CN115762797A - Multi-point triggering infectious disease early warning method based on big data - Google Patents
Multi-point triggering infectious disease early warning method based on big data Download PDFInfo
- Publication number
- CN115762797A CN115762797A CN202211194877.XA CN202211194877A CN115762797A CN 115762797 A CN115762797 A CN 115762797A CN 202211194877 A CN202211194877 A CN 202211194877A CN 115762797 A CN115762797 A CN 115762797A
- Authority
- CN
- China
- Prior art keywords
- data
- early warning
- infectious disease
- real
- big
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- 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
Landscapes
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention discloses a multipoint triggered infectious disease early warning method based on big data, which relates to the technical field of infectious disease early warning and aims to provide a multipoint triggered infectious disease early warning method based on big data, which improves the sensitivity and the accuracy of evaluation and monitoring and prevents and controls unknown infectious diseases, and has the technical key points that the method comprises the main indexes with statistical relevance for screening various infectious diseases; collecting historical data, and bringing index data related to infectious diseases into a regression model to obtain early warning baseline values of various data; obtaining an urban risk early warning baseline value by combining early warning baseline values of data such as symptoms and drug sales; collecting real-time data of various scenes in the region and incorporating the data into a regression model; the relation between the urban risk early warning baseline value and the real-time data is analyzed, the technical effects of realizing multi-point triggered infectious disease prediction early warning analysis, improving the sensitivity and accuracy of evaluation monitoring and realizing prevention and control of unknown infectious diseases are achieved.
Description
Technical Field
The invention relates to the technical field of infectious disease early warning, in particular to a big data-based multi-point triggering infectious disease early warning method.
Background
Infectious diseases accompany human beings since the beginning, however, because the time interval of the outbreak of infectious diseases of the past is extremely long, people cannot keep the sensitivity to various infectious diseases, and patients are scattered in various places before the outbreak, medical staff cannot be alerted quickly before a large scale is formed, and a certain time is needed for determining a diagnosis result, so that great personnel injury and economic loss are easily caused; meanwhile, because the symptoms brought by the initial stage of the infectious disease are unknown, namely whether the occurring symptoms are related to the infectious disease is unknown, only the statistics of the single disease symptoms is carried out, and the sensitivity and the accuracy of the evaluation monitoring cannot be ensured.
The prior patent CN113409952B discloses an infectious disease monitoring, preventing and controlling system and method under a multi-point trigger view, which mainly comprises a monitoring module, wherein the monitoring module is used for collecting data of suspected cases of infectious diseases from at least two dimensions of time and area; in the invention, the suspected cases of the existing infectious diseases are mainly collected from different dimensions, so that multi-point triggering is realized.
However, as is known, not only known infectious diseases but also unknown infectious diseases exist, the unknown infectious diseases are more difficult to control, and in order to improve urban safety and monitor the known and unknown infectious diseases, the invention provides a multipoint triggering infectious disease early warning method based on big data.
Disclosure of Invention
Technical problem to be solved
Aiming at the defects of the prior art, the invention provides a big-data-based multi-point triggering infectious disease early warning method which improves the sensitivity and the accuracy of evaluation and monitoring and prevents and controls unknown infectious diseases.
(II) technical scheme
In order to achieve the purpose, the invention provides the following technical scheme: a multipoint triggering infectious disease early warning method based on big data comprises the following steps:
s1, establishing a model simulation cabin, and screening main indexes with statistical relevance for various infectious diseases by adopting a multivariate analysis method;
s2, collecting historical data, and bringing the historical data such as infectious disease data, lesson absence data, medicine sales data, meteorological data, environmental data, population economics data and other index data related to infectious diseases into a regression model to obtain early warning baseline values of various data;
s3, obtaining an urban risk early warning baseline value by combining early warning baseline values of data such as symptoms, medicine sales and the like;
s4, collecting real-time data of various scenes in the region and bringing the real-time data into a regression model;
s5, analyzing the relation between the urban risk early warning baseline value and the real-time data: if the real-time data is larger than the city early warning baseline value, early warning information is sent out; and if the real-time data is smaller than the city early warning baseline value, not sending early warning information.
Preferably, in S5, the monitored, early-warning and predicted information is dynamically displayed through interactive page visualization.
Preferably, step S6: setting a city map based on a positioning system, calculating baseline values of various data in different scenes in the city, setting a display threshold value based on the baseline values, and analyzing the relation between real-time data and the display threshold value in various scenes: and when the real-time data is larger than the display threshold, marking the corresponding data in the city map.
Preferably, the method comprises a pre-warning system, the pre-warning system comprising:
the data acquisition layer is used for collecting real-time data of various scenes in the region;
the cloud data processing layer is used for comparing real-time data with the early warning baseline value and pushing a comparison result to the data application layer;
and the data application layer classifies and/or hierarchically displays the data pushed by the cloud data processing layer.
Preferably, the cloud data processing layer is further configured to process historical data, analyze the historical data in a period, and derive a data graph.
Preferably, the cloud data processing layer data memory has historical information in a period, and the data application layer includes a display unit, and the display unit is used for displaying the data of the current day, the data of the current year and a data line graph in a period.
Preferably, the display unit comprises a first display page and a second display page, the first display page is used for displaying the data of the day, the data of the current year and the data line graph in one period, and the second display page is used for displaying the city map, the abnormal data and the position of the abnormal data.
Preferably, the data application layer further comprises:
the early warning triggering unit is used for receiving abnormal data sent by the cloud data processing layer;
and the alarm module is electrically connected with the early warning trigger unit and controls the alarm module to be electrified for early warning when the early warning trigger unit receives the abnormal data.
Preferably, the data application layer further comprises a switching unit, the switching unit is electrically connected with the early warning triggering unit, and when the early warning triggering unit receives the abnormal data, the switching unit is controlled to switch the page, so that the information of the second display page is displayed.
(III) advantageous effects
Compared with the prior art, the invention provides a multipoint triggered infectious disease early warning method based on big data, which has the following beneficial effects:
by calculating baseline values of various diseases, medicine sales and other data and combining a plurality of baseline values, the urban risk early warning baseline value is calculated, and simulation exercise is performed on various infectious diseases, so that multi-point triggered infectious disease prediction early warning analysis is realized, the sensitivity and accuracy of evaluation monitoring are improved, and accurate data prediction and decision reports are provided for decision departments; meanwhile, the urban risk early warning baseline value is influenced by a plurality of data, and when unknown infectious diseases occur and one disease or medicine is sold too much, urban early warning can be triggered, so that the unknown infectious diseases are prevented and controlled.
Drawings
FIG. 1 is a flow chart of the steps of the method of the present invention;
fig. 2 is a schematic diagram of the warning system of the present invention.
In the figure: 100. an early warning system; 110. a data acquisition layer; 120. a cloud data processing layer; 130. a data application layer; 131. a display unit; 132. an early warning triggering unit; 133. an alarm module; 134. and a switching unit.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example one
Referring to fig. 1 and 2, a big data-based multi-point triggering infectious disease early warning method includes the following steps:
s1, establishing a model simulation cabin, and screening main indexes with statistical relevance for various infectious diseases by adopting a multivariate analysis method;
s2, collecting historical data, and bringing the historical data such as infectious disease data, lesson absence data, medicine sales data, meteorological data, environmental data, population economics data and other index data related to infectious diseases into a regression model to obtain early warning baseline values of various data;
s3, obtaining an urban risk early warning baseline value by combining early warning baseline values of data such as symptoms and medicine sales;
s4, collecting real-time data of various scenes in the region, and incorporating the real-time data into a regression model;
s5, analyzing the relation between the urban risk early warning baseline value and the real-time data: if the real-time data is larger than the city early warning baseline value, sending early warning information; and if the real-time data is smaller than the city early warning baseline value, not sending early warning information.
In the invention, the infectious disease risk simulation is differentiated into a plurality of parameters: social factors such as different infectious disease types, different city region risk levels, campus lesson lack rate, prevention and control of material reserves and the like are obtained under the condition that the influence of confounding factors is eliminated, and the future change trend is combined to accurately simulate on the basis of a baseline.
It should be noted that, in the present invention, the early warning baseline value of various data is calculated, and the risk level, such as a disease risk level, an urban risk level, etc., can be obtained by comparing the real-time data with the early warning baseline value.
Taking bronchitis as an example:
disease risk rating statement
1. Obtaining the current day of reference data of illness by obtaining the number of patients with bronchitis on the current day, and excluding external influence factors such as climate, environment and the like;
2. taking the bronchitis of the disease as an example, the number of sick people three days before is pulled and taken as an influence interference factor;
3. comparing the interference factors with the reference data to obtain a risk value of the day;
4. comparing the current day risk value with the baseline condition, and deducing the risk condition of the disease by taking 45% of the current specified interval as a threshold value;
and combining a plurality of disease data and incorporating the disease data into a regression model to obtain the disease early warning risk grade of the city on the day.
