CN112768067A - Novel coronavirus region risk index evaluation system - Google Patents
Novel coronavirus region risk index evaluation system Download PDFInfo
- Publication number
- CN112768067A CN112768067A CN202011478018.4A CN202011478018A CN112768067A CN 112768067 A CN112768067 A CN 112768067A CN 202011478018 A CN202011478018 A CN 202011478018A CN 112768067 A CN112768067 A CN 112768067A
- Authority
- CN
- China
- Prior art keywords
- module
- value
- risk
- time
- epidemic
- 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
- 241000711573 Coronaviridae Species 0.000 title claims abstract description 10
- 238000011156 evaluation Methods 0.000 title claims description 8
- 208000015181 infectious disease Diseases 0.000 claims abstract description 23
- 230000009193 crawling Effects 0.000 claims abstract description 13
- 230000002458 infectious effect Effects 0.000 claims abstract description 5
- 238000004364 calculation method Methods 0.000 claims description 18
- 208000025721 COVID-19 Diseases 0.000 claims description 5
- 230000005182 global health Effects 0.000 claims description 4
- 238000012795 verification Methods 0.000 claims description 3
- 208000035473 Communicable disease Diseases 0.000 abstract description 3
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 230000003203 everyday effect Effects 0.000 abstract description 2
- 238000002474 experimental method Methods 0.000 abstract description 2
- 230000036541 health Effects 0.000 description 4
- 201000010099 disease Diseases 0.000 description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- 238000000034 method Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000013213 extrapolation Methods 0.000 description 1
- 230000001524 infective effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000241 respiratory effect Effects 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
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
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
- G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
-
- 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
Abstract
Novel assessment system for risk indexes of various regions of coronavirus relates to the field of artificial intelligence auxiliary infectious disease dynamics, and aims at the problem that the trend prediction accuracy of various regions of epidemic situations in the prior art is low, and comprises the following steps: the system comprises a network crawling module, an Rt value calculating module, an estimated value calculating module, a posterior coefficient calculating module, a risk coefficient calculating module and a verifying module. The risk indexes of various places are predicted by using multi-dimensional data, and the RiskIndex (t) and the Pearson product moment correlation coefficient pccs of newly-increased infectious people every day are obtained through experiments, which shows that the risk indexes can accurately predict epidemic situation trends of various places.
Description
Technical Field
The invention relates to the field of artificial intelligence assisted infectious disease dynamics, in particular to a novel coronavirus local risk index evaluation system.
Background
Since the outbreak of coronavirus disease (COVID-19), there has been a lack of a framework to fully understand and compare the health safety levels of various countries, collect information and measure the ability and available resources of various countries to deal with COVID-19, and assess the risk of infection in local residents. The existing new crown risk assessment system for each region basically provides a risk index for the region according to new infectious population of the region within 14 days, and lacks deeper mining of epidemic situation data.
Disclosure of Invention
The purpose of the invention is: aiming at the problem that the trend prediction accuracy of the epidemic situation in each place is low in the prior art, a novel assessment system for the risk index of each place of the coronavirus is provided.
The technical scheme adopted by the invention to solve the technical problems is as follows:
novel coronavirus region risk index evaluation system, comprising: the system comprises a network crawling module, an Rt value calculating module, an estimated value calculating module, a posterior coefficient calculating module, a risk coefficient calculating module and a verifying module;
the network crawling module is used for crawling the number of people infected, cured and dead by COVID-19 in each country in real time;
the Rt value calculating module is used for calculating the effective infection number Rt value by utilizing the real-time COVID-19 infection, cure and death number data of each country crawled by the network crawling module;
the estimated value calculation module is used for acquiring an estimated value of an epidemic situation outbreak time inflection point;
the posterior coefficient calculation module is used for obtaining posterior coefficients after epidemic outbreak by utilizing a linear model according to the Rt value obtained by the Rt value calculation module, the estimation value of the inflection point of the epidemic outbreak time obtained by the estimation value calculation module and the population conditions of all regions;
the risk coefficient calculation module is used for obtaining risk indexes of various regions according to the global health safety index and the posterior coefficient;
the verification module is used for calculating Pearson correlation coefficients between each local risk index and the number of newly increased infectious people each day.
Further, the estimated value calculation module obtains an estimated value of an inflection point of epidemic outbreak time by using an SEIR model.
Further, the SEIR model is represented as:
wherein S, E, I and R represent the number of susceptible persons, exposed persons, infected persons and removed persons, respectively; t represents time, k represents propagation rate, e represents the reciprocal of mean latency, η represents cure rate, and d represents differential sign.
Further, the epidemic outbreak time inflection point is obtained by using an SIR model.
Further, the SIR model is represented as:
further, the estimated value of the epidemic outbreak time inflection point is represented as:
the k and η are obtained by a grid search.
Further, the effective infection number Rt value is expressed by using bayesian theorem.
Further, the effective infection number Rt value is expressed as:
wherein the likelihood function P (k | R)t) Denotes a given RtThe value of (A), the probability of k newly confirmed cases appearing, P (R)t) Representing a prior probability.
The invention has the beneficial effects that:
the risk indexes of various places are predicted by using multidimensional data, and the RiskIndex (t) and the Pearson product moment correlation coefficient pccs of the number of newly infected people every day are obtained through experiments, which proves that the risk indexes can accurately predict the epidemic situation trend of various places.
Drawings
Fig. 1 is a flow chart of the present application.
Detailed Description
It should be noted that, in the present invention, the embodiments disclosed in the present application may be combined with each other without conflict.
The first embodiment is as follows: specifically, the present embodiment is described with reference to fig. 1, and the system for evaluating each risk index of a novel coronavirus according to the present embodiment includes: the system comprises a network crawling module, an Rt value calculating module, an estimated value calculating module, a posterior coefficient calculating module, a risk coefficient calculating module and a verifying module;
the network crawling module is used for crawling the number of people infected, cured and dead by COVID-19 in each country in real time;
the Rt value calculating module is used for calculating the effective infection number Rt value by utilizing the real-time COVID-19 infection, cure and death number data of each country crawled by the network crawling module;
the estimated value calculation module is used for acquiring an estimated value of an epidemic situation outbreak time inflection point;
the posterior coefficient calculation module is used for obtaining posterior coefficients after epidemic outbreak by utilizing a linear model according to the Rt value obtained by the Rt value calculation module, the estimation value of the inflection point of the epidemic outbreak time obtained by the estimation value calculation module and the population conditions of all regions;
the risk coefficient calculation module is used for obtaining risk indexes of various regions according to the global health safety index and the posterior coefficient;
the verification module is used for calculating Pearson correlation coefficients between each local risk index and the number of newly increased infectious people each day.
The evaluation of the sanitary safety capability before epidemic outbreak in all regions of the world is combined with the posterior data after the epidemic outbreak to comprehensively evaluate the epidemic risk index of one region. Real-time epidemic situation risk indexes of various countries calculated by the model are published on a website (a scientific prediction system (official survey edition) of the epidemic situation of various regions of the novel coronavirus).
RiskIndex(t)＝HealthSecurityIndex×PosteriorCoefficient(t)
The evaluation of the health safety capability of each region before the outbreak of the epidemic situation adopts global health safety index (globalshealthsecurityindex) published in 2019, and the evaluation starts from 6 aspects, 34 indexes, 85 secondary indexes and 140 problems, including the health capability of local hospitals and community care centers, the number of epidemiological researchers, whether infrastructure is sufficient and the like, and is comprehensively evaluated through publicly-obtained data.
The time series data after the epidemic outbreak takes the following dimension information into consideration:
effective infection number Rt(Effect production number), updating R according to the number of new cases reported each day using Bayesian theoremtValue of (A)
Inflection point t from time t to epidemic outbreak time*Distance (calculated from our modified SEIR model)
Infection rate, mortality rate, population density at time t
We used two different extrapolation methods (modified logic growth model and modified SEIR model) to infer the expected saturation of the number of infections and the expected final date. Both methods agree on the order of magnitude of saturation and end date. The same method was used to analyze the overall infection, predict epidemic trends and discuss the relevance and accuracy of these results. The derivatives of the logical growth model are used to fit a weight vector to balance the contribution of each dimension to the risk index. The resulting risk indices are normalized to 0 to 100, where 100 represents the best safety condition.
Calculation of effective infection number Rt
Updating R according to the number of new cases reported each day using Bayesian theoremtValue of (A)
ktThe newly added number of confirmed cases, R, on the t daytFor the effective number of infections, we used P (R) of the previous dayt-1) To estimate P (R) of the dayt) We will assume RtIs distributed as Rt-1A gaussian distribution as a centre, i.e.
Where σ is a hyperparameter.
Thus for the first day there are:
the following day:
given the average number of infections per day lambda, the probability of detecting k new cases satisfies the Poisson distribution
RtAnd λ satisfy the relationship:
where γ is the reciprocal of the sequence spacing (for COVID19, about 7 days)
Inflection point t of epidemic outbreak time*Is estimated by
We used the SEIR model in infectious disease dynamics, which classified the general population into the following four categories: susceptible (susceptibles), persons who are not infected with a disease but who are likely to be infected with the disease; exposition (exposed), a person who has touched the infected person but has had temporary incapacity to transmit to others; infected persons (infectives), persons who have become sick and are contagious; recovered. The differential equation is as follows:
here we normalize the general population as: s + E + I + R ═ 1
To calculate the inflection point t of epidemic outbreak time*We temporarily use the SIR model
Because of the fact that
When S (0) is equal to S0,I(0)＝1-S0When we getExpression to I:
we will use the above expression to calculate the higher derivative of R with respect to t. Since S (t) is a monotonic function of time, it can be obtained using the chain rule with the parameter being
Then, since dR/dt ═ η I is a function with respect to S, the second derivative of time
Also a function of S, so that higher derivatives in time can be obtained iteratively.
We observe that even ones of these higher order derivatives are at time tcReaches its absolute extreme value, and tc∈[ta,tm] (taAnd tmZero for the third and second derivatives respectively),
the greater tcCloser to taSo we use
As inflection point t of epidemic outbreak time*Is estimated.
Guangzhou respiratory health research institute open topic (funding by Hengda, China) -2020GIRHHMS 23.
It should be noted that the detailed description is only for explaining and explaining the technical solution of the present invention, and the scope of protection of the claims is not limited thereby. It is intended that all such modifications and variations be included within the scope of the invention as defined in the following claims and the description.
Claims (8)
1. Novel coronavirus region risk index evaluation system is characterized by comprising: the system comprises a network crawling module, an Rt value calculating module, an estimated value calculating module, a posterior coefficient calculating module, a risk coefficient calculating module and a verifying module;
the network crawling module is used for crawling the number of people infected, cured and dead by COVID-19 in each country in real time;
the Rt value calculating module is used for calculating the effective infection number Rt value by utilizing the real-time COVID-19 infection, cure and death number data of each country crawled by the network crawling module;
the estimated value calculation module is used for acquiring an estimated value of an epidemic situation outbreak time inflection point;
the posterior coefficient calculation module is used for obtaining posterior coefficients after epidemic outbreak by utilizing a linear model according to the Rt value obtained by the Rt value calculation module, the estimation value of the inflection point of the epidemic outbreak time obtained by the estimation value calculation module and the population conditions of all regions;
the risk coefficient calculation module is used for obtaining risk indexes of various regions according to the global health safety index and the posterior coefficient;
the verification module is used for calculating Pearson correlation coefficients between each local risk index and the number of newly increased infectious people each day.
2. The system according to claim 1, wherein the estimated value calculation module uses an SEIR model to obtain the estimated value of the inflection point of the outbreak time of the epidemic situation.
3. The system according to claim 2, wherein the SEIR model is expressed as:
wherein S, E, I and R represent the number of susceptible persons, exposed persons, infected persons and removed persons, respectively; t represents time, k represents propagation rate, e represents the reciprocal of mean latency, η represents cure rate, and d represents differential sign.
4. The system according to claim 3, wherein the inflection point of the outbreak time is obtained by using SIR model.
5. The system according to claim 4, wherein the SIR model is expressed as:
6. the system according to claim 5, wherein the estimated value of the inflection point of the outbreak time of the epidemic is expressed as:
the k and η are obtained by a grid search.
7. The system according to claim 3, wherein the effective infection number Rt value is expressed by Bayesian theorem.
8. The system according to claim 7, wherein the effective infection number Rt is expressed as:
wherein the likelihood function P (k | R)t) Denotes a given RtThe value of (A), the probability of k newly confirmed cases appearing, P (R)t) Representing a prior probability.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011478018.4A CN112768067A (en) | 2020-12-15 | 2020-12-15 | Novel coronavirus region risk index evaluation system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011478018.4A CN112768067A (en) | 2020-12-15 | 2020-12-15 | Novel coronavirus region risk index evaluation system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112768067A true CN112768067A (en) | 2021-05-07 |
Family
ID=75694071
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011478018.4A Pending CN112768067A (en) | 2020-12-15 | 2020-12-15 | Novel coronavirus region risk index evaluation system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112768067A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111540478A (en) * | 2020-04-22 | 2020-08-14 | 第四范式（北京）技术有限公司 | Epidemic situation deduction simulation system and simulation method |
| US20200294680A1 (en) * | 2017-05-01 | 2020-09-17 | Health Solutions Research, Inc. | Advanced smart pandemic and infectious disease response engine |
| CN111681772A (en) * | 2020-05-08 | 2020-09-18 | 自然资源部第一海洋研究所 | Quantitative detection method, system, storage medium and terminal for epidemic situation control effect |
| CN111768873A (en) * | 2020-06-03 | 2020-10-13 | 中国地质大学（武汉） | COVID-19 real-time risk prediction method |
| CN111968749A (en) * | 2020-10-21 | 2020-11-20 | 平安科技（深圳）有限公司 | Risk assessment method and device, terminal equipment and readable storage medium |
-
2020
- 2020-12-15 CN CN202011478018.4A patent/CN112768067A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200294680A1 (en) * | 2017-05-01 | 2020-09-17 | Health Solutions Research, Inc. | Advanced smart pandemic and infectious disease response engine |
| CN111540478A (en) * | 2020-04-22 | 2020-08-14 | 第四范式（北京）技术有限公司 | Epidemic situation deduction simulation system and simulation method |
| CN111681772A (en) * | 2020-05-08 | 2020-09-18 | 自然资源部第一海洋研究所 | Quantitative detection method, system, storage medium and terminal for epidemic situation control effect |
| CN111768873A (en) * | 2020-06-03 | 2020-10-13 | 中国地质大学（武汉） | COVID-19 real-time risk prediction method |
| CN111968749A (en) * | 2020-10-21 | 2020-11-20 | 平安科技（深圳）有限公司 | Risk assessment method and device, terminal equipment and readable storage medium |
Non-Patent Citations (4)
| Title |
|---|
| 曾奥涵等: "知识疫图背后的故事之地区风险预测与基于搜索日志疫情预测技术实践", pages 4, Retrieved from the Internet <URL:https://zhuanlan.zhihu.com/p/142218982> * |
| 正在养病的中年丘八: "传染病中有效再生数的计算", pages 2 - 3, Retrieved from the Internet <URL:https://zhuanlan.zhihu.com/p/267686933> * |
| 范如国等: "基于SEIR的新冠肺炎传播模型及拐点预测分析", 《电子科技大学学报》, vol. 49, no. 3, pages 3 - 4 * |
| 范如国等: "基于SEIR的新冠肺炎传播模型及拐点预测分析", 电子科技大学学报, vol. 49, no. 3, pages 369 - 374 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Memon et al. | Assessing the role of quarantine and isolation as control strategies for COVID-19 outbreak: a case study | |
| Parra-Rojas et al. | The 2017 plague outbreak in Madagascar: Data descriptions and epidemic modelling | |
| CN111768873A (en) | COVID-19 real-time risk prediction method | |
| Ndiaye et al. | Comparative prediction of confirmed cases with COVID-19 pandemic by machine learning, deterministic and stochastic SIR models | |
| Givan et al. | Predicting epidemic thresholds on complex networks: Limitations of mean-field approaches | |
| Xue et al. | Influenza activity surveillance based on multiple regression model and artificial neural network | |
| CN113784292B (en) | Urban epidemic situation risk assessment method based on mobile phone signaling data | |
| Jain et al. | Modelling logistic growth model for COVID-19 pandemic in India | |
| Levy et al. | Modeling influenza-like illnesses through composite compartmental models | |
| Hardelid et al. | Excess mortality monitoring in England and Wales during the influenza A (H1N1) 2009 pandemic | |
| Yi et al. | SEIR-SEI-EnKF: A new model for estimating and forecasting dengue outbreak dynamics | |
| CN112768067A (en) | Novel coronavirus region risk index evaluation system | |
| CN112259248A (en) | COVID-19 overseas input risk assessment and prediction method | |
| Yuan et al. | An improved SEIR model for reconstructing the dynamic transmission of COVID-19 | |
| Tang et al. | A new prediction method of COVID-19 epidemic | |
| CN112420210A (en) | New important infectious disease R based on urban multifactor0Calculation method | |
| Ketcheson et al. | Estimating and forecasting COVID-19 attack rates and mortality | |
| Prieto et al. | COVID-19 impact estimation on ICU capacity at Andalusia, Spain, using Artificial Intelligence | |
| Bhatt et al. | The epidemic trend of COVID-19 in SAARC countries: a predictive modelling and analysis | |
| Wang et al. | Time series neural network-based analysis of hospital material prediction under infectious disease epidemic | |
| Huang et al. | A staging prediction model for Covid-19 pandemic under strong public health interventions | |
| Ju | Statistical methods in infectious disease modeling: agent-based models, computations, and selection biases | |
| Zhang et al. | Strategic release of lockdowns in a covid infection model | |
| Gao et al. | A Modified Heterogeneous Mean-field SEIRS Model | |
| CN115860306B (en) | Method for detecting public risk perception space-time difference of sudden public and guard event area |
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 |