student belongs are stored in an associated manner.
In one embodiment, the system can automatically acquire various health data by continuously collecting the demographic information, the geographic information, the environmental information, the meteorological information, the health information of family members of students, the family address information and other information in the area a, and simultaneously docking with health-related information systems such as an infectious disease report information system, a physical examination information system and a vaccination information system of students, and matching the health data with the student information. For example, the student health database is constructed by clinical information such as symptoms reported when the student leaves, physical signs of physical examination in doctor, abnormal results of laboratory examination and the like.
Step 302: and generating an epidemic situation characteristic set of the epidemic situation object according to the epidemic situation basic data.
In the step, the data analysis is carried out on the basic epidemic situation data of the students, so that characteristic data representing the epidemic situation state of the students are obtained, and an epidemic situation characteristic set is formed.
Step 303: and identifying epidemic situation state information of the epidemic situation object according to the epidemic situation feature set and the region information.
In the step, the relevance between the epidemic situation characteristic set of the student and the regional information to which the student belongs is comprehensively considered, and the epidemic situation state information of the student is identified so as to monitor the health state of the student in real time and improve the disease defense safety.
According to the epidemic situation information identification method, data such as diagnosis and treatment, symptoms, lessons lack, leave requests and the like of students are used as basic data of the epidemic situation to carry out joint analysis and evaluation, and the epidemic situation state information of the students is identified by combining the regional information of the students, so that health units in unit grids such as health service stations, communities, schools and parents in the grids can obtain early warning information of infectious diseases at the first time and carry out early intervention at the first time. The gridding data sharing mode can eliminate school infectious diseases in each grid in an early stage, and the epidemic situation monitoring efficiency is improved.
Please refer to fig. 4A, which is a method for identifying epidemic situation information according to an embodiment of the present application, and the method can be executed by the electronic device 1 shown in fig. 1 as the monitoring server 220, and can be applied to the epidemic situation information monitoring scene shown in fig. 2, so as to identify the epidemic situation state information of an epidemic situation object according to the epidemic situation basic data and the belonging area information of the epidemic situation object. The method comprises the following steps:
step 401: acquiring epidemic situation basic data and affiliated area information of the epidemic situation object. See the description of step 301 in the above embodiments for details.
Step 402: and analyzing the epidemic situation basic data according to the preset parameter types.
In this step, the preset parameter type is a parameter type that can represent epidemic situation characteristics of an epidemic situation object. Multiple preset parameter types can be set based on historical epidemic data and reference material. Analyzing the epidemic situation basic data based on a plurality of preset parameter types, and generating an analysis result.
In one embodiment, before setting the predetermined parameter type, the disease type object for which the parameter is directed is determined. Taking students as epidemic situation objects as an example, the main disease species of the school infectious disease outbreak epidemic situation of the Q district of P city, which forms the Q district, are combed by comprehensively sorting and analyzing the infectious disease outbreak epidemic situation of the school since 2015, and the key infectious disease needing to be screened is finally determined by combining with the key strategy of national infectious disease prevention and control. Then, a parameter database is established based on the determined main disease species. For example, the parameter types of the parameter database are determined according to a large amount of data such as various textbooks, professional books, domestic and foreign documents, domestic and foreign professional websites, infectious disease epidemic situation statistical data, infectious disease outbreak epidemic situation survey reports and the like.
Step 403: and generating an epidemic situation characteristic set of the epidemic situation object according to the analysis result, wherein the epidemic situation characteristic set comprises: one or more of epidemiological characteristic data, symptom characteristic data, and laboratory test result data.
In the step, a data set matched with the preset parameter type is extracted from the analysis result in the epidemic situation basic data to serve as an epidemic situation characteristic set. Taking students as an example, the epidemiological characteristic data of the student A is as follows: male, 8 years old, and family. The symptom characteristic data of student A is as follows: fever, cough, rash, etc. The laboratory examination result data of student A is as follows: leukocyte reduction, etc. The data sets jointly form an epidemic situation characteristic set.
In an embodiment, the epidemic situation feature set may further include geographic location information, weather information, medicine taking information, and the like of the related epidemic situation object.
