Emergency patient intelligent scoring method and system based on special disease scoring tool

Abstract

The embodiment of the invention provides an emergency patient intelligent scoring method and system based on a special disease scoring tool. The method comprises the following steps: capturing pressure fluctuation characteristics and a microbial leakage threshold value of a biological sample of an emergency patient in a transmission process in real time, synchronously analyzing use conditions of an antiviral drug, an antibiotic and an immunomodulator, calculating a transmission risk value of the individualized biological sample, and constructing a dynamic transmission risk map. And by fusing the pressure fluctuation characteristics of the atlas and an immunomodulator administration mode, generating an early warning score grade, triggering a shunting instruction to isolate a high-risk sample, and adjusting the airflow parameter and the drug storage priority of a negative pressure isolation region. The method effectively improves the efficiency and safety of infectious disease patient management, and achieves the precise medical resource distribution and risk control. According to the technical scheme provided by the embodiment of the invention, the capability of coping with infectious disease emergencies of hospitals is remarkably improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of intelligent scoring, and particularly to an intelligent scoring method and system for emergency patients based on a disease-specific scoring tool. Background Art

[0002] In the emergency department environment, quickly and accurately assessing the risk of infectious disease patients is crucial for preventing disease transmission. Specifically, the emergency department requires a method that can real-time monitor and evaluate the potential pathogen diffusion risk during the transmission of respiratory secretions and blood samples.

[0003] Currently, medical institutions usually rely on traditional laboratory testing methods and experience-based clinical judgments to evaluate the infectious disease risk of emergency patients. These methods include collecting patient samples for laboratory analysis to determine the pathogen type and concentration, and formulating treatment plans based on doctors' professional knowledge. At the same time, for hospital infection control, some basic isolation measures are also adopted, such as setting up specific isolation wards and wearing protective equipment. However, these measures often lack a specific quantitative assessment of microbial diffusion during sample transmission and a comprehensive consideration of patients' individualized medical data.

[0004] Existing solutions have several significant drawbacks: First, traditional laboratory testing is time-consuming and cannot meet the rapid response requirements of the emergency department; second, although experience-based clinical judgment has certain guiding significance, due to the lack of full consideration of microbial diffusion during sample transmission and its interaction with drug effects, the risk assessment is not accurate enough; finally, existing isolation measures are mostly general strategies and are difficult to be adjusted individually according to the specific conditions of different patients, which to a certain extent limits their prevention and control effects. Summary of the Invention

[0005] The embodiments of the present application provide an intelligent scoring method and system for emergency patients based on a disease-specific scoring tool to solve the problem of inaccurate risk assessment in the prior art.

[0006] In a first aspect, the embodiments of the present application provide an intelligent scoring method for emergency patients based on a disease-specific scoring tool, including:

[0007] By capturing in real time the pressure fluctuation characteristics of respiratory secretions and blood samples of emergency patients in the pneumatic transmission pipeline and the microbial leakage threshold of the sealed cabin, generating biologic sample pneumatic trajectory data including a sample collection timestamp sequence;

[0008] Synchronously analyzing the antiviral drug usage frequency, antibiotic combination drug usage intensity, and immunomodulator administration interval pattern in the emergency department medication records, and extracting infectious disease-related drug characteristics;

[0009] Perform a time series matching of the sample collection timestamp sequence in the pneumatic trajectory data of the biological sample with the antiviral drug usage frequency in the infectious disease associated drug characteristics, and calculate the patient individualized biological sample transmission risk value in combination with the microbial leakage threshold of the sealed cabin;

[0010] Based on the patient individualized biological sample transmission risk value and the antibiotic combination drug intensity, construct a dynamic transmission risk map reflecting the correlation between the pathogen aerosol diffusion path and the drug usage pattern;

[0011] By fusing the pressure fluctuation characteristics in the dynamic transmission risk map and the immunomodulator administration interval pattern, generate a warning score level for emergency infectious disease patients, and trigger a shunt instruction for the pneumatic transmission pipeline in real time to isolate high-risk samples;

[0012] Dynamically adjust the air flow parameters in the negative pressure isolation area and the priority of infectious disease drug reserves according to the warning score level, and synchronously optimize the monitoring frequency of the antibiotic combination drug intensity in the medication record.

[0013] Optionally, performing a time series matching of the sample collection timestamp sequence in the pneumatic trajectory data of the biological sample with the antiviral drug usage frequency in the infectious disease associated drug characteristics, and calculating the patient individualized biological sample transmission risk value in combination with the microbial leakage threshold of the sealed cabin, includes:

[0014] Based on the sample collection timestamp sequence in the pneumatic trajectory data of the biological sample, establish a time series matching rule through the time distribution characteristics of the antiviral drug usage frequency, and generate an antiviral drug action time interval with a dynamic window length;

[0015] Within the antiviral drug action time interval, perform a segmented analysis of the pressure fluctuation characteristics of the pneumatic transmission pipeline according to the microbial leakage threshold of the sealed cabin, and extract the microbial diffusion probability distribution synchronized with the timestamp sequence;

[0016] Combining the drug concentration gradient change trend in the time series matching rule and the microbial diffusion probability distribution, calculate the initial parameters of the patient individualized biological sample transmission risk value through the spatial superposition effect of the microbial residue amount and the drug metabolism cycle;

[0017] Perform a time decay compensation on the initial parameters based on the immunomodulator administration interval pattern, and correct the weight coefficient of the microbial diffusion path according to the antibiotic combination drug intensity, and output an individualized biological sample transmission risk value that fuses multi-source time series characteristics.

[0018] Optionally, by combining the drug concentration gradient change trend in the timing matching rule with the microbial diffusion probability distribution, and through the spatial superposition effect of the microbial residue amount and the drug metabolism cycle, calculate the initial parameters of the patient's individualized biological sample transmission risk value, including:

[0019] Based on the microbial diffusion probability distribution within the antiviral drug action time interval, establish a dynamic deposition function of the microbial residue amount changing with the transmission path length, and generate a spatial attenuation parameter associated with the drug metabolism cycle;

[0020] According to the drug concentration gradient change trend in the timing matching rule, calculate the dynamic inhibition intensity of the antiviral drug on the microbial diffusion probability distribution, and generate a microbial diffusion correction coefficient with time-dependent characteristics;

[0021] Combine the spatial attenuation parameter and the microbial diffusion correction coefficient, and through the superposition effect of the microbial residue deposition path and the drug metabolism rate, generate the spatio-temporal coupling characteristics of the initial parameters of the biological sample transmission risk;

[0022] Based on the immunomodulator dosing interval pattern, perform dynamic smoothing processing on the spatio-temporal coupling characteristics, and use the interference effect of the antibiotic combination dosing intensity on the microbial deposition path to calculate the initial parameters of the patient's individualized biological sample transmission risk value, and output the multi-dimensional fusion microbial residue distribution characteristics.

[0023] Optionally, within the antiviral drug action time interval, perform segmented analysis on the pressure fluctuation characteristics of the pneumatic transmission pipeline according to the microbial leakage threshold of the sealed cabin, and extract the microbial diffusion probability distribution synchronized with the time stamp sequence, including:

[0024] Based on the pressure fluctuation characteristics of the pneumatic transmission pipeline within the antiviral drug action time interval, combine the microbial leakage threshold of the sealed cabin, and perform segmented analysis on the pressure fluctuation data to generate the pressure fluctuation segmented characteristics synchronized with the sample collection time stamp sequence;

[0025] According to the pressure fluctuation segmented characteristics, extract the microbial diffusion trend within each segment, and combine the microbial leakage threshold of the sealed cabin to perform dynamic modeling on the microbial diffusion path, and generate the microbial diffusion probability distribution synchronized with the time stamp sequence;

[0026] Based on the microbial diffusion probability distribution, combine the drug concentration gradient change trend within the antiviral drug action time interval, calculate the dynamic inhibition intensity of the microbial diffusion probability distribution, and generate a microbial diffusion correction coefficient with time-dependent characteristics;

[0027] Fuse the microbial diffusion correction coefficient with the segmented characteristics of the pressure fluctuation, extract the microbial diffusion probability distribution synchronized with the timestamp sequence, combine the interference effect of the antibiotic combination drug strength on the microbial diffusion path, output the dynamically updated microbial diffusion probability distribution, and use it as the input parameter for subsequent calculation of the patient's individualized biological sample transmission risk value.

[0028] Optionally, combine the spatial attenuation parameter with the microbial diffusion correction coefficient, and generate the spatio-temporal coupling characteristics of the initial parameter of the biological sample transmission risk through the superposition effect of the microbial residue deposition path and the drug metabolism rate, including:

[0029] Based on the microbial diffusion probability distribution within the action time interval of the antiviral drug, combine the dynamic deposition function of the microbial residue amount changing with the transmission path length, and generate the spatial attenuation parameter associated with the drug metabolism cycle;

[0030] According to the trend of the drug concentration gradient change in the timing matching rule, calculate the dynamic inhibition intensity of the antiviral drug on the microbial diffusion probability distribution, and generate the microbial diffusion correction coefficient with time-dependent characteristics;

[0031] Fuse the spatial attenuation parameter with the microbial diffusion correction coefficient, and combine the superposition effect of the microbial residue deposition path and the drug metabolism rate to generate the spatio-temporal coupling characteristics of the initial parameter of the biological sample transmission risk;

[0032] Based on the immunomodulator dosing interval pattern, perform dynamic smoothing on the spatio-temporal coupling characteristics, combine the interference effect of the antibiotic combination drug strength on the microbial deposition path, output the multi-dimensional fusion microbial residue distribution characteristics, and use it as the input parameter for subsequent calculation of the patient's individualized biological sample transmission risk value.

[0033] Optionally, based on the microbial diffusion probability distribution within the action time interval of the antiviral drug, establish a dynamic deposition function of the microbial residue amount changing with the transmission path length, and generate the spatial attenuation parameter associated with the drug metabolism cycle, including:

[0034] Analyze the initial parameter of the patient's individualized biological sample transmission risk value, according to the microbial diffusion probability distribution within the action time interval of the antiviral drug, identify the change rule of the microbial residue amount with the transmission path length, and form the dynamic deposition function of the microbial residue amount;

[0035] According to the trend of the drug concentration gradient change in the timing matching rule, evaluate the dynamic inhibition intensity of the antiviral drug on the microbial diffusion probability distribution, and generate the microbial diffusion correction coefficient with time-dependent characteristics;

[0036] Combining the microbial diffusion correction coefficient with the dynamic deposition function of microbial residue amount, and utilizing the interaction between the microbial residue deposition path and the drug metabolism rate, to construct the spatio-temporal coupling characteristics of the initial parameters of the biological sample transmission risk;

[0037] Based on the administration interval pattern of the immunomodulator, perform dynamic smoothing processing on the spatio-temporal coupling characteristics, and at the same time consider the interference effect of the antibiotic combination drug strength on the microbial deposition path, output the multi-dimensional fusion microbial residue distribution characteristics, and adjust the microbial residue distribution characteristics according to the drug metabolism cycle to generate the spatial attenuation parameters associated with the drug metabolism cycle.

