LU505334B1 - Infectious disease trend prediction system and method based on big data - Google Patents
Infectious disease trend prediction system and method based on big data Download PDFInfo
- Publication number
- LU505334B1 LU505334B1 LU505334A LU505334A LU505334B1 LU 505334 B1 LU505334 B1 LU 505334B1 LU 505334 A LU505334 A LU 505334A LU 505334 A LU505334 A LU 505334A LU 505334 B1 LU505334 B1 LU 505334B1
- Authority
- LU
- Luxembourg
- Prior art keywords
- meteorological
- data
- model
- infectious disease
- threshold
- Prior art date
Links
- 208000035473 Communicable disease Diseases 0.000 title claims abstract description 94
- 208000015181 infectious disease Diseases 0.000 title claims abstract description 50
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000010219 correlation analysis Methods 0.000 claims abstract description 32
- 238000012731 temporal analysis Methods 0.000 claims abstract description 17
- 238000004140 cleaning Methods 0.000 claims abstract description 7
- 238000012216 screening Methods 0.000 claims abstract description 7
- 238000012795 verification Methods 0.000 claims description 18
- 230000000694 effects Effects 0.000 claims description 11
- 230000008859 change Effects 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 6
- 201000010099 disease Diseases 0.000 claims description 6
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000012352 Spearman correlation analysis Methods 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 4
- 238000011425 standardization method Methods 0.000 claims description 4
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 238000007418 data mining Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 2
- RAHZWNYVWXNFOC-UHFFFAOYSA-N Sulphur dioxide Chemical compound O=S=O RAHZWNYVWXNFOC-UHFFFAOYSA-N 0.000 description 4
- 238000005291 chaos (dynamical) Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 208000032163 Emerging Communicable disease Diseases 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000003771 laboratory diagnosis Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 244000052769 pathogen Species 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
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
- 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
- G16H50/70—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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The invention provides an infectious disease trend prediction system and method based on big data. The system includes a data acquisition module, a spatial-temporal analysis module, a correlation analysis module, a threshold acquisition module and a prediction module. The data acquisition module is used for acquiring meteorological data and medical data of infectious diseases, and sorting and cleaning the data; the spatial-temporal analysis module is used for analysing the spatial-temporal distribution; the correlation analysis module is used for carrying out correlation analysis of meteorological elements and screening out meteorological element indexes related to infectious diseases; the threshold acquisition module is used for acquiring the threshold of meteorological element of infectious diseases; the prediction module is used for constructing an infectious disease trend forecasting model based on the meteorological element threshold, the medical data and the SIR model for forecasting the infectious disease trend. The prediction model constructed by the invention has higher prediction accuracy, and the combination of the SIR model and meteorological elements breaks the single prediction of the traditional infectious disease prediction model.
Description
INFECTIOUS DISEASE TREND PREDICTION SYSTEM AND 505984
METHOD BASED ON BIG DATA
The invention belongs to the technical field of infectious disease prediction, and particularly relates to an infectious disease trend prediction system and method based on big data.
Infectious diseases are caused by various pathogens and can spread among people, animals or people. At present, the control measures for emerging infectious diseases in China are mainly to control the confirmed cases and isolate the exposed or susceptible people. However, different infectious diseases have different modes of transmission and the potential high-risk groups are widely distributed, which makes it very difficult to determine the source of infectious diseases and predict the epidemic risk. Therefore, effective prevention and control of infectious diseases is very necessary, which can prevent the occurrence of mass morbidity in a short time.
In the prior art, for example, CN115223728A an infectious disease prediction method and system based on big data: obtaining historical patient information, calculating the probability of historical contacts and establishing a negative binomial distribution model, predicting the personal disease probability, and then predicting the incidence rate in multiple regions. CN107292390A: an information dissemination model based on chaos theory and dissemination method thereof: based on the traditional SIR model of infectious diseases, combined with the similar dissemination mechanism of information diffusion and infectious diseases, considering the dynamic behaviour characteristics, and improving an information dissemination model based on chaos theory and user behaviour.
Obviously, in the prior art, the SIR model is rarely fully utilized. Even if the SIR model is improved, the influence of meteorological elements on the incidence trend of infectious diseases is not taken into account. Meteorological elements have a noticeable influence on the incidence trend of infectious diseases, so it is necessary to 505984 conduct in-depth research.
