CN117747129B - Hospital infection risk spatial distribution prediction method and system based on waiting process - Google Patents
Hospital infection risk spatial distribution prediction method and system based on waiting process Download PDFInfo
- Publication number
- CN117747129B CN117747129B CN202410190107.0A CN202410190107A CN117747129B CN 117747129 B CN117747129 B CN 117747129B CN 202410190107 A CN202410190107 A CN 202410190107A CN 117747129 B CN117747129 B CN 117747129B
- Authority
- CN
- China
- Prior art keywords
- space
- time
- spatial distribution
- hospital
- information
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 96
- 230000008569 process Effects 0.000 title claims abstract description 59
- 206010011409 Cross infection Diseases 0.000 title claims abstract description 51
- 208000015181 infectious disease Diseases 0.000 claims abstract description 40
- 238000009423 ventilation Methods 0.000 claims abstract description 32
- 206010029803 Nosocomial infection Diseases 0.000 claims abstract description 15
- 238000012502 risk assessment Methods 0.000 claims abstract description 7
- 239000002245 particle Substances 0.000 claims description 22
- 241000700605 Viruses Species 0.000 claims description 19
- 230000029058 respiratory gaseous exchange Effects 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000010801 machine learning Methods 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 5
- 238000000967 suction filtration Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 4
- 230000002458 infectious effect Effects 0.000 claims description 3
- 230000000241 respiratory effect Effects 0.000 claims description 3
- 230000008859 change Effects 0.000 abstract description 7
- 239000012678 infectious agent Substances 0.000 abstract description 3
- 238000003745 diagnosis Methods 0.000 description 7
- 230000006399 behavior Effects 0.000 description 6
- 208000035473 Communicable disease Diseases 0.000 description 3
- 239000003814 drug Substances 0.000 description 3
- 239000012530 fluid Substances 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 208000018569 Respiratory Tract disease Diseases 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000009792 diffusion process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000005180 public health Effects 0.000 description 2
- 230000002123 temporal effect Effects 0.000 description 2
- 206010057190 Respiratory tract infections Diseases 0.000 description 1
- 208000036142 Viral infection Diseases 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000011841 epidemiological investigation Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000009385 viral infection Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a hospital infection risk space distribution prediction method and a hospital infection risk space distribution prediction system based on a waiting process, wherein the method comprises the steps of acquiring hospital space information, ventilation operation information of each visit space and waiting process information of each visit space, and extracting characteristic data; taking the extracted characteristic data as an input variable, and inputting the input variable into a trained iF spatial distribution prediction model to obtain real-time iF spatial distribution data; and predicting the risk of nosocomial infection according to the obtained real-time iF spatial distribution data and the acquired real-time personnel space-time distribution data. The method solves the problem of uncertainty of infection risk prediction caused by space-time information change of a personnel waiting process and spread distribution characteristics of infectious agents in hospitals, so as to improve accuracy and flexibility of infection risk assessment, and guide the management of the hospital waiting process and the accurate operation of corresponding building space ventilation equipment.
Description
Technical Field
The invention relates to the technical field of disease risk prediction based on medical big data, in particular to a hospital infection risk spatial distribution prediction method and system based on a waiting process.
Background
Nosocomial infections are a global public health problem, seriously affecting medical quality and medical safety, greatly increasing medical expenses and sanitary burden of the whole society, causing significant economic loss and even affecting social stability. Hospital infection prevention and control work faces more serious challenges and also puts higher demands on hospital infection management workers. Hospitals are special public buildings, and are also "whistle" and "main battlefield" for dealing with major infectious diseases and public health events, and related risk factors accompanying cross infection in waiting process. At present, the existing researches mostly consider that the infection risks of all spaces in hospitals are uniformly distributed, and the characteristics of the infection risk space distribution caused by the uneven spread of viruses are ignored. Moreover, considering that the patient has fluidity characteristics in the hospital waiting process, the existing research does not consider the accumulated infection risk prediction caused by the change of the space-time information of the behavior path under the dynamic waiting process.
