An intelligent infusion monitoring and early warning method and system

Abstract

This invention relates to the field of infusion monitoring and early warning technology, specifically including an intelligent infusion monitoring and early warning method and system. The method includes: detecting infusion particles, establishing an intravenous infusion model to simulate extravasation, establishing a risk assessment model, real-time monitoring of infusion parameters, predicting risk levels, and sending an early warning command to a monitoring platform when an early warning is triggered. This addresses the technical problems of infusion monitoring relying on fixed threshold judgments, which cannot adapt to different infusion conditions, and the insufficient adaptability of dynamic changes in infusion monitoring and early warning. The invention achieves effective identification of potential risk factors during the infusion process through infusion particle detection and intravenous infusion simulation, combined with the physicochemical properties analysis of drugs. It conducts multi-dimensional risk assessment of particulate contamination and drug extravasation, dynamically adjusts risk thresholds and monitoring parameters, precisely controls infusion quality, adapts to different infusion conditions, and improves the effectiveness of infusion monitoring and early warning by combining real-time monitoring of infusion parameters.

Description

Technical Field

[0001] This invention relates to the technical field of infusion monitoring and early warning, specifically to an intelligent infusion monitoring and early warning method and system. Background Technology

[0002] Intravenous infusion is a common treatment method widely used in clinical practice. However, problems such as particulate contamination, drug extravasation, and inappropriate infusion rate or pressure may occur during the infusion process. These problems can lead to poor treatment results or even harm to patients.

[0003] Current infusion monitoring and early warning systems typically monitor infusion rate and remaining volume in real time and provide basic alarm functions, but they lack precise control over infusion quality, which may lead to medical risks or other adverse events.

[0004] In summary, existing technologies suffer from technical problems such as reliance on fixed thresholds for infusion monitoring, inability to adapt to different infusion conditions for infusion risk monitoring, and insufficient adaptability of dynamic changes in infusion monitoring and early warning. Summary of the Invention

[0005] This application provides an intelligent infusion monitoring and early warning method and system, aiming to solve the technical problems in the prior art where infusion monitoring relies on fixed threshold judgments, cannot perform adaptive infusion risk monitoring for different infusion conditions, and has insufficient adaptability to dynamic changes in infusion monitoring and early warning.

[0006] In view of the above problems, the technical solution to achieve the present application is as follows:

[0007] This application provides an intelligent infusion monitoring and early warning method, comprising: performing particle detection on infusion samples to obtain infusion particle information; establishing an intravenous infusion model based on historical intravenous infusion examples, simulating extravasation, and collecting drug pH and osmotic pressure; based on the intravenous infusion model, performing infusion particle contamination risk analysis using the infusion particle information to establish a first-layer risk assessment framework; performing drug extravasation incidence analysis using the drug pH and osmotic pressure to establish a second-layer risk assessment framework; merging the first-layer and second-layer risk assessment frameworks to establish a risk assessment model; acquiring real-time infusion parameters during the infusion process, and performing dynamic risk prediction using the risk assessment model, determining whether an infusion early warning mechanism is triggered based on the risk level in the dynamic risk prediction result and a preset level threshold, wherein the real-time infusion parameters include infusion flow rate, infusion temperature, infusion volume, and infusion pressure; if the infusion early warning mechanism is triggered, adding the infusion coordinates to the early warning cache interval in the corresponding early warning instruction and sending it to the connected infusion monitoring platform.

[0008] In another aspect, this application provides an intelligent infusion monitoring and early warning system, wherein the system includes: a particle detection module for detecting particles in infusion samples and obtaining infusion particle information; an extravasation simulation module for establishing an intravenous infusion model based on historical intravenous infusion examples, simulating extravasation, and collecting drug pH and drug osmolarity; a risk analysis module for performing infusion particle contamination risk analysis based on the intravenous infusion model and the infusion particle information, establishing a first-level risk assessment framework; and an incidence analysis module for performing drug extravasation incidence analysis using the drug pH and drug osmolarity, establishing a second-level risk assessment framework. The system includes an assessment framework; a framework merging module for merging the first-layer risk assessment framework and the second-layer risk assessment framework to establish a risk assessment model; a risk prediction module for acquiring real-time infusion parameters during the infusion process and performing dynamic risk prediction through the risk assessment model, using the risk level in the dynamic risk prediction result and a preset level threshold to determine whether an infusion early warning mechanism is triggered, wherein the real-time infusion parameters include infusion flow rate, infusion temperature, infusion volume, and infusion pressure; and a monitoring and early warning module for adding the infusion coordinates to the early warning cache range in the corresponding early warning instruction and sending it to the connected infusion monitoring platform if the infusion early warning mechanism is triggered.

[0009] In summary, one or more technical solutions provided in this application solve the technical problems of infusion monitoring relying on fixed threshold judgments, which makes it impossible to conduct adaptive infusion risk monitoring for different infusion conditions, and the inadequate adaptability of dynamic changes in infusion monitoring and early warning. These solutions achieve the technical effect of effectively identifying potential risk factors in the infusion process through infusion particle detection and intravenous infusion simulation, combined with the analysis of the physicochemical properties of drugs, conducting multidimensional risk assessments of particle contamination and drug extravasation, dynamically adjusting risk thresholds and monitoring parameters, precisely controlling infusion quality and adapting to different infusion conditions, and improving the effectiveness of infusion monitoring and early warning by combining real-time monitoring of infusion parameters. Attached Figure Description

[0010] Figure 1 This application provides a flowchart illustrating an intelligent infusion monitoring and early warning method;

[0011] Figure 2 This application provides a structural schematic diagram of an intelligent infusion monitoring and early warning system.