The invention aims to solve the shortcomings of the prior art, and provides an infectious disease trend prediction system and method based on big data, which can more accurately predict the incidence trend of infectious diseases through the combination of meteorological elements and an SIR model.
In order to achieve the above objectives, the present invention provides the following scheme.
An infectious disease trend prediction system based on big data comprises a data acquisition module, a spatial-temporal analysis module, a correlation analysis module, a threshold acquisition module and a prediction module; the data acquisition module is used for acquiring meteorological data and medical data of infectious diseases, and sorting and cleaning the data respectively; the spatial-temporal analysis module is used for performing spatial-temporal distribution analysis on the sorted and cleaned medical data and the medical data; the correlation analysis module is used for performing correlation analysis of meteorological elements on the medical data and the meteorological data analysed by the spatial-temporal distribution, and screening out meteorological element indexes associated with infectious diseases; the threshold acquisition module is used for acquiring the threshold of meteorological elements of infectious diseases paroxysm based on the correlation analysis and the meteorological element index; the prediction module is used for constructing an infectious disease trend prediction model based on the threshold of the meteorological element, the medical data and the SIR model, and the infectious disease trend prediction model is used for predicting the infectious disease trend.
Optionally, the spatial-temporal analysis module comprises a probability calculation unit and a spatial-temporal analysis unit;
the probability calculation unit is used for processing the medical data and the 505984 meteorological data respectively by using a moving average method, obtaining the expected daily incidence and the expected meteorological environment, and calculating the Poisson distribution probability; the spatial-temporal analysis unit is used for obtaining the spatial-temporal distribution characteristics of medical data and meteorological data of infectious diseases when the Poisson distribution probability is less than a preset value.
Optionally, the correlation analysıs module comprises a meteorological element acquisition unit, a basic model establishment unit and a core model establishment unit; the meteorological element obtaining unit is used for performing correlation analysis on the medical data and the meteorological data by adopting Spearman correlation analysis method to obtain meteorological elements related to infectious diseases; the basic model building unit is used for fitting the meteorological elements and the medical data based on the Poisson generalized addition model of time series, and adjusting the degree of freedom of the meteorological elements based on the Akachi information criterion and the generalized addition model to build a basic model; the core model building unit is used to calculate the relative risk and confidence interval of the medical data when the meteorological elements change by one unit based on the basic model, and build the core model based on the distributed lag nonlinear model to realize the correlation analysis.
Optionally, the threshold acquisition module comprises a threshold determination unit and an increment determination unit; the threshold determining unit is used for obtaining the threshold of the meteorological element of infectious disease and the applicable range of the threshold of the meteorological element based on the correlation analysis and the meteorological element index; the increment determining unit is used to obtain the change of meteorological element increment before and after the threshold of the meteorological element and the quantitative relationship between the change and the incidence level based on the 17005386 threshold of the meteorological element and the association rule data mining algorithm.
Optionally, the disease grade classification process 1s: performing linear transformation on the medical data by adopting a min-max standardization method to obtain standardized data; classifying the risk grade of infectious diseases based on the standardized data.
Optionally, the prediction module comprises a model construction unit, a verification set construction unit and an effect verification unit; the model building unit is used for introducing the threshold of the meteorological element into the SIR model and building an infectious disease trend prediction model based on the medical data; the verification set construction unit is used for acquiring the meteorological data and the medical data in different time periods from the data acquisition module to construct a verification set; the effect verification unit is used for verifying the prediction effect of the prediction model based on the verification set.
An infectious disease trend prediction method based on big data comprises: collecting meteorological data and medical data of infectious diseases, and arranging and cleaning the data respectively; analysing the sorted and cleaned medical data and the spatial-temporal distribution of the medical data; carrying out meteorological element correlation analysis on the medical data and the meteorological data analysed by the spatial-temporal distribution, and screening out meteorological element indexes associated with infectious diseases; obtaining the threshold value of meteorological elements for infectious diseases based on the correlation analysis and the meteorological element index; building an infectious disease trend prediction model based on the meteorological element threshold, the medical data and the SIR model, wherein the infectious disease trend prediction model is used for predicting the infectious disease 505984 trend.