Step 404: and querying at least one epidemic type with an epidemic characteristic set in the first database.
In this step, the first database may be a disease species database established based on historical epidemic situation data. For example, taking students as epidemic situation objects as an example, by comprehensively sorting and analyzing the epidemic outbreak situations occurring in schools since the year 2015 of the Q area in P city, the main disease species of the school infectious outbreak situations forming the Q area are combed out, and the key infectious disease species needing to be screened is finally determined by combining with the key strategy of national infectious disease prevention and control. An epidemic type may represent a disease species. Each disease species has specific epidemic characteristics, such as influenza disease species, and patients have cough characteristics. But different disease species may have the same epidemic characteristics. And screening all disease seeds meeting the epidemic situation characteristic set in the step 403 from the disease seed database. For example, the possible infectious disease species finally screened based on the epidemic situation characteristic set of the student A are as follows: influenza, hand-foot-and-mouth disease.
Step 405: and (4) counting the conditional probability of each epidemic characteristic in each epidemic type in the epidemic characteristic set.
In this step, a naive bayes classification algorithm can be used to establish an epidemic situation statistical model, as shown in fig. 4B, the principle is as follows:
(1) let disease set D ═ D (D) consisting of j kinds of diseases in the disease type database (first database)1，D2，……，Dj) J is a positive integer, assuming that the j diseases are mutually exclusive, i.e. the same patient can only suffer from one disease and not suffer from the same disease at the same timeTwo or more diseases, and the prior probability of each disease occurrence is known as: p (D1, P (D2) … P (dj)).
(2) An epidemic situation characteristic set S consisting of k kinds of epidemic situation characteristics (including symptom signs, laboratory examination results and epidemiological characteristics) in total is setGeneral assembly：
SGeneral assembly＝{S1，S2，，，Sk}
It is assumed that the epidemic characteristics are independent from each other, i.e. whether one epidemic characteristic appears or not is independent from the appearance or not of other epidemic characteristics.
And the conditional probability of each epidemic situation characteristic in the epidemic situation characteristic set under each disease occurrence condition is known:
P(Sl|Dl)，P(S2|DI)，，，P(Sk|Dl)
P(SI|D2)，P(S2|D2)，，，P(Sk|D2)
……………
P(SI|Dj)，P(S2|Dj)，，，P(Sk|Dj)
k is a positive integer, and the conditional probability of each epidemic feature in the epidemic feature set under each disease occurrence condition is known: p (S1| Dj), P (S2| Dj),, P (Sk | Dj).
(3) If the epidemic situation characteristic set S of the student A consists of n (n is a positive integer) kinds of epidemic situation characteristics (including symptom signs, laboratory examination results and epidemiological characteristics), the epidemic situation characteristic set S of the student A is { S ═ S1，S2，……，Sn}. The conditional probabilities of occurrence of the epidemic situation features in the epidemic situation feature set S under the occurrence conditions of the diseases in the disease set D can be obtained based on historical epidemic situation data statistics and are respectively as follows:
P(S|D1)＝P(Sl|Dl)×P(S2|Dl)×…×P(Sn|Dl)
P(S|D2)＝P(Sl|D2)×P(S2|D2)×…×P(Sn|D2)
……………
P(S|Dj)＝P(S1|Dj)×P(S2|Dj)×…×P(Sn|Dj)
then step 406 is entered to identify epidemic situation state information of the epidemic situation object according to the conditional probability and the regional information.
In one embodiment, the established epidemic statistical model can be verified by using personal survey data of epidemic outbreaks of infectious diseases in the Q region and past schools. And calculating the frequencies of the 1 st bit and the first 3 bits of the output discrimination list of the correct discrimination result of the model, namely the first order discrimination probability and the first three order discrimination probability, so as to evaluate the discrimination effect of the model.
Step 406: and respectively inquiring the prior probability of each epidemic situation type in a second database according to the regional information.
In this step, the second database may be an epidemic situation occurrence probability database established based on the geographic environment, meteorological conditions and human conditions within the specific area information and the historical epidemic situation data. The prior probability of occurrence of each disease can be documented in a probabilistic database. For example, each disease D in the disease set D in the P.city Q region can be searchedjThe prior probabilities of occurrence are: p (D)1)，P(D2)，……，P(Dj)。
In one embodiment, the regional information may be specific to street information where the epidemic object is located.