Existing patents currently approaching the present application are as follows:
The invention provides a hospital infection risk prediction method (CN 116453696B) based on a personnel space-time distribution model, and provides a method for predicting the personnel space-time distribution in a hospital waiting area through machine learning modeling based on hospital registration system data, and further correcting infection risk assessment by using the predicted real-time number of people and residence time. However, the method considers the virus distribution of the whole waiting space in the hospital as uniform mixing, namely considers the infection risk in the same space area to be consistent, and ignores the situation of indoor infection risk distribution difference caused by uneven virus diffusion of an infected person under the real waiting process.
A hospital waiting area respiratory tract infection risk prediction system (CN 114360741A) is provided, which is characterized in that samples generated by combining different input variables, air conditioner terminal forms and typical personnel density changes are constructed, and the concentration of virus transmission particles is calculated through CFD, so that the prediction of the infection risk in the waiting space is completed. Although the method calculates the concentration distribution of the virus particles in the space, the infection risk prediction in the space is still calculated according to the average infection risk, namely the accumulated infection risk difference of the susceptible person caused by the change of the space-time information of the behavior path in the waiting process can not be estimated.
According to the method and the system (CN 116994773A) for dynamically predicting the infectious disease infection risk based on the space-time trajectory data, the dynamic prediction of the infectious disease is realized by fitting the relation between the viral infection risk and the contact characteristics among individuals according to the real infection data and the space-time trajectory data of susceptible people by using algorithms such as a graph neural network and the like. The method considers the space-time trajectory data of the infected person and the susceptible person, but is mainly used in epidemiological investigation process, and does not consider the space distribution characteristic of the infected virus, so that the method is only suitable for calculating the transmission risk after the infection process has occurred, and especially can not predict and control the infection risk of the corresponding space in the hospital building.
In summary, research results in terms of accumulated infection risk prediction under the condition of considering the concentration distribution characteristics of virus particles in space when the spatial and temporal information of patient behavior paths is continuously changed in the hospital waiting process have not been found. Under the background, the application provides a hospital infection risk spatial distribution prediction method based on a waiting process.
Disclosure of Invention
Therefore, the invention aims to provide a hospital infection risk spatial distribution prediction method based on a waiting process, which solves the problem of uncertainty of infection risk prediction caused by the change of space-time information of the waiting process and the spread distribution characteristics of infectious agents of hospitals so as to improve the accuracy and flexibility of infection risk assessment, thereby guiding the management of the waiting process of the hospitals and the accurate operation of corresponding building space ventilation equipment.
In order to achieve the above purpose, the invention provides a hospital infection risk spatial distribution prediction method based on a waiting process, which comprises the following steps:
S1, acquiring hospital space information, ventilation operation information of each treatment space and waiting process information of each treatment space, and extracting characteristic data;
S2, taking the extracted characteristic data as an input variable, and inputting the input variable into the trained iF spatial distribution prediction model to obtain real-time iF spatial distribution data; the iF spatial distribution data includes an average intake fraction of the susceptible patient in the personal breathing zone i in the current visit zone j The calculation is carried out by adopting the following formula (2):
Formula (2)
Wherein,An average intake score for a susceptible patient in personal respiratory region i when the infected person is located in the j-th visit zone; /(I)Mean particle concentration in person breathing zone i, μg/m 3, for the infected person located in the j-th visit zone; /(I)Concentration of infectious particles exhaled by the infected person, μg/m 3;
The iF spatial distribution data includes an average intake score of the infected person in the human breathing zone i throughout the waiting process; the calculation is carried out by adopting the following formula (3):
Formula (3)
Wherein,An average intake score for a susceptible patient in the human breathing zone i throughout the waiting period for an infected person; /(I)A ratio of residence time for the patient in the jth visit zone; /(I)Is the number of areas to be treated;
S3, predicting the risk of nosocomial infection according to the obtained real-time iF space distribution data and the acquired real-time personnel space-time distribution data by adopting the following formula (1):
Formula (1)
Wherein,Is the infection probability; /(I)Quantum generation rate per unit of infected person quanta/h; /(I)Is the initial infection rate; /(I)The residence time for the patient to enter department n at time m; /(I)Is the number of people in the department n at m time; /(I)Taking scores for individuals in different space positions, and taking a weighted average value when the calculated object is the whole space; /(I)Is suction filtration efficiency; /(I)Is the exhale filtering efficiency.