Optionally, respectively processing the medical data and the meteorological data by using a moving average method, obtaining the expected daily incidence and the 5 expected meteorological environment, and calculating the Poisson distribution probability; when the Poisson distribution probability is less than a preset value, the spatial-temporal distribution characteristics of medical data and meteorological data of infectious diseases are obtained.
Compared with the prior art, the invention has the beneficial effects that meteorological elements are introduced into the SIR model, so that the accuracy of the infectious disease prediction model is improved, and the lag of the obtained data is avoided by utilizing the distributed lag linear model. The prediction model of the invention is more scientific and rigorous, and the prediction accuracy is higher.
In order to explain the technical scheme of the present invention more clearly, the drawings needed in the embodiments are briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For ordinary people in the field, other drawings can be obtained according to these drawings without paying creative labour.
Fig. 1 is a schematic structural diagram of an infectious disease trend prediction system based on big data according to an embodiment of the present invention.
In the following, the technical scheme in the embodiment of the invention will be clearly and completely described with reference to the attached drawings. Obviously, the described embodiment is only a part of the embodiment of the invention, but not the whole embodiment. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in the field without creative labour 505984 belong to the scope of protection of the present invention.
In order to make the above objects, features and advantages of the present invention more obvious and easier to understand, the present invention will be further described in detail with the attached drawings and specific embodiments.
Embodiment 1
As shown in Fig. 1, an infectious disease trend prediction system based on big data comprises a data acquisition module, a spatial-temporal analysis module, a correlation analysis module, a threshold acquisition module and a prediction module.
The data acquisition module is used for acquiring meteorological data and medical data of infectious diseases, and sorting and cleaning the data; among them, the medical data includes the data of infectious diseases and emergency treatment, and mainly includes the depersonalized demographic information (gender, date of birth, occupation and address), onset date, date of treatment, medical institution, treatment department, disease diagnosis (clinical diagnosis, laboratory diagnosis) and disease diagnosis code. Acquisition of meteorological data includes: obtaining the ground meteorological observation data and pollutant concentrations (including PM2.5,
PM10, NO2, SO2, etc.) corresponding to the medical data from the Meteorological
Bureau and the environmental monitoring station, where the meteorological observation data include the daily values of the ground daily average temperature (highest and lowest), daily average air pressure (highest and lowest), daily average relative humidity, sunshine hours, daily precipitation, daily average wind speed and other elements.
The spatial-temporal analysis module is used for performing spatial-temporal distribution analysis on the sorted and cleaned medical data and the medical data;the spatial-temporal analysis module comprises a probability calculation unit and a spatial-temporal analysis unit.
The probability calculation unit 1s used for processing the medical data and the meteorological data respectively by using the moving average method, obtaining the expected daily incidence and the expected meteorological environment, and 505984 calculating the Poisson distribution probability.
The spatial-temporal analysis unit is used for obtaining the spatial-temporal distribution characteristics of medical data and meteorological data of infectious diseases when the Poisson distribution probability is less than a preset value.
The moving average method is used to process medical data and meteorological data, that is, each item of the original dynamic series is replaced by the average of this item and its neighbouring items, and a new dynamic series composed of moving averages is obtained, and the irregular changes in the original dynamic series are smoothed to eliminate the fluctuation of the original dynamic series caused by accidental elements.
The correlation analysis module is used for carrying out correlation analysis of meteorological elements on the medical data and meteorological data subjected to temporal and spatial distribution analysis, and screening out meteorological element indexes related to infectious diseases.
The correlation analysis module comprises a meteorological element acquisition unit, a basic model establishment unit and a core model establishment unit.
The meteorological element acquisition unit is used for carrying out correlation analysis on medical data and meteorological data by adopting Spearman correlation analysis method to obtain meteorological elements related to infectious diseases, and respectively counting the number of daily infectious disease cases and the number of emergency patients according to different gender and age groups; the statistical description of main meteorological environment elements adopts the following statistical indicators: mean (X), standard deviation (SD), Minimum (Min), 25th percentile (P25), median (M), 75th percentile (P75) and maximum (Max); because the number of confirmed cases, some meteorological elements and pollution elements are not normally distributed, Spearman correlation analysis is used to identify the meteorological elements related to infectious diseases.
Log 2 (X )| = BX, + s(time,df ) + as. factor(DOW) 7505994 +Holiday + flu + s(suntime,df ) + s(rain, df ) + s(SO,, df) , +s(NO,,df ) + s(PM,,,df ) + s(PM, df ) + a where E (Y;)-the expected value of the number of patients on the i-th day; Xi- the value of a meteorological element on the i-th day; P-coefficient of explanatory variables that have a linear influence on the response variables in the model; s ( ) penalty cubic spline smoothing function; time-time variable; DOW, Holiday, Flu-day of the week, holidays, flu days dummy variables, as confounding elements into the model (as. element); df-degree of freedom; a-intercept.
The above research methods can also quantitatively assign values to influencing elements (such as week effect, etc.) except meteorological elements, and eliminate the influence of interference elements on correlation results to ensure the accuracy of correlation.
The basic model building unit is used for fitting meteorological elements and medical data based on the Poisson generalized addition model of time series, and adjusting the degrees of freedom of meteorological elements and building the basic model based on the Akachi information criterion and the generalized addition model.
The core model building unit is used to calculate the relative risk and confidence interval of medical data when different meteorological elements change by one unit based on the basic model, and build the core model based on the distributed lag nonlinear model to realize correlation analysis. Among them, the relative risk and confidence interval are the relative risk and 95% confidence interval of the natural logarithm of the number of infectious disease patients.
The threshold acquisition module is used for acquiring the threshold of meteorological elements of infectious diseases based on correlation analysis and meteorological element indicators; the threshold acquisition module comprises a threshold determination unit and an increment determination unit;
A threshold determining unit is used for obtaining the meteorological element threshold of infectious diseases and the applicable range of the meteorological element threshold based on correlation analysis and meteorological element indicators;
the thresholds of meteorological elements include the thresholds of variables such as 505984 average temperature, average air pressure, rainfall, average wind speed and sulfur dioxide concentration.
The increment determining unit is used for obtaining the change of the meteorological element increment before and after the meteorological element threshold and the quantitative relationship between the change and the disease level based on the meteorological element threshold and the association rule data mining algorithm.
The process of grading the incidence is as follows: using min-max standardization method, the medical data are linearly transformed to obtain standardized data; classifying the risk grade of infectious diseases based on standardized data.
Specifically, the medical data is standardized by using the min-max standardization method, which is to linearly transform the original data, let Amin and
Amax be the minimum and maximum values of attribute A respectively, and map an original value A into a value A' in the interval [0,1] through the min-max standardization, and its formula is:
A'=(A-Amin)/(Amax-Amin).
The data is standardized by this formula, and the risk grade is divided according to the standardized data.
The forecasting module is used for constructing an infectious disease trend forecasting model based on the meteorological element threshold, the medical data and the SIR model, and the infectious disease trend forecasting model is used for forecasting the infectious disease trend.
Specifically, in the original SIR model, susceptible population S, infected population I and removed population R, the original equation is:
dt N dl rßl a where r represents the number of people in contact with infected people; P is the infection rate; # is the withdrawal rate; N=S+I+R, introducing meteorological elements into the SIR model, namely:
LIE ur pir where ” is the threshold variable of introduced meteorological elements.
The prediction module comprises a model construction unit, a verification set construction unit and an effect verification unit;
A model building unit is used to introduce the threshold of meteorological elements into the SIR model and build an infectious disease trend prediction model based on medical data;
The verification set construction unit is used for acquiring meteorological data and medical data in different time periods from the data acquisition module and constructing a verification set;
The effect verification unit is used for verifying the prediction effect of the prediction model based on the verification set. Specifically, the confusion matrix is used to evaluate the prediction effect:
TPR = rp
FPR = vu where TPR is the true rate, FPR is the false positive rate, TP is the true example,
FP is the false counterexample, FP is the false positive example, TN is the true counterexample, and the predicted results are compared with the real situation to 505984 obtain the above parameter values.
Embodiment 2
An infectious disease trend prediction method based on big data comprises: collecting meteorological data and medical data of infectious diseases, and arranging and cleaning the data respectively; analysing the sorted and cleaned medical data and the spatial-temporal distribution of the medical data; carrying out meteorological element correlation analysis on the medical data and the meteorological data analysed by the spatial-temporal distribution, and screening out meteorological element indexes associated with infectious diseases; obtaining the threshold value of meteorological elements for infectious diseases based on the correlation analysis and the meteorological element index; building an infectious disease trend prediction model based on the meteorological element threshold, the medical data and the SIR model, wherein the infectious disease trend prediction model is used for predicting the infectious disease trend; respectively processing the medical data and the meteorological data by using a moving average method, obtaining the expected daily incidence and the expected meteorological environment, and calculating the Poisson distribution probability; when the Poisson distribution probability is less than a preset value, the spatial-temporal distribution characteristics of medical data and meteorological data of infectious diseases are obtained.
The above-mentioned embodiment is only a description of the preferred mode of the invention, and does not limit the scope of the invention. Under the premise of not departing from the design spirit of the invention, various modifications and improvements made by ordinary technicians in the field to the technical scheme of the invention shall fall within the protection scope determined by the claims of the invention.
Claims (8)
1. An infectious disease trend prediction system based on big data, comprising a data acquisition module, a spatial-temporal analysis module, a correlation analysis module, a threshold acquisition module and a prediction module; the data acquisition module is used for acquiring meteorological data and medical data of infectious diseases, and sorting and cleaning the data respectively; the spatial-temporal analysis module is used for performing spatial-temporal distribution analysis on the sorted and cleaned medical data and the medical data; the correlation analysis module is used for performing correlation analysis of meteorological elements on the medical data and the meteorological data analysed by the spatial-temporal distribution, and screening out meteorological element indexes associated with infectious diseases; the threshold acquisition module is used for acquiring the threshold of meteorological elements of infectious diseases paroxysm based on the correlation analysis and the meteorological element index; the prediction module is used for constructing an infectious disease trend prediction model based on the threshold of the meteorological element, the medical data and the SIR model, and the infectious disease trend prediction model is used for predicting the infectious disease trend.
2. The infectious disease trend prediction system based on big data according to claim 1, wherein the spatial-temporal analysis module comprises a probability calculation unit and a spatial-temporal analysis unit; the probability calculation unit is used for processing the medical data and the meteorological data respectively by using a moving average method, obtaining the expected daily incidence and the expected meteorological environment, and calculating the Poisson distribution probability; the spatial-temporal analysis unit is used for obtaining the spatial-temporal distribution characteristics of medical data and meteorological data of infectious diseases when the Poisson distribution probability is less than a preset value.
3. The infectious disease trend prediction system based on big data according to 505984 claim 1, wherein the correlation analysis module comprises a meteorological element acquisition unit, a basic model establishment unit and a core model establishment unit; the meteorological element obtaining unit is used for performing correlation analysis on the medical data and the meteorological data by adopting Spearman correlation analysis method to obtain meteorological elements related to infectious diseases; the basic model building unit is used for fitting the meteorological elements and the medical data based on the Poisson generalized addition model of time series, and adjusting the degree of freedom of the meteorological elements based on the Akachi information criterion and the generalized addition model to build a basic model; the core model building unit is used to calculate the relative risk and confidence interval of the medical data when the meteorological elements change by one unit based on the basic model, and build the core model based on the distributed lag nonlinear model to realize the correlation analysis.
4. The infectious disease trend prediction system based on big data according to claim 1, wherein the threshold acquisition module comprises a threshold determination unit and an increment determination unit; the threshold determining unit is used for obtaining the threshold of the meteorological element of infectious disease and the applicable range of the threshold of the meteorological element based on the correlation analysis and the meteorological element index; the increment determining unit is used to obtain the change of meteorological element increment before and after the threshold of the meteorological element and the quantitative relationship between the change and the incidence level based on the threshold of the meteorological element and the association rule data mining algorithm.
5. The infectious disease trend prediction system based on big data according to claim 4, wherein the disease grade classification process is:
performing linear transformation on the medical data by adopting a min-max 505984 standardization method to obtain standardized data; classifying the risk grade of infectious diseases based on the standardized data.
6. The infectious disease trend prediction system based on big data according to claim 1, wherein the prediction module comprises a model construction unit, a verification set construction unit and an effect verification unit; the model building unit is used for introducing the threshold of the meteorological element into the SIR model and building an infectious disease trend prediction model based on the medical data; the verification set construction unit is used for acquiring the meteorological data and the medical data in different time periods from the data acquisition module to construct a verification set; the effect verification unit is used for verifying the prediction effect of the prediction model based on the verification set.
7. An infectious disease trend prediction method based on big data, comprising: collecting meteorological data and medical data of infectious diseases, and arranging and cleaning the data respectively; analysing the sorted and cleaned medical data and the spatial-temporal distribution of the medical data; carrying out meteorological element correlation analysis on the medical data and the meteorological data analysed by the spatial-temporal distribution, and screening out meteorological element indexes associated with infectious diseases; obtaining the threshold value of meteorological elements for infectious diseases based on the correlation analysis and the meteorological element index; building an infectious disease trend prediction model based on the meteorological element threshold, the medical data and the SIR model, wherein the infectious disease trend prediction model is used for predicting the infectious disease trend.
8. The infectious disease trend prediction method based on big data according to claim 7, wherein respectively processing the medical data and the meteorological data by using a 505984 moving average method, obtaining the expected daily incidence and the expected meteorological environment, and calculating the Poisson distribution probability; when the Poisson distribution probability is less than a preset value, the spatial-temporal distribution characteristics of medical data and meteorological data of infectious diseases are obtained.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310943355.3A CN116936123A (en) | 2023-07-28 | 2023-07-28 | Infectious disease trend prediction system and method based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| LU505334B1 true LU505334B1 (en) | 2024-04-22 |
Family
ID=88387681
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| LU505334A LU505334B1 (en) | 2023-07-28 | 2023-10-20 | Infectious disease trend prediction system and method based on big data |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN116936123A (en) |
| LU (1) | LU505334B1 (en) |
-
2023
- 2023-07-28 CN CN202310943355.3A patent/CN116936123A/en active Pending
- 2023-10-20 LU LU505334A patent/LU505334B1/en active
Also Published As
| Publication number | Publication date |
|---|---|
| CN116936123A (en) | 2023-10-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108846503B (en) | Dynamic respiratory system disease ill person number prediction method based on neural network | |
| CN111325406B (en) | Thermal-related health risk early warning method based on small spatial scale | |
| CN111179109A (en) | Electricity consumption data processing method for detecting elderly people living alone | |
| He et al. | Stochastic modelling of air pollution impacts on respiratory infection risk | |
| CN112820415B (en) | GIS-based chronic disease spatial-temporal evolution feature analysis and environmental health risk monitoring system and method | |
| KR102088296B1 (en) | Method and apparatus of predicting disease correlation based on air quality data | |
| CN114579818A (en) | Visual carbon emission detection management system and method | |
| CN115575584B (en) | Atmospheric environment cadmium content monitoring and early warning method and system | |
| CN114328075A (en) | Intelligent power distribution room sensor multidimensional data fusion abnormal event detection method and system and computer readable storage medium | |
| CN113361825A (en) | Early warning method and system for trampling accident | |
| CN111222784A (en) | Security monitoring method and system based on population big data | |
| CN113110080A (en) | Household environment intelligent monitoring, regulation and control management cloud system based on Internet of things and cloud computing | |
| CN110555524A (en) | training sample data acquisition method and device based on indoor environment monitoring | |
| CN114217025B (en) | Analysis method for evaluating influence of meteorological data on air quality concentration prediction | |
| Liu et al. | Research on data correction method of micro air quality detector based on combination of partial least squares and random forest regression | |
| BARAN | Air quality Index prediction in besiktas district by artificial neural networks and k nearest neighbors | |
| CN111430040A (en) | Hand-foot-and-mouth disease epidemic situation prediction method based on case, weather and pathogen monitoring data | |
| Xie et al. | Control charts for dynamic process monitoring with an application to air pollution surveillance | |
| LU505334B1 (en) | Infectious disease trend prediction system and method based on big data | |
| CN116520236B (en) | Abnormality detection method and system for intelligent ammeter | |
| AU2021101951A4 (en) | Method of real-time safety warning of tunnel approaching construction based on data fusion | |
| Wang et al. | Research of the early warning analysis of crop diseases and insect pests | |
| CN111105148B (en) | Off-job probability evaluation method, apparatus and computer readable storage medium | |
| CN113689058A (en) | Dormitory management system and method based on smart campus | |
| Poh et al. | Anomaly detection for home activity based on sequence pattern |