[0012] Explanation of reference numerals in the attached diagram: Particulate detection module M100, Extravasation simulation module M200, Risk analysis module M300, Occurrence analysis module M400, Framework merging module M500, Risk prediction module M600, Monitoring and early warning module M700. Detailed Implementation

[0013] Example 1

[0014] The present application will now be described in detail with reference to the accompanying drawings, such as... Figure 1 As shown, this application provides an intelligent infusion monitoring and early warning method, wherein the method includes:

[0015] S1: Perform particle detection on infusion samples to obtain infusion particle information;

[0016] S2: Based on historical intravenous infusion examples, establish an intravenous infusion model, simulate extravasation, and collect data on drug pH and osmotic pressure.

[0017] Long-term infusion monitoring studies have revealed significant deficiencies in particulate contamination monitoring, drug compatibility safety assessment, and personalized infusion parameter management. To put it simply, particulate contamination is a potential hazard in the infusion process. Particulate contamination may originate from infusion equipment, drug preparation processes, or the infusion environment. Once particulates enter the human body, they may cause phlebitis, granulomas, or even more serious blood infections. Drug extravasation, that is, the accidental leakage of drugs into tissues outside blood vessels, not only affects the efficacy of the drug, but may also lead to serious consequences such as local tissue necrosis and pain.

[0018] On the other hand, if the infusion rate and pressure are not adjusted individually according to the patient's specific physiological condition (such as cardiac function, age, and weight), it may cause excessive circulatory load, phlebitis, or drug toxicity. Therefore, for special patient groups, such as infants, the elderly, and patients with heart disease, conventional infusion monitoring methods are difficult to meet their higher requirements for infusion safety.

[0019] Based on this, this application aims to improve the safety and effectiveness of the infusion process. It has functions such as automatic detection of particulate contamination, prediction of drug extravasation risk, dynamic adjustment of infusion parameters, and provision of personalized infusion strategies for different patient characteristics, thus comprehensively ensuring the safety of the infusion process. Specifically, it performs particulate detection on the infusion sample and further determines the drug category to which the infusion sample belongs, because different drugs may contain particulates with different properties, requiring specific detection conditions. According to the infusion category, appropriate detection configuration parameters, such as laser intensity, are selected to ensure the accuracy and sensitivity of the detection.

[0020] According to the detection configuration parameters, adjust the particle detection equipment, such as adjusting the laser intensity, to ensure that the equipment settings are correct; take a sample from the solution to be used for infusion to ensure that the sample is representative; place the sample in the detection equipment and execute the particle detection program. The detection equipment will record information such as the number and size distribution of particles; analyze the detection results to obtain infusion particle information, including data such as particle concentration and size distribution.

[0021] The historical intravenous infusion examples include data from successful and failed cases (such as extravasation and leakage). Basic information about patients, such as age, gender, weight, and underlying diseases, is extracted from these historical examples. Based on this patient information and physiological parameters, and combined with fluid dynamics principles, a mathematical model of intravenous infusion is established to simulate drug flow within blood vessels. Furthermore, extravasation scenarios are simulated within the intravenous infusion model to assess possible drug extravasation pathways and their impact under different conditions. The physicochemical effects of drug-tissue interactions are understood, and relevant drug pH and osmotic pressure data are collected and analyzed. Finally, the drug pH and osmotic pressure data are integrated into the model to further refine its predictive capabilities.

[0022] S3: Based on the intravenous infusion model, the risk analysis of infusion particle contamination is performed using the infusion particle information to establish a first-level risk assessment framework;

[0023] S4: Analyze the incidence of drug extravasation based on the drug's pH and osmotic pressure to establish a second-layer risk assessment framework;

[0024] S5: Merge the first-level risk assessment framework and the second-level risk assessment framework to establish a risk assessment model.

[0025] Based on the intravenous infusion model, and using the infusion particle information, a risk assessment standard for particle contamination is formulated according to medical standards. If the number of particles exceeds a certain threshold, it is considered to be at high risk. The detected infusion particle information is compared and analyzed with the pre-set risk assessment standard to determine whether there is a risk of particle contamination in the infusion. Based on the comparison results, a first-level risk assessment framework for infusion particle contamination is formed, clarifying each risk factor and its corresponding risk level.

[0026] Information on the pH and osmotic pressure of drugs is collected through drug instructions; risk assessment criteria for drug extravasation are developed based on medical literature, such as the increased risk of extravasation when the pH or osmotic pressure of a drug exceeds a certain range; the incidence of drug extravasation is analyzed by combining the drug's pH, osmotic pressure information and risk assessment criteria; based on the analysis results, a second-layer risk assessment framework for drug extravasation is formed, clarifying each risk factor and its corresponding risk level.

[0027] This paper integrates a first-level risk assessment framework targeting particulate contamination in infusions and a second-level risk assessment framework targeting drug extravasation. Based on the importance of each risk factor to infusion safety, corresponding risk weights are assigned. A comprehensive risk score is calculated based on the risk level and risk weight of each risk factor. An overall risk assessment model is then established based on the integrated risk assessment framework and the comprehensive risk score. This risk assessment model comprehensively considers multiple risk factors, including particulate contamination and drug extravasation, providing model support for a comprehensive assessment of infusion safety.

[0028] S6: Obtain real-time infusion parameters during the infusion process, and perform dynamic risk prediction through the risk assessment model. Determine whether to trigger the infusion early warning mechanism based on the risk level in the dynamic risk prediction result and the preset level threshold. The real-time infusion parameters include infusion flow rate, infusion temperature, infusion volume, and infusion pressure.

[0029] S7: If the infusion warning mechanism is triggered, add the infusion coordinates to the warning cache range in the corresponding warning instruction and send it to the connected infusion monitoring platform.

[0030] Ensure that the infusion pump or other monitoring equipment can monitor the infusion flow rate, temperature, infusion volume, and infusion pressure in real time. Set up a data interface or use wireless communication technology (such as Bluetooth or Wi-Fi) to transmit real-time parameters to the central processing unit or monitoring system. Perform data preprocessing on the real-time infusion parameters during the infusion process, and then load the previously established risk assessment model on the central processing unit or cloud server. Use the real-time infusion parameters as input, and predict the risk level of the current infusion process through model calculations. This involves complex mathematical calculations and algorithm execution, such as neural networks and regression analysis.

[0031] Based on the risk score output by the model, different risk levels (such as low, medium, and high risk) are divided; the predicted risk level is compared with the preset safety threshold to determine whether it is close to or reaches the warning level; furthermore, if the predicted risk level exceeds the preset level threshold, an infusion warning is triggered; the infusion coordinates that triggered the warning (such as bed number, infusion pump ID, etc.) are obtained, and the infusion coordinates are associated with the warning command.

[0032] The infusion coordinates are added to the cache range of the early warning command. The command, which includes the infusion coordinates and the early warning level, is sent to the infusion monitoring platform via the internal network or cloud service. Upon receiving the early warning command, the infusion monitoring platform immediately displays the alarm information, including the specific location and risk level. According to the platform rules, medical staff are dispatched to the site for examination and treatment, and necessary corrective measures are taken.

[0033] In practical applications, this also includes recording early warning events and their processing results for subsequent auditing and model optimization; regularly reviewing the efficiency and accuracy of the early warning system; adjusting preset thresholds or optimizing model algorithms based on actual operating conditions; precisely controlling the quality of infusions during the infusion process and adapting to different infusion conditions; and improving the effectiveness of infusion monitoring and early warning by combining dynamic monitoring of real-time infusion parameters.

[0034] Furthermore, the method of this application for detecting particulate matter in infusion samples and obtaining particulate matter information in infusions includes:

[0035] Determine the infusion category, configure particle detection according to the infusion category, and obtain preset detection configuration parameters, including laser intensity;

[0036] When the combined drugs are mixed with the solvent, incompatibility analysis is performed, and the preset detection configuration parameters are adjusted to obtain the adjusted detection configuration parameters;

[0037] Particle detection is performed based on the adjusted detection configuration parameters to obtain infusion particle information.

[0038] Identify the type of infusion requiring particulate matter detection, including different types of drugs, solutions, or nutrient solutions; determine different detection requirements and standards based on the infusion category, for example, some drugs may have specific restrictions on the size, quantity, or type of particles; select the appropriate configuration from preset particulate matter detection parameters based on the identified infusion category, including laser intensity, detection time, and sample volume; select a suitable laser intensity setting based on the characteristics and requirements of the infusion, as the laser intensity affects detection sensitivity and accuracy.

[0039] If intravenous infusion involves the mixing of multiple drugs and solvents, collect basic drug information for the various drugs and solvents involved in the combination, such as drug components, concentrations, and mechanisms of action; use drug interaction analysis tools or databases to perform interaction analysis on the collected basic drug information to identify various incompatibilities; based on the incompatibility analysis results (for the mixing of multiple drugs and solvents), generate a cohort of incompatibilities, listing drug combinations that require special attention and potential risks.

[0040] By combining information from the incompatibilities cohort, assess the potential changes in microparticles that may occur after mixing the combined drugs with the solvent, such as an increase in the number of microparticles or changes in their size. Based on the assessment results, adjust the preset microparticle detection configuration parameters, especially the laser intensity. For example, if more or smaller microparticles are expected to be generated, the laser intensity needs to be increased to improve detection sensitivity.

[0041] Set up the particulate detection device using the adjusted detection configuration parameters; prepare the infusion sample and process it according to the device operation guide, such as dilution and filtration; place the processed infusion sample into the particulate detection device and start the device to perform particulate detection; after the device completes the detection, record and collect the detection results, i.e., the infusion particulate information, including the number, size distribution, and type of particles.

[0042] Preferably, the obtained infusion microparticle information is evaluated to determine whether it meets the preset quality standards and safety requirements; if the test results do not meet the requirements, the cause needs to be further investigated, such as drug compatibility issues, contamination during the production process, etc., and corresponding corrective measures are taken; the test results and evaluation results are fed back to relevant personnel for subsequent quality control and improvement.

[0043] Furthermore, when combining drugs with solvents, incompatibility analysis is performed, and the preset detection configuration parameters are adjusted. The method of this application includes:

[0044] Collect basic drug information for the multiple drugs involved in the combined use;

[0045] Based on the aforementioned basic drug information, interaction analysis is performed to obtain a cohort of incompatibilities.

[0046] When the combined drugs are mixed with the solvent, particle distribution simulation is performed in conjunction with the incompatibility cohort to determine the particle distribution simulation characteristics.

[0047] The preset detection configuration parameters are adjusted by simulating the particle distribution characteristics.

[0048] Determine the types and quantities of drugs to be used in combination, and compile a list of all drugs involved in the combination. For each drug, collect detailed basic information about it, including its components, concentration, pH value, solubility, stability, and pharmacological effects. This information can be obtained by consulting drug instructions, medical databases, or relevant literature.

[0049] By utilizing relevant literature on drug interaction analysis, the collected basic drug information is input into the system; drug interaction analysis is automatically performed to determine whether there are any incompatibilities, which involve aspects such as drug stability, efficacy, and toxicity; based on the analysis results, a drug incompatibility queue is generated, which lists all drug combinations with incompatibilities and indicates the risks involved.

[0050] Based on the formulation and solvent type of the combined drugs, set the parameters for particle distribution simulation, including drug concentration, solvent pH, temperature, and stirring speed; input the drug combinations in the incompatibility queue into the particle distribution simulation system; perform particle distribution simulation based on the set parameters and drug combinations, involving processes such as drug dissolution, precipitation, and reaction, as well as the impact of these processes on particle distribution; after the simulation is completed, output the particle distribution simulation results, including information such as the number, size, shape, and distribution range of particles.

[0051] Analyze the particle distribution simulation results and extract key particle distribution simulation features, including the maximum number of particles, average size, and main distribution area. Based on the particle distribution simulation features, evaluate whether the current preset detection configuration parameters are applicable. If not, adjustments are needed. Adjust the preset detection configuration parameters, including laser intensity, detection time, sample size, and detection sensitivity. Furthermore, adjustments should be made specifically based on the particle distribution simulation features to improve detection accuracy and sensitivity.

[0052] In practical applications, this also includes applying the adjusted preset detection configuration parameters to actual particle detection, and verifying and testing them to ensure that the new configuration parameters can effectively detect various fine particles that may be generated after the combined drugs and solvents are mixed.

[0053] Furthermore, when combining drugs with solvents, particle distribution simulation is performed using the aforementioned incompatibility cohort to determine particle distribution simulation characteristics. The method of this application includes:

[0054] A particle distribution simulation channel is established, which includes a chemical reaction kinetics branch and a pharmacokinetics branch.

[0055] When the combined drugs are mixed with the solvent, a compatibility optimization is performed based on the constraints of the incompatibility queue.

[0056] After compatibility optimization, particle distribution simulation is performed through the particle distribution simulation channel to determine the particle distribution simulation characteristics.

[0057] When combining drugs with solvents, in order to simulate particle distribution and determine the characteristics of particle distribution simulation by incorporating a cohort of incompatibilities, we can follow these detailed steps:

[0058] Define the basic structure and parameters of a particle distribution simulation channel, which is a model that simulates the mixing, reaction and distribution of drugs in a solvent; set up a chemical reaction kinetic branch in the simulation channel, which is used to simulate the chemical reactions that may occur during the mixing process of drugs, such as precipitation, complexation, hydrolysis, etc., which affect the formation and distribution of particles.

[0059] A pharmacokinetic branch is set up in the simulation channel to simulate the intravenous distribution process of drugs in vivo. Although it cannot be completely identical in in vitro simulation, it is sufficient to assist in simulating the dynamic changes of drugs in solvents. Based on the incompatibility cohort, it is possible to identify which drug combinations have incompatibilities and the potential risks or problems. The causes of incompatibilities are analyzed, such as chemical reactions between drugs and pharmacodynamic competition, to identify key factors that need optimization. According to the constraints of incompatibilities, the formulation of combined drugs and solvents is adjusted to eliminate or mitigate the impact of incompatibilities, including changing drug concentrations, changing the type of solvent, or adjusting the order of drug administration. A compatibility optimization test is performed on the adjusted formulation to ensure that the new formulation can reduce or avoid the occurrence of incompatibilities.

[0060] The optimized combination drug and solvent formulation is input into the particle distribution simulation channel. This channel simulates the mixing and reaction process of the combination drugs in the solvent. Furthermore, the chemical reaction kinetics branch and pharmacokinetic branch simulate the chemical reactions between drugs and the dynamic changes of the drugs in the solvent, respectively. The formation and distribution of particles during the simulation are monitored by observing parameters such as the number, size, shape, and distribution range of particles in the simulation results. Based on the simulation results, the characteristics and patterns of particle distribution are analyzed to determine the stability and compatibility of the drugs in the solvent, as well as potential particulate contamination issues.

[0061] Extract key data from the simulation results, such as the maximum number of particles, average size, and main distribution areas; analyze and determine the main characteristics and patterns of particle distribution, including the trend of particle number changes over time, the distribution range of particle size, and the spatial distribution of particles in the solvent; compare and analyze the determined particle distribution simulation characteristics with the preset quality standards and safety requirements. Furthermore, if the simulation results meet the standards, it indicates that the current combination drug and solvent formulation is feasible; if they do not meet the standards, further adjustments to the formulation or other measures are needed to reduce the risk of particulate contamination.

[0062] Furthermore, based on historical intravenous infusion examples, an intravenous infusion model is established. The method of this application includes:

[0063] Extract basic user information based on historical intravenous infusion examples;

[0064] Based on the user's basic information, an intravenous infusion model was established through hemodynamic analysis.

[0065] Collect and organize data from historical intravenous infusion instances, including intravenous infusion records for different patients, including but not limited to patient age, gender, weight, height, disease type, type of infusion medication, infusion rate, and infusion time; extract basic user information from historical intravenous infusion instances, including patient physiological parameters (such as age, gender, weight, and height) and pathological parameters (such as disease type and severity); clean and preprocess the extracted basic user information, including handling missing values ​​and outliers, to ensure data accuracy and completeness.

[0066] This study analyzes the fundamental principles of hemodynamics, the study of blood flow and circulation within the vascular system, used to understand the movement and distribution of blood and drugs within blood vessels during intravenous infusion. Based on user information, a hemodynamic model is constructed for each patient, reflecting their specific physiological and pathological conditions, such as vessel diameter, blood flow velocity, and vessel wall elasticity. The intravenous infusion process is incorporated into the hemodynamic model, including simulating the entry of drugs into blood vessels, their diffusion and distribution within the vessels, and the effects of drugs on blood flow and vessel walls.

[0067] The accuracy of the model can be verified through experiments or simulations. Furthermore, this can be achieved by comparing the model's predictions with data observed during actual intravenous infusion. If there is a significant difference between the model's predictions and the actual data, adjustments and optimizations are necessary. Based on the verification results, the intravenous infusion model can be optimized and improved, including adjusting model parameters, improving the model structure, or introducing new influencing factors, in order to improve the model's prediction accuracy and applicability, thereby better understanding patients' infusion needs, optimizing infusion protocols, improving treatment outcomes, and reducing infusion risks.

[0068] Furthermore, in establishing an intravenous infusion model through hemodynamic analysis, the method of this application also includes:

[0069] The insertion position information of the infusion is obtained, and combined with the intravenous infusion model, a flow safety perception analysis is performed to obtain the flow resistance perception information and pressure distribution perception information of the infusion flow area.

[0070] Based on the aforementioned flow resistance sensing information and pressure distribution sensing information, sensitive flow resistance sensing information and sensitive pressure distribution sensing information of sensitive population groups are obtained.

[0071] By adjusting the model parameters of the intravenous infusion model using the sensitive flow resistance perception information and sensitive pressure distribution perception information of the sensitive population, a limited type intravenous infusion model corresponding to the sensitive population is obtained.

[0072] Before starting intravenous infusion, the insertion site is determined, usually at a point on the patient's vein, such as the back of the hand or forearm. Medical equipment (such as ultrasound or vascular imaging) is used to obtain detailed vascular structure and blood flow information of the insertion site, including vessel diameter, blood flow velocity, and vessel wall elasticity. The detailed vascular structure and blood flow information of the insertion site are then input into the established intravenous infusion model as input parameters for the model.

[0073] The infusion process is simulated in the intravenous infusion model, including the process of drug entering the blood vessel from the infusion tube, and its diffusion and distribution in the blood vessel; the flow resistance perception information of the infusion flow area is analyzed, including the resistance encountered by the drug when flowing in the blood vessel, such as the increased resistance at narrowing, tortuosity, and bifurcation of the blood vessel; the pressure distribution perception information of the infusion flow area is analyzed, including the pressure changes generated when the drug flows in the blood vessel, and how the pressure changes affect the blood vessel wall and surrounding tissues.

[0074] Define sensitive population groups, such as the elderly, children, and people with cardiovascular diseases. In short, these are people who are more sensitive to the flow resistance and pressure distribution during infusion due to physiological or pathological reasons. Set parameters related to sensitive population groups in the intravenous infusion model, such as reduced vascular elasticity and fragile vascular walls. Simulate the infusion process and focus on the flow resistance and pressure distribution perception information of sensitive population groups during the infusion process.

[0075] The model parameters of the intravenous infusion model are adjusted by analyzing the sensitive flow resistance and sensitive pressure distribution perception information of sensitive populations. Specifically, the sensitive flow resistance and sensitive pressure distribution perception information of sensitive populations are analyzed to determine which factors have the greatest impact on these populations. Based on the analysis results, the parameters of the intravenous infusion model, such as infusion rate, infusion tubing diameter, and drug concentration, are adjusted to reduce the flow resistance and pressure changes encountered by sensitive populations during infusion. The simulation and analysis process is repeated until the model can better simulate the flow resistance and pressure distribution of sensitive populations during infusion.

[0076] A restricted-type intravenous infusion model corresponding to the sensitive population was obtained. Furthermore, the adjusted model was used as the restricted-type intravenous infusion model for the sensitive population to provide a safer and more effective intravenous infusion solution. Feedback and data were continuously collected in practical applications and optimized and improved.

[0077] Furthermore, to obtain sensitive flow resistance perception information and sensitive pressure distribution perception information of sensitive population groups, the method of this application also includes:

[0078] Based on the sensitive population category, a search is performed within the infusion population to obtain the first sensitive category population, where the first sensitive category is children;

[0079] Within the infusion population, a second sensitive category search was performed to obtain the second sensitive category population, which is the elderly;

[0080] Based on the second sensitive category identifier, secondary matching optimization is performed through the constraint of the matching taboo queue.

[0081] To identify the first sensitive category population (children), specifically, among those receiving intravenous infusions, a search for the first sensitive category (children) is conducted based on the patient's age information or other relevant identifiers (such as height, weight, etc.); an age threshold (e.g., 0–14 years) is set to define pediatric patients, and all patients within this age range are selected as the first sensitive category population; relevant data for the first sensitive category population (children) are collected, including physiological parameters (such as blood vessel diameter, blood vessel wall elasticity, etc.), pathological parameters (such as disease type, severity of condition, etc.), as well as the type of infusion medication, infusion rate, etc.

[0082] The first sensitivity category is children, which is preferred. Based on children's physiological characteristics, such as lower blood volume, immature liver and kidney function, and specific high-risk factors, the effects of high-risk drugs such as antibiotics are especially considered. The infusion rate is automatically set and maintained according to the child's weight, age and drug characteristics, while preventing unauthorized rate changes to ensure infusion safety.

[0083] To identify the second sensitive category (elderly), specifically, within the infusion population, continue to search for the second sensitive category (elderly) based on patient age information or other relevant markers (such as physical function status); set an age threshold (e.g., 65 years and older) to define elderly patients, and screen all patients within this age range as the second sensitive category; collect relevant data for the second sensitive category (elderly), including physiological parameters (such as the degree of vascular aging, vascular wall elasticity, etc.), pathological parameters (such as possible chronic diseases, drug tolerance, etc.), as well as the type of infusion drug and infusion rate, etc.

[0084] The second sensitive category is the elderly. Preferred options are based on the physiological characteristics of the elderly (such as slowed metabolism, decreased kidney function, etc.) and the presence of complications, taking into account the potential interactions between drugs, especially when multiple drugs are administered simultaneously via intravenous route, and dynamically assessing the risk level of drug combinations; taking into account the differences in tolerance of the elderly to infusion rate and drug concentration, the infusion parameters can be automatically adjusted according to individualized data (such as renal function indicators, cardiac function status) to avoid excessive circulatory load or other complications.

[0085] After identifying the second sensitive group (elderly), check for any drug incompatibilities in the patients' current medications. Drug incompatibilities refer to adverse reactions or reduced efficacy that may result from the simultaneous use of two or more drugs. The drug incompatibility cohort contains all known drug combinations that are incompatible. By going through the drug incompatibilities cohort, we can traverse the list of drugs currently used by the second sensitive group and check for any combinations that match those in the cohort. If a drug incompatibility is found, secondary drug compatibility optimization is performed, including changing the drug, adjusting the drug dosage or infusion rate, and changing the infusion sequence, to ensure patient safety.

[0086] Then, by comparing the first and second sensitive groups within the sensitive population, the corresponding sensitive flow resistance perception information and sensitive pressure distribution perception information were obtained. Based on the collected relevant data of the sensitive population (children and the elderly), the established intravenous infusion model was used for simulation analysis. During the simulation, the focus was on the flow resistance and pressure distribution issues encountered by the sensitive population during infusion, including analyzing the resistance encountered by the drug when flowing in the blood vessels and the pressure changes of the blood vessel walls.

[0087] Based on the simulation results, sensitive flow resistance perception information and sensitive pressure distribution perception information of sensitive groups are obtained. The intravenous infusion model is then further adjusted and optimized to better adapt to the needs of sensitive groups, obtain sensitive flow resistance perception information and sensitive pressure distribution perception information of sensitive groups more accurately, and provide safer and more effective intravenous infusion solutions for sensitive groups.

[0088] In summary, the beneficial effects of the embodiments of this application are:

[0089] 1. By integrating particulate detection and drug property analysis, it can monitor and provide early warning of particulate contamination and drug extravasation risks in real time, significantly improving the safety of infusion.

[0090] 2. Establish personalized infusion models based on basic patient information and hemodynamic analysis to achieve customized risk assessment for different sensitive populations (such as children and the elderly).

[0091] 3. By combining historical intravenous infusion examples and real-time infusion parameters, the risk assessment model is dynamically adjusted to predict and prevent potential risks in advance. Through refined management of the infusion process, more precise treatment control can be achieved.

[0092] 4. Due to the adoption of

[0093] Example 2

[0094] Based on the same inventive concept as the intelligent infusion monitoring and early warning method in the foregoing embodiments, such as Figure 2As shown in the figure, this application provides an intelligent infusion monitoring and early warning system, wherein the system includes:

[0095] The particle detection module M100 is used to detect particles in infusion samples and obtain infusion particle information;

[0096] The extravasation simulation module M200 is used to establish an intravenous infusion model based on historical intravenous infusion examples, simulate extravasation, and collect drug pH and drug osmotic pressure.

[0097] The risk analysis module M300 is used to perform risk analysis of intravenous infusion particulate contamination based on the intravenous infusion model and the infusion particulate information, and to establish a first-level risk assessment framework.

[0098] The incidence analysis module M400 is used to analyze the incidence of drug extravasation based on the drug's pH and osmotic pressure, and to establish a second-layer risk assessment framework.

[0099] The framework merging module M500 is used to merge the first-layer risk assessment framework and the second-layer risk assessment framework to establish a risk assessment model.

[0100] The risk prediction module M600 is used to acquire real-time infusion parameters during the infusion process and perform dynamic risk prediction through the risk assessment model. The risk level in the dynamic risk prediction result is compared with the preset level threshold to determine whether to trigger the infusion early warning mechanism. The real-time infusion parameters include infusion flow rate, infusion temperature, infusion volume, and infusion pressure.

[0101] The monitoring and early warning module M700 is used to add the infusion coordinates to the early warning cache range in the corresponding early warning command and send it to the connected infusion monitoring platform if the infusion early warning mechanism is triggered.

[0102] Furthermore, the particle detection module M100 is used to perform the following method:

[0103] Determine the infusion category, configure particle detection according to the infusion category, and obtain preset detection configuration parameters, including laser intensity;

[0104] When the combined drugs are mixed with the solvent, incompatibility analysis is performed, and the preset detection configuration parameters are adjusted to obtain the adjusted detection configuration parameters;

[0105] Particle detection is performed based on the adjusted detection configuration parameters to obtain infusion particle information.

[0106] Furthermore, the particle detection module M100 is also used to perform the following method:

[0107] Collect basic drug information for the multiple drugs involved in the combined use;

[0108] Based on the aforementioned basic drug information, interaction analysis is performed to obtain a cohort of incompatibilities.

[0109] When the combined drugs are mixed with the solvent, particle distribution simulation is performed in conjunction with the incompatibility cohort to determine the particle distribution simulation characteristics.

[0110] The preset detection configuration parameters are adjusted by simulating the particle distribution characteristics.

[0111] Furthermore, the particle detection module M100 is also used to perform the following method:

[0112] A particle distribution simulation channel is established, which includes a chemical reaction kinetics branch and a pharmacokinetics branch.

[0113] When the combined drugs are mixed with the solvent, a compatibility optimization is performed based on the constraints of the incompatibility queue.

[0114] After compatibility optimization, particle distribution simulation is performed through the particle distribution simulation channel to determine the particle distribution simulation characteristics.

[0115] Furthermore, the extravasation simulation module M200 is used to perform the following method:

[0116] Extract basic user information based on historical intravenous infusion examples;

[0117] Based on the user's basic information, an intravenous infusion model was established through hemodynamic analysis.

[0118] Furthermore, the extravasation simulation module M200 is also used to perform the following methods:

[0119] The insertion position information of the infusion is obtained, and combined with the intravenous infusion model, a flow safety perception analysis is performed to obtain the flow resistance perception information and pressure distribution perception information of the infusion flow area.

[0120] Based on the aforementioned flow resistance sensing information and pressure distribution sensing information, sensitive flow resistance sensing information and sensitive pressure distribution sensing information of sensitive population groups are obtained.

[0121] By adjusting the model parameters of the intravenous infusion model using the sensitive flow resistance perception information and sensitive pressure distribution perception information of the sensitive population, a limited type intravenous infusion model corresponding to the sensitive population is obtained.

[0122] Furthermore, the extravasation simulation module M200 is also used to perform the following methods:

[0123] Based on the sensitive population category, a search is performed within the infusion population to obtain the first sensitive category population, where the first sensitive category is children;

[0124] Within the infusion population, a second sensitive category search was performed to obtain the second sensitive category population, which is the elderly;

[0125] Based on the second sensitive category identifier, secondary matching optimization is performed through the constraint of the matching taboo queue.

[0126] In summary, any step can be stored as a computer instruction or program in an unrestricted computer memory and can be called and recognized by an unrestricted computer processor; no further restrictions are imposed here.

[0127] Furthermore, the above technical solutions only embody the preferred technical solutions of the embodiments of this application. Any changes that those skilled in the art may make to certain parts of these solutions embody the novel principles of the embodiments of this application. Obviously, those skilled in the art can make various modifications and variations to this application without departing from the scope of this application.

Claims

1. An intelligent infusion monitoring and early warning method, characterized in that, The method includes: Microparticle detection is performed on infusion samples to obtain microparticle information. Based on historical intravenous infusion examples, an intravenous infusion model was established to simulate extravasation scenarios, evaluate the possible extravasation pathways and effects of drugs under different conditions, and collect data on drug pH and osmolarity. Based on medical standards, risk assessment standards for particulate contamination are formulated. Using the infusion particulate information, risk analysis of infusion particulate contamination is conducted to establish a first-level risk assessment framework. By analyzing the drug's pH and osmotic pressure, the incidence of drug extravasation is determined, and a second-layer risk assessment framework is established. The first-level risk assessment framework and the second-level risk assessment framework are merged to establish a risk assessment model; Real-time infusion parameters during the infusion process are acquired, and dynamic risk prediction is performed through the risk assessment model. The risk level in the dynamic risk prediction result is compared with the preset level threshold to determine whether to trigger the infusion early warning mechanism. The real-time infusion parameters include infusion flow rate, infusion temperature, infusion volume, and infusion pressure. If the infusion warning mechanism is triggered, the infusion coordinates will be added to the warning cache range in the corresponding warning command and sent to the connected infusion monitoring platform; The method for establishing an intravenous infusion model based on historical intravenous infusion examples includes: extracting basic user information based on historical intravenous infusion examples; and establishing an intravenous infusion model based on the basic user information through hemodynamic analysis. The process of establishing an intravenous infusion model based on the user's basic information through hemodynamic analysis includes: constructing a hemodynamic model for each patient based on the user's basic information, wherein the individual patient's hemodynamic model can reflect the patient's specific physiological and pathological state, including blood vessel diameter, blood flow velocity, and blood vessel wall elasticity; incorporating the intravenous infusion process into the hemodynamic model, including simulating the process of drug entering the blood vessel, spreading and distributing in the blood vessel, and the effect of the drug on blood flow and blood vessel wall during the infusion process; The method for establishing an intravenous infusion model through hemodynamic analysis further includes: acquiring the insertion location information of the infusion tube; combining the intravenous infusion model with flow safety perception analysis to acquire flow resistance perception information and pressure distribution perception information of the infusion flow area; acquiring sensitive flow resistance perception information and sensitive pressure distribution perception information for sensitive population groups based on the flow resistance perception information and pressure distribution perception information of sensitive population groups; adjusting the model parameters of the intravenous infusion model based on the sensitive flow resistance perception information and sensitive pressure distribution perception information of sensitive population groups to reduce the flow resistance and pressure changes encountered by sensitive population groups during infusion; the model parameters include infusion rate, infusion tube diameter, and drug concentration; repeating the simulation and analysis process until the model can simulate the flow resistance and pressure distribution of sensitive population groups during infusion, thus obtaining a limited type of intravenous infusion model corresponding to the sensitive population group.

2. The intelligent infusion monitoring and early warning method as described in claim 1, characterized in that, The method for detecting particulate matter in infusion samples to obtain particulate information includes: Determine the infusion category, configure particle detection according to the infusion category, and obtain preset detection configuration parameters, including laser intensity; When the combined drugs are mixed with the solvent, incompatibility analysis is performed, and the preset detection configuration parameters are adjusted to obtain the adjusted detection configuration parameters; Particle detection is performed based on the adjusted detection configuration parameters to obtain infusion particle information.

3. The intelligent infusion monitoring and early warning method as described in claim 2, characterized in that, When combining drugs with solvents, incompatibility analysis is performed, and the preset detection configuration parameters are adjusted. The method includes: Collect basic drug information for the multiple drugs involved in the combined use; Based on the aforementioned basic drug information, interaction analysis is performed to obtain a cohort of incompatibilities. When the combined drugs are mixed with the solvent, particle distribution simulation is performed in conjunction with the incompatibility cohort to determine the particle distribution simulation characteristics. The preset detection configuration parameters are adjusted by simulating the particle distribution characteristics.

4. The intelligent infusion monitoring and early warning method as described in claim 3, characterized in that, When combining drugs with solvents, particle distribution simulation is performed using the incompatibility cohort to determine particle distribution simulation characteristics. The method includes: A particle distribution simulation channel is established, which includes a chemical reaction kinetics branch and a pharmacokinetics branch. When the combined drugs are mixed with the solvent, a compatibility optimization is performed based on the constraints of the incompatibility queue. After compatibility optimization, particle distribution simulation is performed through the particle distribution simulation channel to determine the particle distribution simulation characteristics.

5. The intelligent infusion monitoring and early warning method as described in claim 1, characterized in that, The method for acquiring sensitive flow resistance perception information and sensitive pressure distribution perception information of sensitive population groups further includes: Based on the sensitive population category, a search is performed within the infusion population to obtain the first sensitive category population, where the first sensitive category is children; Within the infusion population, a second sensitive category search was performed to obtain the second sensitive category population, which is the elderly; Based on the second sensitive category identifier, secondary matching optimization is performed through the constraint of the matching taboo queue.

6. An intelligent infusion monitoring and early warning system, characterized in that, The system is used to implement the intelligent infusion monitoring and early warning method according to any one of claims 1-5, the system comprising: The particle detection module is used to detect particles in infusion samples and obtain particle information in the infusion. The extravasation simulation module is used to establish an intravenous infusion model based on historical intravenous infusion examples. In the intravenous infusion model, extravasation scenarios are simulated to evaluate the possible extravasation pathways and effects of drugs under different conditions, and to collect drug pH and drug osmotic pressure. The risk analysis module is used to develop risk assessment standards for particulate contamination based on medical standards, and to conduct risk analysis of particulate contamination in infusions using the infusion particulate information to establish a first-level risk assessment framework. The incidence analysis module is used to analyze the incidence of drug extravasation based on the drug's pH and osmotic pressure, and to establish a second-layer risk assessment framework. The framework merging module is used to merge the first-layer risk assessment framework and the second-layer risk assessment framework to establish a risk assessment model. The risk prediction module is used to acquire real-time infusion parameters during the infusion process and perform dynamic risk prediction through the risk assessment model. The risk level in the dynamic risk prediction result is compared with the preset level threshold to determine whether to trigger the infusion early warning mechanism. The real-time infusion parameters include infusion flow rate, infusion temperature, infusion volume, and infusion pressure. The monitoring and early warning module is used to add the infusion coordinates to the early warning cache range in the corresponding early warning command and send it to the connected infusion monitoring platform if the infusion early warning mechanism is triggered.

Images