Step 407: and calculating the posterior probability of each epidemic situation type of the epidemic situation object according to the conditional probability and the prior probability.
In this step, let us assume that the student A in the Q district of P city has epidemic situation feature set S ═ S1，S2，……，SnCalculating the posterior probability of each epidemic situation type of the student A according to the following formula:
wherein, P (D)fS) represents the posterior probability of the f-th disease in the disease set D of the student a in the presence of the epidemic feature set S. P (D)f) Indicates the f disease D in the disease set DfA priori probability of occurrence. P (S/D)f) Indicates disease DfConditional probability of occurrence of the epidemic feature set S under the occurrence condition. P (D)i) Indicates the ith disease D in the disease set DiA priori probability of occurrence. P (S/D)i) Indicates disease DiConditional probability of occurrence of the epidemic feature set S under the occurrence condition. P (S)m/Df) Indicates disease DfAnd the conditional probability of the m th epidemic situation characteristic in the epidemic situation characteristic set S under the occurrence condition. P (S)m/Di) Indicates disease DiAnd the conditional probability of the m th epidemic situation characteristic in the epidemic situation characteristic set S under the occurrence condition. Wherein f is a positive integer less than j, and m is a positive integer less than n. According to the above method, the posterior probabilities corresponding to all the epidemic types queried in step 404 are respectively calculated, and then step 408 is entered to calculate the posterior probabilities according to the posterior probability P (D)fand/S) generating epidemic situation state information.
Step 408: and sequencing all epidemic types in turn according to the sequence of the posterior probability from large to small.
In this step, in order to clarify the epidemic situation state of the student a, the posterior probabilities corresponding to the respective epidemic situation types obtained in step 407 are sequentially ordered from large to small.
Step 409: and outputting the sequencing result of each epidemic situation type as epidemic situation state information of the epidemic situation object.
In this step, the ranking result information of the posterior probability corresponding to each epidemic situation type is output, such as student a suffering from: the posterior probability of influenza is 70%. The posterior probability of hand-foot-and-mouth disease is 22% … …. According to P (D)fThe size of the disease/S) can judge the type of the disease of the student A, if P (Dg | S) is the largest in all j posterior probabilities, the probability that the student A suffers from the g-th disease in the disease set D is the largest for the epidemic situation characteristic set S. Therefore, the sequencing result can be used as a final identification result of epidemic situation state information of the student A.
In one embodiment, the classification model shown in fig. 4B can be programmed by using SAS (Statistical Analysis System) 9.i.3 software, for example, as follows:
description of the procedure: this procedure was used to build a bayesian classification model. According to the following description, the probability of various possible diseases can be calculated by inputting the disease area and the characteristic attribute (namely epidemic situation characteristics including symptom signs, laboratory examination results and epidemiological characteristics) in the corresponding process, and the diseases are classified by sequencing according to the probability and outputting a discrimination list.
The advantages of the Bayesian classification algorithm applied in this embodiment are as follows:
(1) the prior information is fully utilized, and the prior probability and the conditional probability are skillfully combined; and not one or several of the attributes determine the classification, but all attributes participate in the classification. The incidence of disease, clinical signs, laboratory indices and epidemiological characteristics are all related to disease classification, and this embodiment makes full use of various information to classify and distinguish diseases.
(2) The probability of the classification result can be described quantitatively, is expressed by the probability size, is more objective in a measuring mode, and can be used for making a posteriori inference. Step 410: and calculating the epidemic situation grade of the epidemic situation object according to the epidemic situation state information.
In this step, the epidemic situation grade of each student can be calculated according to the epidemic situation state information, and the efficiency of epidemic situation monitoring is improved accordingly. For example, a student health database can be established, a symptom monitoring system mainly collects data such as symptom/syndrome, disease diagnosis and the like, meanwhile, the symptom monitoring system is in butt joint with ports such as a national disease prevention control information management system, a P city student health examination system, a provincial immunity planning information management system, a Q region health platform and the like to realize data exchange, student identity data, hospital diagnosis data, health examination data, vaccination data and the like are automatically picked up, and the data are associated through names and identity card numbers to form the student health database.