[0038] Optionally, based on the pressure fluctuation characteristics of the pneumatic transmission pipeline within the action time interval of the antiviral drug, combined with the microbial leakage threshold of the sealed cabin, perform segmented analysis on the pressure fluctuation data to generate the pressure fluctuation segmented characteristics synchronized with the sample collection timestamp sequence, including:

[0039] Analyze the pressure fluctuation characteristics of the pneumatic transmission pipeline during the transmission of the patient's individualized biological samples, and according to the drug concentration gradient change trend within the action time interval of the antiviral drug, identify the pressure fluctuation pattern synchronized with the sample collection timestamp sequence to form a preliminary set of pressure fluctuation segmented characteristics;

[0040] Analyze the set of pressure fluctuation segmented characteristics obtained in the first step according to the microbial leakage threshold of the sealed cabin, extract the microbial diffusion trend within each segment, and dynamically model the microbial diffusion path in combination with the microbial leakage threshold of the sealed cabin to generate the microbial diffusion probability distribution synchronized with the timestamp sequence;

[0041] Based on the microbial diffusion probability distribution, combined with the drug concentration gradient change trend within the action time interval of the antiviral drug, calculate the dynamic inhibition intensity of the microbial diffusion probability distribution to generate a microbial diffusion correction coefficient carrying time-dependent characteristics;

[0042] Combine the microbial diffusion correction coefficient with the preliminary set of pressure fluctuation segmented characteristics, and utilize the interaction between the microbial diffusion path and the drug metabolism rate to generate the pressure fluctuation segmented characteristics synchronized with the sample collection timestamp sequence.

[0043] In a second aspect, an intelligent scoring system for emergency patients based on a disease-specific scoring tool provided by an embodiment of the present application includes:

[0044] A capture module, configured to generate biological sample pneumatic trajectory data including a sample collection timestamp sequence by capturing the pressure fluctuation characteristics of the emergency patient's respiratory secretions and blood samples in the pneumatic transmission pipeline and the microbial leakage threshold of the sealed cabin;

[0045] An analysis module for synchronously analyzing the usage frequency of antiviral drugs, the combined antibiotic usage intensity, and the administration interval pattern of immunomodulators in the emergency department medication records, and extracting the drug characteristics associated with infectious diseases;

[0046] A calculation module for performing temporal matching on the sample collection timestamp sequence in the pneumatic trajectory data of the biological sample and the usage frequency of antiviral drugs in the drug characteristics associated with infectious diseases, and calculating the individualized biological sample transmission risk value of the patient in combination with the microbial leakage threshold of the sealed cabin;

[0047] A construction module for constructing a dynamic transmission risk map reflecting the correlation between the pathogen aerosol diffusion path and the medication pattern based on the individualized biological sample transmission risk value of the patient and the combined antibiotic usage intensity;

[0048] A fusion module for generating an early warning score level for emergency infectious disease patients by fusing the pressure fluctuation characteristics in the dynamic transmission risk map and the administration interval pattern of immunomodulators, and triggering a shunt instruction for the pneumatic transmission pipeline in real time to isolate high-risk samples;

[0049] A synchronization module for dynamically adjusting the air flow parameters in the negative pressure isolation area and the priority of infectious disease drug reserves according to the early warning score level, and synchronously optimizing the monitoring frequency of the combined antibiotic usage intensity in the medication records.

[0050] In a third aspect, an embodiment of the present application provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement an intelligent scoring method for emergency patients based on a disease-specific scoring tool as described in the first aspect above.

[0051] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program, and when the computer program is executed by a computer, it implements an intelligent scoring method for emergency patients based on a disease-specific scoring tool as described in the first aspect.

[0052] In the embodiments of the present application, by capturing in real time the pressure fluctuation characteristics of emergency patients' respiratory secretions and blood samples in the pneumatic transmission pipeline and the microbial leakage threshold of the sealed cabin, biological sample pneumatic trajectory data including a sample collection timestamp sequence is generated; the usage frequency of antiviral drugs, the combined antibiotic usage intensity, and the immunomodulator administration interval pattern in the emergency department medication records are synchronously analyzed to extract infectious disease-related drug characteristics; the sample collection timestamp sequence in the biological sample pneumatic trajectory data is temporally matched with the usage frequency of antiviral drugs in the infectious disease-related drug characteristics, and the patient's individualized biological sample transmission risk value is calculated in combination with the microbial leakage threshold of the sealed cabin; based on the patient's individualized biological sample transmission risk value and the combined antibiotic usage intensity, a dynamic transmission risk map reflecting the correlation between the pathogen aerosol diffusion path and the medication pattern is constructed; by fusing the pressure fluctuation characteristics and the immunomodulator administration interval pattern in the dynamic transmission risk map, an early warning score level for emergency infectious disease patients is generated, and a shunt instruction for the pneumatic transmission pipeline is triggered in real time to isolate high-risk samples; according to the early warning score level, the air flow parameters in the negative pressure isolation area and the priority of infectious disease drug reserves are dynamically adjusted, and the monitoring frequency of the combined antibiotic usage intensity in the medication record is synchronously optimized.

[0053] The technical solution of the present application has the following beneficial effects:

[0054] By capturing in real time the pressure fluctuation characteristics of emergency patients' respiratory secretions and blood samples in the pneumatic transmission pipeline and the microbial leakage threshold of the sealed cabin, biological sample pneumatic trajectory data including a sample collection timestamp sequence can be generated immediately. This enables medical staff to quickly understand the potential risks during sample transmission, providing a basis for timely isolation measures; synchronously analyzing the usage frequency of antiviral drugs, the combined antibiotic usage intensity, and the immunomodulator administration interval pattern in the emergency department medication records helps to extract infectious disease-related drug characteristics, thereby guiding clinical medication more precisely, optimizing the treatment plan, and improving the cure rate; the patient's individualized biological sample transmission risk value calculated by combining the above information not only reflects the interaction between the patient's own condition and external environmental influencing factors, but also provides a scientific basis for formulating personalized prevention and control strategies, effectively reducing the risk of nosocomial infection; the dynamic transmission risk map constructed based on the patient's individualized biological sample transmission risk value and the combined antibiotic usage intensity can intuitively reflect the relationship between the pathogen aerosol diffusion path and the medication pattern, assisting the hospital in optimizing the spatial layout and resource allocation, and also providing support for the early warning of infectious diseases; the early warning score level for emergency infectious disease patients generated by fusing various factors in the dynamic transmission risk map can not only help medical institutions trigger the shunt instruction for the pneumatic transmission pipeline in real time to isolate high-risk samples, but also dynamically adjust the air flow parameters in the negative pressure isolation area and the priority of infectious disease drug reserves according to the early warning score level, greatly improving the emergency management efficiency.

[0055] Furthermore, by performing temporal matching between the sample collection timestamp sequence in the pneumatic trajectory data of biological samples and the antiviral drug usage frequency in the infectious disease-associated drug characteristics, and combining with the microbial leakage threshold of the sealed cabin, the individualized biological sample transmission risk value of the patient is calculated. This process first establishes a temporal matching rule based on the sample collection timestamp sequence and the temporal distribution characteristics of antiviral drugs to generate an antiviral drug action time interval with a dynamic window length; then, within this interval, the pipeline pressure fluctuation characteristics are segmented and analyzed according to the microbial leakage threshold to extract the synchronous microbial diffusion probability distribution; then, by combining the drug concentration gradient change trend and the above distribution, the initial parameters are calculated through the spatial superposition effect; finally, the time decay compensation is performed using the immunomodulator dosing interval pattern and the microbial diffusion path weight coefficient is corrected to output the individualized biological sample transmission risk value that integrates multi-source temporal features. This method can accurately evaluate the risk caused by microbial diffusion during the transmission of patient samples at different time periods. By comprehensively considering the drug action time, microbial diffusion probability, and the influence of immunomodulators, it provides a more accurate and personalized biological sample transmission risk assessment, helps to take effective isolation measures in a timely manner, reduces the possibility of cross-infection, and improves the safety of the hospital environment.

[0056] Furthermore, the initial parameters of the individualized biological sample transmission risk value of the patient are calculated through the spatial superposition effect of the microbial residue amount and the drug metabolism cycle. The specific steps include: based on the microbial diffusion probability distribution within the antiviral drug action time interval, establishing a dynamic deposition function of the microbial residue amount changing with the transmission path length to generate spatial decay parameters associated with the drug metabolism cycle; then calculating the dynamic inhibition intensity of the antiviral drug on the microbial diffusion probability distribution to generate a microbial diffusion correction coefficient carrying time-dependent characteristics; subsequently, combining these factors to construct a spatio-temporal coupling feature; finally, based on the immunomodulator dosing interval pattern, performing dynamic smoothing processing on this feature, and considering the interference effect of the antibiotic combination drug use intensity, outputting the multi-dimensional integrated microbial residue distribution feature as the basis for subsequent risk assessment. This method realizes a more detailed and comprehensive assessment of the biological sample transmission risk by deeply analyzing the variation law of the microbial residue amount with time and path length, combining the drug metabolism cycle and the action mechanism of antiviral drugs. It not only improves the accuracy of risk prediction but also provides a scientific basis for formulating more targeted prevention and control strategies, helps to more effectively manage the infectious disease transmission risk in the emergency environment, and ensures the health and safety of medical staff and patients.

[0057] These aspects or other aspects of the present application will be more clearly understood in the following description of the embodiments. Description of the Drawings

[0058] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0059] Figure 1 Shows a flowchart of an intelligent scoring method for emergency patients based on a disease-specific scoring tool provided by the present application;

[0060] Figure 2 Shows a structural schematic diagram of an intelligent scoring system for emergency patients based on a disease-specific scoring tool provided by the present application;

[0061] Figure 3 Shows a structural schematic diagram of a computing device provided by the present application. Detailed implementation manners

[0062] To enable those skilled in the art to better understand the solutions of the present application, the following will clearly and completely describe the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application.

[0063] In some processes described in the specification and claims of the present application and the above drawings, there are multiple operations that appear in a specific order. However, it should be clearly understood that these operations may not be executed in the order in which they appear in this article or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions such as "first" and "second" in this article are used to distinguish different messages, devices, modules, etc., do not represent a sequence, and do not limit that "first" and "second" are of different types.

[0064] The research and development of the intelligent scoring method of the present application aims to achieve a comprehensive assessment and management of the infectious disease risk of emergency patients by integrating multi-source data. First, by real-time monitoring of the pressure fluctuation characteristics and microbial leakage thresholds during the sample transmission process, pneumatic trajectory data of biological samples is established; then, combined with detailed medication record analysis, drug characteristics related to infectious diseases are extracted; then, a personalized biological sample transmission risk value is calculated using time series matching technology, and a dynamic transmission risk map is constructed; finally, an early warning score level is generated based on the above information, triggering corresponding triage instructions and optimizing resource allocation. The design goal of the entire process is to improve the ability of the emergency department to respond to infectious diseases, reduce the risk of cross-infection, and at the same time improve the utilization efficiency of medical resources.

[0065] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0066] Figure 1 The following is a flowchart of an intelligent scoring method for emergency patients based on a disease-specific scoring tool provided by an embodiment of the present application. As Figure 1 shown, the method includes:

[0067] 101. Generate biologic sample pneumatic trajectory data including a sample collection timestamp sequence by capturing in real time the pressure fluctuation characteristics of respiratory secretions and blood samples of emergency patients in a pneumatic transmission pipeline and the microbial leakage threshold of a sealed cabin.

[0068] The biologic sample pneumatic trajectory data (BSTD) includes the timestamp sequence, pressure fluctuation characteristics, and microbial leakage threshold of respiratory secretions and blood samples of emergency patients during transmission. This data is used to evaluate the safety and timeliness of sample transmission and is the basis for calculating the risk value in subsequent steps.

[0069] First, the pressure fluctuation data generated by the sample during transmission is captured in real time by sensors installed in the pneumatic transmission pipeline; second, the detection device on the sealed cabin is used to determine the threshold of microbial leakage. Then, this data is combined with the collection timestamp to form BSTD. This process uses high-precision sensor technology and data analysis algorithms, such as time series analysis methods, to ensure the accuracy and real-time nature of the data. The final result is to generate BSTD containing all the above information, providing basic data support for the next step.

[0070] For example, in a specific case in the emergency department, after a suspected infectious disease patient was admitted, their respiratory secretions and blood samples were immediately collected and sent to the laboratory through the pneumatic transmission system. During this process, BSTD successfully recorded the data of the entire process from collection to delivery, providing an important basis for subsequent risk assessment.

[0071] 102. Synchronously analyze the usage frequency of antiviral drugs, the combined use intensity of antibiotics, and the administration interval pattern of immunomodulators in the emergency department medication records, and extract infectious disease-related drug characteristics.

[0072] The infectious disease-related drug characteristics (IDCF) refer to the information extracted through the analysis of the usage frequency of antiviral drugs, the combined use intensity of antibiotics, and the administration interval pattern of immunomodulators in the emergency department medication records, and are used to reveal the relationship between the patient's treatment pattern and potential infectious diseases.

[0073] First, conduct data mining on the medication records in the electronic health record system to identify the usage of antiviral drugs, antibiotics, and immunomodulators. Then, apply statistical methods to analyze the usage patterns of these drugs, including parameters such as frequency, dosage, and interval. Finally, integrate this information to form the IDCF. This process relies on machine learning algorithms, such as decision trees or random forests, to identify potential associations between drug usage patterns and diseases.

[0074] For example, based on the case of the suspected infectious disease patient mentioned in the previous step, further analysis reveals that the patient has frequently used a certain antiviral drug recently and has a history of combined use of multiple antibiotics. This information is incorporated into the IDCF, providing a key reference for subsequent risk assessment.

[0075] 103. Perform a time series matching of the sample collection timestamp sequence in the pneumatic trajectory data of the biological sample with the frequency of antiviral drug usage in the infectious disease-associated drug characteristics, and calculate the individualized biological sample transmission risk value for the patient in combination with the microbial leakage threshold of the sealed cabin.

[0076] The individualized biological sample transmission risk value (I BSTRV) is a risk quantification index calculated by combining the timestamp sequence in the pneumatic trajectory data of the patient's biological sample with the frequency of antiviral drug usage, and is used to evaluate the likelihood of microbial leakage occurring during the transmission of a specific patient's sample.

[0077] First, perform a time series matching of the timestamp sequence of the BSTD generated in step 101 with the frequency of antiviral drug usage in the IDCF extracted in step 102. Then, use the preset microbial leakage threshold of the sealed cabin as a reference standard, and calculate the I BSTRV corresponding to each sample through a risk assessment model. This model includes probability theory and statistical analysis methods to determine the degree of influence of different factors on the risk value. The final result is a numerical value reflecting the safety of the patient's sample transmission, providing a basis for constructing a dynamic transmission risk map in the future.

[0078] For example, continuing with the previous case, based on the patient's medication history and sample transmission data, calculate their I BSTRV. It is found that due to the frequent use of antiviral drugs and certain abnormal pressure fluctuations during the sample transmission process, the patient's I BSTRV is higher than the average level, indicating that additional preventive measures need to be taken to ensure the safe transmission of the sample.

[0079] 104. Based on the individualized biological sample transmission risk value of the patient and the antibiotic combination medication intensity, construct a dynamic transmission risk map reflecting the correlation between the pathogen aerosol diffusion path and the medication pattern.

[0080] The Dynamic Propagation Risk Map (PRG) of the Correlation between Pathogen Aerosol Diffusion Pathways and Medication Patterns is a visualization tool that shows the spread of pathogens in hospitals in the form of aerosols and links it to patients' medication patterns to guide the allocation of medical resources and the formulation of isolation strategies.

[0081] First, the I BSTRV obtained in step 103 is integrated with the antibiotic combination intensity information, and then the diffusion path of pathogen aerosols is mapped using geographic information system (GIS) technology and fluid dynamics simulation algorithms. In this process, factors such as the pressure fluctuation characteristics of the pneumatic transmission pipeline and the ventilation conditions inside the hospital are considered. Finally, a real-time updated PRG is generated to help medical staff understand potential risk areas and take timely actions.

[0082] For example, based on the results of the previous step, PRG shows the infection risk level of the path that high-risk samples have passed through and the surrounding environment. For the patients mentioned above, PRG pointed out several key points where protective measures need to be strengthened, such as adding negative pressure isolation areas and adjusting ventilation system parameters.

[0083] 105. By integrating the pressure fluctuation characteristics in the dynamic transmission risk map and the interval mode of immunomodulator administration, a warning score level for emergency infectious disease patients is generated, and the diversion instruction of the pneumatic transmission pipeline is triggered in real time to isolate high-risk samples;

[0084] The Warning Score Level (WSL) is a comprehensive scoring system generated based on the pressure fluctuation characteristics in the dynamic transmission risk map and the interval pattern of immunomodulator administration. It is used to assess the risk level of emergency infectious disease patients in real time and trigger the corresponding emergency response mechanism accordingly.

[0085] By analyzing the PRG and immunomodulator dosing interval pattern in step 104, an expert system or a neural network algorithm is used to calculate WSL. This scoring system takes into account a variety of factors, including but not limited to aerosol diffusion rate, patient immunity status, etc. Once WSL reaches a predetermined threshold, the system will automatically issue an instruction to start the pneumatic transmission pipeline diversion program to isolate high-risk samples.

[0086] For example, in the case of the patient mentioned above, WSL indicated that there was a high risk of infection, thus triggering the diversion instruction of the pneumatic transport system to ensure that his sample was handled separately to avoid mixing with other samples and causing cross contamination.

[0087] 106. Dynamically adjust the airflow parameters and infectious disease drug reserve priority of the negative pressure isolation area according to the warning score level, and simultaneously optimize the monitoring frequency of the intensity of antibiotic combination use in the medication record.

[0088] Negative Pressure Isolation Area Airflow Parameter Optimization (NPAPO) and Infectious Disease Drug Reserve Priority Adjustment (IDRPPA) are key measures dynamically adjusted according to the early warning score level, aiming to improve the hospital's ability to respond to public health emergencies.

[0089] When the WSL changes, the system automatically adjusts the airflow parameters in the negative pressure isolation area, such as the air exchange rate and filtration efficiency, and simultaneously re-evaluates the demand for infectious disease drugs based on the current inventory situation, giving priority to replenishing scarce drugs. These adjustments rely on the support of a real-time monitoring system and supply chain management software.

[0090] For example, given the high WSL of the patient, the hospital immediately adjusted the airflow parameters in the relevant area and accelerated the replenishment process of essential drugs to ensure a rapid response to any possible epidemic outbreak. In this way, the entire process not only improves the success rate of patient treatment but also effectively protects the safety of medical staff and other patients.

[0091] Overall, this set of processes has greatly improved the management and prevention and control capabilities of medical institutions for emergency infectious disease patients. Through accurate risk assessment and timely response measures, the occurrence of nosocomial infections has been effectively reduced, ensuring public health.

[0092] To further improve the accuracy and personalization of calculating the risk value of individualized biological sample transmission for emergency patients, an optional solution is proposed. This solution establishes a time series matching rule by introducing the time distribution characteristics of the antiviral drug usage frequency and conducts comprehensive analysis in combination with the microbial leakage threshold of the sealed cabin, so as to more accurately evaluate the potential risk of the sample during transmission. This method not only considers the changes in the time dimension but also incorporates multi-source information such as drug concentration gradients, microbial diffusion probability distributions, and immunomodulator dosing interval patterns to ensure that the finally output risk value is closer to the actual situation.

[0093] In some embodiments, performing time series matching on the sample collection timestamp sequence in the pneumatic trajectory data of the biological sample and the antiviral drug usage frequency in the infectious disease-related drug characteristics, and calculating the risk value of individualized biological sample transmission for the patient in combination with the microbial leakage threshold of the sealed cabin, includes:

[0094] 201. Based on the sample collection timestamp sequence in the pneumatic trajectory data of the biological sample, establish a time series matching rule through the time distribution characteristics of the antiviral drug usage frequency to generate an antiviral drug action time interval with a dynamic window length;

[0095] In step 201, the Antiviral Drug Action Time Interval (AVDTI) is a time period with a dynamic window length established based on the sample collection timestamps in the pneumatic trajectory data of biological samples and the time distribution characteristics of the frequency of antiviral drug use. The AVDTI is used to identify the effective action period of the antiviral drug within a specific time period, thereby providing a time benchmark for subsequent risk assessment.

[0096] In the embodiments of the present application, first, the medication records of patients are collected, and the time distribution characteristics of the frequency of antiviral drug use are determined through data analysis techniques. Then, based on these characteristics, a time series matching rule is established to define the AVDTI with a dynamic window length. This process uses a time series analysis algorithm to process the data to ensure that the AVDTI can accurately reflect the drug action cycle.

[0097] 202. Within the Antiviral Drug Action Time Interval, segmentally analyze the pressure fluctuation characteristics of the pneumatic transmission pipeline according to the microbial leakage threshold of the sealed cabin, and extract the microbial diffusion probability distribution synchronized with the timestamp sequence.

[0098] In step 202, the Microbial Diffusion Probability Distribution (MDPD) refers to the probability distribution situation synchronized with the timestamp sequence extracted after segmentally analyzing the pressure fluctuation characteristics of the pneumatic transmission pipeline according to the microbial leakage threshold of the sealed cabin within the Antiviral Drug Action Time Interval. The MDPD is used to quantify the possibility of microbial leakage occurring during the transmission of samples.

[0099] In the embodiments of the present application, sensors installed in the pneumatic transmission pipeline are used to monitor the pressure fluctuation characteristics, and the microbial leakage threshold is determined in combination with the detection device on the sealed cabin. Then, the pressure fluctuation data is segmentally analyzed within the AVDTI, and the MDPD is calculated using a statistical model. The key to this step lies in accurate data collection and the application of effective statistical methods.

[0100] 203. Combine the drug concentration gradient change trend in the time series matching rule with the microbial diffusion probability distribution, and calculate the initial parameter of the patient's individualized biological sample transmission risk value through the spatial superposition effect of the microbial residue amount and the drug metabolism cycle.

[0101] In step 203, the Initial Parameter (IP) is the basic parameter of the patient's individualized biological sample transmission risk value calculated by combining the drug concentration gradient change trend with the microbial diffusion probability distribution by considering the spatial superposition effect of the microbial residue amount and the drug metabolism cycle. The IP is used to preliminarily evaluate the safety of sample transmission.

[0102] In the embodiments of the present application, first, the changing trend of drug concentration over time is analyzed. Combining with MDPD, a mathematical modeling method is used to calculate the spatial superposition effect of microbial residue amount and drug metabolism cycle, thereby obtaining the IP. This process relies on complex mathematical models and algorithms to comprehensively consider the influence of various factors to ensure the accuracy of the IP.

[0103] 204. Perform time decay compensation on the initial parameters based on the immunomodulator dosing interval pattern, and correct the weight coefficient of the microbial diffusion path according to the antibiotic combination drug strength, and output an individualized biological sample transmission risk value that integrates multi-source time series features.

[0104] In step 204, time decay compensation (TDC) and weight coefficient correction (WCM) are processes of adjusting the initial parameters based on the immunomodulator dosing interval pattern, and correcting the importance index of the microbial diffusion path according to the antibiotic combination drug strength, and finally outputting an individualized biological sample transmission risk value that integrates multi-source time series features. TDC and WCM are used to optimize the accuracy and reliability of the risk assessment results.

[0105] In the embodiments of the present application, time decay compensation is performed on the IP according to the immunomodulator dosing interval pattern, and at the same time, the weight coefficient of the microbial diffusion path is adjusted according to the antibiotic combination drug strength. The whole process uses machine learning algorithms to dynamically adjust the parameters to ensure that the finally output risk value can truly reflect the specific situation of the patient.

[0106] The following is a specific example: After a suspected infectious disease patient is admitted to the hospital, their respiratory secretions and blood samples are quickly collected and sent to the laboratory through a pneumatic transmission system. During this process, an AVDTI is established by analyzing the patient's medication records, and the sample transmission process is monitored in detail within this interval to generate MDPD. Combining the drug concentration change trend with MDPD, the IP is calculated. Finally, considering the immunomodulator dosing interval and the situation of antibiotic combination use, TDC and WCM are performed on the IP to obtain a result that comprehensively reflects the individualized biological sample transmission risk value of the patient.

[0107] Overall, this set of processes not only improves the accuracy of the management of emergency infectious disease patients, but also effectively reduces the risk of microbial leakage during the transmission of biological samples, greatly ensuring the safety of the medical environment and the treatment effect of the patients. Through scientific data analysis and technical means, accurate assessment and timely response to potential risks are achieved.

[0108] To further optimize the calculation of the individualized biological sample transmission risk value for emergency patients, especially considering the impact of drug concentration changes on microbial diffusion and the variation law of microbial residue quantity with time and path length, this solution proposes an improved method. By combining the drug concentration gradient change trend in the time sequence matching rule with the microbial diffusion probability distribution, and utilizing the spatial superposition effect of microbial residue quantity and drug metabolism cycle, the individualized biological sample transmission risk of patients can be evaluated more accurately. This method not only improves the accuracy of risk prediction but also provides a scientific basis for formulating more personalized prevention and control strategies. In some embodiments, by combining the drug concentration gradient change trend in the time sequence matching rule with the microbial diffusion probability distribution, through the spatial superposition effect of microbial residue quantity and drug metabolism cycle, the initial parameters of the individualized biological sample transmission risk value of patients are calculated, including:

[0109] 301. Based on the microbial diffusion probability distribution within the action time interval of the antiviral drug, establish a dynamic deposition function of microbial residue quantity varying with the transmission path length, and generate a spatial attenuation parameter associated with the drug metabolism cycle;

[0110] The dynamic deposition function (DDF) is a function model established based on the microbial diffusion probability distribution within the action time interval of the antiviral drug. It describes the relationship between the microbial residue quantity and the change of the transmission path length, and generates a spatial attenuation parameter (SAP) associated with the drug metabolism cycle. DDF is used to quantify the microbial residue situation on the sample transmission path.

[0111] First, within the action time interval of the antiviral drug, according to the microbial diffusion probability distribution, use mathematical modeling techniques to construct the DDF. This model considers the diffusion and deposition characteristics of microorganisms at different positions, as well as the impact of drug metabolism on the survival ability of microorganisms. Determine the change law of microbial residue quantity with distance through experimental data, and adjust the spatial attenuation parameter in combination with the drug metabolism cycle. The final result is a DDF that can accurately predict the change of microbial residue quantity with the transmission path, providing basic data support for subsequent steps.

[0112] 302. According to the drug concentration gradient change trend in the time sequence matching rule, calculate the dynamic inhibition intensity of the antiviral drug on the microbial diffusion probability distribution, and generate a microbial diffusion correction coefficient carrying time-dependent characteristics;

[0113] The microbial diffusion correction coefficient (MDC) is a parameter carrying time-dependent characteristics calculated according to the drug concentration gradient change trend in the time sequence matching rule. It reflects the effectiveness of the antiviral drug against microbial diffusion. MDC is used to adjust the microbial diffusion probability distribution to more accurately reflect the actual transmission situation.

[0114] First, analyze the trend of the antiviral drug concentration changing over time, and use statistical methods to calculate its influence degree on the probability distribution of microbial diffusion. Then, optimize the MDC through machine learning algorithms to enable it to dynamically reflect the drug inhibition effect. This process needs to consider various factors, such as drug dosage, action time, and microbial species, etc. The final result is an MDC that can dynamically adjust the probability distribution of microbial diffusion, improving the accuracy of microbial diffusion prediction.

[0115] 303. Combine the spatial decay parameter with the microbial diffusion correction coefficient, and generate the spatio-temporal coupling characteristics of the initial parameters of the biological sample transmission risk through the superposition effect of the microbial residue deposition path and the drug metabolism rate.

[0116] The spatio-temporal coupling feature (STCF) is a multi-dimensional feature generated by combining the spatial decay parameter with the microbial diffusion correction coefficient through the superposition effect of the microbial residue deposition path and the drug metabolism rate. The STCF is used to comprehensively evaluate the microbial residue distribution characteristics in the biological sample transmission process.

[0117] First, combine the spatial decay parameter and the microbial diffusion correction coefficient, and use numerical simulation technology to calculate the superposition effect of the microbial residue deposition path and the drug metabolism rate. Then, extract the key features through data analysis methods to form the STCF. This process needs to process a large amount of real-time data and use complex algorithms to ensure the accuracy of feature extraction. The final result is an STCF that comprehensively reflects the biological sample transmission risk, providing a data basis for the next step.

[0118] 304. Perform dynamic smoothing processing on the spatio-temporal coupling characteristics based on the immunomodulator dosing interval pattern, use the interference effect of the antibiotic combination dosing intensity on the microbial deposition path, calculate the initial parameters of the patient's individualized biological sample transmission risk value, and output the multi-dimensional fusion microbial residue distribution characteristics.

[0119] The multi-dimensional fusion microbial residue distribution characteristics (MFMD) is the final output result calculated based on the dynamic smoothing processing of the spatio-temporal coupling characteristics according to the immunomodulator dosing interval pattern and using the interference effect of the antibiotic combination dosing intensity on the microbial deposition path. The MFMD is used to accurately evaluate the patient's individualized biological sample transmission risk value.

[0120] First, perform dynamic smoothing processing on the spatio-temporal coupling characteristics according to the immunomodulator dosing interval pattern to eliminate the errors caused by data fluctuations. Then, adjust the weight of the microbial deposition path using the antibiotic combination dosing intensity and optimize the MFMD through machine learning algorithms. This process needs to consider factors such as the patient's individual differences and treatment responses, etc. The final result is an MFMD that accurately reflects the patient's individualized biological sample transmission risk value, providing an important basis for clinical decision-making.

[0121] For example, after a suspected infectious disease patient is admitted to the hospital, their respiratory secretions and blood samples are quickly collected and sent to the laboratory through a pneumatic transmission system. During this process, a dynamic deposition function is first established to accurately predict the change of microbial residue amount with the transmission path. Then, the microbial diffusion correction coefficient is calculated to dynamically adjust the probability distribution of microbial diffusion. Subsequently, combining the spatial attenuation parameter with the microbial diffusion correction coefficient, a spatio-temporal coupling feature is generated to comprehensively evaluate the risk of biological sample transmission. Finally, considering the administration interval of immunomodulators and the combination of antibiotics, dynamic smoothing is performed to obtain a multi-dimensional fusion microbial residue distribution feature that accurately reflects the individualized biological sample transmission risk value of the patient.

[0122] This process significantly improves the accurate assessment ability of microbial residue amount during the biological sample transmission of emergency infectious disease patients, not only enhancing the scientificity and effectiveness of risk management, but also optimizing the allocation of medical resources. Through the comprehensive analysis of microbial diffusion, drug metabolism and patient individual characteristics, the accurate identification and timely response to potential risks are achieved, greatly ensuring the safety of the medical environment and the treatment effect of patients.

[0123] In order to further improve the accuracy of calculating the individualized biological sample transmission risk value of emergency patients, especially considering the pressure fluctuation characteristics of the pneumatic transmission pipeline and its relationship with microbial diffusion, this solution proposes a new method. By segmentally analyzing the pressure fluctuation characteristics of the pneumatic transmission pipeline according to the microbial leakage threshold of the sealed cabin within the antiviral drug action time interval, and combining the microbial diffusion trend and the change trend of drug concentration gradient, the probability distribution of microbial diffusion synchronized with the timestamp sequence can be more accurately extracted. This method not only helps to monitor the potential risks during the sample transmission process in real time, but also provides a scientific basis for formulating effective isolation measures. In some embodiments, in step 202, within the antiviral drug action time interval, segmentally analyzing the pressure fluctuation characteristics of the pneumatic transmission pipeline according to the microbial leakage threshold of the sealed cabin to extract the probability distribution of microbial diffusion synchronized with the timestamp sequence includes:

[0124] 2021. Based on the pressure fluctuation characteristics of the pneumatic transmission pipeline within the antiviral drug action time interval, combining the microbial leakage threshold of the sealed cabin, segmentally analyzing the pressure fluctuation data to generate a pressure fluctuation segmented feature synchronized with the sample collection timestamp sequence;

[0125] The pressure fluctuation segmented feature (PWFS) is a data set generated by segmentally analyzing the pressure fluctuation characteristics of the pneumatic transmission pipeline within the antiviral drug action time interval, combining the microbial leakage threshold of the sealed cabin. The PWFS is used to describe the change of the transmission environment of the sample in different time periods.

[0126] First, high-precision sensors installed on the pneumatic transmission pipeline are used to monitor the pressure fluctuation data in real time and combine it with the microbial leakage threshold of the sealed cabin. Then, data analysis techniques are used to segment these data to generate PWFS. This process uses time series analysis algorithms to identify the pressure fluctuation patterns in different time periods. The final result is a PWFS that can reflect the environmental changes during the sample transmission process, providing basic data support for the subsequent steps.

[0127] 2022. According to the pressure fluctuation segmentation characteristics, extract the microbial diffusion trend within each segment, and combine the microbial leakage threshold of the sealed cabin to dynamically model the microbial diffusion path, generating a microbial diffusion probability distribution synchronized with the time stamp sequence;

[0128] The microbial diffusion trend (MDT) refers to the probability distribution obtained by extracting the microbial diffusion trend within each segment according to the pressure fluctuation segmentation characteristics and dynamically modeling it in combination with the microbial leakage threshold of the sealed cabin. MDT is used to quantify the diffusion possibility of microorganisms at specific time periods and locations.

[0129] First, based on PWFS, fluid mechanics simulation technology is applied to calculate the microbial diffusion trend within each segment. Then, statistical models are used to convert these trends into probability distributions, considering the influence of the microbial leakage threshold of the sealed cabin. This process requires complex mathematical modeling and simulation technologies to ensure the accuracy of MDT. The final result is a probability distribution map that can dynamically reflect the microbial diffusion path, providing a data basis for the next step.

[0130] 2023. Based on the microbial diffusion probability distribution, combine the change trend of the drug concentration gradient within the action time interval of the antiviral drug to calculate the dynamic inhibition intensity of the microbial diffusion probability distribution, generating a microbial diffusion correction coefficient with time-dependent characteristics;

[0131] The microbial diffusion correction coefficient (MDC) is a parameter with time-dependent characteristics calculated based on the microbial diffusion probability distribution and the change trend of the drug concentration gradient within the action time interval of the antiviral drug. MDC is used to adjust the microbial diffusion probability distribution to more accurately reflect the actual transmission situation.

[0132] First, analyze the change trend of the drug concentration over time, and use machine learning algorithms to calculate its influence on the microbial diffusion probability distribution. Then, dynamically adjust MDC through optimization algorithms so that it can reflect the drug inhibition effect in real time. This process needs to comprehensively consider various factors, such as drug dosage, action time, and microbial species, etc. The final result is an MDC that can dynamically adjust the microbial diffusion probability distribution, improving the accuracy of prediction.

[0133] In 2024, fuse the microbial diffusion correction coefficient with the segmented characteristics of the pressure fluctuation, extract the microbial diffusion probability distribution synchronized with the timestamp sequence, and combine the interference effect of the antibiotic combination drug strength on the microbial diffusion path to output a dynamically updated microbial diffusion probability distribution, which is used as an input parameter for subsequent calculation of the patient's individualized biological sample transmission risk value.

[0134] The dynamically updated microbial diffusion probability distribution (DUMDP) is the final output result calculated by fusing the microbial diffusion correction coefficient with the segmented characteristics of the pressure fluctuation and combining the interference effect of the antibiotic combination drug strength on the microbial diffusion path. The DUMDP is used to accurately evaluate the microbial diffusion risk during the sample transmission process.

[0135] First, combine the MDC with the PWFS and use numerical simulation technology to calculate the actual influence of the microbial diffusion path. Then, adjust the weight of the microbial diffusion path in combination with the antibiotic combination drug strength, and optimize the DUMDP through complex algorithms. This process requires processing a large amount of real-time data and using advanced algorithms to ensure the accuracy of the results. The final result is a DUMDP that comprehensively reflects the microbial diffusion risk during the biological sample transmission process, providing a key input parameter for subsequent calculation of the patient's individualized biological sample transmission risk value.

[0136] For example, after a suspected infectious disease patient is admitted to the hospital, their respiratory secretions and blood samples are quickly collected and sent to the laboratory through a pneumatic transmission system. During this process, first, the pressure fluctuation data of the pneumatic transmission pipeline is monitored and analyzed using sensors, and the PWFS is generated in combination with the microbial leakage threshold of the sealed cabin. Next, the microbial diffusion trend within each segment is extracted based on the PWFS, and the MDT is dynamically modeled. Subsequently, the MDC is calculated in combination with the change trend of the drug concentration gradient to adjust the microbial diffusion probability distribution. Finally, the MDC and the PWFS are fused, considering the situation of antibiotic combination drugs, to generate the DUMDP, which accurately reflects the microbial diffusion risk during the sample transmission process.

[0137] This set of processes significantly improves the accuracy of evaluating the microbial diffusion risk of biological samples of emergency infectious disease patients during pneumatic transmission. Through comprehensive analysis of the pressure fluctuation characteristics, microbial diffusion trend, and drug effect, accurate identification and timely response to potential risks are achieved. This method not only improves the scientificity and effectiveness of risk management but also optimizes the allocation of medical resources, greatly ensuring the safety of the medical environment and the treatment effect of patients.

[0138] To further optimize the calculation of the individualized biological sample transmission risk value for emergency patients, especially considering the variation law of microbial residue quantity with time and path length and its relationship with the drug metabolism cycle, this solution proposes an improved method. By combining the spatial attenuation parameter and the microbial diffusion correction coefficient, and utilizing the superposition effect of the microbial residue deposition path and the drug metabolism rate, the spatio-temporal coupling characteristics of the initial parameters of biological sample transmission risk can be generated more precisely. This method not only improves the accuracy of risk prediction but also provides a scientific basis for formulating more personalized prevention and control strategies. In some embodiments, by combining the spatial attenuation parameter and the microbial diffusion correction coefficient, through the superposition effect of the microbial residue deposition path and the drug metabolism rate, the spatio-temporal coupling characteristics of the initial parameters of biological sample transmission risk are generated, including:

[0139] 401. Based on the microbial diffusion probability distribution within the action time interval of the antiviral drug, combined with the dynamic deposition function of the microbial residue quantity changing with the transmission path length, generate a spatial attenuation parameter associated with the drug metabolism cycle;

[0140] The spatial attenuation parameter (SAP) is a parameter associated with the drug metabolism cycle generated based on the microbial diffusion probability distribution within the action time interval of the antiviral drug, combined with the dynamic deposition function of the microbial residue quantity changing with the transmission path length. SAP is used to describe the variation law of the microbial residue quantity at different positions.

[0141] First, analyze the microbial diffusion probability distribution within the action time interval of the antiviral drug, and establish a dynamic deposition function model to predict the change of the microbial residue quantity with the transmission path. This process utilizes mathematical modeling techniques and considers the influencing factors of the drug metabolism rate and the microbial living environment. Then, calibrate the model parameters through experimental data to ensure its accuracy. The final result is a spatial attenuation parameter that can reflect the change of the microbial residue quantity with distance, providing basic data support for the subsequent steps.

[0142] 402. According to the change trend of the drug concentration gradient in the timing matching rule, calculate the dynamic inhibition intensity of the antiviral drug on the microbial diffusion probability distribution, and generate a microbial diffusion correction coefficient with time-dependent characteristics;

[0143] The microbial diffusion correction coefficient (MDC) is a parameter with time-dependent characteristics calculated according to the change trend of the drug concentration gradient in the timing matching rule, which reflects the effective inhibition intensity of the antiviral drug on microbial diffusion. MDC is used to adjust the microbial diffusion probability distribution to make it more accurately reflect the actual transmission situation.

[0144] First, analyze the changing trend of the antiviral drug concentration over time, and use statistical methods to calculate its influence on the probability distribution of microbial diffusion. Then, apply machine learning algorithms to optimize the MDC so that it can reflect the drug inhibition effect in real time. This process requires comprehensive consideration of various factors, such as drug dosage, action time, and microbial species, etc. The final result is an MDC that can dynamically adjust the probability distribution of microbial diffusion, improving the accuracy of microbial diffusion prediction.

[0145] 403. Integrate the spatial decay parameter with the microbial diffusion correction coefficient, and combine the superposition effect of the microbial residue deposition path and the drug metabolism rate to generate the spatio-temporal coupling characteristics of the initial parameters of the biological sample transmission risk.

[0146] The spatio-temporal coupling feature (STCF) is a multi-dimensional feature generated by integrating the spatial decay parameter with the microbial diffusion correction coefficient and combining the superposition effect of the microbial residue deposition path and the drug metabolism rate. The STCF is used to comprehensively evaluate the microbial residue distribution characteristics during the biological sample transmission process.

[0147] First, combine the spatial decay parameter with the microbial diffusion correction coefficient, and use numerical simulation techniques to calculate the superposition effect of the microbial residue deposition path and the drug metabolism rate. Then, extract the key features through data analysis methods to form the STCF. This process requires processing a large amount of real-time data and using complex algorithms to ensure the accuracy of feature extraction. The final result is an STCF that comprehensively reflects the biological sample transmission risk, providing a data basis for the next step.

[0148] 404. Based on the immunomodulator dosing interval pattern, perform dynamic smoothing processing on the spatio-temporal coupling characteristics, and combine the interference effect of the antibiotic combination dosing intensity on the microbial deposition path to output the multi-dimensionally fused microbial residue distribution characteristics, which are used as the input parameters for calculating the patient's individualized biological sample transmission risk value in the subsequent steps.

[0149] The multi-dimensionally fused microbial residue distribution characteristic (MFMD) is the final output result calculated based on the immunomodulator dosing interval pattern for dynamic smoothing processing of the spatio-temporal coupling characteristics and combining the interference effect of the antibiotic combination dosing intensity on the microbial deposition path. The MFMD is used to accurately evaluate the patient's individualized biological sample transmission risk value.

[0150] First, the spatio-temporal coupling characteristics are dynamically smoothed according to the administration interval pattern of the immunomodulator to eliminate the errors caused by data fluctuations. Then, the weight of the microbial deposition path is adjusted by the antibiotic combination intensity, and the MFMD is optimized through a machine learning algorithm. This process needs to consider factors such as the individual differences and treatment responses of patients. The final result is an MFMD that accurately reflects the individualized biological sample transmission risk value of the patient, providing an important basis for clinical decision-making.

[0151] For example, after a suspected infectious disease patient is admitted to the hospital, their respiratory secretions and blood samples are quickly collected and sent to the laboratory through a pneumatic transmission system. During this process, first, the spatial attenuation parameter is established to accurately predict the change of microbial residue quantity along the transmission path. Then, the microbial diffusion correction coefficient is calculated to dynamically adjust the microbial diffusion probability distribution. Subsequently, by combining the spatial attenuation parameter and the microbial diffusion correction coefficient, the spatio-temporal coupling characteristics are generated to comprehensively evaluate the risk of biological sample transmission. Finally, considering the administration interval of the immunomodulator and the situation of antibiotic combination, dynamic smoothing is carried out to obtain a multi-dimensional fusion microbial residue distribution feature that accurately reflects the individualized biological sample transmission risk value of the patient.

[0152] This set of processes significantly improves the ability to accurately evaluate the microbial residue quantity during the biological sample transmission of emergency infectious disease patients, not only enhancing the scientificity and effectiveness of risk management, but also optimizing the allocation of medical resources. Through the comprehensive analysis of microbial diffusion, drug metabolism, and patient individual characteristics, the accurate identification and timely response to potential risks are achieved, greatly ensuring the safety of the medical environment and the treatment effect of patients. This method provides more reliable decision-making support for clinical practice, helping to improve the quality and safety of the overall medical service.

[0153] To further refine the calculation of the individualized biological sample transmission risk value for emergency patients, especially to focus on the variation law of microbial residue quantity with time and path length and its relationship with the drug metabolism cycle, this solution proposes an improved method. By establishing a dynamic deposition function of microbial residue quantity changing with the transmission path length based on the microbial diffusion probability distribution within the action time interval of the antiviral drug, and generating a spatial attenuation parameter associated with the drug metabolism cycle, the potential risks during the sample transmission process can be more accurately evaluated. This method not only improves the accuracy of risk prediction but also provides a scientific basis for formulating more personalized prevention and control strategies. In some embodiments, based on the microbial diffusion probability distribution within the action time interval of the antiviral drug, establishing a dynamic deposition function of microbial residue quantity changing with the transmission path length and generating a spatial attenuation parameter associated with the drug metabolism cycle includes:

[0154] 501. Analyze the initial parameters of the transmission risk value of the patient's individualized biological sample, identify the variation law of the microbial residue quantity with the transmission path length according to the microbial diffusion probability distribution within the antiviral drug action time interval, and form a dynamic deposition function of the microbial residue quantity;

[0155] The microbial residue quantity dynamic deposition function (MRDDF) is a function model established after identifying the variation law of the microbial residue quantity with the transmission path length according to the microbial diffusion probability distribution within the antiviral drug action time interval. The MRDDF is used to describe the variation of the microbial residue quantity at different positions and provides basic data support for subsequent calculations.

[0156] First, analyze the microbial diffusion probability distribution within the antiviral drug action time interval, and use mathematical modeling techniques to predict the variation of the microbial residue quantity with the transmission path. This process calibrates the model parameters by combining experimental data to ensure its accuracy. Determine the variation law of the microbial residue quantity through hydrodynamic simulation and statistical analysis methods to form the MRDDF. The final result is a dynamic deposition function that can accurately reflect the variation of the microbial residue quantity with distance.

[0157] 502. Evaluate the dynamic inhibition intensity of the antiviral drug on the microbial diffusion probability distribution according to the variation trend of the drug concentration gradient in the timing matching rule, and generate a microbial diffusion correction coefficient with time-dependent characteristics;

[0158] The microbial diffusion correction coefficient (MDC) is a parameter with time-dependent characteristics generated after evaluating the dynamic inhibition intensity of the antiviral drug on the microbial diffusion probability distribution according to the variation trend of the drug concentration gradient in the timing matching rule. The MDC is used to adjust the microbial diffusion probability distribution to more accurately reflect the actual transmission situation.

[0159] First, analyze the variation trend of the antiviral drug concentration with time, and use machine learning algorithms to calculate its influence degree on the microbial diffusion probability distribution. Then, apply an optimization algorithm to dynamically adjust the MDC so that it can reflect the drug inhibition effect in real time. This process needs to comprehensively consider various factors, such as drug dosage, action time, and microbial species, etc. The final result is an MDC that can dynamically adjust the microbial diffusion probability distribution, improving the accuracy of microbial diffusion prediction.

[0160] 503. Combine the microbial diffusion correction coefficient with the microbial residue quantity dynamic deposition function, and use the interaction between the microbial residue deposition path and the drug metabolism rate to construct the spatio-temporal coupling characteristics of the initial parameters of the biological sample transmission risk;

[0161] The Spatiotemporal Coupling Feature (STCF) is a multi-dimensional feature constructed by combining the microbial diffusion correction coefficient with the dynamic deposition function of microbial residue, and using the interaction between the microbial residue deposition path and the drug metabolism rate. The STCF is used to comprehensively evaluate the microbial residue distribution characteristics during the transmission of biological samples.

[0162] First, combine the microbial diffusion correction coefficient with the MRDDF, and use numerical simulation technology to calculate the superposition effect of the microbial residue deposition path and the drug metabolism rate. Then, extract key features through data analysis methods to form the STCF. This process requires processing a large amount of real-time data and using complex algorithms to ensure the accuracy of feature extraction. The final result is an STCF that comprehensively reflects the transmission risk of biological samples, providing a data basis for the next step.

[0163] 504. Dynamically smooth the spatiotemporal coupling feature based on the administration interval pattern of immunomodulators, and at the same time consider the interference effect of the antibiotic combination intensity on the microbial deposition path, output the multi-dimensional fusion microbial residue distribution feature, adjust the microbial residue distribution feature according to the drug metabolism cycle, and generate the spatial attenuation parameter associated with the drug metabolism cycle.

[0164] The multi-dimensional fusion microbial residue distribution feature (MFMD) is the final output result calculated by dynamically smoothing the spatiotemporal coupling feature based on the administration interval pattern of immunomodulators and combining the interference effect of the antibiotic combination intensity on the microbial deposition path. At the same time, adjust the microbial residue distribution feature according to the drug metabolism cycle to generate the spatial attenuation parameter (SAP) associated with the drug metabolism cycle. The MFMD is used to accurately evaluate the individualized biological sample transmission risk value of patients.

[0165] First, dynamically smooth the STCF according to the administration interval pattern of immunomodulators to eliminate the errors caused by data fluctuations. Then, use the antibiotic combination intensity to adjust the weight of the microbial deposition path, and optimize the MFMD through machine learning algorithms. This process needs to consider factors such as the individual differences and treatment responses of patients, and adjust the microbial residue distribution feature according to the drug metabolism cycle to generate the SAP. The final result is an MFMD that accurately reflects the individualized biological sample transmission risk value of patients, providing an important basis for clinical decision-making.

[0166] After a suspected infectious disease patient was admitted to the hospital, their respiratory secretions and blood samples were quickly collected and sent to the laboratory through a pneumatic transmission system. During this process, the probability distribution of microbial diffusion within the antiviral drug action time interval was first analyzed, and a microbial residue dynamic deposition function (MRDDF) was established to accurately predict the change of microbial residue with the transmission path. Then, the microbial diffusion correction coefficient (MDC) was calculated to dynamically adjust the probability distribution of microbial diffusion. Subsequently, by combining MDC with MRDDF, a spatio-temporal coupling feature (STCF) was generated to comprehensively evaluate the risk of biological sample transmission. Finally, considering the dosing interval of immunomodulators and the combination use of antibiotics, dynamic smoothing was performed, and the microbial residue distribution characteristics were adjusted according to the drug metabolism cycle, obtaining a multi-dimensional integrated microbial residue distribution feature (MFMD) that accurately reflects the individual biological sample transmission risk value of the patient.

[0167] This process significantly improves the ability to accurately evaluate the microbial residue in the transmission of biological samples from emergency infectious disease patients. It not only enhances the scientificity and effectiveness of risk management but also optimizes the allocation of medical resources. Through the comprehensive analysis of microbial diffusion, drug metabolism, and patient individual characteristics, it realizes the accurate identification and timely response to potential risks, greatly ensuring the safety of the medical environment and the treatment effect of patients. This method provides more reliable decision-making support for clinical practice, helping to improve the quality and safety of the overall medical service.

[0168] To further improve the accuracy of calculating the individual biological sample transmission risk value for emergency patients, especially considering the pressure fluctuation characteristics of the pneumatic transmission pipeline and its relationship with microbial diffusion, this solution proposes a new method. By based on the pressure fluctuation characteristics of the pneumatic transmission pipeline within the antiviral drug action time interval and combining with the microbial leakage threshold of the sealed cabin for segmented analysis, the pressure fluctuation segmented characteristics synchronized with the sample collection timestamp sequence can be generated more accurately. This method not only helps to monitor the potential risks during the sample transmission process in real time but also provides a scientific basis for formulating effective isolation measures. In some embodiments, based on the pressure fluctuation characteristics of the pneumatic transmission pipeline within the antiviral drug action time interval and combining with the microbial leakage threshold of the sealed cabin, the pressure fluctuation data is segmented and analyzed to generate the pressure fluctuation segmented characteristics synchronized with the sample collection timestamp sequence, including:

[0169] 601. Analyze the pressure fluctuation characteristics of the pneumatic transmission pipeline during the transmission of the patient's individual biological samples, identify the pressure fluctuation pattern synchronized with the sample collection timestamp sequence according to the drug concentration gradient change trend within the antiviral drug action time interval, and form a preliminary set of pressure fluctuation segmented characteristics;

[0170] The Initial Pressure Waveform Segment Feature Set (IPWFS) is a set formed based on the pressure fluctuation characteristics in the pneumatic transmission pipeline within the time interval of antiviral drug action. After identifying the pressure fluctuation patterns synchronized with the sample collection timestamp sequence according to the changing trend of the drug concentration gradient, IPWFS is used to describe the pressure fluctuation conditions in different time periods during sample transmission.

[0171] First, use the sensors installed on the pneumatic transmission pipeline to monitor the pressure fluctuation data in real time, and analyze it in combination with the changing trend of the drug concentration gradient within the time interval of antiviral drug action. Identify the pressure fluctuation patterns synchronized with the sample collection timestamp sequence through time series analysis algorithms to form IPWFS. This process uses high-precision sensor technology and data analysis methods to ensure the accuracy and real-time nature of the data. The final result is a set that can reflect the pressure fluctuation characteristics in different time periods during sample transmission, providing basic data support for the subsequent steps.

[0172] 602. Analyze the pressure waveform segment feature set obtained in the first step according to the microbial leakage threshold of the sealed cabin, extract the microbial diffusion trend within each segment, and dynamically model the microbial diffusion path in combination with the microbial leakage threshold of the sealed cabin to generate a microbial diffusion probability distribution synchronized with the timestamp sequence;

[0173] The Microbial Diffusion Probability Distribution (MDPD) is a probability distribution generated by analyzing the initial pressure waveform segment feature set according to the microbial leakage threshold of the sealed cabin, extracting the microbial diffusion trend within each segment, and dynamically modeling the microbial diffusion path in combination with the microbial leakage threshold of the sealed cabin. MDPD is used to quantify the diffusion possibility of microorganisms at specific time periods and locations.

[0174] First, based on IPWFS, apply fluid mechanics simulation technology to calculate the microbial diffusion trend within each segment. Then, use statistical models to convert these trends into probability distributions, considering the influence of the microbial leakage threshold of the sealed cabin. This process requires complex mathematical modeling and simulation technologies to ensure the accuracy of MDPD. The final result is a probability distribution map that can dynamically reflect the microbial diffusion path, providing a data basis for the next step.

[0175] 603. Based on the microbial diffusion probability distribution, in combination with the changing trend of the drug concentration gradient within the time interval of antiviral drug action, calculate the dynamic inhibition intensity of the microbial diffusion probability distribution to generate a microbial diffusion correction coefficient carrying time-dependent characteristics;

[0176] The Microbial Diffusion Correction Coefficient (MDC) is a parameter with time-dependent characteristics calculated based on the probability distribution of microbial diffusion and the changing trend of drug concentration gradient within the time interval of antiviral drug action. MDC is used to adjust the probability distribution of microbial diffusion to more accurately reflect the actual transmission situation.

[0177] First, analyze the changing trend of drug concentration over time, and use machine learning algorithms to calculate its influence on the probability distribution of microbial diffusion. Then, dynamically adjust MDC through an optimization algorithm so that it can reflect the drug inhibition effect in real time. This process needs to comprehensively consider various factors, such as drug dosage, action time, and microbial species, etc. The final result is an MDC that can dynamically adjust the probability distribution of microbial diffusion, improving the accuracy of prediction.

[0178] 604. Combine the microbial diffusion correction coefficient with the preliminary pressure fluctuation segmented feature set, and utilize the interaction between the microbial diffusion path and the drug metabolism rate to generate pressure fluctuation segmented features synchronized with the sample collection timestamp sequence.

[0179] The Synchronized Pressure Fluctuation Segmented Feature (SPWFS) is a pressure fluctuation segmented feature generated by combining the microbial diffusion correction coefficient with the preliminary pressure fluctuation segmented feature set and utilizing the interaction between the microbial diffusion path and the drug metabolism rate, which is synchronized with the sample collection timestamp sequence. SPWFS is used to comprehensively evaluate the pressure fluctuation during the transmission of biological samples and its impact on microbial diffusion.

[0180] First, combine MDC with IPWFS, and use numerical simulation technology to calculate the superposition effect of the microbial diffusion path and the drug metabolism rate. Then, extract key features through data analysis methods to form SPWFS. This process requires processing a large amount of real-time data and using advanced algorithms to ensure the accuracy of feature extraction. The final result is an SPWFS that comprehensively reflects the pressure fluctuation during the transmission of biological samples and its impact on microbial diffusion, providing an important basis for clinical decision-making.

[0181] For example, after a suspected infectious disease patient is admitted to the hospital, their respiratory secretions and blood samples are quickly collected and sent to the laboratory through a pneumatic transmission system. During this process, first, sensors are used to monitor and analyze the pressure fluctuation data of the pneumatic transmission pipeline, and combined with the changing trend of the drug concentration gradient within the action time interval of antiviral drugs, a preliminary set of pressure fluctuation segmented features (IPWFS) is formed. Next, based on the IPWFS, the microbial diffusion trend within each segment is extracted, and a microbial diffusion probability distribution (MDPD) is dynamically modeled. Subsequently, the microbial diffusion correction coefficient (MDC) is calculated in combination with the changing trend of the drug concentration gradient to adjust the microbial diffusion probability distribution. Finally, the MDC is fused with the IPWFS, and considering the interaction between the microbial diffusion path and the drug metabolism rate, a synchronous pressure fluctuation segmented feature (SPWFS) is generated to comprehensively evaluate the pressure fluctuation during the transmission of biological samples and its impact on microbial diffusion.

[0182] This process significantly improves the ability to accurately assess the risk of microbial diffusion during the transmission of biological samples of emergency infectious disease patients. It not only enhances the scientific nature and effectiveness of risk management but also optimizes the allocation of medical resources. Through the comprehensive analysis of pressure fluctuation characteristics, microbial diffusion trends, and drug effects, the accurate identification and timely response to potential risks are achieved, greatly ensuring the safety of the medical environment and the treatment effect of patients. This method provides more reliable decision-making support for clinical practice, helping to improve the quality and safety of the overall medical service.

[0183] Figure 2 The structure diagram of an intelligent scoring system for emergency patients based on a disease-specific scoring tool is provided for the embodiments of this application, as Figure 2 shown, the device includes:

[0184] A capture module 21, configured to generate biological sample pneumatic trajectory data including a sample collection timestamp sequence by capturing in real time the pressure fluctuation characteristics of the respiratory secretions and blood samples of emergency patients in the pneumatic transmission pipeline and the microbial leakage threshold of the sealed cabin;

[0185] An analysis module 22, configured to synchronously analyze the usage frequency of antiviral drugs, the combined use intensity of antibiotics, and the administration interval pattern of immunomodulators in the emergency department medication records to extract infectious disease-related drug characteristics;

[0186] A calculation module 23, configured to perform temporal matching between the sample collection timestamp sequence in the biological sample pneumatic trajectory data and the usage frequency of antiviral drugs in the infectious disease-related drug characteristics, and calculate the patient-specific biological sample transmission risk value in combination with the microbial leakage threshold of the sealed cabin;

[0187] A building module 24, configured to construct a dynamic transmission risk map reflecting the correlation between the pathogen aerosol diffusion path and the medication pattern based on the patient individualized biological sample transmission risk value and the antibiotic combination medication intensity;

[0188] A fusion module 25, configured to generate an early warning score level for emergency infectious disease patients by fusing the pressure fluctuation characteristics in the dynamic transmission risk map and the immunomodulator administration interval pattern, and trigger a shunt instruction for the pneumatic transmission pipeline in real time to isolate high-risk samples;

[0189] A synchronization module 26, configured to dynamically adjust the air flow parameters in the negative pressure isolation area and the priority of infectious disease drug reserves according to the early warning score level, and synchronously optimize the monitoring frequency of the antibiotic combination medication intensity in the medication record.

[0190] Figure 2 The intelligent scoring device for emergency patients based on a disease-specific scoring tool described above can execute Figure 1 The intelligent scoring method for emergency patients based on a disease-specific scoring tool described in the illustrated embodiment, and its implementation principle and technical effects will not be elaborated. For the intelligent scoring device for emergency patients based on a disease-specific scoring tool in the above embodiment, the specific manners in which each module and unit perform operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0191] In a possible design, Figure 2 The intelligent scoring device for emergency patients based on a disease-specific scoring tool in the illustrated embodiment can be implemented as a computing device, such as Figure 3 shown, and this computing device can include a storage component 31 and a processing component 32;

[0192] The storage component 31 stores one or more computer instructions, and among them, the one or more computer instructions are called and executed by the processing component 32.

[0193] The processing component 32 is used for the Figure 1 intelligent scoring method for emergency patients based on a disease-specific scoring tool described in the above

[0194] embodiment. Among them, the processing component 32 can include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component can also be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components for executing the above method.

[0195] The storage component 31 is configured to store various types of data to support the operation of the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0196] Of course, the computing device may necessarily further include other components, such as an input / output interface, a display component, a communication component, etc.

[0197] The input / output interface provides an interface between the processing component and the peripheral interface module, and the peripheral interface module may be an output device, an input device, etc.

[0198] The communication component is configured to facilitate communication between the computing device and other devices in a wired or wireless manner, etc.

[0199] Among them, the computing device may be a physical device or an elastic computing host provided by a cloud computing platform, etc. At this time, the computing device may refer to a cloud server, and the above-mentioned processing component, storage component, etc. may be basic server resources leased or purchased from a cloud computing platform.

[0200] The embodiment of the present application also provides a computer storage medium storing a computer program, and when the computer program is executed by a computer, it can implement the above Figure 1 intelligent scoring method for emergency patients based on a special disease scoring tool shown in the above embodiments.

[0201] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments, and will not be described herein again.

[0202] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative labor.

[0203] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0204] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An intelligent scoring method for emergency patients based on a disease-specific scoring tool, characterized in that: include: By capturing the pressure fluctuation characteristics of emergency patients' respiratory secretions and blood samples in the pneumatic transmission pipeline and the microbial leakage threshold of the sealed cabin in real time, the pneumatic trajectory data of biological samples containing the sample collection timestamp sequence is generated; The frequency of antiviral drug use, the intensity of antibiotic combination therapy, and the interval pattern of immunomodulator administration in the emergency department medication records were simultaneously analyzed to extract the characteristics of drugs associated with infectious diseases; Perform time-series matching of the sample collection timestamp sequence in the biological sample pneumatic trajectory data with the antiviral drug usage frequency in the infectious disease-related drug feature, and calculate the patient's individualized biological sample transmission risk value in combination with the sealed cabin microbial leakage threshold; Based on the transmission risk value of the individualized biological sample of the patient and the intensity of the combined use of antibiotics, a dynamic transmission risk map reflecting the correlation between the pathogen aerosol diffusion path and the medication pattern is constructed; By integrating the pressure fluctuation characteristics in the dynamic transmission risk map with the interval pattern of immunomodulator administration, an early warning score level for emergency infectious disease patients is generated, and a diversion instruction of the pneumatic transmission pipeline is triggered in real time to isolate high-risk samples; The airflow parameters of the negative pressure isolation area and the priority of infectious disease drug reserves are dynamically adjusted according to the warning score level, and the monitoring frequency of the intensity of antibiotic combination use in the medication records is simultaneously optimized.

2. The method according to claim 1, characterized in that The sample collection timestamp sequence in the biological sample pneumatic trajectory data is matched with the antiviral drug usage frequency in the infectious disease-related drug feature, and the patient's individualized biological sample transmission risk value is calculated in combination with the sealed cabin microbial leakage threshold, including: Based on the sample collection timestamp sequence in the pneumatic trajectory data of the biological sample, a time series matching rule is established through the time distribution characteristics of the frequency of use of antiviral drugs to generate an antiviral drug action time interval with a dynamic window length; During the time interval of the antiviral drug action, the pressure fluctuation characteristics of the pneumatic transmission pipeline are segmented and analyzed according to the microbial leakage threshold of the sealed cabin, and the microbial diffusion probability distribution synchronized with the timestamp sequence is extracted; Combining the drug concentration gradient change trend in the time series matching rule with the microbial diffusion probability distribution, the initial parameters of the patient's individualized biological sample transmission risk value are calculated through the spatial superposition effect of microbial residues and drug metabolism cycles; Based on the immunomodulator dosing interval mode, the initial parameters are compensated for time decay, the weight coefficient of the microbial diffusion path is corrected according to the intensity of the combined antibiotic use, and the individualized biological sample transmission risk value that integrates multi-source time series characteristics is output.

3. The method according to claim 2, characterized in that Combining the drug concentration gradient change trend in the time series matching rule with the microbial diffusion probability distribution, the initial parameters of the patient's individualized biological sample transmission risk value are calculated through the spatial superposition effect of microbial residues and drug metabolism cycles, including: Based on the probability distribution of microbial diffusion within the time interval of the antiviral drug action, a dynamic deposition function of the microbial residue varying with the transmission path length is established to generate a spatial attenuation parameter associated with the drug metabolism cycle; According to the drug concentration gradient change trend in the time series matching rule, the dynamic inhibition strength of the antiviral drug on the probability distribution of microbial diffusion is calculated to generate a microbial diffusion correction coefficient carrying time-dependent characteristics; Combining the spatial attenuation parameter with the microbial diffusion correction coefficient, the spatiotemporal coupling characteristics of the initial parameters of the biological sample transmission risk are generated through the superposition effect of the microbial residue deposition path and the drug metabolism rate; Based on the immunomodulator dosing interval pattern, the spatiotemporal coupling characteristics are dynamically smoothed, and the interference effect of the intensity of combined antibiotic use on the microbial deposition path is used to calculate the initial parameters of the patient's individualized biological sample transmission risk value, and output multi-dimensional fused microbial residual distribution characteristics.

4. The method according to claim 2, characterized in that: During the antiviral drug action time interval, the pressure fluctuation characteristics of the pneumatic transmission pipeline are segmented and analyzed according to the microbial leakage threshold of the sealed cabin, and the microbial diffusion probability distribution synchronized with the timestamp sequence is extracted, including: Based on the pressure fluctuation characteristics of the pneumatic transmission pipeline within the time interval of the antiviral drug action, combined with the microbial leakage threshold of the sealed cabin, the pressure fluctuation data is segmented and analyzed to generate pressure fluctuation segmentation characteristics synchronized with the sample collection timestamp sequence; According to the segmented characteristics of the pressure fluctuation, the microbial diffusion trend in each segment is extracted, and the microbial diffusion path is dynamically modeled in combination with the microbial leakage threshold of the sealed cabin to generate a microbial diffusion probability distribution synchronized with the timestamp sequence; Based on the microbial diffusion probability distribution and the drug concentration gradient change trend within the antiviral drug action time interval, the dynamic inhibition strength of the microbial diffusion probability distribution is calculated to generate a microbial diffusion correction coefficient with time-dependent characteristics; The microbial diffusion correction coefficient is fused with the pressure fluctuation segmentation feature to extract the microbial diffusion probability distribution synchronized with the timestamp sequence. Combined with the interference effect of the intensity of combined antibiotic use on the microbial diffusion path, a dynamically updated microbial diffusion probability distribution is output and used as an input parameter for the subsequent calculation of the patient's individualized biological sample transmission risk value.

5. The method according to claim 3, characterized in that: Combining the spatial attenuation parameters with the microbial diffusion correction coefficient, the spatiotemporal coupling characteristics of the initial parameters of biological sample transmission risk are generated through the superposition effect of the microbial residue deposition path and the drug metabolism rate, including: Based on the probability distribution of microbial diffusion within the time interval of the antiviral drug action, combined with the dynamic deposition function of the microbial residue varying with the transmission path length, a spatial attenuation parameter associated with the drug metabolism cycle is generated; According to the drug concentration gradient change trend in the time series matching rule, the dynamic inhibition strength of the antiviral drug on the probability distribution of microbial diffusion is calculated to generate a microbial diffusion correction coefficient carrying time-dependent characteristics; The spatial attenuation parameter is integrated with the microbial diffusion correction coefficient, and the superposition effect of the microbial residue deposition path and the drug metabolism rate is combined to generate the spatiotemporal coupling characteristics of the initial parameters of the biological sample transmission risk; Based on the immunomodulator dosing interval pattern, the spatiotemporal coupling characteristics are dynamically smoothed, and combined with the interference effect of the intensity of combined antibiotic use on the microbial deposition path, a multi-dimensional fusion of microbial residual distribution characteristics is output and used as an input parameter for the subsequent calculation of the patient's individualized biological sample transmission risk value.

6. The method according to claim 3, characterized in that Based on the probability distribution of microbial diffusion within the time interval of the antiviral drug action, a dynamic deposition function of the microbial residue varying with the transmission path length is established to generate spatial attenuation parameters associated with the drug metabolism cycle, including: Analyze the initial parameters of the transmission risk value of the patient's individualized biological sample, identify the variation law of microbial residue with the transmission path length according to the probability distribution of microbial diffusion within the time interval of antiviral drug action, and form a dynamic deposition function of microbial residue; According to the drug concentration gradient change trend in the time series matching rule, the dynamic inhibition strength of antiviral drugs on the probability distribution of microbial diffusion is evaluated, and a microbial diffusion correction coefficient with time-dependent characteristics is generated; The microbial diffusion correction coefficient is combined with the dynamic deposition function of the microbial residue, and the interaction between the microbial residue deposition path and the drug metabolism rate is used to construct the spatiotemporal coupling characteristics of the initial parameters of the biological sample transmission risk; The spatiotemporal coupling characteristics are dynamically smoothed based on the immunomodulator dosing interval pattern. The interference effect of the intensity of combined antibiotic use on the microbial deposition path is considered, and the multi-dimensional fused microbial residue distribution characteristics are output. The microbial residue distribution characteristics are adjusted according to the drug metabolic cycle, and the spatial attenuation parameters associated with the drug metabolic cycle are generated.

7. The method according to claim 4, characterized in that Based on the pressure fluctuation characteristics of the pneumatic transmission pipeline within the time interval of the antiviral drug action, combined with the microbial leakage threshold of the sealed cabin, the pressure fluctuation data is segmented and analyzed to generate pressure fluctuation segmentation features synchronized with the sample collection timestamp sequence, including: Analyze the pressure fluctuation characteristics of the pneumatic transmission pipeline during the transmission of individualized biological samples of patients, identify the pressure fluctuation pattern synchronized with the sample collection timestamp sequence according to the drug concentration gradient change trend within the antiviral drug action time interval, and form a preliminary pressure fluctuation segmentation feature set; The pressure fluctuation segmented feature set obtained in the first step is analyzed according to the microbial leakage threshold of the sealed cabin, the microbial diffusion trend in each segment is extracted, and the microbial diffusion path is dynamically modeled in combination with the microbial leakage threshold of the sealed cabin to generate a microbial diffusion probability distribution synchronized with the timestamp sequence; Based on the microbial diffusion probability distribution and the drug concentration gradient change trend within the antiviral drug action time interval, the dynamic inhibition strength of the microbial diffusion probability distribution is calculated to generate a microbial diffusion correction coefficient with time-dependent characteristics; The microbial diffusion correction coefficient is combined with the preliminary pressure fluctuation segmentation feature set, and the interaction between the microbial diffusion path and the drug metabolism rate is used to generate the pressure fluctuation segmentation feature synchronized with the sample collection timestamp sequence.

8. An intelligent scoring system for emergency patients based on a disease-specific scoring tool, characterized in that: include: A capture module is used to capture the pressure fluctuation characteristics of respiratory secretions and blood samples of emergency patients in the pneumatic transmission pipeline and the microbial leakage threshold of the sealed cabin in real time, and generate pneumatic trajectory data of biological samples including a sample collection timestamp sequence; The analysis module is used to simultaneously analyze the frequency of antiviral drug use, the intensity of antibiotic combination therapy, and the interval pattern of immunomodulator administration in the emergency department medication records, and extract the characteristics of infectious disease-related drugs; A calculation module, for performing time-series matching of a sample collection timestamp sequence in the biological sample pneumatic trajectory data with the antiviral drug usage frequency in the infectious disease-related drug feature, and calculating a patient-individualized biological sample transmission risk value in combination with the sealed cabin microbial leakage threshold; A construction module is used to construct a dynamic transmission risk map reflecting the correlation between the pathogen aerosol diffusion path and the medication mode based on the transmission risk value of the individualized biological sample of the patient and the intensity of the combined use of antibiotics; A fusion module, for generating an early warning score level for emergency infectious disease patients by fusing the pressure fluctuation characteristics in the dynamic transmission risk map with the immunomodulator administration interval pattern, and triggering a diversion instruction of the pneumatic transmission pipeline in real time to isolate high-risk samples; The synchronization module is used to dynamically adjust the airflow parameters and infectious disease drug reserve priorities of the negative pressure isolation area according to the warning score level, and simultaneously optimize the monitoring frequency of the intensity of antibiotic combination medication in the medication record.

9. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement an intelligent scoring method for emergency patients based on a special disease scoring tool as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, an intelligent scoring method for emergency patients based on a special disease scoring tool as described in any one of claims 1 to 7 is implemented.

Images