Further preferably, in S1, the step of acquiring hospital space information, ventilation operation information of each of the doctor 'S rooms, and waiting process information of each of the doctor' S rooms, and extracting feature data includes the steps of:
extracting space function information and space position information from the hospital space information as first key features;
extracting ventilation working conditions in unit time from ventilation operation information as second key features;
and extracting the time occupation ratio of the waiting link from the waiting process information of each visit space as a third key feature.
Further preferably, the training process of the iF spatial distribution prediction model includes the following steps:
s201, using the first key feature and the second key feature as boundary conditions, and obtaining virus particle concentration space distribution data in a diagnosis space by using hydrodynamics;
S202, calculating individual intake fraction iF spatial distribution data according to spatial distribution data of virus particle concentration in space and third key features, and taking a calculation result as fourth key features;
S203, taking the first key feature, the second key feature and the third key feature as input variables, and taking the fourth key feature as output variables; training an iF spatial distribution prediction model established based on machine learning; obtaining the trained model parameters.
The invention also provides a hospital infection risk spatial distribution prediction system based on the waiting process, which is characterized by comprising the following steps of: the system comprises a data acquisition module, an iF spatial distribution prediction module and a nosocomial infection risk assessment module;
The data acquisition module is used for acquiring hospital space information, ventilation operation information of each treatment space and waiting process information of each treatment space, and extracting characteristic data;
The iF spatial distribution prediction module is used for taking the extracted characteristic data as an input variable, and inputting the extracted characteristic data into the trained iF spatial distribution prediction model to obtain real-time iF spatial distribution data;
The nosocomial infection risk assessment module is used for predicting nosocomial infection risk according to the obtained real-time iF spatial distribution data and the acquired real-time personnel space-time distribution data by adopting the following formula (1):
Formula (1)
Wherein,Is the infection probability; /(I)Quantum generation rate per unit of infected person quanta/h; /(I)Is the initial infection rate; /(I)The residence time for the patient to enter department n at time m; /(I)Is the number of people in the department n at m time; /(I)Taking scores for individuals in different spatial positions, wherein the scores are weighted average values when the calculated object is the whole space; /(I)Is suction filtration efficiency; /(I)Is the exhale filtering efficiency.
Further preferably, the data acquisition module further includes a feature extraction unit, where the feature extraction unit is configured to extract spatial function information and spatial location information from the hospital spatial information as first key features;
extracting ventilation working conditions in unit time from ventilation operation information as second key features;
and extracting the time occupation ratio of the waiting link from the waiting process information of each visit space as a third key feature.
The invention also provides an electronic device, which comprises a processor and a memory, wherein the memory stores executable instructions, and when the electronic device is operated, the executable instructions control the processor to execute the steps of the hospital infection risk spatial distribution prediction method.
The invention also provides a computer storage medium, wherein a computer program is stored on the computer storage medium, and the computer program realizes the steps of the hospital infection risk spatial distribution prediction method when being executed by a processor.
Compared with the prior art, the hospital infection risk spatial distribution prediction method and system disclosed by the application have at least the following advantages:
1. The application changes the conventional calculation mode of taking the hospital waiting space virus particles as uniform mixed space distribution in the original infection risk prediction, fully considers the diffusion characteristic and the space distribution characteristic of the virus particles, and thereby realizes the hospital infection risk space distribution prediction.
2. The influence of the spatial and temporal information change of the patient behavior path on the prediction of the risk of the nosocomial infection is comprehensively considered. According to the application, on the basis of considering the distribution characteristics of virus particles in each space of a hospital, double change information of a patient behavior path in time and space is added, so that the accumulated infection risk under different virus particle concentration distribution in the waiting process of the patient is calculated.
3. And realizing the spatial distribution characteristic of the virus particles and the real-time prediction of the hospital infection risk by using machine learning modeling. On the basis of combining the virus particle distribution characteristics and the space-time information change of the personnel behavior paths, compared with the existing method for simulating and calculating the infection risk distribution by depending on software, the method realizes the rapid prediction of the hospital infection risk space distribution, thereby guiding the hospital space design and the air conditioner operation more accurately in real time.
Drawings
Fig. 1 is a flow diagram of a method for predicting spatial distribution of risk of nosocomial infection based on a waiting process.
Figure 2 is a schematic illustration of a typical waiting space in an embodiment.
FIG. 3 is a functional division of a planar person's breathing zone and waiting area in an embodiment.
FIG. 4 is a graph comparing the spatial distribution prediction of the uptake score of an individual with the actual spatial distribution according to 2 beats per hour.
FIG. 5 is a graph comparing the spatial distribution prediction of the uptake score of an individual with the actual spatial distribution according to 6 per hour ventilation.
FIG. 6 is a graph comparing the spatial distribution prediction of the uptake score of an individual at 12 beats per hour with the actual spatial distribution.
Fig. 7 shows the prediction result of the spatial distribution of risk of nosocomial infections based on the waiting process in department 1.
Fig. 8 is a prediction result of hospital infection risk spatial distribution based on a waiting process in department 2.
Fig. 9 shows the prediction result of the spatial distribution of risk of nosocomial infections based on the waiting process in department 3.
Fig. 10 shows the prediction result of the spatial distribution of risk of nosocomial infection based on waiting process in department 4.
Fig. 11 shows the prediction result of the spatial distribution of risk of nosocomial infections based on the waiting process in department 5.
Fig. 12 is a prediction result of hospital infection risk spatial distribution based on a waiting process in department 6.
Fig. 13 is a prediction result of hospital infection risk spatial distribution based on a waiting process in department 7.
Fig. 14 is a prediction result of hospital infection risk spatial distribution based on a waiting process in department 8.
Fig. 15 is a prediction result of hospital infection risk spatial distribution based on a waiting process in department 9.
Fig. 16 is a prediction result of the spatial distribution of risk of nosocomial infections based on a waiting procedure in the department 10.
Detailed Description
The invention is described in further detail below with reference to the drawings and the detailed description.
As shown in fig. 1, the method for predicting the spatial distribution of risk of nosocomial infection according to an embodiment of the present invention includes the following steps:
S1, acquiring hospital space information, ventilation operation information of each treatment space and waiting process information of each treatment space, and extracting characteristic data;
In S1, the hospital spatial information includes a spatial location variable, a spatial function variable; the ventilation operation information comprises ventilation working conditions, wherein the ventilation working conditions comprise ventilation frequency variable and space volume variable; the waiting process information comprises process time duty ratio variables.
The spatial function variables should include a consultation area, a primary waiting area, and a secondary waiting area. Each spatial position coordinate point in the space calculated by the spatial position variable.
S2, taking the extracted characteristic data as an input variable, and inputting the input variable into the trained iF spatial distribution prediction model to obtain real-time iF spatial distribution data;
Wherein the feature extraction process comprises the following steps:
S201, extracting space functions and space positions from hospital space information as first key features, and extracting ventilation operation information as second key features;
s202, extracting the time ratio of each waiting link according to the waiting process information to serve as a third key feature;
The iF spatial distribution prediction process includes:
S203, using first and second key features as boundary conditions to obtain spatial distribution data of virus particle concentration in space by using computational fluid dynamics;
s204, calculating the spatial distribution of the individual intake fraction (iF) according to the spatial distribution data of the concentration of the virus particles in the space and the third key feature, and taking the calculation result as a fourth key feature.
Formula (2)
Formula (3)
Wherein,An average intake score for a susceptible patient in personal respiratory region i when the infected person is located in the j-th visit zone; /(I)Mean particle concentration in person breathing zone i, μg/m 3, for the infected person located in the j-th visit zone; /(I)Concentration of infectious particles exhaled by the infected person, μg/m 3; /(I)An average intake score for a susceptible patient in the human breathing zone i throughout the waiting period for an infected person; /(I)A ratio of residence time for the patient in the jth visit zone; /(I)Is the number of areas to be treated.
Taking the first key feature, the second key feature and the third key feature as input variables, and taking the fourth key feature as output variables; training an iF spatial distribution prediction model established based on machine learning; obtaining the trained model parameters. Specifically, the machine learning may be any form such as the existing neural network.
S3, predicting the risk of nosocomial infection according to the obtained real-time iF space distribution data and the acquired real-time personnel space-time distribution data by adopting the following formula (1):
Formula (1)
Wherein,Is the infection probability; /(I)Quantum generation rate per unit of infected person quanta/h; /(I)Is the initial infection rate; /(I)The residence time of the patient entering the department n at the moment m is h; /(I)Is the number of people in the department n at m time; taking scores for individuals in different spatial positions, wherein the scores are weighted average values when the calculated object is the whole space; /(I) Is suction filtration efficiency; /(I)Is the exhale filtering efficiency.
The method for predicting the infection risk of the respiratory tract disease is characterized in that the real-time personnel space-time distribution data adopts a patent number application ' 202310700348.0 ' named as a respiratory tract disease infection risk prediction method based on a personnel space-time distribution model, and the patent refers to ' according to acquired real-time diagnosis information and diagnosis space data; and inputting the diagnosis information and the diagnosis space data into a trained prediction model of the space-time distribution of the staff based on machine learning, and obtaining the real-time number of people and the residence time of the staff.
When the scheme is actually implemented and verified, 10 departments of a comprehensive hospital outpatient building such as a third class A in a cold region are selected to explain the embodiment of the invention. For convenience of explanation, the data acquisition mode will be explained in detail by taking one of departments as an example. The space is composed of a waiting room and two waiting hallways, and the total area of the case area is 225m 2 in terms of space size. In the ventilation layout, the embodiment selects an upper-and-lower-return ventilation mode, which comprises 10 air inlets with length-width dimensions of 0.5×0.5 m at the top and 6 return air with length-width dimensions of 0.5×0.2 m at the side walls of two sides of a waiting area. The waiting space area in this case includes three waiting scenes of consultation area, primary waiting and secondary waiting, and the detailed plane information is shown in fig. 2.
To predict indoor infectious agent spatial distribution, the whole waiting area is divided into 23 human breathing areas for calculation in the case implementation process, and the specific division situation is shown in fig. 3. Wherein the waiting room is divided into 15 human breath areas (area numbers 1-15) with a size of 3.00 m ×3.24 m, and the waiting corridor is divided into 8 human breath areas (area numbers 16-23) with a size of 3.30 m ×3.00 m. From the aspect of functional attributes, the whole waiting area is divided into four functional areas, including three main waiting areas of a consultation area, a primary waiting area and a secondary waiting area and a temporary travelling area at an entrance, and the distribution situation of the four functional areas is shown in fig. 3. In the actual operation process, the ventilation operation condition of the waiting area of each department of the hospital comprises seven typical ventilation frequency scenes, namely 2 h -1、4h-1、6 h-1、8 h-1、10 h-1、12 h-1 and 14 h -1. The typical waiting process time ratio common to the corresponding departments is consultation: primary waiting diagnosis: secondary waiting = 1:7:2.
Based on the 3 waiting area scenes and the 7 typical ventilation times scenes, particle track models of patients at different spatial positions can be simulated and calculated through CFD (computational fluid dynamics) fluid dynamics simulation software, and 21 simulation working conditions are calculated in total. Based on the calculation result, by combining the formula (2) and the formula (3), the intake score of the 23 person breathing area can be calculated under different ventilation times and waiting flows of the case waiting area, and the iF calculation result can be obtained.
The position numbers of the 23 person breathing areas and the corresponding functional areas are collected to be first key features, the ventilation times are collected to be second features, the typical visit procedure time ratio is collected to be third features, and the iF calculation result is collected to be fourth key features. Taking the first key feature, the second key feature and the third key feature as input variables, and taking the fourth key feature as output variables; training an iF spatial distribution prediction model established based on machine learning; obtaining the trained model parameters. Fig. 4, fig. 5, and fig. 6 are respectively the comparison of the actual distribution situation and the predicted distribution situation of the indoor IF space in the three different ventilation frequency scenes of the treatment area, namely, 2 times/h, 6 times/h, and 12 times/h, in fig. 4-fig. 6, the size of the IF value is represented according to different gray values in the square, the darker the color, the larger the value; the average prediction residual is close to 1 x 10 -2, which proves that the model meets the prediction accuracy requirement. Modeling the rest typical departments according to the method to obtain the iF spatial distribution prediction model of 10 hospital typical departments.
The 10 typical departments are departments 1-1; department 2-internal medicine 2; department 3-internal medicine 3; department 4-department of traditional Chinese medicine; department 5-dermatology; department 6-stomatology; department 7-special consulting room; department 8-ophthalmology; department 9-otorhinolaryngology department; department 10-operating room.
And (3) calculating the infection probability of the space in diagnosis under space-time distribution by using a formula (1) by combining the real-time iF space distribution prediction result obtained in the last step with the prediction results of the number of people and the residence time of 10 departments in one day calculated based on registration information, wherein the results are shown in figures 7-16.
It is apparent that the above examples are given by way of illustration only and are not limiting of the embodiments. Other variations or modifications of the above teachings will be apparent to those of ordinary skill in the art. It is not necessary here nor is it exhaustive of all embodiments. While still being apparent from variations or modifications that may be made by those skilled in the art are within the scope of the invention.
Claims (7)
1. A hospital infection risk spatial distribution prediction method based on a waiting process is characterized in that: the method comprises the following steps:
S1, acquiring hospital space information, ventilation operation information of each treatment space and waiting process information of each treatment space, extracting characteristic data, and acquiring real-time personnel space-time distribution data;
S2, taking the extracted characteristic data as an input variable, and inputting the input variable into the trained iF spatial distribution prediction model to obtain real-time iF spatial distribution data; the iF spatial distribution data includes an average intake fraction of the susceptible patient in the personal breathing zone i in the current visit zone j The calculation is carried out by adopting the following formula (2):
Formula (2)
Wherein,An average intake score for a susceptible patient in personal respiratory region i when the infected person is located in the j-th visit zone; /(I)Mean particle concentration in person breathing zone i, μg/m 3, for the infected person located in the j-th visit zone; /(I)Concentration of infectious particles exhaled by the infected person, μg/m 3;
Calculating the average intake score of the susceptible patient in the breathing zone i of the person during the whole waiting process; the calculation is carried out by adopting the following formula (3):
Formula (3)
Wherein,An average intake score for a susceptible patient in the human breathing zone i throughout the waiting period for an infected person; /(I)A ratio of residence time for the patient in the jth visit zone; /(I)Is the number of areas to be treated;
S3, predicting the risk of nosocomial infection according to the obtained real-time iF space distribution data and the acquired real-time personnel space-time distribution data by adopting the following formula (1):
Formula (1)
Wherein,Is the infection probability; /(I)Quantum generation rate per unit of infected person quanta/h; /(I)Is the initial infection rate; /(I)The residence time for the patient to enter department n at time m; /(I)Is the number of people in the department n at m time; /(I)Taking scores for individuals in different space positions, and taking a weighted average value when the calculated object is the whole space; /(I)Is suction filtration efficiency; /(I)Is the exhale filtering efficiency.
2. The method for predicting hospital infection risk spatial distribution based on a waiting process according to claim 1, wherein in S1, the steps of obtaining hospital spatial information, ventilation operation information of each of the doctor 'S rooms, and waiting process information of each of the doctor' S rooms, and extracting feature data include the steps of:
extracting space function information and space position information from the hospital space information as first key features;
extracting ventilation working conditions in unit time from ventilation operation information as second key features;
and extracting the time occupation ratio of the waiting link from the waiting process information of each visit space as a third key feature.
3. The method for predicting the spatial distribution of risk of nosocomial infections based on a waiting procedure according to claim 2, wherein the training process of the spatial distribution prediction model of iF comprises the following steps:
s201, using a first key feature and a second key feature as boundary conditions, and obtaining virus particle concentration space distribution data in space by using hydrodynamics;
S202, calculating individual intake fraction iF spatial distribution data according to spatial distribution data of virus particle concentration in space and third key features, and taking a calculation result as fourth key features;
s203, taking the first key feature, the second key feature and the third key feature as input variables, and taking the fourth key feature as output variables; and training the iF spatial distribution prediction model established based on machine learning to obtain trained model parameters.
4. A hospital infection risk spatial distribution prediction system based on a waiting process, for implementing the hospital infection risk spatial distribution prediction method according to any one of claims 1 to 3, comprising: the system comprises a data acquisition module, an iF spatial distribution prediction module and a nosocomial infection risk assessment module;
The data acquisition module is used for acquiring hospital space information, ventilation operation information of each treatment space and waiting process information of each treatment space, extracting characteristic data and acquiring real-time personnel space-time distribution data;
The iF spatial distribution prediction module is used for taking the extracted characteristic data as an input variable, and inputting the extracted characteristic data into the trained iF spatial distribution prediction model to obtain real-time iF spatial distribution data;
The nosocomial infection risk assessment module is used for predicting nosocomial infection risk according to the obtained real-time iF spatial distribution data and the acquired real-time personnel space-time distribution data by adopting the following formula (1):
Formula (1)
Wherein,Is the infection probability; /(I)Quantum generation rate per unit of infected person quanta/h; /(I)Is the initial infection rate; /(I)The residence time for the patient to enter department n at time m; /(I)Is the number of people in the department n at m time; /(I)Taking scores for individuals in different spatial positions, wherein the scores are weighted average values when the calculated object is the whole space; /(I)Is suction filtration efficiency; /(I)Is the exhale filtering efficiency.
5. The hospital infection risk spatial distribution prediction system based on a waiting process according to claim 4, wherein the data acquisition module further comprises a feature extraction unit, and the feature extraction unit is used for extracting spatial function information and spatial position information from the hospital spatial information as first key features;
extracting ventilation working conditions in unit time from ventilation operation information as second key features; and extracting the time occupation ratio of the waiting link from the waiting process information of each visit space as a third key feature.
6. An electronic device comprising a processor and a memory, the memory storing executable instructions that when run the electronic device control the processor to perform the steps of the waiting procedure based hospital infection risk spatial distribution prediction method according to claims 1-3.
7. A computer storage medium, wherein a computer program is stored on the computer storage medium, and when the computer program is executed by a processor, the steps of the hospital infection risk spatial distribution prediction method based on the waiting process according to any one of claims 1 to 3 are implemented.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410190107.0A CN117747129B (en) | 2024-02-21 | 2024-02-21 | Hospital infection risk spatial distribution prediction method and system based on waiting process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410190107.0A CN117747129B (en) | 2024-02-21 | 2024-02-21 | Hospital infection risk spatial distribution prediction method and system based on waiting process |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117747129A CN117747129A (en) | 2024-03-22 |
| CN117747129B true CN117747129B (en) | 2024-04-30 |
Family
ID=90251227
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410190107.0A Active CN117747129B (en) | 2024-02-21 | 2024-02-21 | Hospital infection risk spatial distribution prediction method and system based on waiting process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117747129B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107220482A (en) * | 2017-05-09 | 2017-09-29 | 清华大学 | Respiratory infectious disease risk evaluating system and appraisal procedure |
| CN111311018A (en) * | 2020-03-04 | 2020-06-19 | 苏州远征魂车船技术有限公司 | Accurate management and control system of epidemic situation |
| CN114360741A (en) * | 2022-01-29 | 2022-04-15 | 天津大学 | Respiratory infectious disease infection risk prediction system in waiting area of hospital |
| CN116453696A (en) * | 2023-06-14 | 2023-07-18 | 天津大学 | Respiratory tract disease infection risk prediction method based on personnel space-time distribution model |
| CN116798604A (en) * | 2023-06-27 | 2023-09-22 | 首都医科大学附属北京地坛医院 | Heating respiratory syndrome monitoring and early warning method and system based on multi-source data |