In one embodiment, student health risks may be assessed based on a student health database. Firstly, an evaluation index system is established, and each index is weighted by combining literature retrieval and expert conference methods. And (3) carrying out normalization processing on data corresponding to each index through data conversion, calculating the relative risk value of each index by utilizing a TOPSIS (technique for Order Preference by Similarity to an Ideal solution) method, and then combining the weight value of each index to obtain the absolute risk value of each index.
In one embodiment, health data is continuously collected for each school and each grade student, and the grade and threshold of health risk for each age are calculated. And comparing the absolute risk value of a certain student with the risk threshold value to obtain the health grade of the student.
Step 411: and when the epidemic situation level exceeds the safety threshold value, sending out alarm information.
In this step, can compare student's epidemic situation grade and safety threshold value in real time to when the epidemic situation grade exceedes safety threshold value, send alarm information in real time. The alarm information may be sent to the user terminal 230 so that the parent user may know the epidemic situation of the student in real time.
According to the epidemic situation information identification method, the symptom information and the disease diagnosis information of students are taken as the basis, meanwhile, data butt joint with other various health related systems is achieved, the health data of the students are continuously acquired in multiple directions and multiple angles, health risk analysis is conducted on each student according to the data, and the monitoring system issues health prompts and related health knowledge to parents and schools in real time according to the analysis results.
By daily registration and reporting of student symptom monitoring information, the daily morbidity of students in schools in the whole area can be accurately mastered, and indexes such as student symptoms, family addresses, family member morbidity, hospital diagnosis and the like are collected. The method is characterized by utilizing the determined data of symptoms, signs, laboratory inspection results, epidemiological characteristics, disease morbidity and the like of important infectious diseases in schools to integrate the data of a plurality of monitoring systems such as infectious disease network direct report, school disease monitoring, pharmacy sales monitoring, hospital sentry point monitoring, meteorological monitoring and the like, and establishing a model by using a Bayesian classification algorithm. The auxiliary classification judgment model of the common infectious diseases of the students is established by applying the Bayesian classification algorithm, so that public health personnel can rapidly and scientifically identify the types of the epidemic situations, and strive for the first opportunity for the epidemic situation treatment, so that the pertinent control measures can be timely and effectively taken, clues are provided for the laboratory etiology detection, and the cost benefit of the epidemic situation treatment is improved.
The Bayesian classification algorithm is adopted for modeling, prior information is fully utilized, prior probability and conditional probability are combined, and the incidence of diseases, main symptoms/syndromes, clinical signs, laboratory indexes, epidemiological characteristics, geographic, meteorological and family attributes and the like are synthesized to participate in classification, so that accuracy of epidemic outbreak recognition is improved, and the aggregation of each syndrome in students on time and space is found in advance. Please refer to fig. 5, which is an epidemic situation information identification apparatus 500 according to an embodiment of the present application, and the apparatus can be applied to the electronic device 1 shown in fig. 1 and can be applied to the epidemic situation information monitoring scene shown in fig. 2 to identify the epidemic situation state information of an epidemic situation object according to the epidemic situation basic data and the belonging region information of the epidemic situation object. The device includes: the system comprises an acquisition module 501, a generation module 502 and an identification module 503, wherein the principle relationship of each module is as follows:
the obtaining module 501 is configured to obtain epidemic situation basic data and affiliated area information of an epidemic situation object. See the description of step 301 in the above embodiments for details.
The generating module 502 is configured to generate an epidemic situation feature set of an epidemic situation object according to the epidemic situation basic data. See the description of step 302 in the above embodiments for details.
The identifying module 503 is configured to identify epidemic situation state information of the epidemic situation object according to the epidemic situation feature set and the area information. See the description of step 304 in the above embodiments for details.
In one embodiment, the generating module 502 is configured to: and analyzing the epidemic situation basic data according to the preset parameter types. And generating an epidemic situation characteristic set of the epidemic situation object according to the analysis result, wherein the epidemic situation characteristic set comprises: one or more of epidemiological characteristic data, symptom characteristic data, and laboratory test result data. See the description of steps 402 to 403 in the above embodiments for details.
In one embodiment, the identification module 503 is configured to: and querying at least one epidemic type with an epidemic characteristic set in the first database. And (4) counting the conditional probability of each epidemic characteristic in each epidemic type in the epidemic characteristic set. And identifying epidemic situation state information of the epidemic situation object according to the conditional probability and the region information. See the above embodiments for a detailed description of steps 404 to 405.
In one embodiment, identifying epidemic situation state information of an epidemic situation object according to the conditional probability and the regional information includes: and respectively inquiring the prior probability of each epidemic situation type in a second database according to the regional information. And calculating the posterior probability of each epidemic situation type of the epidemic situation object according to the conditional probability and the prior probability. And generating epidemic situation state information according to the posterior probability. See the description of step 406 to step 407 in the above embodiments in detail.
In one embodiment, generating epidemic situation status information according to the posterior probability includes: and sequencing all epidemic types in turn according to the sequence of the posterior probability from large to small. And outputting the sequencing result of each epidemic situation type as epidemic situation state information of the epidemic situation object. See the description of steps 408 to 409 in the above embodiments for details.
In one embodiment, the apparatus further comprises: the calculating module 504 is configured to calculate an epidemic situation level of the epidemic situation object according to the epidemic situation state information. And the alarm module 505 is used for sending out alarm information when the epidemic situation level exceeds a safety threshold. Refer to the description of steps 410 to 411 in the above embodiments in detail.
For a detailed description of the epidemic situation information identification apparatus 500, please refer to the description of the related method steps in the above embodiments.
An embodiment of the present invention further provides a non-transitory electronic device readable storage medium, including: a program that, when run on an electronic device, causes the electronic device to perform all or part of the procedures of the methods in the above-described embodiments. The storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a Flash Memory (Flash Memory), a Hard Disk (Hard Disk Drive, abbreviated as HDD), a Solid State Drive (SSD), or the like. The storage medium may also comprise a combination of memories of the kind described above.
Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations fall within the scope defined by the appended claims.
Claims (10)
1. An epidemic situation information identification method is characterized by comprising the following steps:
acquiring epidemic situation basic data and affiliated region information of an epidemic situation object;
generating an epidemic situation characteristic set of the epidemic situation object according to the epidemic situation basic data;
and identifying epidemic situation state information of the epidemic situation object according to the epidemic situation feature set and the region information.
2. The method of claim 1, wherein generating an epidemic feature set of the epidemic object based on the epidemic basic data comprises:
analyzing the epidemic situation basic data according to a preset parameter type;
generating an epidemic situation characteristic set of the epidemic situation object according to the analysis result, wherein the epidemic situation characteristic set comprises: one or more of epidemiological characteristic data, symptom characteristic data, and laboratory test result data.
3. The method of claim 2, wherein said identifying epidemic status information of said epidemic subject based on said epidemic feature set and said regional information comprises:
inquiring at least one epidemic type with the epidemic characteristic set in a first database;
counting the conditional probability of each epidemic situation feature in the epidemic situation feature set in each epidemic situation type;
and identifying epidemic situation state information of the epidemic situation object according to the conditional probability and the region information.
4. The method of claim 3, wherein identifying the epidemic status information of the epidemic object based on the conditional probability and the regional information comprises:
respectively inquiring the prior probability of each epidemic situation type in a second database according to the region information;
calculating the posterior probability of each epidemic type of the epidemic object according to the conditional probability and the prior probability;
and generating the epidemic situation state information according to the posterior probability.
5. The method of claim 4, wherein generating the epidemic status information based on the posterior probability comprises:
sequencing all the epidemic types in turn according to the sequence of the posterior probability from large to small;
and outputting the sequencing result of each epidemic situation type as epidemic situation state information of the epidemic situation object.
6. The method of claim 1, further comprising:
calculating the epidemic situation grade of the epidemic situation object according to the epidemic situation state information;
and when the epidemic situation level exceeds a safety threshold value, sending out alarm information.
7. An epidemic situation information identification apparatus, comprising:
the acquisition module is used for acquiring epidemic situation basic data and affiliated region information of the epidemic situation object;
the generating module is used for generating an epidemic situation characteristic set of the epidemic situation object according to the epidemic situation basic data;
and the identification module is used for identifying the epidemic situation state information of the epidemic situation object according to the epidemic situation feature set and the region information.
8. The apparatus of claim 7, wherein the generating module is configured to:
analyzing the epidemic situation basic data according to a preset parameter type;
generating an epidemic situation characteristic set of the epidemic situation object according to the analysis result, wherein the epidemic situation characteristic set comprises: one or more of epidemiological characteristic data, symptom characteristic data, and laboratory test result data.
9. The apparatus of claim 8, wherein the identification module is configured to:
inquiring at least one epidemic type with the epidemic characteristic set in a first database;
counting the conditional probability of each epidemic situation feature in the epidemic situation feature set in each epidemic situation type;
identifying epidemic situation state information of the epidemic situation object according to the conditional probability and the region information;
according to the conditional probability and the region information, epidemic situation state information of the epidemic situation object is identified, and the method comprises the following steps:
respectively inquiring the prior probability of each epidemic situation type in a second database according to the region information;
calculating the posterior probability of each epidemic type of the epidemic object according to the conditional probability and the prior probability;
generating the epidemic situation state information according to the posterior probability;
generating the epidemic situation state information according to the posterior probability, comprising:
sequencing all the epidemic types in turn according to the sequence of the posterior probability from large to small;
outputting the sequencing result of each epidemic situation type as epidemic situation state information of the epidemic situation object; and the apparatus further comprises:
the computing module is used for computing the epidemic situation grade of the epidemic situation object according to the epidemic situation state information;
and the alarm module is used for sending out alarm information when the epidemic situation grade exceeds a safety threshold value.
10. An electronic device, comprising:
a memory to store a computer program;
a processor configured to perform the method of any one of claims 1 to 6 to identify epidemic status information of an epidemic subject.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011478200.XA CN112562862A (en) | 2020-12-15 | 2020-12-15 | Epidemic situation information identification method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011478200.XA CN112562862A (en) | 2020-12-15 | 2020-12-15 | Epidemic situation information identification method, device and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112562862A true CN112562862A (en) | 2021-03-26 |
Family
ID=75063693
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011478200.XA Pending CN112562862A (en) | 2020-12-15 | 2020-12-15 | Epidemic situation information identification method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112562862A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113871019A (en) * | 2021-12-06 | 2021-12-31 | 江西易卫云信息技术有限公司 | Disease public opinion monitoring method, system, storage medium and equipment |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101894309A (en) * | 2009-11-05 | 2010-11-24 | 南京医科大学 | Epidemic situation predicting and early warning method of infectious diseases |
| CN103310083A (en) * | 2012-03-09 | 2013-09-18 | 李晓松 | Infectious disease cluster detection and early warning system |
| KR20150098402A (en) * | 2014-02-20 | 2015-08-28 | 메티스정보주식회사 | An apparatus for modeling epidemic spreading area and the method thereof |
| CN107239647A (en) * | 2016-03-28 | 2017-10-10 | 孙少燕 | A kind of disease analysis system based on bayesian algorithm |
| KR101874994B1 (en) * | 2017-04-05 | 2018-08-02 | 동국대학교 산학협력단 | Device and method for predicting chances of norovirus infectious disease outbreak |
| CN109949930A (en) * | 2019-03-22 | 2019-06-28 | 武汉工程大学 | Animal epidemics diagnostic method and system based on Bayesian network |
| CN110377847A (en) * | 2019-07-15 | 2019-10-25 | 中国人民解放军军事科学院军事医学研究院 | A kind of electronic map visualization method and system towards epidemic distribution |