Early warning for predicting urban risk grade by medicine, prevention and control material and the like
And combining data such as diseases, medicine material consumption and the like, thereby calculating the risk grade and early warning of the city on the same day.
1. Taking the sales condition of the medicine N days before the current day as a reference value
2. The reference value is compared with the daily drug sale, the more the daily drug sale is, the more the material is used, the higher the infectious disease risk level is, the drug sale data is seriously lost, and a serious error may exist
The number of patients does not necessarily have a direct correlation with the risk level of the infectious disease. If the temperature suddenly drops in a certain place at a certain day, symptoms such as large-area cold, cough and fever appear, the number of sick people, the medicine consumption and the school class shortage rate are greatly improved, but the method belongs to a controllable category and is not directly related to the risk level of infectious diseases.
Of course, in the invention, whether the real-time data is abnormally high or not is judged mainly through the urban risk early warning baseline value.
Here, the bronchus is also taken as an example
City risk early warning explanation
The effect of environmental factors such as air temperature, air quality, demographics and the like in cities on epidemic diseases may have time delay and is not necessarily fed back in real time. We therefore integrated the disease with the baseline case of the city.
1. Based on the data of bronchitis before N years, such as the number of diseases in 1 day, 17 years, 18 years, 19 years and 20 years in 3 months, respectively deducting the external influence factors such as environment and climate on the day of the same year, thereby obtaining the disease baseline value of the bronchitis on the day;
2. combining with a plurality of disease data, bringing the disease data into a regression model according to different weights, and obtaining a disease early warning baseline value of the city on the day;
3. similarly, medical data and drug sales early warning baseline values can be calculated by the smooth movement of past data in a time series;
and combining the data of diseases, medicine sales and the like so as to calculate the urban risk early warning baseline value.
By using the existing multivariate data of disease factors, different urban conditions, medicine and material consumption and the like and taking a set time period as self contrast, the baseline condition of infectious diseases after the infectious diseases are removed of confounding factors is mined, and the sensitivity of a model algorithm is ensured. The virtual simulation and dynamics modeling technologies are comprehensively adopted to carry out simulation drilling on various infectious diseases, so that multi-point triggered infectious disease prediction early warning analysis is realized, the sensitivity and the accuracy of evaluation monitoring are improved, and accurate data prediction and decision reports are provided for decision departments.
The invention mainly uses a regression model, and a risk assessment model algorithm is described as follows:
the estimation of the disease rate and the infected people number is carried out based on a multiple linear regression method, a multiple linear regression model is usually used for describing the random linear relation between the variables y and x,
Yk＝β 0 +β 1 X 1 +β 2 X 2 +……+β k X k x1, X2 \8230, xk is a non-random variable, yk is a random dependent variable, and beta is a parameter simulated by regression fitting. And an accurate model which changes along with the dependent variable can be obtained after parameter estimation and significance test. After epidemic situation related parameters are taken as independent variables and are included into the model, the estimated value of the regional infection rate or the number of infected people can be obtained, and the difference between different regions can be reflected by a regression model.
Further, in S5, the monitored, early-warned and predicted information is dynamically displayed through interactive page views.
And page visualization dynamic display is realized, and the accurate and visual tracking of the state of illness development is realized.
Specifically, the early warning method includes an early warning system 100, and the early warning system 100 includes:
the data acquisition layer 110, the data acquisition layer 110 is used for collecting real-time data of a plurality of scenes in an area;
the cloud data processing layer 120 is used for storing early warning baseline values of common multiple infectious diseases, and the cloud data processing layer 120 is used for comparing real-time data with the early warning baseline values and pushing comparison results to the data application layer 130;
and the data application layer 130 classifies and/or hierarchically displays the data pushed by the cloud data processing layer 120.
Further, the cloud data processing layer 120 is further configured to process historical data, analyze the historical data in a period, and derive a data graph.
Specifically, the cloud data processing layer 120 has historical information in a period in a data memory, the data application layer 130 includes a display unit 131, and the display unit 131 is configured to display data of the current day, data of the calendar year, and a data line graph in a period.
In order to facilitate direct observation of the variation of the infectious disease in a period of time, the cloud data processing layer 120 of the present invention may store and analyze data of one period, and then convert the data into a graph to be exported.
It should be noted that a period in the present invention may be 3 days, 5 days, or a week; the derived chart is typically a line graph.
Example two
Referring to fig. 1 and 2, in the present invention, real-time data of indexes related to infectious diseases are collected, and when the real-time data is greater than a city early warning baseline value, which represents that there is an abnormality in some data or multiple data, such as infectious disease data, the infectious disease data originates from multiple hospitals, and in order to quickly find and manage an infectious disease concentrated area, in this embodiment, step S6 is added on the basis of the first embodiment.
S6, setting a city map based on a positioning system, calculating baseline values of various data in different scenes in the city, setting a display threshold value based on the baseline values, and analyzing the relation between real-time data and the display threshold value in various scenes: and when the real-time data is larger than the display threshold, marking the corresponding data in the city map.
In the method, a city map can be displayed, when the data is abnormal, abnormal data in different scenes can be correspondingly displayed in the map, and if the infectious disease in a certain hospital is greater than a display threshold value, the abnormal data can be directly displayed on the position of the community.
It should be noted that, because the data error in a single scene is large and easily exceeds the baseline value, in the present invention, the display threshold is set based on the baseline value, and the data can be displayed only if the display threshold is exceeded.
It should also be noted that there may be multiple data anomalies in a scene, such as infectious diseases and drugs in a hospital, so different data may be identified with different colors or different symbols.
Specifically, the display unit 131 includes a first display page and a second display page, the first display page is used for displaying the data of the current day, the data of the current year and a data line graph in one period, and the second display page is used for displaying a city map, abnormal data and the position of the abnormal data.
Because abnormal data used for early warning do not appear frequently, two display pages are arranged, the city map is independently displayed on the second display page, and when the abnormal data appear, the city map can be switched to the second display page.
Further, the data application layer 130 further includes:
the early warning triggering unit 132, where the early warning triggering unit 132 is configured to receive abnormal data sent by the cloud data processing layer 120;
and an alarm module 133 electrically connected to the early warning triggering unit 132, and controlling the alarm module 133 to perform power-on early warning when the early warning triggering unit 132 receives the abnormal data.
In the present invention, the early warning triggering unit 132 is provided, and when it receives abnormal data, the alarm module 133 is controlled to be powered on to send out an alarm, so as to remind the staff of abnormal data and check the abnormal data in time.
Further, the data application layer 130 further includes a switching unit 134, the switching unit 134 is electrically connected to the early warning triggering unit 132, and when the early warning triggering unit 132 receives the abnormal data, the switching unit 134 is controlled to switch the page, so that the information of the second display page is displayed.
When the data is normal, the real-time data, the historical data and the line graph in the period in the first display page are displayed, and can be checked by workers to observe the variation trend of the infectious diseases and the difference between the variation trend and the historical data; when the data is abnormal, the early warning triggering unit 132 controls the alarm module 133 to send out an early warning signal, and controls the switching unit 134 to switch the page, and the information of the second display page is automatically displayed, so that the direct positioning of the infectious disease concentrated area by the staff is ensured, and the infectious disease prevention and control efficiency is improved.
The above is only a specific embodiment of the present invention, but the technical features of the present invention are not limited thereto. Any simple changes, equivalent substitutions or modifications made based on the present invention to solve the same technical problems and achieve the same technical effects are within the scope of the present invention.
Claims (9)
1. A multipoint triggering infectious disease early warning method based on big data is characterized by comprising the following steps:
s1, establishing a model simulation cabin, and screening main indexes with statistical relevance for various infectious diseases by adopting a multivariate analysis method;
s2, collecting historical data, and bringing the historical data such as infectious disease data, lesson absence data, medicine sales data, meteorological data, environmental data, population economics data and other index data related to infectious diseases into a regression model to obtain early warning baseline values of various data;
s3, obtaining an urban risk early warning baseline value by combining early warning baseline values of data such as symptoms, medicine sales and the like;
s4, collecting real-time data of various scenes in the region and bringing the real-time data into a regression model;
s5, analyzing the relation between the urban risk early warning baseline value and the real-time data: if the real-time data is larger than the city early warning baseline value, sending early warning information; and if the real-time data is smaller than the city early warning baseline value, not sending out early warning information.
2. The big-data-based multi-point triggered infectious disease early warning method as claimed in claim 1, wherein in S5, the monitored, early-warned and predicted information is dynamically displayed through interactive page views.
3. The big-data-based multi-point infectious disease early warning method as claimed in claim 2, wherein the step S6: setting a city map based on a positioning system, calculating baseline values of various data in different scenes in the city, setting a display threshold value based on the baseline values, and analyzing the relation between real-time data and the display threshold value in various scenes: and when the real-time data is larger than the display threshold, marking the corresponding data in the city map.
4. An early warning method for an infectious disease based on big data multipoint trigger according to claim 2 or 3, characterized by comprising an early warning system (100), the early warning system (100) comprising:
a data acquisition layer (110), the data acquisition layer (110) for aggregating real-time data of a plurality of scenes within an area;
the cloud data processing layer (120) is used for storing early warning baseline values of common multiple infectious diseases, the cloud data processing layer (120) is used for comparing real-time data with the early warning baseline values and pushing comparison results to the data application layer (130);
the data application layer (130), the data application layer (130) classifies and/or hierarchically displays the data pushed by the cloud data processing layer (120).
5. The big-data-based multi-point infectious disease early warning method as claimed in claim 4, wherein: the cloud data processing layer (120) is further configured to process historical data, analyze the historical data in a period, and derive a data graph.
6. The big-data-based multi-point infectious disease early warning method as claimed in claim 5, wherein: historical information in one period is stored in the data memory of the cloud data processing layer (120), the data application layer (130) comprises a display unit (131), and the display unit (131) is used for displaying the current day data, the calendar year current day data and a data line graph in one period.
7. The big-data-based multi-point triggered infectious disease early warning method as claimed in claim 6, wherein: the display unit (131) comprises a first display page and a second display page, wherein the first display page is used for displaying the data of the day, the data of the current year and a data line graph in one period, and the second display page is used for displaying a city map, abnormal data and the position of the abnormal data.
8. The big-data-based multi-point triggered infectious disease early warning method as claimed in claim 7, wherein: the data application layer (130) further comprises:
the early warning triggering unit (132), the early warning triggering unit (132) is used for receiving the abnormal data sent by the cloud data processing layer (120);
and the alarm module (133) is electrically connected with the early warning trigger unit (132), and controls the alarm module (133) to be electrified for early warning when the early warning trigger unit (132) receives abnormal data.
9. The big-data-based multi-point triggered infectious disease early warning method as claimed in claim 8, wherein: the data application layer (130) further comprises a switching unit (134), the switching unit (134) is electrically connected with the early warning triggering unit (132), and when the early warning triggering unit (132) receives abnormal data, the switching unit (134) is controlled to switch pages, so that information of the second display page is displayed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211194877.XA CN115762797A (en) | 2022-09-28 | 2022-09-28 | Multi-point triggering infectious disease early warning method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211194877.XA CN115762797A (en) | 2022-09-28 | 2022-09-28 | Multi-point triggering infectious disease early warning method based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115762797A true CN115762797A (en) | 2023-03-07 |
Family
ID=85350536
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211194877.XA Pending CN115762797A (en) | 2022-09-28 | 2022-09-28 | Multi-point triggering infectious disease early warning method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115762797A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111403048A (en) * | 2020-03-18 | 2020-07-10 | 唐宓 | Unknown infectious disease early warning and tracing method |
| US20210090749A1 (en) * | 2019-09-24 | 2021-03-25 | Siemens Healthcare Gmbh | System and method for infectious disease notification |
| CN112562863A (en) * | 2020-12-17 | 2021-03-26 | 北京三快在线科技有限公司 | Epidemic disease monitoring and early warning method and device and electronic equipment |
| CN113409952A (en) * | 2021-08-20 | 2021-09-17 | 苏州市疾病预防控制中心 | Infectious disease monitoring, prevention and control system and method under multi-point trigger view angle |
| CN113763658A (en) * | 2021-10-09 | 2021-12-07 | 南通市疾病预防控制中心 | Multi-point triggered infectious disease early warning device and method based on big data and 5G |
| WO2022078186A1 (en) * | 2020-10-14 | 2022-04-21 | 中国银联股份有限公司 | Data real-time monitoring method and apparatus based on machine learning |
| CN114386807A (en) * | 2021-12-30 | 2022-04-22 | 中国电信股份有限公司 | Public health event emergency system and method |
| CN115101216A (en) * | 2022-08-25 | 2022-09-23 | 南京汉卫公共卫生研究院有限公司 | New infectious disease monitoring and coping system based on big data |
-
2022
- 2022-09-28 CN CN202211194877.XA patent/CN115762797A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210090749A1 (en) * | 2019-09-24 | 2021-03-25 | Siemens Healthcare Gmbh | System and method for infectious disease notification |
| CN111403048A (en) * | 2020-03-18 | 2020-07-10 | 唐宓 | Unknown infectious disease early warning and tracing method |
| WO2022078186A1 (en) * | 2020-10-14 | 2022-04-21 | 中国银联股份有限公司 | Data real-time monitoring method and apparatus based on machine learning |
| CN112562863A (en) * | 2020-12-17 | 2021-03-26 | 北京三快在线科技有限公司 | Epidemic disease monitoring and early warning method and device and electronic equipment |
| CN113409952A (en) * | 2021-08-20 | 2021-09-17 | 苏州市疾病预防控制中心 | Infectious disease monitoring, prevention and control system and method under multi-point trigger view angle |
| CN113763658A (en) * | 2021-10-09 | 2021-12-07 | 南通市疾病预防控制中心 | Multi-point triggered infectious disease early warning device and method based on big data and 5G |
| CN114386807A (en) * | 2021-12-30 | 2022-04-22 | 中国电信股份有限公司 | Public health event emergency system and method |
| CN115101216A (en) * | 2022-08-25 | 2022-09-23 | 南京汉卫公共卫生研究院有限公司 | New infectious disease monitoring and coping system based on big data |
Non-Patent Citations (2)
| Title |
|---|
| 丁翀等: ""多点触发视角下的传染病监测预警系统的设计与实现"", 《中国数字医学》, pages 70 - 74 * |
| 杨维中等: ""建立我国传染病智慧化预警多点触发机制和多渠道监测预警机制"", 《中华流行病学杂志》, pages 1753 - 1757 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5185785B2 (en) | Health condition judgment device | |
| Martínez‐Beneito et al. | Bayesian Markov switching models for the early detection of influenza epidemics | |
| JP5511077B2 (en) | User interface program, system and method for changing time scale according to density of time series data | |
| CN109298697A (en) | Thermal power plant's various parts working state evaluation method based on DBM Dynamic Baseline Model | |
| CN103562810A (en) | Process state monitoring device | |
| Argyle et al. | Investigating the relationship between eye movements and situation awareness in weather forecasting | |
| CN105955357A (en) | Cloud map display method for environment monitoring information | |
| KR102053604B1 (en) | Method for sleeping analysis and device for sleeping analysis using the same | |
| Sherlaw-Johnson et al. | Likely variations in perioperative mortality associated with cardiac surgery: when does high mortality reflect bad practice? | |
| US20190220051A1 (en) | System operation decision-making assistance device and method | |
| CN113539492A (en) | Urban health index prediction system, prediction analysis method and storage medium thereof | |
| Shiloh et al. | Early warning/track-and-trigger systems to detect deterioration and improve outcomes in hospitalized patients | |
| CN115760210A (en) | Medicine sales prediction system and method based on IPSO-LSTM model | |
| CN107121943A (en) | A kind of method and apparatus for being used to obtain the health forecast information of intelligence instrument | |
| Johnson et al. | Improved situational awareness in emergency management through automated data analysis and modeling | |
| EP3790016A1 (en) | Disease network construction method considering stratification according to confounding variable of cohort data and occurrence time between diseases, method for visualizing same, and computer-readable recording medium recording same | |
| Zhang et al. | Multi-index measurement of fatigue degree under the simulated monitoring task of a nuclear power plant | |
| Verma et al. | Developing and validating a prediction model for death or critical illness in hospitalized adults, an opportunity for human-computer collaboration | |
| CN115762797A (en) | Multi-point triggering infectious disease early warning method based on big data | |
| CN108597616A (en) | Disease abnormal deviation data examination method and device, computer installation and storage medium | |
| CN110455370B (en) | Flood-prevention drought-resisting remote measuring display system | |
| CN116098592A (en) | High-temperature early warning method and device based on physiological index and wearable equipment | |
| Novakovic et al. | Introducing the DM-P approach for analysing the performances of real-time clinical decision support systems | |
| CN111813922B (en) | High-temperature event detection method and system based on microblog text data | |
| CN113724891A (en) | Hospital epidemic situation monitoring method, device and related equipment |
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 |