| CN117198518A (en) * | 2023-06-28 | 2023-12-08 | 招商局邮轮研究院(上海)有限公司 | Quantitative risk assessment method for cross-regional transmission of viruses in mail wheel and application |
| CN117238504A (en) * | 2023-11-01 | 2023-12-15 | 江苏亿通高科技股份有限公司 | Smart city CIM data optimization processing method |
-
2024
- 2024-02-21 CN CN202410190107.0A patent/CN117747129B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107220482A (en) * | 2017-05-09 | 2017-09-29 | 清华大学 | Respiratory infectious disease risk evaluating system and appraisal procedure |
| CN111311018A (en) * | 2020-03-04 | 2020-06-19 | 苏州远征魂车船技术有限公司 | Accurate management and control system of epidemic situation |
| CN114360741A (en) * | 2022-01-29 | 2022-04-15 | 天津大学 | Respiratory infectious disease infection risk prediction system in waiting area of hospital |
| CN116453696A (en) * | 2023-06-14 | 2023-07-18 | 天津大学 | Respiratory tract disease infection risk prediction method based on personnel space-time distribution model |
| CN116798604A (en) * | 2023-06-27 | 2023-09-22 | 首都医科大学附属北京地坛医院 | Heating respiratory syndrome monitoring and early warning method and system based on multi-source data |
| CN117198518A (en) * | 2023-06-28 | 2023-12-08 | 招商局邮轮研究院(上海)有限公司 | Quantitative risk assessment method for cross-regional transmission of viruses in mail wheel and application |
| CN117238504A (en) * | 2023-11-01 | 2023-12-15 | 江苏亿通高科技股份有限公司 | Smart city CIM data optimization processing method |
Non-Patent Citations (2)
| Title |
|---|
| 呼吸道传染病空气传播的感染概率的预测模型;钱华等;东南大学学报（自然科学版）;20120531;第42卷(第3期);第1-3节 * |
| 考虑人员密度分布的儿童医院候诊空间感染风险研究;刘刚等;天津大学学报（自然科学与工程技术版）;20221231;第55卷(第12期);1-2节 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117747129A (en) | 2024-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Singh et al. | Generalized SIR (GSIR) epidemic model: An improved framework for the predictive monitoring of COVID-19 pandemic | |
| Al-Refaie et al. | Applying simulation and DEA to improve performance of emergency department in a Jordanian hospital | |
| Ramos et al. | A simple but complex enough θ-SIR type model to be used with COVID-19 real data. Application to the case of Italy | |
| Singh et al. | An integrated fog and Artificial Intelligence smart health framework to predict and prevent COVID-19 | |
| CN113192645B (en) | Discrete grid-based infectious disease space-time diffusion evolution and artificial prevention and control simulation method | |
| Soltanzadeh et al. | Performance evaluation of refuge floors in combination with egress components in high-rise buildings | |
| Allahi et al. | The COVID-19 epidemic and evaluating the corresponding responses to crisis management in refugees: a system dynamic approach | |
| CN113077907B (en) | Novel infectious disease road infection probability calculation model | |
| Kwok et al. | Rule-base derivation for intensive care ventilator control using ANFIS | |
| Bai | Simulations of COVID-19 spread by spatial agent-based model and ordinary differential equations | |
| Xuan et al. | Optimal policies for a pandemic: A stochastic game approach and a deep learning algorithm | |
| Ghoroghi et al. | Impact of ventilation and avoidance measures on SARS-CoV-2 risk of infection in public indoor environments | |
| CN116453696B (en) | Respiratory tract disease infection risk prediction method based on personnel space-time distribution model | |
| Cui et al. | Virus transmission risk of college students in railway station during Post-COVID-19 era: Combining the social force model and the virus transmission model | |
| Aroua et al. | Forecast emergency room visits–a major diagnostic categories based approach | |
| CN117747129B (en) | Hospital infection risk spatial distribution prediction method and system based on waiting process | |
| Wang et al. | Real-time adaptive allocation of emergency department resources and performance simulation based on stochastic timed petri nets | |
| CN105046390A (en) | Hospital department layout method and hospital department layout apparatus | |
| Kumar et al. | Image analysis and data processing for COVID-19 | |
| Djiomba Njankou | Mathematical models of Ebola virus disease with socio-economic dynamics | |
| Hegde et al. | Modeling Social Distancing and Quantifying Epidemic Disease Exposure in a Built Environment | |
| Bongolan et al. | Covid-19 agent-based model: An epidemiological simulator applied in vaccination scenarios for quezon city, philippines | |
| Long et al. | OR's next top model: Decision models for infectious disease control | |
| Veloz et al. | On the interplay between mobility and hospitalization capacity during the COVID-19 pandemic: The SEIRHUD model | |
| Vasanthan et al. | Cognitive Epidemic Supervision And Control By Interpretation Of Infected Patients |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |