CN110047594A - Respiratory disease Prediction of Incidence Trend method based on weather environment monitoring data - Google Patents
Respiratory disease Prediction of Incidence Trend method based on weather environment monitoring data Download PDFInfo
- Publication number
- CN110047594A CN110047594A CN201910444353.3A CN201910444353A CN110047594A CN 110047594 A CN110047594 A CN 110047594A CN 201910444353 A CN201910444353 A CN 201910444353A CN 110047594 A CN110047594 A CN 110047594A
- Authority
- CN
- China
- Prior art keywords
- average
- respiratory disease
- data
- period
- prediction
- 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
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
- G16H50/50—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
Landscapes
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The respiratory disease Prediction of Incidence Trend method based on weather environment monitoring data that the present embodiments relate to a kind of, establishes the multiple linear regression model of respiratory disease Prediction of Incidence Trend；Obtain the weather environment monitoring data in the first period；The weather environment monitoring data include: temperature on average, average gas pressure, the maximum temperature difference in first period and average air quality index AQI；Based on the weather environment monitoring data in the multiple linear regression model and first period, the respiratory disease disease index of the second period after first period is obtained；Data analysis is carried out to the weather environment monitoring data, obtains the temperature on average, average gas pressure, the maximum temperature difference level parameters corresponding with average AQI；According to the respiratory disease disease index and the level parameters, respiratory disease Prediction of Incidence Trend prompt information is generated.
Description
Technical field
The present invention relates to Meteorological Services technical field more particularly to a kind of respiratory systems based on weather environment monitoring data
Disease incidence trend forecasting method.
Background technique
Meteorological Services are related to the every aspect of people's life, in recent years in global climate anomalous variation, extreme weather weather
Under the overall background that event increased significantly, influence of the anomalous variation of synoptic climate and corresponding meteorologic factor to human health has been got over
It more highlights, by the concern of scientific and technological circle, health care workers and general public.
For respiratory disease as one of the principal disease for endangering human health, it is especially quick to the variation of synoptic climate
Sense.How by the observation to current weather element and its variation, exhaled in scientific and effective prediction following a period of time
The incidence of desorption system disease, and effective prevention prompt is provided for the common people, it is the problem of present invention discusses.
Summary of the invention
The purpose of the present invention is purposes to pass through the morbidity case fallen ill to respiratory disease and point of meteorological element relationship
Analysis, establishes respiratory disease Prediction of Incidence Trend model, disease incidence prediction and prophylactic measures forecast is made, to help the common people
Xie Bingneng makes reply in advance, to mitigate the harm that may cause.
To achieve the above object, the respiratory disease morbidity based on weather environment monitoring data that the present invention provides a kind of
Trend forecasting method, comprising:
Establish the multiple linear regression model of respiratory disease Prediction of Incidence Trend；
Obtain the weather environment monitoring data in the first period；The weather environment monitoring data include: temperature on average, put down
Equal air pressure, the maximum temperature difference in first period and average air quality index AQI；
Based on the weather environment monitoring data in the multiple linear regression model and first period, described is obtained
The respiratory disease disease index of second period after one period；
Data analysis is carried out to the weather environment monitoring data, obtains the temperature on average, average gas pressure, the maximum
Temperature difference level parameters corresponding with average AQI；
According to the respiratory disease disease index and the level parameters, it is pre- to generate respiratory disease incidence trend
Survey prompt information.
Preferably, the multiple linear regression model for establishing the respiratory disease Prediction of Incidence Trend specifically wraps
It includes:
Obtain the potential sample data within the scope of certain time；The potential sample data include: wind speed, temperature on average,
Average gas pressure, precipitation, medial humidity, the highest temperature, the lowest temperature, average AQI and case load；
Characteristics of Distribution is carried out to each data in the potential sample data, each potential sample data is obtained and is based on
The data distribution characteristics of time shaft；
Data distribution characteristics based on the case data carry out data screening to remaining described each potential sample data, obtain
To sample data and prediction lead；The sample data includes: temperature on average, average gas pressure, average AQI and the highest temperature
With the difference of the lowest temperature；
After carrying out data cleansing to the sample data, model training is carried out with multiple linear regression method, obtains described exhale
The multiple linear regression model of desorption system disease incidence trend prediction.
Preferably, the multiple linear regression model specifically:
Y=(coef1 × A+coef2 × B+coef3 × C+coef4 × D)+73.9849320209；
Wherein, coef1=-0.94727278, coef2=0.07566679, coef3=-0.67417332, coef4=-
0.17595693；Y is the respiratory disease disease index of the second period, and A is the temperature on average in the first period, B first
Average gas pressure in period, C are the maximum temperature difference in the first period, and D is the average AQI in the first period；First period
Initial time to the second period initial time be the prediction lead.
Preferably, described that data analysis is carried out to the weather environment monitoring data, obtain the temperature on average, average air
Pressure, the maximum temperature difference level parameters corresponding with average AQI specifically include:
Obtain the grade setting threshold parameter of the temperature on average, average gas pressure, the maximum temperature difference and average AQI；
According to the temperature on average, average gas pressure, the maximum temperature difference and average AQI grade setting threshold parameter, it is right
The weather environment monitoring data are analyzed, and the temperature on average, average gas pressure, the maximum temperature difference and average AQI are obtained
Corresponding level parameters.
Preferably, described according to the respiratory disease disease index and the level parameters, generate respiratory system disease
Sick Prediction of Incidence Trend prompt information specifically includes:
Respiratory disease disease index and the level parameters inquiry respiratory disease morbidity are stated according to described
Index, temperature on average, average gas pressure, maximum temperature difference signal language information corresponding with the average level parameters of AQI；
According to setting rule, by the respiratory disease disease index, temperature on average, average gas pressure, maximum temperature difference and
The level parameters of average AQI are spliced, and output code is generated；
According to the output code, the signal language information obtained to inquiry is spliced, and generates the respiratory disease
Prediction of Incidence Trend prompt information.
Preferably, data analysis is carried out to the weather environment monitoring data described, obtains the temperature on average, is averaged
Before air pressure, maximum temperature difference level parameters corresponding with average AQI, the method also includes:
The respiratory disease disease index, temperature on average, average gas pressure, the maximum temperature difference are established respectively and are averaged
The classification look-up table of AQI；The classification look-up table includes threshold parameter, the corresponding signal language information of each threshold parameter and rank ginseng
Number.
It is further preferred that the weather environment monitoring data further include average relative humidity, the method also includes:
Establish the classification look-up table of the average relative humidity.
Preferably, the method also includes:
Count the data of the actual case number of second period；
The data of weather environment monitoring data and the actual case number of second period in first period are made
For Modifying model sample data, the multiple linear regression model of the respiratory disease Prediction of Incidence Trend is modified.
The meteorological benchmark index generation method towards outdoor physical exercises that the present invention provides a kind of, to by current gas
As element and its observation of variation, analysis to the morbidity case and meteorological element relationship of respiratory disease morbidity, to breathe
Systemic disease Prediction of Incidence Trend model carries out the scientific and effective morbidity for predicting following a period of time acquired respiratory disease
Situation, and effective prevention prompt is provided for the common people.
Detailed description of the invention
Fig. 1 is the respiratory disease Prediction of Incidence Trend provided in an embodiment of the present invention based on weather environment monitoring data
Method flow diagram；
Fig. 2 is the practical medical number of the present invention certain hospital's respiratory disease within one period and passes through prediction model meter
The corresponding contrast curve chart for predicting medical number of the respiratory system disease index of calculation.
Specific embodiment
Below by drawings and examples, technical scheme of the present invention will be described in further detail.
The present invention establishes breathing system by the morbidity case fallen ill to respiratory disease and the analysis of meteorological element relationship
System disease incidence trend prediction model makes disease incidence prediction and prophylactic measures forecast, to help the common people to understand and can make in advance
It copes with out, to mitigate the harm that may cause.It is multi-party that this method can apply to Meteorological Services, medical services, environment, education etc.
In the service system of position.
Fig. 1 is the respiratory disease Prediction of Incidence Trend provided in an embodiment of the present invention based on weather environment monitoring data
Method, as shown, this method comprises the following steps:
Step 110, the multiple linear regression model of respiratory disease Prediction of Incidence Trend is established；
Its specific steps may include:
Step 111, the potential sample data within the scope of certain time is obtained；
Potential sample data may include the relevant data of meteorological element, such as: wind speed, temperature on average, average gas pressure, drop
Water, medial humidity, the highest temperature, the lowest temperature, average air quality index (Air Quality Index, AQI), certainly
It further include case load within this time range.This case load is the opposite case load for being able to reflect overall condition.
During the present invention establishes the multiple linear regression model of respiratory disease Prediction of Incidence Trend, used
Case load, be by the Beijing 2013-2017 hospital's respiratory disease go to a doctor number on the basis of data.It can be by its phase
That answers is split as the data with day, 3 days, week, 10 days, half a month etc. for chronomere, the meteorological element phase with same chronomere
The data of pass form potential sample data.But in potential sample data, the selection section of meteorological data is earlier than case load
Constituency section a cycle.For example, when carrying out data fractionation as unit of by week, with the meteorological data in a certain week and next all
Case load forms one group of potential sample data.
Step 112, Characteristics of Distribution is carried out to each data in potential sample data, obtains each potential sample data
Data distribution characteristics based on time shaft；
Specifically, by drawing distribution map to each data in potential sample data, it will be able to can intuitively find out disease
The features such as high-incidence season, low hair phase and some other index distribution characteristics.
Step 113, the data distribution characteristics based on case data carry out data screening to remaining each potential sample data, obtain
To sample data and prediction lead；
Specifically, the relevant data of meteorological element are analyzed, case load data relevant to meteorological element are obtained
Multivariate Linear correlation.In conjunction with above-mentioned distribution characteristics, so that it may which identify has stronger phase with case load in potential sample data
The data of closing property, as sample data.The unconspicuous meteorological data of not related or correlation is rejected.
By screening, the sample data that we obtain includes: temperature on average, average gas pressure, average AQI and the highest temperature
With the difference of the lowest temperature.
In the process, similarly for meteorological data choose section earlier than the constituency section of case load unit period into
Row rationally determines.In this example, preferably determine that the period is one week.
Step 114, after carrying out data cleansing to sample data, model training is carried out with multiple linear regression method, is exhaled
The multiple linear regression model of desorption system disease incidence trend prediction.
Specifically, the temperature on average for including by sample data, average gas pressure, average AQI and the highest temperature and minimum gas
The difference of temperature carries out data cleansing, can be using sides such as average Shift Method, recurrence Shift Methods to some data for not meeting specification
Method carries out data normalization pretreatment, then carries out model instruction using multiple linear regression method with the sample data after data cleansing
Practice, obtains the multiple linear regression model of respiratory disease Prediction of Incidence Trend.
In a specific example of the invention, obtained prediction model are as follows:
Y=(coef1 × A+coef2 × B+coef3 × C+coef4 × D)+73.9849320209；
Wherein, coef1=-0.94727278, coef2=0.07566679, coef3=-0.67417332, coef4=-
0.17595693；Y is the respiratory disease disease index of the second period, and A is the temperature on average in the first period, B first
Average gas pressure in period, C are the maximum temperature difference in the first period, and D is the average AQI in the first period；First period rose
The initial time of time to the second period beginning is to predict lead, specially one week.
In the example of above-mentioned concrete model, prediction lead is one week.Prediction lead and base can certainly be changed
The weighted value (i.e. A, B, C, D) and intercept of model are determined in the above method, to obtain adapting to the prediction mould of different prediction leads
Type.
Step 120, the weather environment monitoring data in the first period are obtained；
Weather environment monitoring data include: temperature on average, average gas pressure, maximum temperature difference and AQI in the first period.First
Period is in this example as described above, be using one week period as data statistics.
Step 130, based on the weather environment monitoring data in multiple linear regression model and the first period, when obtaining first
The respiratory disease disease index of second period after section；
Specifically, this step is according to specific prediction model above-mentioned, with temperature on average, average gas pressure, in the first period
Maximum temperature difference and AQI are argument data input model, and respiratory disease disease index can be obtained.
In this example, respiratory disease disease index and case load are equal proportion data, it is of course also possible to first by case
Number carries out normalization processing, is re-used as sample data.The respiratory disease disease index being achieved in that is exactly the finger of normalization
Number data.
Fig. 2 be certain hospital's respiratory disease within one period for actually obtaining of the present invention it is practical go to a doctor number with pass through
The corresponding contrast curve chart for predicting medical number of the respiratory system disease index that prediction model calculates.Wherein dotted line is prediction
Value, solid line are practical medical number value.It can be seen that the two fitting is relatively good, illustrate that prediction model of the invention can be fine
Carry out respiratory disease incidence trend prediction.
Step 140, data analysis is carried out to weather environment monitoring data, obtains temperature on average, average gas pressure, maximum temperature difference
Level parameters corresponding with average AQI；
Specifically, available temperature on average, average gas pressure, maximum temperature difference and average AQI grade setting threshold parameter；
According to temperature on average, average gas pressure, maximum temperature difference and average AQI grade setting threshold parameter, to weather environment
Monitoring data are analyzed, and temperature on average, average gas pressure, maximum temperature difference level parameters corresponding with average AQI are obtained.?
Here we can be by way of establishing look-up table, to facilitate the correspondence difference for carrying out meteorological data to level parameters.
In a specific example, respiratory disease disease index, temperature on average, average air can be established respectively
The classification look-up table of pressure, maximum temperature difference and average AQI.Be classified includes threshold parameter, the corresponding grade of each threshold parameter in look-up table
Other parameter can also include signal language information, mention for generating respiratory disease Prediction of Incidence Trend in following step 150
Show information.
For example, respiratory disease disease index numberical range is between 0-200, it is possible to by respiratory tract disease index
It is divided into Pyatyi: higher, high, medium, lower, low.Respiratory disease disease index-classification level-signal language information searching table
It can be arranged such as the following table 1:
| Index value | Grade | Signal language |
| 0-40 | It is low | Respiratory disease disease incidence is low |
| 41-80 | It is lower | Respiratory disease disease incidence is lower |
| 81-120 | It is medium | Respiratory disease disease incidence is medium |
| 121-160 | It is higher | Respiratory disease disease incidence is higher |
| 161-200 | It is high | Respiratory disease disease incidence is high |
Table 1
In another example using temperature on average as reference data, it is contemplated that the actual influence of crowd, we are specifically being calculated
Correspond to this parameter of sendible temperature preferably in the process to substitute temperature on average.
Sendible temperature can also be with local air humidity in addition to related with temperature, and mean wind speed, sunlight strength etc. is all
There is relationship.There are many different conversion modes in the industry.
Such as it can be calculated according to sendible temperature Tg=To+Tu-Tv.In formula, To is blinds box outside temperature, and Tu is humidity
To the value of correcting of sendible temperature, Tv is that wind speed corrects value to sendible temperature.Wherein blinds box outside temperature To can be by thermometer screen
Temperature T calculates to obtain, and is usually added one and corrects value, needs to comprehensively consider sunshine time, highest in total amount of cloud and thermometer screen
Temperature etc. can be calculated by formula, have notable difference in Various Seasonal and different regions.Other two are corrected value and are also required to
According to the difference in area and period, consider in conjunction with local climatic characteristic.
In another example can be calculated according to sendible temperature Tg=Ta+Tr+Tu+Tv；Wherein, Tr=0.42Ca (1-0.9Mc)
La；Tg is sendible temperature.Ta is temperature.Tr is the correction value that radiation influences sendible temperature；Tu is humidity to sendible temperature shadow
Loud correction value；Tv is the correction value that wind speed influences sendible temperature；Ca is coat heat absorption capacity, for example, white cloak=0.2,
Variegated coat=0.6, infrablack clothing=0.9；Mc is cloud amount coefficient, for example, fine=0.0, partly cloudy=0.3, cloudy=0.7, yin=
1.0；La is that radiation heats coefficient.
Using which kind of conversion mode, it is that insider can voluntarily select, does not discuss herein.
In the present embodiment method therefor, interval division, sendible temperature-classification established etc. are carried out according to sendible temperature
Grade-signal language information searching table, can be as shown in table 2 below.
| Sendible temperature rank | Sendible temperature | Prompt |
| 1 grade | 4 DEG C of < | It is terribly cold |
| 2 grades | 4~8 DEG C | It is cold |
| 3 grades | 8~13 DEG C | It is cool |
| 4 grades | 13~18 DEG C | It is nice and cool |
| 5 grades | 18~23 DEG C | Comfortably |
| 6 grades | 23~29 DEG C | It is warm |
| 7 grades | 29~35 DEG C | Warm heat |
| 8 grades | 35~41 DEG C | Heat |
| 9 grades | 41 DEG C of > | It is very hot |
Table 2
In the present embodiment method therefor, for maximum temperature difference, then mode as shown in table 3 below can be used, established maximum
The temperature difference-classification level-signal language information searching table.
Table 3
It, similarly can be according to air pressure height numerical value and the difference in locating geographical location, to set for average gas pressure
Different judgment criterias, and corresponding signal language is set.
, then can be as shown in table 4 below for AQI, establish AQI index-classification level-signal language information searching table.
Table 4
Above-mentioned each table is only for example, and the meteorological data classification being not intended to limit the present invention is only capable of according to the feelings divided in table
Condition is classified, and is certainly also not only that can export prompt information according to the signal language set in table.
Step 150, according to respiratory disease disease index and level parameters, it is pre- to generate respiratory disease incidence trend
Survey prompt information.
Specifically, can according to state respiratory disease disease index and level parameters inquiry respiratory disease morbidity refer to
Number, temperature on average, average gas pressure, maximum temperature difference signal language information corresponding with the average level parameters of AQI；Then according to
Setting rule, by respiratory disease disease index, temperature on average, average gas pressure, maximum temperature difference and average AQI level parameters
Spliced, generates output code；Further according to output code, the signal language information obtained to inquiry is spliced, and generates breathing
Systemic disease Prediction of Incidence Trend prompt information.
Those skilled in the art can select part of or be completely used for from above-mentioned several parameters according to actual needs
Prompt information output.For example, being obtained in a specific example according to respiratory disease disease index, AQI, temperature on average
To splicing sentence can be as enumerated in the following table 5.
Table 5
In preferred example, average relative humidity can also be used as one in weather data.In data statistics
In the process it was found that humidity has more specific influence also for the incidence trend of respiratory disease.Therefore above-mentioned
During generating respiratory disease Prediction of Incidence Trend prompt information, the shadow of the data of average relative humidity can also be added
It rings.By establishing the classification look-up table of average relative humidity, then according to average relative humidity, correspondence obtains phase from look-up table
To the rank of humidity, and prompt information is obtained, carries out sentence splicing according to rule, export respiratory disease Prediction of Incidence Trend
Prompt information.
In a specific example, we carry out writing writing for signal language, 6 coding difference with 6 coding rules
Corresponding respiratory disease disease index, AQI, temperature on average, maximum temperature difference, average gas pressure and medial humidity.It is each according to them
From data correspond to classification level and obtain corresponding signal language information, pass through sentence splicing and generate respiratory disease morbidity
Trend prediction prompt information.
Certainly an alternate code can also finally retained, to facilitate carry out Function Extension.
Meteorological benchmark index generation method provided in an embodiment of the present invention towards outdoor physical exercises, to by current
The observation of meteorological element and its variation, the analysis to the morbidity case and meteorological element relationship of respiratory disease morbidity, to exhale
Desorption system disease incidence trend prediction model carries out the scientific and effective hair for predicting following a period of time acquired respiratory disease
State of an illness condition, and effective prevention prompt is provided for the common people.
After based on the weather environment monitoring data in multiple linear regression model and the first period, obtaining for the first period
After the respiratory disease disease index of second period, it can also be carried out by the data of the actual case number with the second period
Comparison, is further modified model.To carry out the morbidity of gradual perfection respiratory disease by each continuous amendment
The model of trend prediction.
Specifically can the data of actual case number to the second period count, then by the meteorological ring in the first period
The data of the actual case number of border monitoring data and the second period fall ill to respiratory disease as Modifying model sample data
The multiple linear regression model of trend prediction is modified.
Professional should further appreciate that, described in conjunction with the examples disclosed in the embodiments of the present disclosure
Unit and algorithm steps, can be realized with electronic hardware, computer software, or a combination of the two, hard in order to clearly demonstrate
The interchangeability of part and software generally describes each exemplary composition and step according to function in the above description.
These functions are implemented in hardware or software actually, the specific application and design constraint depending on technical solution.
Professional technician can use different methods to achieve the described function each specific application, but this realization
It should not be considered as beyond the scope of the present invention.
The step of method described in conjunction with the examples disclosed in this document or algorithm, can be executed with hardware, processor
The combination of software module or the two is implemented.Software module can be placed in random access memory (RAM), memory, read-only memory
(ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technical field
In any other form of storage medium well known to interior.
Above-described specific embodiment has carried out further the purpose of the present invention, technical scheme and beneficial effects
It is described in detail, it should be understood that being not intended to limit the present invention the foregoing is merely a specific embodiment of the invention
Protection scope, all within the spirits and principles of the present invention, any modification, equivalent substitution, improvement and etc. done should all include
Within protection scope of the present invention.
Claims (8)
1. a kind of respiratory disease Prediction of Incidence Trend method based on weather environment monitoring data, which is characterized in that described
Method includes:
Establish the multiple linear regression model of respiratory disease Prediction of Incidence Trend；
Obtain the weather environment monitoring data in the first period；The weather environment monitoring data include: temperature on average, average air
Pressure, the maximum temperature difference in first period and average air quality index AQI；
Based on the weather environment monitoring data in the multiple linear regression model and first period, when obtaining described first
The respiratory disease disease index of second period after section；
Data analysis is carried out to the weather environment monitoring data, obtains the temperature on average, average gas pressure, the maximum temperature difference
Level parameters corresponding with average AQI；
According to the respiratory disease disease index and the level parameters, generates respiratory disease Prediction of Incidence Trend and mention
Show information.
2. respiratory disease Prediction of Incidence Trend method according to claim 1, which is characterized in that described in the foundation
The multiple linear regression model of respiratory disease Prediction of Incidence Trend specifically includes:
Obtain the potential sample data within the scope of certain time；The potential sample data includes: wind speed, temperature on average, is averaged
Air pressure, precipitation, medial humidity, the highest temperature, the lowest temperature, average AQI and case load；
Characteristics of Distribution is carried out to each data in the potential sample data, each potential sample data is obtained and is based on the time
The data distribution characteristics of axis；
Data distribution characteristics based on the case data carry out data screening to remaining described each potential sample data, obtain sample
Notebook data and prediction lead；The sample data include: temperature on average, average gas pressure, average AQI and the highest temperature with most
The difference of low temperature；
After carrying out data cleansing to the sample data, model training is carried out with multiple linear regression method, obtains the breathing system
The multiple linear regression model of system disease incidence trend prediction.
3. respiratory disease Prediction of Incidence Trend method according to claim 2, which is characterized in that the Multivariate Linear
Regression model specifically:
Y=(coef1 × A+coef2 × B+coef3 × C+coef4 × D)+73.9849320209；
Wherein, coef1=-0.94727278, coef2=0.07566679, coef3=-0.67417332, coef4=-
0.17595693；Y is the respiratory disease disease index of the second period, and A is the temperature on average in the first period, B first
Average gas pressure in period, C are the maximum temperature difference in the first period, and D is the average AQI in the first period；First period
Initial time to the second period initial time be the prediction lead.
4. respiratory disease Prediction of Incidence Trend method according to claim 1, which is characterized in that described to the gas
As environmental monitoring data progress data analysis, obtains the temperature on average, average gas pressure, the maximum temperature difference and average AQI and divide
Not corresponding level parameters specifically include:
Obtain the grade setting threshold parameter of the temperature on average, average gas pressure, the maximum temperature difference and average AQI；
According to the temperature on average, average gas pressure, the maximum temperature difference and average AQI grade setting threshold parameter, to described
Weather environment monitoring data are analyzed, and the temperature on average, average gas pressure, the maximum temperature difference and average AQI difference are obtained
Corresponding level parameters.
5. respiratory disease Prediction of Incidence Trend method according to claim 1 or 4, which is characterized in that the basis
The respiratory disease disease index and the level parameters generate respiratory disease Prediction of Incidence Trend prompt information tool
Body includes:
According to it is described state respiratory disease disease index and the level parameters inquire the respiratory disease disease index,
Temperature on average, average gas pressure, maximum temperature difference signal language information corresponding with the average level parameters of AQI；
According to setting rule, by the respiratory disease disease index, temperature on average, average gas pressure, maximum temperature difference and it is averaged
The level parameters of AQI are spliced, and output code is generated；
According to the output code, the signal language information obtained to inquiry is spliced, and generates the respiratory disease morbidity
Trend prediction prompt information.
6. respiratory disease Prediction of Incidence Trend method according to claim 1 or 4, which is characterized in that described right
The weather environment monitoring data carry out data analysis, obtain the temperature on average, average gas pressure, the maximum temperature difference and are averaged
Before the corresponding level parameters of AQI, the method also includes:
The respiratory disease disease index, temperature on average, average gas pressure, the maximum temperature difference and average AQI are established respectively
Classification look-up table；The classification look-up table includes threshold parameter, the corresponding signal language information of each threshold parameter and level parameters.
7. respiratory disease Prediction of Incidence Trend method according to claim 6, which is characterized in that the weather environment
Monitoring data further include average relative humidity, the method also includes:
Establish the classification look-up table of the average relative humidity.
8. respiratory disease Prediction of Incidence Trend method according to claim 1, which is characterized in that the method is also wrapped
It includes:
Count the data of the actual case number of second period；
Using the data of weather environment monitoring data and the actual case number of second period in first period as mould
Type corrects sample data, is modified to the multiple linear regression model of the respiratory disease Prediction of Incidence Trend.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910444353.3A CN110047594A (en) | 2019-05-27 | 2019-05-27 | Respiratory disease Prediction of Incidence Trend method based on weather environment monitoring data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910444353.3A CN110047594A (en) | 2019-05-27 | 2019-05-27 | Respiratory disease Prediction of Incidence Trend method based on weather environment monitoring data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110047594A true CN110047594A (en) | 2019-07-23 |
Family
ID=67283675
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910444353.3A Pending CN110047594A (en) | 2019-05-27 | 2019-05-27 | Respiratory disease Prediction of Incidence Trend method based on weather environment monitoring data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110047594A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110598937A (en) * | 2019-09-18 | 2019-12-20 | 柳州市工人医院 | CO poisoning prediction method based on meteorological data |
| CN110633856A (en) * | 2019-09-18 | 2019-12-31 | 柳州市工人医院 | CO poisoning prediction method based on meteorological and atmospheric pollutant data |
| CN111326261A (en) * | 2020-02-20 | 2020-06-23 | 武汉东湖大数据交易中心股份有限公司 | Upper respiratory disease prediction system based on meteorological data and prediction method thereof |
| CN111554404A (en) * | 2020-04-13 | 2020-08-18 | 吾征智能技术(北京)有限公司 | Disease prediction system based on indoor environment and prediction method thereof |
| CN112151185A (en) * | 2020-09-28 | 2020-12-29 | 山东财经大学 | Child respiratory disease and environment data correlation analysis method and system |
| CN112349420A (en) * | 2020-10-24 | 2021-02-09 | 武汉东湖大数据交易中心股份有限公司 | Method and system for constructing disease prediction model based on meteorological data |
| CN112582058A (en) * | 2019-11-07 | 2021-03-30 | 广州医科大学 | Slow obstructive pulmonary disease prediction method and system based on air quality |
| CN112669976A (en) * | 2021-03-18 | 2021-04-16 | 清华大学 | Crowd health assessment method and system based on ecological environment change |
| CN113571201A (en) * | 2021-08-09 | 2021-10-29 | 中国科学院地理科学与资源研究所 | Method for predicting number of epidemic respiratory system diseases and rising trend |
| CN114386874A (en) * | 2022-01-21 | 2022-04-22 | 北京国讯医疗软件有限公司 | Multi-module linkage based medical and moral medical treatment and treatment integrated management method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104809335A (en) * | 2015-04-10 | 2015-07-29 | 上海卫生信息工程技术研究中心有限公司 | Analytical prediction module of disease incidence affected by environmental change |
| CN108231195A (en) * | 2016-12-19 | 2018-06-29 | 普天信息技术有限公司 | Health risk method for early warning, server, device and Urban Air Pollution Methods |
| WO2019057887A1 (en) * | 2017-09-22 | 2019-03-28 | Universite de Bordeaux | Method for simulating respiratory dynamics of a virtual lung with modelling of muscular pressure, virtual simulator |
| CN109656918A (en) * | 2019-01-04 | 2019-04-19 | 平安科技（深圳）有限公司 | Prediction technique, device, equipment and the readable storage medium storing program for executing of epidemic disease disease index |
-
2019
- 2019-05-27 CN CN201910444353.3A patent/CN110047594A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104809335A (en) * | 2015-04-10 | 2015-07-29 | 上海卫生信息工程技术研究中心有限公司 | Analytical prediction module of disease incidence affected by environmental change |
| CN108231195A (en) * | 2016-12-19 | 2018-06-29 | 普天信息技术有限公司 | Health risk method for early warning, server, device and Urban Air Pollution Methods |
| WO2019057887A1 (en) * | 2017-09-22 | 2019-03-28 | Universite de Bordeaux | Method for simulating respiratory dynamics of a virtual lung with modelling of muscular pressure, virtual simulator |
| CN109656918A (en) * | 2019-01-04 | 2019-04-19 | 平安科技（深圳）有限公司 | Prediction technique, device, equipment and the readable storage medium storing program for executing of epidemic disease disease index |
Non-Patent Citations (2)
| Title |
|---|
| 乐满: "气象条件和空气污染对遵义市呼吸和循环系统疾病的影响及预测研究", 《中国硕士学位论文全文数据库（电子期刊）》 * |
| 赵笑颜: "气象要素对农村地区呼吸和循环系统疾病影响及干预方案研究与效果评估", 《中国博士学位论文全文数据库（电子期刊）》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110598937A (en) * | 2019-09-18 | 2019-12-20 | 柳州市工人医院 | CO poisoning prediction method based on meteorological data |
| CN110633856A (en) * | 2019-09-18 | 2019-12-31 | 柳州市工人医院 | CO poisoning prediction method based on meteorological and atmospheric pollutant data |
| CN112582058A (en) * | 2019-11-07 | 2021-03-30 | 广州医科大学 | Slow obstructive pulmonary disease prediction method and system based on air quality |
| CN111326261A (en) * | 2020-02-20 | 2020-06-23 | 武汉东湖大数据交易中心股份有限公司 | Upper respiratory disease prediction system based on meteorological data and prediction method thereof |
| CN111554404A (en) * | 2020-04-13 | 2020-08-18 | 吾征智能技术(北京)有限公司 | Disease prediction system based on indoor environment and prediction method thereof |
| CN111554404B (en) * | 2020-04-13 | 2023-09-08 | 吾征智能技术(北京)有限公司 | Disease prediction system and method based on indoor environment |
| CN112151185A (en) * | 2020-09-28 | 2020-12-29 | 山东财经大学 | Child respiratory disease and environment data correlation analysis method and system |
| CN112349420A (en) * | 2020-10-24 | 2021-02-09 | 武汉东湖大数据交易中心股份有限公司 | Method and system for constructing disease prediction model based on meteorological data |
| CN112669976A (en) * | 2021-03-18 | 2021-04-16 | 清华大学 | Crowd health assessment method and system based on ecological environment change |
| CN113571201A (en) * | 2021-08-09 | 2021-10-29 | 中国科学院地理科学与资源研究所 | Method for predicting number of epidemic respiratory system diseases and rising trend |
| CN114386874A (en) * | 2022-01-21 | 2022-04-22 | 北京国讯医疗软件有限公司 | Multi-module linkage based medical and moral medical treatment and treatment integrated management method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110047594A (en) | Respiratory disease Prediction of Incidence Trend method based on weather environment monitoring data | |
| Eludoyin et al. | Air temperature, relative humidity, climate regionalization and thermal comfort of Nigeria | |
| Mishra et al. | Bias-corrected climate projections for South Asia from coupled model intercomparison project-6 | |
| Pour et al. | Model output statistics downscaling using support vector machine for the projection of spatial and temporal changes in rainfall of Bangladesh | |
| Herrera et al. | A review of current and future weather data for building simulation | |
| Lam et al. | An analysis of future building energy use in subtropical Hong Kong | |
| Lee et al. | The estimation of base temperature for heating and cooling degree-days for South Korea | |
| Naik et al. | Projected changes in drought characteristics over the Western Cape, South Africa | |
| Royé | The effects of hot nights on mortality in Barcelona, Spain | |
| Carlucci | Thermal comfort assessment of buildings | |
| Sa’adi et al. | Selection of general circulation models for the projections of spatio-temporal changes in temperature of Borneo Island based on CMIP5 | |
| Sun et al. | Multiple drought indices for agricultural drought risk assessment on the Canadian prairies | |
| Boata et al. | Functional fuzzy approach for forecasting daily global solar irradiation | |
| Conte et al. | Bootstrap Pettitt test for detecting change points in hydroclimatological data: Case study of Itaipu Hydroelectric Plant, Brazil | |
| Roshan et al. | A comprehensive analysis of physiologically equivalent temperature changes of Iranian selected stations for the last half century | |
| Nguyen | Sustainable housing in Vietnam: Climate responsive design strategies to optimize thermal comfort | |
| Hemri et al. | Discrete postprocessing of total cloud cover ensemble forecasts | |
| CN109670670B (en) | Power load splitting method for dividing seasonal attributes | |
| Prettenthaler et al. | ‘Weather Value at Risk’: A uniform approach to describe and compare sectoral income risks from climate change | |
| Basconcillo et al. | Statistically downscaled projected changes in seasonal mean temperature and rainfall in Cagayan Valley, Philippines | |
| Panjwani et al. | Prioritization of global climate models using fuzzy analytic hierarchy process and reliability index | |
| Wang et al. | Separating out the influence of climatic trend, fluctuations, and extreme events on crop yield: A case study in Hunan Province, China | |
| Kanwal et al. | Evaluation of reanalysis and analysis datasets against measured wind data for wind resource assessment | |
| Rajagopalan et al. | Investigating thermal comfort and energy impact through microclimate monitoring-a citizen science approach | |
| You et al. | Heavy rain-producing terrestrial low pressure systems over the East Asian summer monsoon region: Evolution, energetics, and trend |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190723 |