Monitoring method and system based on portal vein blood pressure data

Abstract

The invention discloses a monitoring method and system based on portal vein blood pressure data, and relates to the technical field of data monitoring. A lumped parameter model is constructed according to postoperative clinical data, and parameters related to the lumped parameter model are optimized and calibrated; performing steady-state simulation by using the optimized and calibrated lumped parameter model, and calculating portal vein blood pressure and other related hemodynamic parameters; the portal vein blood pressure is monitored in real time on the basis of the lumped parameter model application condition determined through steady state simulation, and the disease change and the treatment effect of the patient are evaluated; whether the monitoring result is abnormal or not is judged according to the monitoring result and patient personalized parameters, and then clinical feedback and suggestions are provided; a patient personalized updating and adjusting period is set based on the patient personalized parameters, and the lumped parameter model is updated and optimized based on the patient personalized updating and adjusting period. Continuous monitoring and personalized treatment of the condition of the patient are achieved, and the diagnosis accuracy and the treatment effect are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data monitoring, and particularly to a monitoring method and system based on portal vein blood pressure data. Background Art

[0002] Monitoring of portal vein blood pressure is of crucial significance in the field of liver diseases and related treatments. Many liver diseases, such as liver cirrhosis, liver cancer, etc., often lead to portal hypertension, which in turn causes a series of serious complications, such as rupture and bleeding of esophageal and gastric fundus varices, ascites, etc., seriously threatening the life and health of patients. Accurately monitoring portal vein blood pressure plays a key role in early detection of portal hypertension, assessment of the severity of the disease, formulation of a reasonable treatment plan, and monitoring of the treatment effect.

[0003] However, currently in clinical practice, monitoring of portal vein blood pressure faces many challenges. The accuracy and reliability of the portal vein blood pressure data monitoring method need to be improved, and it is difficult to comprehensively and real-time reflect the hemodynamic changes of the portal vein system. Moreover, there is a lack of personalized monitoring and evaluation systems, and individual differences of different patients cannot be fully considered. At the same time, existing technologies have deficiencies in data processing, model construction, and clinical feedback, etc., which limit the application effect of portal vein blood pressure monitoring in clinical practice.

[0004] Therefore, aiming at the above problems, there is an urgent need for a monitoring method and system based on portal vein blood pressure data. Summary of the Invention

[0005] Aiming at the deficiencies of the prior art, the present invention provides a monitoring method and system based on portal vein blood pressure data, and solves the problem that it is difficult to monitor and accurately evaluate portal vein blood pressure in real time.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: A monitoring method based on portal vein blood pressure data, comprising the following steps: S1, obtaining postoperative clinical data, where the postoperative clinical data includes portal vein blood pressure-related data, mean abdominal aortic blood pressure, inferior vena cava blood pressure, and related vascular resistance data; S2, performing quality screening and correction on the postoperative clinical data, and then constructing a lumped parameter model based on the quality-screened and corrected postoperative clinical data, and optimizing and calibrating the parameters involved in the lumped parameter model; S3, using the optimized and calibrated lumped parameter model for steady-state simulation, calculating the portal vein blood pressure and other related hemodynamic parameters, and verifying the calculation results; S4, based on the application status of the lumped parameter model determined by the steady-state simulation, performing real-time monitoring of the portal vein blood pressure, and evaluating the patient's condition change and treatment effect based on the monitored change of the portal vein blood pressure; S5, outputting the real-time monitoring results, and at the same time, based on the monitoring results and the patient's personalized parameters, determining whether the monitoring results are abnormal, and then providing clinical feedback and suggestions; S6, setting a patient-specific update and adjustment cycle based on the patient's personalized parameters, and updating and optimizing the lumped parameter model based on the patient-specific update and adjustment cycle.

[0007] Further, the specific steps of S2 include: constructing a three-dimensional geometric model of the patient's portal vein system based on the postoperative clinical data, and simplifying the patient's vascular system into a circuit model based on the three-dimensional geometric model; based on the characteristics of the circuit model, combining the postoperative clinical data to determine and calculate the blood pressure parameters at each point in the circuit model, and then identifying the hepatic vein system flow rate and the blood flow resistance parameter values in the lumped parameter model, and minimizing the difference between the output result of the lumped parameter model and the actual postoperative clinical data by adjusting the parameters involved in the lumped parameter model.

[0008] Further, the specific steps of verifying the calculation results in S3 include: setting steady-state boundary conditions and initial conditions, and then performing steady-state simulation based on the optimized and calibrated lumped parameter model to output the portal vein blood pressure and other related hemodynamic parameters; adjusting the input of the lumped parameter model, fitting the relationship between the output portal vein blood pressure and the mean abdominal aortic blood pressure corresponding to each adjustment to obtain the sensitivity coefficient between the portal vein blood pressure and the mean abdominal aortic blood pressure, comparing the sensitivity coefficient between the portal vein blood pressure and the mean abdominal aortic blood pressure with a preset sensitivity threshold, and when the sensitivity coefficient between the portal vein blood pressure and the mean abdominal aortic blood pressure is less than the sensitivity threshold, updating and adjusting the parameters involved in the lumped parameter model, otherwise applying the lumped parameter model to the actual portal vein blood pressure monitoring.

[0009] Further, the specific steps of S4 include: obtaining the mean abdominal aortic blood pressure, inferior vena cava blood pressure, and related vascular resistance data in real time based on clinical monitoring; using the mean abdominal aortic blood pressure, inferior vena cava blood pressure, and related vascular resistance data as inputs to a lumped parameter model to output the portal vein blood pressure; sorting and arranging the output portal vein blood pressure according to time nodes, and then identifying the change trend of the portal vein blood pressure to obtain the trend change parameter of the portal vein blood pressure; and identifying the treatment effect of the patient based on the correlation between the trend change parameter of the portal vein blood pressure and the treatment effect.

[0010] Further, the specific steps of S5 include: obtaining patient-specific parameters, which include but are not limited to the patient's body fat percentage, patient age, patient drug allergy records, patient surgical history, current medications used by the patient, and patient underlying disease records; identifying the association model between the patient-specific parameters and the trend change parameter of the portal vein blood pressure based on the portal vein blood pressure monitoring records stored in the medical system, and then verifying the trend change parameter of the portal vein blood pressure according to the association model. When the trend change parameter of the patient's portal vein blood pressure conforms to the patient-specific parameters in the association model, it is determined that there is no abnormal condition in the monitoring result, and the medical advice for this type of patient is retrieved and transmitted based on the patient-specific parameters; when the trend change parameter of the patient's portal vein blood pressure does not conform to the patient-specific parameters in the association model, the monitoring result of the lumped parameter model is verified. When the monitoring result is verified to be qualified, it is marked that there is an abnormal condition in the monitoring result of the patient's portal vein blood pressure data, and a prompt text message is sent to the medical monitoring personnel based on the alarm mechanism; when the monitoring result is verified to be unqualified, the latest postoperative clinical data is obtained, the lumped parameter model of the patient is updated and optimized, and the patient's portal vein blood pressure data is monitored based on the updated and optimized lumped parameter model.

[0011] Further, the specific method for setting the patient-specific update and adjustment cycle based on the patient-specific parameters is: constructing a relationship model between the patient-specific parameters and the patient-specific update and adjustment cycle, and then inputting the patient-specific parameters into the relationship model between the patient-specific parameters and the patient-specific update and adjustment cycle to output the patient-specific update and adjustment cycle.

[0012] A monitoring system based on portal vein blood pressure data, which applies the above-mentioned monitoring method based on portal vein blood pressure data, includes: a data acquisition module for acquiring postoperative clinical data, where the postoperative clinical data includes portal vein blood pressure-related data, mean abdominal aortic blood pressure, inferior vena cava blood pressure, and related vascular resistance data; a model construction and parameter calibration module for performing quality screening and correction on the postoperative clinical data, and then constructing a lumped parameter model based on the quality-screened and corrected postoperative clinical data, and optimizing and calibrating the parameters involved in the lumped parameter model; a steady-state simulation module for performing steady-state simulation using the optimized and calibrated lumped parameter model, calculating the portal vein blood pressure and other related hemodynamic parameters, and verifying the calculation results; a portal vein blood pressure monitoring module for monitoring the portal vein blood pressure in real time based on the application status of the lumped parameter model determined by the steady-state simulation, and evaluating the patient's condition change and treatment effect based on the monitored change of the portal vein blood pressure; a result output and feedback module for outputting the real-time monitoring results, and at the same time judging whether the monitoring results are abnormal according to the monitoring results and the patient's personalized parameters, and then providing clinical feedback and suggestions; a continuous optimization module for setting a patient-specific update and adjustment cycle based on the patient's personalized parameters, and updating and optimizing the lumped parameter model based on the patient-specific update and adjustment cycle.

[0013] The present invention has the following beneficial effects:

[0014] The monitoring method and system based on portal vein blood pressure data can accurately track the change of portal vein blood pressure by acquiring portal vein blood pressure-related data, mean abdominal aortic blood pressure, inferior vena cava blood pressure, and related vascular resistance data, and constructing a lumped parameter model for steady-state simulation and real-time monitoring, providing a solid data basis for accurately evaluating the patient's condition change and treatment effect, helping doctors detect subtle changes in the condition in a timely manner and make more accurate diagnosis and treatment decisions; considering the patient's personalized parameters, setting a personalized update and adjustment cycle to optimize the lumped parameter model, and at the same time providing clinical feedback and suggestions according to the monitoring results and personalized parameters, this personalized method can fully consider the unique physiological conditions and disease characteristics of different patients, customize medical plans for each patient, improve the pertinence and effectiveness of treatment, and improve the patient's treatment experience and prognosis; regularly updating and adjusting the lumped parameter model based on the patient's personalized parameters enables the model to reflect the dynamic changes of the patient's condition in real time. As the patient's treatment process progresses and the physical condition changes, the model is continuously optimized to ensure that the accuracy of monitoring and evaluation always remains at a high level and adapts to the complex and changeable clinical environment; outputting the real-time monitoring results and combining clinical feedback and suggestions provides intuitive and comprehensive information for doctors, and doctors can quickly make reasonable clinical decisions based on this information, such as adjusting the treatment plan and judging the treatment timing, improving the efficiency and quality of medical services. Description of the Drawings

[0015] Figure 1 This is a flowchart of a monitoring method based on portal vein blood pressure data according to the present invention.

[0016] Figure 2 This is a structural diagram of a monitoring system based on portal vein blood pressure data according to the present invention. Specific embodiments

[0017] In the embodiments of the present application, a monitoring method and system based on portal vein blood pressure data are adopted to achieve continuous monitoring of the patient's condition and personalized treatment, significantly improving the diagnostic accuracy and treatment effect.

[0018] The general idea of the embodiments of the present application is as follows: First, comprehensively collect postoperative clinical data, including data related to portal vein blood pressure and other data closely related to blood circulation. Through strict data quality screening and calibration, a lumped parameter model is constructed and its parameters are optimized and calibrated; use the optimized model for steady-state simulation to calculate and verify the portal vein blood pressure and other hemodynamic parameters; on this basis, based on the steady-state simulation results, perform real-time monitoring of the portal vein blood pressure, and evaluate the patient's condition and treatment effect according to the monitoring changes; at the same time, combine the patient's personalized parameters to judge whether there are abnormalities in the monitoring results and provide clinical feedback and suggestions; and, set an update and adjustment cycle according to the patient's personalized parameters, and regularly update and optimize the lumped parameter model to form a closed-loop system from data collection, model construction, real-time monitoring, evaluation and feedback to model optimization, so as to achieve accurate, personalized and dynamic monitoring and evaluation of the portal vein blood pressure and provide strong support for clinical treatment.

[0019] Please refer to Figure 1 , the embodiments of the present invention provide a technical solution: A monitoring method based on portal vein blood pressure data, including the following steps: S1, obtain postoperative clinical data, and the postoperative clinical data includes data related to portal vein blood pressure, mean abdominal aortic blood pressure, inferior vena cava blood pressure and related vascular resistance data; S2, perform quality screening and calibration on the postoperative clinical data, and then construct a lumped parameter model according to the postoperative clinical data after quality screening and calibration, and optimize and calibrate the parameters involved in the lumped parameter model; S3, use the optimized and calibrated lumped parameter model for steady-state simulation, calculate the portal vein blood pressure and other related hemodynamic parameters, and verify the calculation results; S4, based on the application status of the lumped parameter model determined by the steady-state simulation, perform real-time monitoring of the portal vein blood pressure, and evaluate the patient's condition change and treatment effect based on the monitoring change of the portal vein blood pressure; S5, output the real-time monitoring results, and at the same time, according to the monitoring results and the patient's personalized parameters, judge whether there are abnormalities in the monitoring results, and then provide clinical feedback and suggestions; S6, set a patient personalized update and adjustment cycle based on the patient's personalized parameters, and update and optimize the lumped parameter model based on the patient personalized update and adjustment cycle.

[0020] Specifically, the specific steps of S2 include: constructing a three-dimensional geometric model of the patient's portal vein system based on postoperative clinical data, and simplifying the patient's vascular system into a circuit model based on the three-dimensional geometric model; based on the characteristics of the circuit model and combined with postoperative clinical data, determining and calculating the blood pressure parameters at each point in the circuit model, and then identifying the blood flow resistance parameter values in the hepatic vein system flow and lumped parameter model. By adjusting the parameters involved in the lumped parameter model, the difference between the output result of the lumped parameter model and the actual postoperative clinical data is minimized.

[0021] In this implementation plan, the specific steps for constructing a three-dimensional geometric model of the patient's portal vein system are as follows: collecting the imaging data of the enhanced abdominal CT venous phase before the patient's surgery, which contains the detailed structural information of the portal vein system and provides the original data for subsequent model construction; using MIMICS or other professional medical image processing software to process and analyze the collected imaging data; through techniques such as image segmentation and feature extraction, realizing the reconstruction of the three-dimensional geometric model of the larger branches of the patient's portal vein system and accurately restoring the anatomical structure of the portal vein system; based on the reconstructed three-dimensional geometric model of the portal vein system, using relevant software to construct a geometric model of the specified parameters of the TIPS shunt channel, and accurately constructing the geometric shape and size of the shunt channel according to the specific surgical plan and shunt channel design parameters of the patient, so that it is combined with the portal vein system model to form a complete three-dimensional geometric model of the portal vein system including the shunt channel.

[0022] The specific analysis of simplifying the patient's vascular system into a circuit model based on the three-dimensional geometric model is as follows: For the analysis of vascular structure: deeply analyzing the constructed three-dimensional geometric model of the portal vein system to determine the key features such as the branch structure, diameter size, and blood vessel direction of the blood vessels, which will be used for the subsequent construction of the circuit model to ensure that the circuit model can accurately reflect the hemodynamic characteristics of the vascular system. For the mapping of circuit elements: According to the vascular structure and hemodynamic principles, different parts of the vascular system are mapped into circuit elements. For example, blood flow resistance is regarded as resistance, and its resistance value is related to factors such as the length and diameter of the blood vessel and the viscosity of the blood, and the blood pressure characteristics are mapped into potentiometers; the blood vessels are regarded as circuits; through this mapping relationship, the complex vascular system is transformed into a relatively simple circuit model. Specific examples of the construction and analysis of the circuit model include: mapping the splenic vein, superior mesenteric vein, main portal vein branch, left portal vein branch, right portal vein branch, and shunt channel into circuit wires, mapping the average blood pressure of the abdominal aorta, inferior vena cava blood pressure, portal vein blood pressure, and blood pressure at the hepatic sinus level into potentiometers, and mapping the mesenteric blood flow resistance, blood flow resistance of other upstream organs of the portal vein such as the spleen and stomach, hepatic artery system blood flow resistance, blood flow resistance in the perfusion area of the left portal vein branch, blood flow resistance in the perfusion area of the right portal vein branch, and hepatic vein system blood flow resistance into resistors.

[0023] The lumped parameter model is specifically the lumped parameter model of the isolated free hepatic circulation. This model includes the shunt channel and the main portal vein vessels, as well as the zero-dimensional models of the complete hepatic circulation upstream and downstream of them. It can realize the monitoring and simulation of the local small-scale flow field of the TIPS shunt channel and the large-scale hemodynamic state of the liver blood circulation system. This lumped parameter model is constructed based on the measured clinical data after the operation and the parameters are calibrated. Based on this, it is possible to monitor the portal vein blood pressure for different shunt channel conditions after the operation. Using steady-state simulation, the relevant numerical solutions can be implemented based on open-source programming languages such as the R language, or also based on high-level programming languages such as Python.

[0024] The specific construction steps of the lumped parameter model are as follows: collect the image data of the venous phase of the enhanced abdominal CT of the patient before the operation, use MIMICS or other software to realize the reconstruction of the three-dimensional geometric model of the larger branches of the patient's portal vein system, and on this basis, use relevant software to construct the geometric model with specified parameters of the TIPS shunt channel; based on the above geometric model, simplify the complex vascular system into a circuit model for easy calculation and analysis; use R / Python or other software to realize the setting of boundary conditions and calculation parameters, and complete the numerical solution.

[0025] In the lumped parameter model, each model parameter is calibrated according to the measured clinical data after the operation. The specific operation steps are as follows: after the TIPS stent is implanted, use a monitor to measure the arterial blood pressure of the patient and calculate the mean blood pressure PAO, use a catheter to measure the inferior vena cava blood pressure PIVC and the portal vein blood pressure PPV of the patient, and estimate the blood pressure PSIN representing the hepatic sinusoid level from the portal vein and inferior vena cava blood pressures; while the above measurements are being taken, use Doppler ultrasound to measure the mean flow velocity of the hepatic artery and the flow velocity in the middle of the main portal vein. In addition, calculate the pressure of the hepatic artery system according to the empirical formula, equivalently replace the hepatic vein pressure with the right atrial pressure and take the population-averaged data; obtain the flow of the hepatic vein system by summing the difference between the hepatic artery flow and the total portal vein flow and the shunt channel flow; the parameter values of each blood flow resistance in the model can be determined by the ratio of the upstream and downstream pressure differences to the corresponding flows, and the blood pressures at each required point and the flows of each path have been clarified in the above steps.

[0026] Constructing a lumped parameter model for a separate free hepatic circulation can achieve the monitoring and simulation of the local small-scale flow field of the TIPS shunt and the large-scale hemodynamic state of the liver blood circulation system. This precise simulation helps doctors deeply understand the hemodynamic changes of the portal vein system under different shunt conditions, provides a reliable basis for accurately monitoring the portal vein blood pressure, and thus more precisely evaluates the patient's condition and treatment effect. The lumped parameter model is constructed and calibrated based on the measured clinical data after the operation to make the model more in line with the actual situation of the patient. By adjusting the model parameters to minimize the difference between the output result and the actual clinical data after the operation, the accuracy of the model is continuously optimized to ensure the reliability of the monitoring result and provide strong support for clinical decision-making. Simplifying the complex vascular system into a circuit model and using open-source programming languages (such as R) or high-level programming languages (such as Python) to implement the setting of boundary conditions and calculation parameters and numerical solution improves the calculation efficiency and the generality of the model, facilitating adjustment and application by different medical institutions and research teams according to their own needs, and promoting the development of related research and clinical practice. Determining the hepatic vein system flow rate and the blood flow resistance parameter values in the lumped parameter model through a series of clear operation steps comprehensively covers the key factors affecting the hemodynamics of the portal vein system, helps to deeply analyze the blood flow change mechanism of the portal vein system, and provides detailed information for formulating personalized treatment plans.

[0027] Specifically, the specific steps for verifying the calculation results in S3 include: setting steady-state boundary conditions and initial conditions, and then performing steady-state simulation based on the optimized and calibrated lumped parameter model to output the portal vein blood pressure and other related hemodynamic parameters; adjusting the input of the lumped parameter model, fitting the relationship between the output portal vein blood pressure and the mean abdominal aortic blood pressure corresponding to each adjustment to obtain the sensitivity coefficient between the portal vein blood pressure and the mean abdominal aortic blood pressure, comparing the sensitivity coefficient between the portal vein blood pressure and the mean abdominal aortic blood pressure with the preset sensitivity threshold. When the sensitivity coefficient between the portal vein blood pressure and the mean abdominal aortic blood pressure is less than the sensitivity threshold, update and adjust the parameters involved in the lumped parameter model, otherwise apply the lumped parameter model to the actual portal vein blood pressure monitoring.

[0028] In this implementation scheme, the specific steps for setting the steady-state boundary conditions and initial conditions are as follows: First, it is necessary to clarify various physiological parameters related to the portal vein system, such as the diameter, length, elasticity of blood vessels, and the physical properties of blood, such as density, viscosity, etc. These parameters are obtained through preoperative imaging examinations (such as enhanced abdominal CT), postoperative clinical measurements (such as catheter blood pressure measurement, Doppler ultrasound flow velocity measurement, etc.), and relevant medical literature and empirical data; according to the clinical measurement data, determine the boundary pressure conditions of the model. For example, input the inferior vena cava blood pressure, mean abdominal aortic blood pressure, etc. as known boundary pressure values into the model, and the specific pressure values are obtained through specific measurement devices during the operation or after the operation; according to the data such as the mean hepatic artery flow velocity measured by Doppler ultrasound and the flow velocity in the middle of the main portal vein, set the initial blood flow velocity and flow rate of each blood vessel in the model. At the same time, according to the principle of continuity of blood flow and the law of conservation of mass, ensure that the initial blood flow state remains balanced throughout the blood vessel system; according to empirical formulas or existing research results, determine the resistance and compliance parameters of blood vessels. The blood vessel resistance is calculated by the ratio of the pressure difference between upstream and downstream to the corresponding flow rate, and the compliance reflects the expansion and contraction characteristics of blood vessels under the action of pressure.

[0029] The specific steps for performing steady-state simulation based on the optimized and calibrated lumped parameter model are as follows: Input the various parameters of the optimized and calibrated lumped parameter model, including blood vessel resistance, compliance, pressure boundary conditions, and initial blood flow state, into the simulation software or calculation program; use numerical calculation methods, such as the finite element method, finite difference method, etc., to perform iterative calculations on the model. In each iteration, according to the basic equations of blood flow (such as the Navier-Stokes equation) and the geometric structure of the blood vessel system, calculate the hemodynamic parameters such as pressure, flow velocity, and flow rate at each point in the blood vessel. Through continuous iteration, make the calculation results gradually converge to a stable state; during the iteration process, it is necessary to check the convergence of the calculation results. Specifically, use convergence criteria, such as the parameter change between two adjacent iterations is less than a certain threshold, or the calculated hemodynamic parameters remain stable within a certain range. When the convergence criteria are met, it is considered that the simulation has reached a steady state; once the simulation reaches a steady state, output the portal vein blood pressure and other relevant hemodynamic parameters, such as hepatic artery flow rate, portal vein flow rate, shunt channel flow rate, and blood vessel wall pressure.

[0030] The specific steps to fit the relationship between the output portal vein blood pressure and the mean abdominal aortic blood pressure corresponding to each adjustment to obtain the sensitivity coefficient between the portal vein blood pressure and the mean abdominal aortic blood pressure are as follows: Through steady-state simulation, under different input conditions (i.e., adjusting the input to the lumped parameter model), multiple sets of corresponding portal vein blood pressure and mean abdominal aortic blood pressure data are obtained, and these data constitute the sample set for relationship fitting; According to the characteristics and distribution of the data, a suitable fitting method is selected. Common fitting methods include linear regression, non-linear regression, etc. If the relationship between the portal vein blood pressure and the mean abdominal aortic blood pressure is approximately linear, the linear regression method can be used. If the relationship is more complex, non-linear regression methods such as polynomial regression and exponential regression may be required; Substitute the collected data into the selected fitting method, and through optimization algorithms such as the least squares method, determine the parameters of the fitting curve. For example, in linear regression, by calculating to minimize the sum of the squares of the errors between the fitting line and the data points, the slope and intercept of the line are obtained; The slope of the fitting curve is the sensitivity coefficient between the portal vein blood pressure and the mean abdominal aortic blood pressure, indicating the degree of corresponding change in the portal vein blood pressure when the mean abdominal aortic blood pressure changes by one unit, and is used to quantify the sensitivity of the portal vein blood pressure to the mean abdominal aortic blood pressure.

[0031] The sensitivity threshold is set as follows: The doctor determines a reasonable sensitivity threshold based on past clinical experience and understanding of the relationship between the portal vein blood pressure and the mean abdominal aortic blood pressure, combined with the statistical analysis of data from a large number of patients. For example, in long-term clinical practice, it is found that when the sensitivity coefficient is less than a certain specific value, the accuracy of the model may be affected and the model needs to be adjusted; It is also possible to consult existing medical literature and research results to understand what the commonly used sensitivity thresholds are in similar models and monitoring methods, refer to the thresholds determined by other research teams in the study of portal vein system hemodynamics, and make appropriate adjustments in combination with the specific situation of this study; It is also possible to conduct a series of pre-experiments before formally applying this monitoring method. In the pre-experiments, evaluate the accuracy and stability of the model under different sensitivity coefficients, observe the differences between the model output results and the actual clinical data, and determine a sensitivity threshold that can enable the model to accurately reflect the changes in the portal vein blood pressure in most cases through the analysis of the pre-experiment data; The sensitivity threshold can be dynamically adjusted according to the specific situation of the patient and different disease stages. For example, for patients with relatively stable conditions, a relatively low sensitivity threshold can be adopted to reduce the frequency of model update and adjustment, while for patients with rapidly changing conditions or in special treatment stages, the sensitivity threshold can be appropriately increased to more timely detect the deviation between the model and the actual situation and make adjustments.

[0032] By adjusting the input of the lumped parameter model and analyzing the sensitivity coefficient between the portal vein blood pressure and the mean blood pressure of the abdominal aorta, the model can be optimized and updated according to the actual situation, making the model more accurately reflect the physiological state of the patient and improving the adaptability of the model to individual differences among different patients. Comparing the sensitivity coefficient with a preset sensitivity threshold to determine whether to update and adjust the model parameters helps ensure the reliability and stability of the lumped parameter model when applied to actual portal vein blood pressure monitoring, and avoid monitoring errors caused by inaccurate model parameters.

[0033] Specifically, the specific steps of S4 include: obtaining the mean blood pressure of the abdominal aorta, the blood pressure of the inferior vena cava, and relevant vascular resistance data in real time based on clinical monitoring; using the mean blood pressure of the abdominal aorta, the blood pressure of the inferior vena cava, and relevant vascular resistance data as the input of the lumped parameter model, and outputting the portal vein blood pressure; sorting and arranging the output portal vein blood pressure according to time nodes, and then identifying the change trend of the portal vein blood pressure to obtain the trend change parameter of the portal vein blood pressure; identifying the treatment effect of the patient based on the correlation between the trend change parameter of the portal vein blood pressure and the treatment effect.

[0034] In this implementation scheme, the specific steps for identifying the change trend of the portal vein blood pressure and obtaining the trend change parameter are as follows: at a set time interval (such as every 5 minutes or every 15 minutes), continuously obtain the mean blood pressure of the abdominal aorta, the blood pressure of the inferior vena cava, and relevant vascular resistance data from the clinical monitoring device, and use these data as the input to calculate and output the portal vein blood pressure data at the corresponding time points through the lumped parameter model; arrange the output portal vein blood pressure data in chronological order to form a sequence that changes over time, ensuring that each data point corresponds to an accurate timestamp; select the linear regression method, and through linear regression analysis of the portal vein blood pressure time series, obtain a linear equation describing the change of blood pressure over time: P PV = a + b * t, where P PV represents the portal vein blood pressure, t represents the time node, a represents the intercept, and b is the slope, that is, the trend change parameter of the portal vein blood pressure. a and b are obtained by fitting using the least squares method.

[0035] The steps for confirming the correlation between the trend change parameters of portal vein blood pressure and the treatment effect are as follows: Collect the data of the trend change parameters of portal vein blood pressure for a group of patients receiving the same or similar treatment regimens, and at the same time record the corresponding treatment effect evaluation results for each patient. The treatment effect evaluation is comprehensively judged based on the improvement of clinical symptoms (such as reduction of ascites, reduction of the risk of esophageal and gastric variceal bleeding, etc.) and laboratory test indicators (such as improvement of liver function indicators, etc.). Then, the Pearson correlation coefficient is used to measure the linear correlation between the trend change parameters of portal vein blood pressure and the treatment effect. For the Pearson correlation coefficient, if the absolute value of the result is closer to 1, it indicates a stronger linear correlation between the trend change parameters of portal vein blood pressure and the treatment effect. When the result is positive, it is a positive correlation, that is, the larger the trend change parameters of portal vein blood pressure (such as the larger the slope indicating the faster the blood pressure rises), the better the treatment effect. When the result is negative, it is a negative correlation, that is, the larger the trend change parameters of portal vein blood pressure, the worse the treatment effect. A specific example of the correlation calculation expression is: In the formula, r is the Pearson correlation coefficient, X is the sample of the trend change parameters of portal vein blood pressure, and xi represents the trend change parameters of portal vein blood pressure of the i-th sample. represents the mean value of the sample of the trend change parameters of portal vein blood pressure, E represents the sample of the treatment effect evaluation results, and E i represents the treatment effect evaluation result of the i-th sample. represents the mean value of the sample of the treatment effect evaluation results, and n represents the number of samples.

[0036] By obtaining the mean blood pressure of the abdominal aorta, the blood pressure of the inferior vena cava, and the relevant vascular resistance data in real time, it can timely reflect the immediate state of the patient's internal blood circulation system, making the monitoring of portal vein blood pressure no longer limited to static or intermittent measurements, and can capture the changes that may occur in the condition at any time, providing a more timely basis for clinical decision-making; identifying the treatment effect of patients based on the correlation between the trend change parameters of portal vein blood pressure and the treatment effect can more comprehensively and accurately judge whether the treatment regimen is effective compared to simply relying on a single blood pressure measurement value, because the treatment process of the disease is often a dynamic process, and the trend change of blood pressure can better reflect the long-term impact of treatment on the internal physiological mechanisms of the patient's body; using multiple data closely related to blood circulation as the input of the lumped parameter model and using the powerful analysis ability of the model to output the portal vein blood pressure provides a scientific decision-making method based on data and models for clinicians, reducing the uncertainty of subjective judgment and making medical decisions more objective and accurate.

[0037] Specifically, the specific steps of S5 include: obtaining patient personalized parameters, which include but are not limited to the patient's body fat percentage, age, drug allergy record, surgical history, currently used medications, and basic disease record; identifying the association model between the patient personalized parameters and the portal vein blood pressure trend change parameters based on the portal vein blood pressure monitoring records stored in the medical system, and then verifying the trend change parameters of the portal vein blood pressure according to the association model. When the trend change parameters of the patient's portal vein blood pressure match the personalized parameters in the association model, it is determined that there is no abnormal condition in the monitoring result, and the medical advice for this type of patient is retrieved and transmitted based on the patient personalized parameters; when the trend change parameters of the patient's portal vein blood pressure do not match the personalized parameters in the association model, the monitoring result of the centralized parameter model is verified. When the monitoring result is verified to be qualified, it is marked that there is an abnormal condition in the monitoring result of the patient's portal vein blood pressure data, and a prompt text message is sent to the medical monitoring personnel based on the alarm mechanism; when the monitoring result is verified to be unqualified, the latest postoperative clinical data is obtained, the patient's centralized parameter model is updated and optimized, and the patient's portal vein blood pressure data is monitored based on the updated and optimized centralized parameter model.

[0038] In this implementation plan, the patient's body fat percentage is measured using bioelectrical impedance analysis. The patient stands on a body fat scale, and the body fat percentage is estimated by measuring the body's bioelectrical impedance; dual-energy X-ray absorptiometry can also be used, where the body fat percentage is calculated by scanning the body with X-rays and measuring the differences in X-ray absorption by different tissues; or the skinfold thickness measurement method can be used, where a skinfold thickness caliper is used to measure the skinfold thickness at specific body parts (such as the triceps brachii, subscapular angle, etc.), and then the body fat percentage is calculated according to a formula. The body fat percentage is expressed as a percentage. For example, if the calculated body fat percentage is 25%, the quantified value is 25.

[0039] The patient's age is obtained through the patient's ID card information, date of birth in the medical record file, etc., and is represented by the actual age value.

[0040] The patient's drug allergy record is identified by consulting the patient's medical record file, asking the patient or their family members, and querying relevant records from the hospital's electronic medical record system. It is recorded in a classified manner, and the names of the allergic drugs are recorded, such as "penicillin", "cephalosporin", etc. The number of types of allergic drugs can be used as a quantified index. For example, if the patient is allergic to 3 drugs, the quantified value is 3.

[0041] The patient's surgical history is identified by checking the patient's medical record file, which details information such as the names and times of the patient's past surgeries, and can also be obtained through a detailed interview with the patient or their family members. The number of surgeries is used as a quantified index. For example, if the patient has had 2 surgeries in the past, the quantified value is 2.

[0042] The drugs currently used by the patient are obtained by asking the patient about the drugs being taken, checking the patient's prescription records, and retrieving the drug dispensing records from the hospital pharmacy. Record the drug name and dosage, such as "enteric-coated aspirin tablets, 100 mg / tablet, once a day", and the number of types of drugs being used can also be counted. For example, if the patient is currently taking 5 drugs, the quantified value is 5.

[0043] The records of the patient's underlying diseases are identified by consulting the patient's medical records, including outpatient medical records and inpatient medical records, which detail the underlying diseases the patient has. It can also be obtained by communicating with the patient or their family members. Classify and record the underlying diseases, such as "liver cirrhosis", "hypertension", "diabetes", etc., and count the number of types of underlying diseases. For example, if the patient has 3 underlying diseases, the quantified value is 3.

[0044] The specific steps for identifying the association model between the patient's personalized parameters and the parameters of the portal vein blood pressure trend changes are as follows: Extract the patient's portal vein blood pressure monitoring records from the medical system, including the portal vein blood pressure values and corresponding timestamps at different time points. At the same time, collect the patient's personalized parameter data to ensure that the monitoring records and personalized parameter data of each patient are accurately corresponding. Clean the collected data to remove outliers and missing values to ensure data quality; Analyze the characteristics of the personalized parameters and the parameters of the portal vein blood pressure trend changes, and select the features that have a significant impact on the construction of the association model; According to the data characteristics and analysis purposes, select an appropriate model to establish the association relationship, such as multiple linear regression model, logistic regression model, decision tree model, neural network model, etc. Taking the multiple linear regression model as an example, the specific calculation expression example is: In the formula, b is the parameter of the portal vein blood pressure trend change, β0, β1, β2,..., β m represent the regression coefficients, which are determined by optimization algorithms such as the least squares method, and c1, c2,..., c m represent the patient's personalized parameters, m represents the number of samples of the patient's personalized parameters, represents the error term, which is determined by optimization algorithms such as the least squares method.

[0045] The specific steps for verifying the trend change parameters of portal vein blood pressure based on the association model are as follows: Obtain the personalized parameter data of the patient to be verified, and organize and encode it according to the format required by the association model. At the same time, obtain the trend change parameters of the patient's portal vein blood pressure through calculation using the lumped parameter model or other monitoring methods; Input the patient's personalized parameters into the established association model. The model predicts the value of the trend change parameters of the patient's portal vein blood pressure that should be based on its internal parameters and logical relationships; Compare the model prediction value with the trend change parameters of the patient's portal vein blood pressure obtained through actual monitoring, and calculate the difference between the two. If the calculated error is within the threshold range, it is considered that the trend change parameters of the patient's portal vein blood pressure and the personalized parameters conform to the association model, and the monitoring result is normal. If the error exceeds the threshold, it is considered that the two do not conform to the association model, and the monitoring result may be abnormal.

[0046] The specific steps for retrieving and transmitting medical advice for this type of patient based on the patient's personalized parameters are as follows: Match and classify according to the patient's personalized parameters in the medical knowledge base or database. For example, classify the patient according to age range, types of underlying diseases, surgical history, etc., and determine the specific category to which the patient belongs; For the category to which the patient belongs, retrieve the corresponding medical advice in the medical knowledge base. The medical knowledge base stores information such as treatment plans, drug usage suggestions, diet and lifestyle guidance for different combinations of patient characteristics. For example, for patients over 60 years old with liver cirrhosis, the retrieved medical advice may include regular liver function tests, use of specific liver-protecting drugs, and following a low-salt and low-fat diet; Organize the retrieved medical advice so that it is presented in a clear and understandable manner, and transmit the medical advice to doctors and patients through the hospital's information system, electronic medical record platform, or text messages.

[0047] The specific steps for verifying the monitoring results of the lumped parameter model are as follows: Collect other reliable portal vein blood pressure monitoring data as a reference, such as the portal vein blood pressure value obtained through invasive measurement methods (when clinically permitted), or blood pressure data obtained using other validated non-invasive monitoring techniques. Compare the portal vein blood pressure value monitored by the lumped parameter model with the reference data and calculate the difference between the two; Evaluate the performance of the lumped parameter model under different conditions according to its characteristics. For example, check the adaptability of the model to different individual patient differences, observe the stability of the model during long-term monitoring, and analyze the response ability of the model to abnormal situations (such as sudden blood pressure changes), etc.; Medical experts can also be invited to evaluate the monitoring results of the lumped parameter model. The experts judge whether the monitoring results conform to the actual condition of the patient based on their clinical experience and professional knowledge.

[0048] By obtaining the patient's personalized parameters and identifying the association model between them and the parameters of the portal vein blood pressure trend change, it is possible to customize the monitoring criteria for different patients, which helps to more accurately judge whether the monitoring results of the portal vein blood pressure of each patient are abnormal, improve the accuracy and pertinence of monitoring, and avoid misjudgment caused by general criteria. When it is found that the parameters of the portal vein blood pressure trend change of the patient do not conform to the association model with the personalized parameters, a clear abnormal handling process is designed to verify the monitoring results of the centralized parameter model. If it is qualified, it marks the abnormality and notifies the medical monitoring personnel. If it is unqualified, it updates and optimizes the centralized parameter model. This efficient abnormal handling mechanism can timely discover and solve the problems occurring in the monitoring process and ensure the health and safety of the patient. Retrieving and transmitting medical advice for this type of patient based on the patient's personalized parameters provides targeted treatment guidance for doctors and patients, helps doctors formulate treatment plans more in line with the individual conditions of the patients, improves the treatment effect, and at the same time facilitates patients to understand their own conditions and corresponding treatment advice, enhancing the patients' compliance with the treatment. Obtaining the latest postoperative clinical data to update and optimize the centralized parameter model enables the model to continuously adapt to the changes in the patient's condition and individual differences. By continuously optimizing the model, the accuracy and reliability of portal vein blood pressure monitoring are further improved, providing more powerful support for clinical decision-making.

[0049] Specifically, the specific method for setting the patient's personalized update and adjustment cycle based on the patient's personalized parameters is as follows: construct a relationship model between the personalized parameters and the personalized update and adjustment cycle, and then input the patient's personalized parameters into the relationship model between the personalized parameters and the personalized update and adjustment cycle, and the patient's personalized update and adjustment cycle is output.

[0050] In this implementation plan, by constructing a relationship model between the personalized parameters and the personalized update and adjustment cycle, it is possible to customize the update and adjustment cycle of the centralized parameter model according to the unique physiological characteristics, disease history, and treatment conditions of each patient. Different patients have different disease development speeds and responses to treatment. For example, patients who are young and have few underlying diseases recover quickly and their conditions are relatively stable, so the centralized parameter model does not need to be updated frequently. However, for elderly patients or patients with multiple complex underlying diseases, the condition changes may be more frequent, and a shorter update cycle is required to timely reflect the changes in the physical condition, thus realizing precision medicine. Reasonably setting the update and adjustment cycle can avoid unnecessary frequent model updates and reduce the waste of computing resources and labor costs in the medical system. A timely and appropriate update and adjustment cycle can ensure that the centralized parameter model is always closely fitted to the current actual situation of the patient.

[0051] The specific steps for constructing a relationship model between personalized parameters and personalized update adjustment cycles are as follows: Comprehensively collect personalized parameter data of patients, and at the same time record the actual requirements for the update adjustment cycles of the centralized parameter models corresponding to each patient (obtained specifically through clinical observations, expert evaluations, etc.). Integrate this data to ensure the accuracy and consistency of the data, and form a data set for model construction; Analyze the potential impact of each personalized parameter on the update adjustment cycle, and screen out the features with significant impacts. For example, the severity and quantity of underlying diseases may have a greater impact on the update cycle, while the drug allergy record may have a relatively small relationship with the update cycle; Standardize or normalize the screened features to make different features have a unified dimension and scale, which is convenient for subsequent model training and analysis; According to the data characteristics and analysis purposes, select an appropriate model to construct the relationship. You can choose a linear regression model, a decision tree model, a neural network model, etc. Taking the linear regression model as an example, a specific calculation expression example is: T = T0 - ε1*c1 - ε2*c2 -... - ε w *c w + κ, where T represents the personalized update adjustment cycle, T0 represents the initial update adjustment cycle, which can be set to 30 days, for example, ε1, ε2,..., ε w represent the regression coefficients, determined by optimization algorithms such as the least squares method, κ represents the error term, determined by optimization algorithms such as the least squares method, c1, c2,..., c w represent the patient's personalized parameters, and w represents the number of patient personalized parameter samples.

[0052] Please refer to Figure 2, A monitoring system based on portal vein blood pressure data, applying the above-mentioned monitoring method based on portal vein blood pressure data, includes: a data acquisition module for acquiring postoperative clinical data, where the postoperative clinical data includes portal vein blood pressure-related data, mean abdominal aortic blood pressure, inferior vena cava blood pressure, and related vascular resistance data; a model construction and parameter calibration module for performing quality screening and correction on the postoperative clinical data, and then constructing a lumped parameter model based on the quality-screened and corrected postoperative clinical data, and optimizing and calibrating the parameters involved in the lumped parameter model; a steady-state simulation module for performing steady-state simulation using the optimized and calibrated lumped parameter model, calculating the portal vein blood pressure and other related hemodynamic parameters, and verifying the calculation results; a portal vein blood pressure monitoring module for monitoring the portal vein blood pressure in real time based on the application status of the lumped parameter model determined by the steady-state simulation, and evaluating the patient's condition change and treatment effect based on the monitored change of the portal vein blood pressure; a result output and feedback module for outputting the real-time monitoring results, and at the same time judging whether the monitoring results are abnormal according to the monitoring results and the patient's personalized parameters, and then providing clinical feedback and suggestions; a continuous optimization module for setting a patient's personalized update and adjustment cycle based on the patient's personalized parameters, and updating and optimizing the lumped parameter model based on the patient's personalized update and adjustment cycle.

[0053] In summary, the present application has at least the following effects:

[0054] Real-time monitoring of the portal vein blood pressure can thus timely capture the subtle changes in the patient's condition, providing accurate diagnostic basis for doctors. Combining the mean abdominal aortic blood pressure, inferior vena cava blood pressure, and related vascular resistance data, this method can more comprehensively evaluate the patient's hemodynamic state, improving the comprehensiveness and accuracy of diagnosis; by monitoring and adjusting according to the patient's personalized parameters, individualized treatment can be achieved, thereby improving the treatment effect. The real-time monitoring results can be timely fed back to doctors, enabling doctors to timely adjust the treatment plan to ensure the maximization of the treatment effect; continuous monitoring of the portal vein blood pressure can issue early warnings in a timely manner once abnormal changes are found, reducing medical risks. By optimizing the treatment plan and timely adjusting the monitoring parameters, this method helps to reduce the occurrence of postoperative complications and improve the patient's rehabilitation quality; adopting automated monitoring technology can reduce the workload of medical staff and improve medical efficiency.

[0055] Those skilled in the art should understand that the embodiments of the present invention can be provided as methods, systems. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0056] The present invention is described with reference to the flowcharts and block diagrams of methods and systems according to embodiments of the present invention. It should be understood that each flow and combination of blocks in the flowcharts and block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing devices to generate a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices produce means for implementing the functions specified in one Figure 1 flow or multiple flows and block diagrams Figure 1 or multiple blocks.

[0057] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufacture including instruction means that implement the functions specified in one Figure 1 flow or multiple flows and block diagrams Figure 1 or multiple blocks.

[0058] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one Figure 1 flow or multiple flows and block diagrams Figure 1 or multiple blocks.

[0059] Although the preferred embodiments of the present invention have been described, additional changes and modifications can be made by those skilled in the art once they learn the basic creative concepts. Therefore, the appended claims are intended to be construed to include the preferred embodiments and all changes and modifications falling within the scope of the present invention.

[0060] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these changes and modifications.

Claims

1. A monitoring method based on portal vein blood pressure data, characterized in that, It includes the following steps: S1. Obtain postoperative clinical data, which includes portal vein blood pressure-related data, mean abdominal aortic blood pressure, inferior vena cava blood pressure, and related vascular resistance data; S2. Conduct quality screening and calibration on the postoperative clinical data, and then construct a lumped parameter model based on the quality-screened and calibrated postoperative clinical data, and optimize and calibrate the parameters involved in the lumped parameter model; S3. Use the optimized and calibrated lumped parameter model for steady-state simulation, calculate the portal vein blood pressure and other related hemodynamic parameters, and verify the calculation results; S4. Based on the application status of the lumped parameter model determined by the steady-state simulation, monitor the portal vein blood pressure in real time, and evaluate the patient's condition change and treatment effect based on the monitored change of the portal vein blood pressure; S5. Output the real-time monitoring results, and at the same time, based on the monitoring results and the patient's personalized parameters, judge whether the monitoring results are abnormal, and then provide clinical feedback and suggestions; S6. Set the patient's personalized update and adjustment cycle based on the patient's personalized parameters, and update and optimize the lumped parameter model based on the patient's personalized update and adjustment cycle.

2. The monitoring method based on portal vein blood pressure data according to claim 1, wherein The specific steps of S2 include: constructing a three-dimensional geometric model of the patient's portal vein system based on the postoperative clinical data, and simplifying the patient's vascular system into a circuit model based on the three-dimensional geometric model; Based on the characteristics of the circuit model, combine the postoperative clinical data to determine and calculate the blood pressure parameters at each point in the circuit model, and then identify the hepatic vein system flow rate and the blood flow resistance parameter values in the lumped parameter model. By adjusting the parameters involved in the lumped parameter model, the difference between the output result of the lumped parameter model and the actual postoperative clinical data is minimized.

3. The monitoring method based on portal vein blood pressure data according to claim 1, wherein The specific steps of verifying the calculation results in S3 include: setting steady-state boundary conditions and initial conditions, and then conducting steady-state simulation based on the optimized and calibrated lumped parameter model to output the portal vein blood pressure and other related hemodynamic parameters; Adjust the input of the lumped parameter model, fit the relationship between the output portal vein blood pressure and the mean abdominal aortic blood pressure corresponding to each adjustment to obtain the sensitivity coefficient between the portal vein blood pressure and the mean abdominal aortic blood pressure, and compare the sensitivity coefficient between the portal vein blood pressure and the mean abdominal aortic blood pressure with the preset sensitivity threshold. When the sensitivity coefficient between the portal vein blood pressure and the mean abdominal aortic blood pressure is less than the sensitivity threshold, update and adjust the parameters involved in the lumped parameter model, otherwise apply the lumped parameter model to the actual portal vein blood pressure monitoring.

4. A monitoring method based on portal vein blood pressure data according to claim 1, characterized in that The specific steps of S4 include: obtaining the mean abdominal aortic blood pressure, inferior vena cava blood pressure, and related vascular resistance data in real time based on clinical monitoring; Use the mean abdominal aortic blood pressure, inferior vena cava blood pressure, and related vascular resistance data as the input of the lumped parameter model to output the portal vein blood pressure; Sort the output portal vein blood pressure according to time nodes, and then identify the change trend of the portal vein blood pressure to obtain the trend change parameters of the portal vein blood pressure; Identify the patient's treatment effect based on the correlation between the trend change parameters of the portal vein blood pressure and the treatment effect.

5. The monitoring method based on portal vein blood pressure data according to claim 4, characterized in that, The specific steps of S5 include: obtaining patient personalized parameters, which include but are not limited to the patient's body fat percentage, patient age, patient drug allergy record, patient surgical history, patient's current medications, and patient's underlying disease record; Identifying the association model between the patient personalized parameters and the trend change parameters of portal vein blood pressure based on the portal vein blood pressure monitoring records stored in the medical system, and then verifying the trend change parameters of the portal vein blood pressure according to the association model. When the trend change parameters of the patient's portal vein blood pressure match the personalized parameters in the association model, it is determined that there is no abnormal condition in the monitoring result, and the medical advice for this type of patient is retrieved and transmitted based on the patient personalized parameters; When the trend change parameters of the patient's portal vein blood pressure do not match the personalized parameters in the association model, verifying the monitoring result of the lumped parameter model. When the monitoring result is verified to be qualified, it is marked that there is an abnormal condition in the monitoring result of the patient's portal vein blood pressure data, and a prompt text message is sent to the medical monitoring personnel based on the alarm mechanism; When the monitoring result is verified to be unqualified, obtaining the latest postoperative clinical data, updating and optimizing the patient's lumped parameter model, and monitoring the patient's portal vein blood pressure data based on the updated and optimized lumped parameter model.

6. The monitoring method based on portal vein blood pressure data according to claim 1, wherein The specific method for setting the patient personalized update and adjustment cycle based on the patient personalized parameters is as follows: Constructing a relationship model between the personalized parameters and the personalized update and adjustment cycle, and then inputting the patient personalized parameters into the relationship model between the personalized parameters and the personalized update and adjustment cycle to output the patient personalized update and adjustment cycle.

7. A monitoring system based on portal vein blood pressure data, applying the monitoring method based on portal vein blood pressure data according to any one of claims 1-6, characterized in that, It includes: A data acquisition module for acquiring postoperative clinical data, where the postoperative clinical data includes portal vein blood pressure related data, mean abdominal aortic blood pressure, inferior vena cava blood pressure, and related vascular resistance data; A model construction and parameter calibration module for performing quality screening and correction on the postoperative clinical data, and then constructing a lumped parameter model based on the quality screened and corrected postoperative clinical data, and optimizing and calibrating the parameters involved in the lumped parameter model; A steady-state simulation module for performing steady-state simulation using the optimized and calibrated lumped parameter model, calculating the portal vein blood pressure and other related hemodynamic parameters, and verifying the calculation results; A portal vein blood pressure monitoring module for monitoring the portal vein blood pressure in real time based on the application status of the lumped parameter model determined by the steady-state simulation, and evaluating the patient's condition change and treatment effect based on the monitoring change of the portal vein blood pressure; A result output and feedback module for outputting the real-time monitoring result, and at the same time judging whether there is an abnormality in the monitoring result according to the monitoring result and the patient personalized parameters, and then providing clinical feedback and suggestions; A continuous optimization module for setting the patient personalized update and adjustment cycle based on the patient personalized parameters, and updating and optimizing the lumped parameter model based on the patient personalized update and adjustment cycle.

Images