| CN111816324A (en) * | 2020-09-10 | 2020-10-23 | 平安国际智慧城市科技股份有限公司 | Epidemic situation monitoring method and device, epidemic situation prevention and control platform and readable storage medium |
| CN111916193A (en) * | 2020-08-07 | 2020-11-10 | 平安科技（深圳）有限公司 | Intelligent medical seeking method and device, computer equipment and storage medium |
-
2020
- 2020-12-15 CN CN202011478200.XA patent/CN112562862A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101894309A (en) * | 2009-11-05 | 2010-11-24 | 南京医科大学 | Epidemic situation predicting and early warning method of infectious diseases |
| CN103310083A (en) * | 2012-03-09 | 2013-09-18 | 李晓松 | Infectious disease cluster detection and early warning system |
| KR20150098402A (en) * | 2014-02-20 | 2015-08-28 | 메티스정보주식회사 | An apparatus for modeling epidemic spreading area and the method thereof |
| CN107239647A (en) * | 2016-03-28 | 2017-10-10 | 孙少燕 | A kind of disease analysis system based on bayesian algorithm |
| KR101874994B1 (en) * | 2017-04-05 | 2018-08-02 | 동국대학교 산학협력단 | Device and method for predicting chances of norovirus infectious disease outbreak |
| CN109949930A (en) * | 2019-03-22 | 2019-06-28 | 武汉工程大学 | Animal epidemics diagnostic method and system based on Bayesian network |
| CN110377847A (en) * | 2019-07-15 | 2019-10-25 | 中国人民解放军军事科学院军事医学研究院 | A kind of electronic map visualization method and system towards epidemic distribution |
| CN111916193A (en) * | 2020-08-07 | 2020-11-10 | 平安科技（深圳）有限公司 | Intelligent medical seeking method and device, computer equipment and storage medium |
| CN111816324A (en) * | 2020-09-10 | 2020-10-23 | 平安国际智慧城市科技股份有限公司 | Epidemic situation monitoring method and device, epidemic situation prevention and control platform and readable storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 牟瑾;吕秋莹;马汉武;王昕;: "深圳市传染病暴发疫情监测系统的建立与运行结果分析", 疾病监测, no. 09, pages 9 - 12 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113871019A (en) * | 2021-12-06 | 2021-12-31 | 江西易卫云信息技术有限公司 | Disease public opinion monitoring method, system, storage medium and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111916215B (en) | Cluster/chronic disease early automatic alarm, preliminary feature analysis and risk assessment system | |
| Best et al. | A comparison of Bayesian spatial models for disease mapping | |
| WO2021217867A1 (en) | Xgboost-based data classification method and apparatus, computer device, and storage medium | |
| CN112786205B (en) | Data model-based syndrome early warning method, device, medium and equipment | |
| Senders et al. | Natural language processing for automated quantification of brain metastases reported in free-text radiology reports | |
| Li et al. | Modelling and analysing the dynamics of disease progression from cross-sectional studies | |
| CN112151130B (en) | Decision support system based on literature retrieval and construction method | |
| CN111696656B (en) | Doctor evaluation method and device of Internet medical platform | |
| Umemoto et al. | A prescription trend analysis using medical insurance claim big data | |
| CN113362959A (en) | Sudden respiratory infectious disease risk prediction model for regional epidemic prevention and control | |
| CN110827159A (en) | Financial medical insurance fraud early warning method, device and terminal based on relational graph | |
| CN109192312B (en) | Intelligent management system and method for adverse events of heart failure patients | |
| Alshahrni et al. | An intelligent deep convolutional network based COVID-19 detection from chest X-rays | |
| Ha et al. | A unified comparison of user modeling techniques for predicting data interaction and detecting exploration bias | |
| CN112562862A (en) | Epidemic situation information identification method, device and equipment | |
| Kraemer et al. | The low dimensionality of development | |
| US20210225513A1 (en) | Method to Create Digital Twins and use the Same for Causal Associations | |
| US20150339602A1 (en) | System and method for modeling health care costs | |
| CN116153496A (en) | Neural network model training method and depression emotion detection method | |
| WO2022141929A1 (en) | Health self-test system, server, and health testing system | |
| Lingelbach et al. | Identifying the effects of COVID-19 on psychological well-being through unsupervised clustering for mixed data | |
| Fotheringham | Analysing numerical spatial data | |
| CN115359917A (en) | Patient identification method and system based on space-time multi-attention residual error mechanism | |
| CN114664400A (en) | Medical record filing method and device | |
| CN113990514A (en) | Abnormality detection device for doctor diagnosis and treatment behavior, computer device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |