A method and system for monitoring the care of a patient undergoing surgery for acute pancreatitis

Abstract

This invention discloses a nursing monitoring method and system for patients undergoing surgery for acute pancreatitis. By collecting multi-dimensional physiological parameters at set times within a preset monitoring period after the patient's surgery, and performing weighted fusion, a postoperative recovery index for pancreatitis involving multi-dimensional parameters is constructed. This enables continuous and quantitative assessment of the patient's condition and early risk warning, thereby promoting the patient's rapid and safe recovery.

Description

Technical Field

[0001] This invention relates to the field of medical monitoring technology, and more specifically, to a method and system for monitoring the nursing care of patients undergoing surgery for acute pancreatitis. Background Technology

[0002] Postoperative conditions of patients with acute pancreatitis, especially severe acute pancreatitis (SAP), are complex and variable, with a high risk of complications. Current clinical nursing monitoring largely relies on the timed and discrete observation and recording of individual vital signs (such as heart rate and blood pressure) and laboratory indicators (such as serum amylase and C-reactive protein). This model has significant shortcomings: First, each indicator is judged in isolation, lacking a holistic and systematic assessment of the patient's overall condition; second, the early warning response is delayed, with intervention measures typically only taken after indicators have significantly worsened; and third, adjustments to nursing plans depend on experience, lacking a dynamic optimization mechanism based on individualized data. Summary of the Invention

[0003] In order to solve at least one of the above-mentioned technical problems, the purpose of this invention is to provide a method and system for monitoring the nursing care of patients undergoing surgery for acute pancreatitis, which can realize continuous and quantitative assessment of the patient's condition and early risk warning.

[0004] The first aspect of this invention provides a method for monitoring the nursing care of patients undergoing surgery for acute pancreatitis, comprising: During the patient's pre-set postoperative monitoring period, multi-dimensional physiological parameters were collected at set times and standardized to obtain a time-series data stream. For each monitoring time node, extract the time series data within the preceding time window, calculate the change trend of each parameter within the time window, and dynamically assign real-time weight coefficients to each parameter based on the change trend. Based on the preset fusion function, and according to the data of the monitoring time nodes and the real-time weight coefficients of each parameter, an intermediate fusion sub-item representing the physiological homeostasis and inflammatory metabolic state is obtained. The intermediate fusion sub-item is sent to the preset core algorithm model to obtain the postoperative recovery index of pancreatitis at the current monitoring time point; If the postoperative recovery index of pancreatitis at the current monitoring time point exceeds the preset first threshold, an alert message will be triggered for the corresponding patient.

[0005] In this scheme, the steps of calculating the change trend of each parameter within the time window and dynamically assigning real-time weight coefficients to each parameter based on the change trend specifically include: Extract the same parameter within the time window, and construct a linear equation for the corresponding parameter within the time window based on a preset linear fitting formula; Extract the slope of the linear equation and set it as the trend of change of the parameter within the time window; Based on the preset numerical range into which the absolute value of the changing trend falls, the real-time weighting coefficient of the corresponding parameter is matched.

[0006] In this scheme, the formula for obtaining the intermediate fusion term representing physiological homeostasis and inflammatory metabolic state based on the data from the monitoring time points and the real-time weighting coefficients of each parameter is as follows: ; ;in This represents an intermediate fusion sub-item that indicates the patient's physiological homeostasis at the current monitoring time point. The intermediate fusion sub-item representing the patient's inflammatory metabolic status at the current monitoring time point. , , and The following values ​​represent the real-time weighting coefficients for the corresponding parameters: HR(t) represents the patient's heart rate at the current monitoring time t; MAP(t) represents the patient's mean arterial pressure at the current monitoring time t; IAP(t) represents the patient's intra-abdominal pressure at the current monitoring time t; CRP(t) represents the patient's C-reactive protein level at the current monitoring time t; PCT(t) represents the patient's procalcitonin level at the current monitoring time t; and AMY(t) represents the patient's serum amylase level at the current monitoring time t. This indicates the preset normal heart rate. This indicates the preset target mean arterial pressure. This indicates the preset upper limit of normal serum amylase levels.

[0007] In this solution, the formula for sending the intermediate fusion sub-item to the preset core algorithm model to obtain the postoperative recovery index of pancreatitis at the current monitoring time point is as follows: Where PRI(t) represents the patient's recovery index at monitoring time point t. and For the individualized calibration baseline value corresponding to the intermediate fusion sub-item, Postoperative time factor, and Here, represents the corresponding weighting coefficient, and y represents the smoothing constant. Indicates the time decay coefficient. These represent the structural damage coefficient and the baseline value of the structural damage coefficient, respectively.

[0008] In this solution, the steps for obtaining the structural damage coefficient specifically include: Based on the monitoring time points, abdominal CT images of patients were acquired within a set time period; Features and feature values ​​are extracted from abdominal CT images, and the feature values ​​are quantified and scored to obtain the feature score. The features include at least the peripancreatic effusion range, the proportion of pancreatic necrosis area, and the effusion density value. The structural damage score is obtained by weighted summation of the scores of each feature. The structural damage score was compared and normalized with the structural damage score of the patient's preoperative abdominal CT image to obtain the structural damage coefficient.

[0009] In this solution, the steps for obtaining the baseline value of the structural damage coefficient specifically include: Obtain the patient's characteristics and corresponding characteristic values; The pre-set case database is filtered based on the patient's characteristics and corresponding feature values ​​to obtain a similar case dataset; Extract the historical structural damage coefficient of the corresponding patient from any similar case data in the similar case dataset; After traversing the entire similar case dataset, a set of historical structural damage coefficients is obtained, and the values ​​in the set of historical structural damage coefficients are arranged in descending order. Extract the first n values ​​from the historical structural damage coefficients and take the average value to obtain the baseline value of the structural damage coefficient.

[0010] This plan also includes: Obtain the patient's age and glomerular filtration rate; If a patient's age is greater than a preset first age threshold and their glomerular filtration rate is less than a preset first filtration rate threshold, the system will automatically mark the patient as a special monitoring patient and activate the special monitoring mode.

[0011] This solution also includes the following when the special monitoring mode is activated: The original measurements of serum amylase and C-reactive protein were corrected for renal function dependence based on a preset first correction formula, wherein the preset first correction formula is: ,in This represents the raw measurement value of serum amylase or C-reactive protein. This represents the corresponding correction value, and k represents the correction coefficient. This indicates the normal reference value for glomerular filtration rate, while eGFR represents the patient's glomerular filtration rate.

[0012] This solution also includes the following when the special monitoring mode is activated: Subtract the preset first age threshold from the patient's age to obtain the age difference; Set the age correction factor to Its formula is Where Age represents the patient's age. This indicates the preset first age threshold; The revised individualized calibration baseline value is obtained by multiplying the individualized calibration baseline value by the corresponding age correction factor.

[0013] A second aspect of the present invention provides a nursing monitoring system for patients undergoing surgery for acute pancreatitis, comprising a memory and a processor, wherein the memory stores a nursing monitoring method for patients undergoing surgery for acute pancreatitis as described in any one of the above descriptions.

[0014] One or more technical solutions proposed in this application have at least the following technical effects: 1. Existing technologies typically monitor various vital signs and laboratory indicators in isolation. However, this invention, through dynamic weight fusion and a core algorithm model, systematically integrates multi-dimensional physiological parameters, such as vital signs, inflammatory markers, and perfusion parameters, into a continuous and quantitative "Postoperative Recovery Index (PRI) for Pancreatitis," providing clinicians with a single, intuitive, and comprehensive indicator for assessing patient status, greatly enhancing the systematicness and scientific rigor of the assessment. 2. Existing monitoring methods often neglect the quantitative tracking of imaging changes. This invention quantifies the imaging manifestations of abdominal CT, such as peripancreatic effusion and necrosis, into structural damage coefficients and organically integrates them into PRI calculation, so that the assessment simultaneously covers the recovery of physiological function and anatomical structure, making the assessment dimensions more complete. 3. This invention has designed a unique correction formula and a relaxed baseline establishment rule, which effectively eliminates the interference of renal function decline on the interpretation of indicators, adapts to the physiological characteristics of elderly patients, and significantly improves the accuracy and safety of monitoring in this high-risk subgroup. In summary, this invention, through continuous and quantitative assessment of patient status and early risk warning, can help clinical teams adjust treatment plans and nursing priorities more promptly, thereby potentially reducing the incidence and severity of postoperative complications (such as infection and organ failure), shortening hospital stays, and ultimately ensuring faster and more stable recovery for patients. Attached Figure Description

[0015] Figure 1 A flowchart of a nursing monitoring method for patients undergoing surgery for acute pancreatitis according to the present invention is shown; Figure 2 A block diagram of a patient care monitoring system for acute pancreatitis surgery is shown. Detailed Implementation

[0016] To better understand the above-mentioned objectives, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0017] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and therefore the scope of protection of the invention is not limited to the specific embodiments disclosed below.

[0018] Figure 1 A flowchart of a method for monitoring the nursing care of surgical patients with acute pancreatitis according to the present invention is shown.

[0019] like Figure 1 As shown, this invention discloses a method for monitoring the nursing care of patients undergoing surgery for acute pancreatitis, comprising: S101: During the patient's postoperative pre-set monitoring period, multi-dimensional physiological parameters are collected at set times and standardized to obtain a time-series data stream. S102, For each monitoring time node, extract the time series data within the preceding time window, calculate the change trend of each parameter within the time window, and dynamically assign real-time weight coefficients to each parameter based on the change trend. S103, Based on the preset fusion function, according to the data of the monitoring time nodes and the real-time weight coefficients of each parameter, an intermediate fusion sub-item representing the physiological homeostasis and inflammatory metabolic state is obtained; S104, The intermediate fusion sub-item is sent to the preset core algorithm model to obtain the postoperative recovery index of pancreatitis at the current monitoring time point; S105, If the postoperative recovery index of pancreatitis at the current monitoring time point exceeds the preset first threshold, an alert message for the corresponding patient will be triggered.

[0020] According to an embodiment of the present invention, the multidimensional physiological parameters include at least a set of vital signs parameters, a set of biochemical and inflammatory parameters, and a set of local perfusion and metabolic parameters. The vital signs parameters include at least heart rate and mean arterial pressure. The set of biochemical and inflammatory parameters includes at least serum amylase, C-reactive protein, and procalcitonin. The set of local perfusion and metabolic parameters includes at least intra-abdominal pressure. For example, if the time window is 3, then the parameters corresponding to the previous 3 monitoring time nodes are extracted as the benchmark, and the time series data within the preceding time window are extracted. The data of the monitoring time nodes and the real-time weight coefficients of each parameter are input into the corresponding preset fusion function to calculate the corresponding intermediate fusion sub-items. The preset core algorithm model includes a calculation formula for calculating the postoperative recovery index of pancreatitis at the current monitoring time node. The lower the postoperative recovery index of pancreatitis, the better the patient's overall recovery status and the lower the risk. An increase in the value indicates a deterioration in the condition or an increased risk of complications.

[0021] According to an embodiment of the present invention, the step of calculating the change trend of each parameter within the time window and dynamically assigning real-time weight coefficients to each parameter based on the change trend specifically includes: Extract the same parameter within the time window, and construct a linear equation for the corresponding parameter within the time window based on a preset linear fitting formula; Extract the slope of the linear equation and set it as the trend of change of the parameter within the time window; Based on the preset numerical range into which the absolute value of the changing trend falls, the real-time weighting coefficient of the corresponding parameter is matched.

[0022] It should be noted that the absolute value of the trend change is divided into multiple preset value ranges in advance, and each preset value range corresponds to a real-time weight coefficient. The larger the value in the preset value range, the larger the corresponding real-time weight coefficient. For example, if the postoperative patient's heart rate fluctuates steadily from 85 beats / min to 88 beats / min, the absolute value of its slope is small, falling into a higher preset value range, and the corresponding weight is low. If the postoperative patient's heart rate continuously rises from 85 beats / min to 100 beats / min, the absolute value of its slope is large, falling into a higher preset value range, and the corresponding weight is large.

[0023] According to an embodiment of the present invention, the formula for obtaining the intermediate fusion term characterizing physiological homeostasis and inflammatory metabolic state based on the data from the monitoring time points and the real-time weighting coefficients of each parameter is specifically as follows: ; ;in This represents an intermediate fusion sub-item that indicates the patient's physiological homeostasis at the current monitoring time point. The intermediate fusion sub-item representing the patient's inflammatory metabolic status at the current monitoring time point. , , and The following values ​​represent the real-time weighting coefficients for the corresponding parameters: HR(t) represents the patient's heart rate at the current monitoring time t; MAP(t) represents the patient's mean arterial pressure at the current monitoring time t; IAP(t) represents the patient's intra-abdominal pressure at the current monitoring time t; CRP(t) represents the patient's C-reactive protein level at the current monitoring time t; PCT(t) represents the patient's procalcitonin level at the current monitoring time t; and AMY(t) represents the patient's serum amylase level at the current monitoring time t. This indicates the preset normal heart rate. This indicates the preset target mean arterial pressure. This indicates the preset upper limit of normal serum amylase levels.

[0024] According to an embodiment of the present invention, the intermediate fusion sub-item representing physiological homeostasis is obtained by weighted fusion of vital sign parameter set and local perfusion and metabolic parameter set, and the intermediate fusion sub-item representing inflammatory metabolic state is obtained by weighted fusion of parameters in biochemical and inflammatory parameter set.

[0025] Furthermore, after calculating the intermediate fusion sub-items representing physiological homeostasis / inflammatory metabolic status at different monitoring time points, the intermediate fusion sub-items are compared and analyzed to obtain the standard deviation of the corresponding intermediate fusion sub-items. If the standard deviation is less than the preset standard deviation threshold, the parameter corresponding to the intermediate fusion sub-item is set to enter the stable period. The mean of the intermediate fusion sub-items in the stable period is calculated to obtain the individualized baseline of the corresponding intermediate fusion sub-item.

[0026] Furthermore, if the patient has not entered a stable period, the preset case database is filtered according to the patient's characteristics and corresponding feature values ​​to obtain a similar case dataset. Then, the mean of the individualized baselines of the corresponding intermediate fusion sub-items in the similar cases is calculated to obtain the individualized baseline of the corresponding intermediate fusion sub-items of the current patient, until the parameters corresponding to the current patient enter a stable period.

[0027] It should be noted that the formula for sending the intermediate fusion sub-item to the preset core algorithm model to obtain the postoperative recovery index of pancreatitis at the current monitoring time point is as follows: Where PRI(t) represents the patient's recovery index at monitoring time point t. and For the individualized calibration baseline value corresponding to the intermediate fusion sub-item, Postoperative time factor, and Here, represents the corresponding weighting coefficient, and y represents the smoothing constant. Indicates the time decay coefficient. These represent the structural damage coefficient and the baseline value of the structural damage coefficient, respectively.

[0028] It should be noted that the above and satisfy The specific values ​​are set based on clinical experience, for example... , The The number of days post-surgery, and the smoothing constant is not zero, for example, y=1.

[0029] Furthermore, during nursing monitoring, if an intermediate fusion item representing the inflammatory metabolic state is outside the corresponding preset standard value range, it is considered an abnormal inflammatory marker; if an intermediate fusion item representing physiological homeostasis is outside the corresponding preset standard value range, it is considered a deterioration of vital signs; when an abnormal inflammatory marker occurs before a deterioration of vital signs, the weighting coefficient corresponding to the intermediate fusion item representing the inflammatory metabolic state is increased by a preset proportion, for example, by increasing the weighting coefficient of the intermediate fusion item representing the inflammatory metabolic state. Adjust from 0.4 to 0.55, Adjusted from 0.6 to 0.45.

[0030] According to an embodiment of the present invention, the step of obtaining the structural damage coefficient specifically includes: Based on the monitoring time points, abdominal CT images of patients were acquired within a set time period; Features and feature values ​​are extracted from abdominal CT images, and the feature values ​​are quantified and scored to obtain the feature score. The features include at least the peripancreatic effusion range, the proportion of pancreatic necrosis area, and the effusion density value. The structural damage score is obtained by weighted summation of the scores of each feature. The structural damage score was compared and normalized with the structural damage score of the patient's preoperative abdominal CT image to obtain the structural damage coefficient.

[0031] It should be noted that the set time includes a period of time, and the corresponding period of time includes the corresponding monitoring time node. For example, if the set time is 4 hours with the base point as the middle time, then the patient can have abdominal CT images taken 2 hours before and after the monitoring time node. The peripancreatic effusion range is scored according to the number of quadrants involved, and the more quadrants involved, the higher the score. The greater the proportion of pancreatic necrosis area, the higher the corresponding score. For example, if the proportion of pancreatic necrosis area is less than 30%, the corresponding score is 1; if the proportion of pancreatic necrosis area is between 30% and 50%, the score is 2; if the proportion of pancreatic necrosis area is greater than 50%, the score is 3. The higher the effusion density value, the higher the corresponding score. For example, if the effusion density value is less than 20 (unit: HU), the corresponding score is 1; if the effusion density value is greater than or equal to 20 and less than 40, the corresponding score is 2; if the effusion density value is greater than or equal to 40 and less than 60, the corresponding score is 3, and so on.

[0032] According to an embodiment of the present invention, the step of obtaining the reference value of the structural damage coefficient specifically includes: Obtain the patient's characteristics and corresponding characteristic values; The pre-set case database is filtered based on the patient's characteristics and corresponding feature values ​​to obtain a similar case dataset; Extract the historical structural damage coefficient of the corresponding patient from any similar case data in the similar case dataset; After traversing the entire similar case dataset, a set of historical structural damage coefficients is obtained, and the values ​​in the set of historical structural damage coefficients are arranged in descending order. Extract the first n values ​​from the historical structural damage coefficients and take the average value to obtain the baseline value of the structural damage coefficient.

[0033] It should be noted that the patient's characteristics include age, gender, disease parameters, etc. For example, the patient's age is compared with the ages of patients in a preset case database to determine the age feature similarity value, and the patient's disease parameters are compared with the disease parameters of patients in the preset case database to determine the disease parameter feature similarity value. When the feature similarity value is lower than the preset similarity threshold, the corresponding case is screened out from the preset case database. After traversing all feature similarity values, a similar case dataset is obtained.

[0034] According to an embodiment of the present invention, it further includes: Obtain the patient's age and glomerular filtration rate; If a patient's age is greater than a preset first age threshold and their glomerular filtration rate is less than a preset first filtration rate threshold, the system will automatically mark the patient as a special monitoring patient and activate the special monitoring mode.

[0035] It should be noted that advanced age and renal insufficiency are two overlapping high-risk factors. Elderly patients have poor physiological reserves and are more sensitive to volume fluctuations and infections; renal insufficiency leads to impaired clearance of many drugs and inflammatory metabolites, complicating the interpretation of routine laboratory indicators (such as AMY and CRP). For example, the preset first age threshold is set at 70, and the preset first filtration rate threshold is 60 ml / min / 1.73 ml / min. 2 .

[0036] According to an embodiment of the present invention, when a special monitoring mode is activated, it further includes: The original measurements of serum amylase and C-reactive protein were corrected for renal function dependence based on a preset first correction formula, wherein the preset first correction formula is: ,in This represents the raw measurement value of serum amylase or C-reactive protein. This represents the corresponding correction value, and k represents the correction coefficient. This indicates the normal reference value for glomerular filtration rate, while eGFR represents the patient's glomerular filtration rate.

[0037] It should be noted that when the special monitoring mode is activated, the intermediate fusion term for the inflammatory metabolic state is calculated based on the corrected serum amylase and C-reactive protein (CRP) values. The correction coefficients for serum amylase and CRP differ in their respective formulas. Serum amylase (AMY) has a small molecular weight and is primarily excreted through the kidneys; renal function significantly affects it, hence its k-value is higher, ranging from 0.5 to 0.7. CRP is mainly driven by inflammation; although it is also metabolized by the kidneys, its dependence is lower, hence its k-value is smaller, ranging from 0.2 to 0.3. For example, if the normal reference value for glomerular filtration rate is set to 90 ml / min / 1.73 ml... 2 .

[0038] According to an embodiment of the present invention, when a special monitoring mode is activated, it further includes: Subtract the preset first age threshold from the patient's age to obtain the age difference; Set the age correction factor to Its formula is Where Age represents the patient's age. This indicates the preset first age threshold; The revised individualized calibration baseline value is obtained by multiplying the individualized calibration baseline value by the corresponding age correction factor.

[0039] It should be noted that elderly patients may have a slower baseline heart rate, and poorer vascular elasticity leads to a narrower blood pressure regulation range. It is unscientific to apply the standard range for healthy adults (e.g., heart rate 60-100 beats / min) to them. Therefore, an age correction factor is introduced to adjust the individualized calibration baseline value of the intermediate fusion component representing physiological homeostasis and inflammatory metabolic status. For example... This would relax the corresponding individualized calibration baseline value by 10%; for example, for a 78-year-old patient with an eGFR of 50, where 78 is greater than 70 and 50 is less than 90, a special monitoring mode would be activated for this patient, with the corresponding age correction factor... .

[0040] Figure 2 A block diagram of a patient care monitoring system for acute pancreatitis surgery is shown.

[0041] like Figure 2 As shown, a second aspect of the present invention provides a nursing monitoring system 2 for patients undergoing surgery for acute pancreatitis, comprising a memory 21 and a processor 22, wherein the memory stores a nursing monitoring method for patients undergoing surgery for acute pancreatitis as described in any one of the above descriptions.

[0042] This invention discloses a nursing monitoring method and system for patients undergoing surgery for acute pancreatitis. By collecting multi-dimensional physiological parameters at set times within a preset monitoring period after the patient's surgery, and performing weighted fusion, a postoperative recovery index for pancreatitis involving multi-dimensional parameters is constructed. This enables continuous and quantitative assessment of the patient's condition and early risk warning, thereby promoting the patient's rapid and safe recovery.

[0043] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0044] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0045] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0046] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0047] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

Claims

1. A method for nursing monitoring of patients undergoing surgery for acute pancreatitis, characterized in that, include: During the patient's pre-set postoperative monitoring period, multi-dimensional physiological parameters were collected at set times and standardized to obtain a time-series data stream. For each monitoring time node, extract the time series data within the preceding time window, calculate the change trend of each parameter within the time window, and dynamically assign real-time weight coefficients to each parameter based on the change trend. Based on the preset fusion function, and according to the data of the monitoring time nodes and the real-time weight coefficients of each parameter, an intermediate fusion sub-item representing the physiological homeostasis and inflammatory metabolic state is obtained. The intermediate fusion sub-item is sent to the preset core algorithm model to obtain the postoperative recovery index of pancreatitis at the current monitoring time point; If the postoperative recovery index of pancreatitis at the current monitoring time point exceeds the preset first threshold, an alert message will be triggered for the corresponding patient.

2. The method for nursing monitoring of patients undergoing surgery for acute pancreatitis according to claim 1, characterized in that, The step of calculating the change trend of each parameter within the time window and dynamically assigning real-time weight coefficients to each parameter based on the change trend specifically includes: Extract the same parameter within the time window, and construct a linear equation for the corresponding parameter within the time window based on a preset linear fitting formula; Extract the slope of the linear equation and set it as the trend of change of the parameter within the time window; Based on the preset numerical range into which the absolute value of the changing trend falls, the real-time weighting coefficient of the corresponding parameter is matched.

3. The method for nursing monitoring of patients undergoing surgery for acute pancreatitis according to claim 1, characterized in that, The formula for obtaining the intermediate fusion term characterizing physiological homeostasis and inflammatory metabolic state based on the data from the monitoring time points and the real-time weighting coefficients of each parameter is as follows: ; ;in This represents an intermediate fusion sub-item that indicates the patient's physiological homeostasis at the current monitoring time point. The intermediate fusion sub-item representing the patient's inflammatory metabolic status at the current monitoring time point. , , and The following values ​​represent the real-time weighting coefficients for the corresponding parameters: HR(t) represents the patient's heart rate at the current monitoring time t; MAP(t) represents the patient's mean arterial pressure at the current monitoring time t; IAP(t) represents the patient's intra-abdominal pressure at the current monitoring time t; CRP(t) represents the patient's C-reactive protein level at the current monitoring time t; PCT(t) represents the patient's procalcitonin level at the current monitoring time t; and AMY(t) represents the patient's serum amylase level at the current monitoring time t. This indicates the preset normal heart rate. This indicates the preset target mean arterial pressure. This indicates the preset upper limit of normal serum amylase levels.

4. The method for nursing monitoring of patients undergoing surgery for acute pancreatitis according to claim 1, characterized in that, The formula for sending the intermediate fusion sub-item to the preset core algorithm model to obtain the postoperative recovery index of pancreatitis at the current monitoring time point is as follows: Where PRI(t) represents the patient's recovery index at monitoring time point t. and For the individualized calibration baseline value corresponding to the intermediate fusion sub-item, Postoperative time factor, and Here, represents the corresponding weighting coefficient, and y represents the smoothing constant. Indicates the time decay coefficient. These represent the structural damage coefficient and the baseline value of the structural damage coefficient, respectively.

5. A method for monitoring and caring for patients undergoing surgery for acute pancreatitis according to claim 4, characterized in that, The steps for obtaining the structural damage coefficient specifically include: Based on the monitoring time points, abdominal CT images of patients were acquired within a set time period; Features and feature values ​​are extracted from abdominal CT images, and the feature values ​​are quantified and scored to obtain the feature score. The features include at least the peripancreatic effusion range, the proportion of pancreatic necrosis area, and the effusion density value. The structural damage score is obtained by weighted summation of the scores of each feature. The structural damage score was compared and normalized with the structural damage score of the patient's preoperative abdominal CT image to obtain the structural damage coefficient.

6. The method of claim 4, wherein the method is used for monitoring the patient care of a patient undergoing surgery for acute pancreatitis. The steps for obtaining the baseline value of the structural damage coefficient specifically include: Obtain the patient's characteristics and corresponding characteristic values; The pre-set case database is filtered based on the patient's characteristics and corresponding feature values ​​to obtain a similar case dataset; Extract the historical structural damage coefficient of the corresponding patient from any similar case data in the similar case dataset; After traversing the entire dataset of similar cases, a set of historical structural damage coefficients is obtained, and the values ​​in the set of historical structural damage coefficients are arranged in descending order. Extract the first n values ​​from the historical structural damage coefficients and take the average value to obtain the baseline value of the structural damage coefficient.

7. The method for nursing monitoring of patients undergoing surgery for acute pancreatitis according to claim 1, characterized in that, Also includes: Obtain the patient's age and glomerular filtration rate; If a patient's age is greater than a preset first age threshold and their glomerular filtration rate is less than a preset first filtration rate threshold, the system will automatically mark the patient as a special monitoring patient and activate the special monitoring mode.

8. A method for monitoring and caring for patients undergoing surgery for acute pancreatitis according to claim 7, characterized in that, When the special monitoring mode is activated, it also includes: The original measurements of serum amylase and C-reactive protein were corrected for renal function dependence based on a preset first correction formula, wherein the preset first correction formula is: ,in This represents the raw measurement value of serum amylase or C-reactive protein. This represents the corresponding correction value, and k represents the correction coefficient. This indicates the normal reference value for glomerular filtration rate, while eGFR represents the patient's glomerular filtration rate.

9. A method for monitoring and nursing care of patients undergoing surgery for acute pancreatitis according to claim 7, characterized in that, When the special monitoring mode is activated, it also includes: Subtract the preset first age threshold from the patient's age to obtain the age difference; Set the age correction factor to Its formula is Where Age represents the patient's age. This indicates the preset first age threshold; The revised individualized calibration baseline value is obtained by multiplying the individualized calibration baseline value by the corresponding age correction factor.

10. An acute pancreatitis surgical patient care monitoring system, characterized by, It includes a memory and a processor, wherein the memory stores a method for monitoring the care of a surgical patient with acute pancreatitis as described in any one of claims 1 to 9.

Images