A method for real-time monitoring and early warning of complications in pediatric peritoneal dialysis

Abstract

This invention relates to the field of dialysis complication monitoring technology, specifically to a method for real-time monitoring and early warning of peritoneal dialysis complications in children. Based on the fluctuation of analytical data for each type of patient and the degree of difference between each monitoring and previous monitoring data, the method adjusts the degree of change in the turbidity value of the dialysis solution for each dialysis session, obtaining the turbidity variability of each analytical data point for each type of patient in each monitoring session. Based on the differences in turbidity variability of the same biochemical indicators between the patient and a control patient at different sampling times, and the differences in turbidity variability of the flow rate sequence at different dialysis sessions, the method obtains biochemical variability and flow rate variability, and adjusts these using the differences in renal function between the patient and the control patient. Based on a determined risk level, the method monitors and provides early warning for complications in the current dialysis session. This invention considers both individual differences and behavioral specificities, effectively reducing misdiagnosis of peritoneal dialysis complications.

Description

Technical Field

[0001] This invention relates to the field of dialysis complication monitoring technology, specifically to a method for real-time monitoring and early warning of peritoneal dialysis complications in children. Background Technology

[0002] The principle of peritoneal dialysis is to use the peritoneum as a semi-permeable membrane. Prepared dialysate is regularly and periodically infused into the patient's peritoneal cavity through a catheter. Due to the concentration gradient of solutes across the peritoneum, solutes from the high-concentration side move to the low-concentration side, while water moves from the hypotonic side to the hypertonic side. By continuously replacing the peritoneal dialysate, metabolic waste products and toxins are removed from the body, and water and electrolyte imbalances are corrected. However, peritoneal dialysis is often accompanied by complications such as peritonitis. If these complications are not detected and treated promptly, they can severely damage peritoneal function, leading to treatment failure and even endangering the child's life. Therefore, real-time monitoring and early warning of complications during pediatric peritoneal dialysis are crucial.

[0003] Current technologies rely on data collected during dialysis, such as dialysate flow rate, pressure, turbidity, and glucose concentration, to monitor for complications, typically using fixed thresholds or simple trend analysis. However, pediatric patients exhibit both individual and behavioral differences. Specifically, children have significant physiological variations; their age, weight, and residual renal function directly influence abnormal parameter changes during dialysis. Furthermore, children are more prone to physical activity during dialysis, such as turning over or crying, which can lead to catheter compression or positional changes, causing abnormal fluctuations in dialysate flow rate and pressure. These abnormal changes are easily misdiagnosed as complications, resulting in significant errors in early warning systems. Summary of the Invention

[0004] To address the technical problem of misdiagnosis of peritoneal dialysis complications due to differences in objective factors among children, the present invention aims to provide a method for real-time monitoring and early warning of peritoneal dialysis complications in children. The specific technical solution adopted is as follows: This invention proposes a method for real-time monitoring and early warning of complications in pediatric peritoneal dialysis, the method comprising: Obtain the turbidity and flow rate sequences of the solution from the current and previous dialysis sessions for the child under test, as well as the concentration values ​​of each biochemical indicator from different sampling sessions; record the flow rate sequences and the concentration values ​​of the biochemical indicators as the analytical data, with dialysis and sampling being different monitoring types; Based on the degree of fluctuation of the analytical data of each type of patient and the degree of difference between each monitoring and the previous monitoring, the degree of change of the turbidity value of the dialysis solution is adjusted to obtain the degree of turbidity change of each analytical data of each type of patient in each monitoring. Obtain a reference patient for the child to be tested; based on the difference in turbidity variability of the same biochemical index between the child to be tested and the reference patient at different sampling times, and the difference in turbidity variability of the flow rate sequence at different dialysis times, obtain the biochemical difference and flow rate difference in sequence. Based on the degree of difference in renal function between the child to be tested and the reference child, the biochemical difference and the flow rate difference are adjusted to obtain the complication risk of the child to be tested in the current dialysis session, and to monitor and provide early warning of complications in the current dialysis session.

[0005] Furthermore, the acquisition of the turbidity variability of each analytical data point for each type of monitoring in the child under test includes: The differences between the child under test and all previous monitoring data of the same type in each monitoring session are obtained, and the mean of all differences is calculated; the differences between all pairwise monitoring data of the same type in all monitoring sessions before each monitoring session in each type are obtained, and the variance of all differences is calculated; the mean is adjusted using the variance to obtain the data difference of each type of analysis data for each monitoring session in each type for the child under test. The initial turbidity variability for each dialysis session is obtained by comparing the trend of turbidity changes in the solution during each dialysis session with the trend of turbidity changes in the solution during previous dialysis sessions. If the analyzed data is a flow rate sequence, the product of the fluctuation degree and the data difference is negatively correlated and normalized, and the normalized result of the product of the processing result and the initial turbidity abrupt change is taken as the turbidity abrupt change; if the analyzed data is the concentration value of a biochemical indicator, the data difference is normalized, and the normalized result of the product of the processing result and the initial turbidity abrupt change is taken as the turbidity abrupt change.

[0006] Furthermore, obtaining the initial turbidity variation for each dialysis session includes: The ratio of the difference between the turbidity value of the solution in each dialysis session and the previous dialysis session to the time interval is recorded as the current turbidity trend value. A linear fit is performed on the turbidity values ​​of all dialysis solutions of the child before each dialysis session, and the absolute value of the slope of the fitted line is recorded as the historical turbidity trend value. The ratio of the current turbidity trend value to the historical turbidity trend value is used as the initial turbidity change rate for each dialysis session.

[0007] Furthermore, the acquisition of biochemical differences and flow rate differences includes: Calculate the mean turbidity variability of each child under all monitoring conditions for each type of analysis, and record it as the overall variability; sum the absolute values ​​of the differences between the overall variability of the child under test and all reference children under the same type of monitoring for each analysis, and record it as the overall variability difference of each analysis. Choose any type of analytical data and record it as the example data; for the same type of monitoring, select the effective monitoring data related to the example data of the child to be tested from all the monitoring data of the reference child; if the example data is the concentration value of a biochemical indicator, then the mean of the example data of the child to be tested under all monitoring is equal to the example data of the reference child under the corresponding effective monitoring; if the example data is a flow rate sequence, then there is an element in any flow rate sequence of the child to be tested that is equal to the element in the flow rate sequence of the reference child under the corresponding effective monitoring in all the monitoring data. Calculate the variance of turbidity variation in all valid monitoring data related to the sample data of the test child for all reference children, and denote it as the validity of each analysis data; use the validity to adjust the overall variation difference to obtain the effective variation difference of each analysis data; If the example data is the concentration values ​​of biochemical indicators, the sum of the effective mutation differences of all biochemical indicators is recorded as the biochemical difference degree; if the analysis data is a flow rate sequence, the effective mutation difference of the flow rate sequence is recorded as the flow rate difference degree.

[0008] Furthermore, obtaining the risk of complications for the child undergoing dialysis in the current session includes: The degree of difference in renal function is obtained by comparing the concentration values ​​of the same biochemical indicators between the tested children and the control children. The product of the time interval between the current dialysis session and the previous dialysis session and the degree of difference in renal function is normalized to obtain a risk adjustment coefficient. The product of the flow rate difference and the biochemical difference is weighted using the risk adjustment coefficient, and the weighted result is normalized to obtain the complication risk of the child under test in the current dialysis session.

[0009] Furthermore, the method of obtaining the degree of difference in renal function based on the concentration differences of the same biochemical indicators between the tested child and the reference child includes: The average concentration of the same biochemical indicator from all samples taken by each child is recorded as the overall concentration of the corresponding biochemical indicator. The sum of the absolute values ​​of the differences in the overall concentration of each biochemical indicator between the tested child and all reference children is calculated as the reference concentration difference for each biochemical indicator of the tested child. The absolute value of the difference between the overall concentration of each biochemical data of the child under test and the preset standard concentration value is recorded as the standard concentration difference of the corresponding biochemical indicator. Based on the difference between the reference concentration and the standard concentration, the comprehensive concentration difference of each biochemical indicator of the child to be tested is obtained; the sum of the comprehensive concentration differences of all biochemical indicators of the child to be tested is taken as the degree of difference in renal function.

[0010] Furthermore, the acquisition of reference children for the child to be tested includes: The basic information of the child to be tested and the historical children who have undergone peritoneal dialysis is obtained, including age, height and weight; the body surface area is calculated based on the weight and height of each child; the child to be tested and historical children of the same age are clustered based on the body surface area to obtain different clusters; other historical children in the cluster to be tested are used as reference children.

[0011] Furthermore, methods for obtaining the differences in the same type of analytical data and the degree of fluctuation in the analytical data monitored each time include: If the analytical data is a flow rate sequence, the fluctuation of the analytical data monitored each time is the arithmetic mean difference of the flow rates in the flow rate sequence of each dialysis, and the difference between the same analytical data monitored twice is the DTW value of the flow rate sequence of the two dialysis sessions; if the analytical data is the concentration value of biochemical indicators, the difference between the same analytical data monitored twice is the absolute value of the difference in the concentration value of each biochemical indicator monitored twice.

[0012] Furthermore, the effectiveness is negatively correlated with the effective mutation difference.

[0013] Furthermore, the method for clustering the child to be tested with historical children of the same age is the K-means algorithm.

[0014] The present invention has the following beneficial effects: In this embodiment of the invention, the degree of fluctuation in the analytical data monitored each time reflects the severity of the data fluctuation, and the degree of difference between each monitoring and the previous monitoring reflects the duration of the data fluctuation. Simultaneously, the flow rate of the solution in the dialysis catheter is affected by both changes in body position and complications. Complications can disrupt the stable state of biochemical indicators. By comprehensively considering these two factors and adjusting the degree of change in the turbidity value of the solution during each dialysis session, the turbidity of the dialysate during each dialysis session can be accurately analyzed to determine whether it is caused by changes in body position or complications, thus obtaining the turbidity mutation rate. The child under testing may have pre-existing conditions that cause variations in the analytical data during dialysis. This approach considers the differences between the data of the tested child and the analytical data of a reference child with a similar physical condition, determining whether these differences are normal physiological changes or abnormal changes caused by complications. Flow rate and biochemical differences are assessed, respectively, based on the flow rate of the solution in the catheter and renal function-related biochemical indicators. By analyzing the differences in dialysis data between the tested and reference children, the likelihood of complications arising from physiological changes is determined. Simultaneously, the concentration levels of biochemical indicators affected by residual renal function are used to adjust the biochemical and flow rate differences, thus determining the probability of complications occurring in the current dialysis session. This protocol fully considers both individual heterogeneity and behavioral specificities, greatly improving the specificity of complication warnings, effectively reducing misdiagnosis of peritoneal dialysis complications, and significantly improving the safety and quality of pediatric peritoneal dialysis. Attached Figure Description

[0015] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a flowchart illustrating the steps of a method for real-time monitoring and early warning of complications in pediatric peritoneal dialysis, provided in one embodiment of the present invention. Figure 2 This is a flowchart illustrating a method for obtaining turbidity abrupt change in degree according to an embodiment of the present invention. Figure 3 A flowchart illustrating a method for obtaining concurrency risk level according to an embodiment of the present invention; Figure 4 This is a system structure diagram of a real-time monitoring and early warning system for complications of peritoneal dialysis in children, provided in one embodiment of the present invention; Figure 5 This is a schematic diagram of a computer device for real-time monitoring and early warning of complications in pediatric peritoneal dialysis, provided as an embodiment of the present invention. Detailed Implementation

[0017] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a method for real-time monitoring and early warning of peritoneal dialysis complications in children according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0019] The specific scenario addressed by this invention is: peritoneal dialysis performed on children at home. By analyzing the changes in dialysis parameters after each dialysis session of the intelligent dialysis machine and the fluctuations in the current pediatric patient's own condition, it is determined whether there are any abnormalities in the current dialysis, and then a graded early warning is issued based on the abnormal behavior.

[0020] The following description, in conjunction with the accompanying drawings, details the specific scheme of a method for real-time monitoring and early warning of complications in pediatric peritoneal dialysis provided by the present invention.

[0021] Example 1: This invention proposes a method for real-time monitoring and early warning of complications in pediatric peritoneal dialysis. Please refer to [link / reference]. Figure 1 The diagram illustrates a flowchart of a method for real-time monitoring and early warning of peritoneal dialysis complications in children, according to an embodiment of the present invention. The method includes: Step S1: Obtain the turbidity value and flow rate sequence of the solution for the child to be tested during the current dialysis and previous dialysis, as well as the concentration value of each biochemical indicator in different samplings; record the flow rate sequence and the concentration value of the biochemical indicator as the analysis data, with dialysis and sampling being different monitoring types.

[0022] Basic information of the children to be tested was collected, including age, weight, and height. During each peritoneal dialysis treatment, the flow rate in the dialysis catheter was continuously collected at a sampling frequency of 1 Hz using a flow sensor built into the home portable peritoneal dialysis device. The flow rates at all times were arranged chronologically to obtain a flow rate sequence. After each dialysis treatment, the turbidity of the discharged dialysate was measured using a turbidity sensor, reflecting the degree of turbidity of the dialysate, and recorded as the solution turbidity value. Each dialysis session corresponds to an independent turbidity value.

[0023] From the start of the first dialysis session to the current dialysis session, blood samples were collected from the child at the hospital every two weeks. The clinical laboratory used a standard biochemical analyzer to determine the concentration values ​​of biochemical indicators related to kidney function in the samples, including urea, creatinine, sodium, potassium, and calcium. A concentration value was generated for each biochemical indicator for each sampling.

[0024] Historical patients are those who have completed the entire course of peritoneal dialysis without experiencing any acute complications. The collection methods for physiological indicators are the same for both historical and target patients; the difference is that physiological indicator collection for historical patients must be performed within the corresponding time period of the entire peritoneal dialysis course.

[0025] Step S2: Based on the fluctuation of the analysis data of each type of patient and the difference between each monitoring and the previous monitoring data, adjust the degree of change of the turbidity value of the dialysis solution for each monitoring, and obtain the turbidity mutation degree of each type of analysis data for each type of patient.

[0026] Complications of peritoneal dialysis, such as coagulation and hemolysis, often lead to abnormal and rapid changes in the turbidity of the dialysate. For example, mild coagulation in the dialyzer or blood tubing can activate platelets and inflammatory cells. These cell fragments and protein aggregates can enter the dialysate, causing the turbidity of the dialysate to rise sharply in a short period of time. Therefore, the degree of change in the turbidity value of the solution during each dialysis session can measure the probability of complications.

[0027] The substances in the dialysate are affected by the flow rate in the dialysis catheter. For example, when the flow rate is low, an increase in dialysate turbidity may be caused by the slow flow rate. The effect of flow rate changes needs to be considered when analyzing changes in dialysate turbidity. The flow rate of the solution in the dialysis catheter is affected by both changes in body position and complications. Children experience more changes in body position, which may put pressure on the dialysis catheter, leading to unstable fluid flow rate. Once the patient returns to rest, the flow pattern should quickly return to baseline, so the effect of body position on the solution flow rate is transient and dramatic. However, complications usually cause a trend of deterioration. Coagulation or fibrin sheath formation narrows the lumen through which the fluid flows, and a drop in the patient's systemic blood pressure reduces the driving pressure of blood flow through the vascular pathway. Substantial changes in the physical channel or driving pressure lead to a trend of slight changes in the fluid flow rate in the dialysis catheter. When the peritoneal dialysis process is stable and no complications occur, the patient's blood biochemical indicators are stable. Complications can disrupt this stability, potentially causing abnormal increases or decreases in multiple biochemical indicators. Changes in physiological indicators caused by body position are relatively minor and can be ignored.

[0028] The degree of fluctuation in the analytical data of each monitoring session reflects the severity of the data fluctuation in that monitoring session, and the degree of difference between the analytical data of each monitoring session and the previous monitoring session reflects the duration of the data fluctuation in that monitoring session. By combining the above two factors and adjusting the degree of change in the turbidity value of the dialysis solution for each dialysis session, it is possible to accurately analyze whether the turbidity of the dialysate in each dialysis session is caused by changes in body position or complications, obtain the turbidity mutation degree, greatly improve the specificity of complication early warning, and thus significantly reduce the false alarm rate.

[0029] Step S3: Obtain the reference child for the child to be tested; based on the difference in turbidity variation of the same biochemical index between the child to be tested and the reference child in different sampling, and the difference in turbidity variation of the flow rate sequence in different dialysis sessions, obtain the biochemical difference and flow rate difference in sequence.

[0030] Children have significant individual physiological differences, and key factors such as age, weight, and residual renal function can directly affect abnormal changes in parameters during dialysis. To ensure the accuracy of the analysis, reference children with similar physical conditions to the children being tested were selected.

[0031] Because the pre-existing conditions of the children being tested cause variations in their dialysis data, it is crucial to consider not only their own data changes but also the differences between their data and those of the control group. This difference must be determined to be either a normal physiological change or an abnormal change caused by complications. Flow rate and biochemical differences are analyzed, focusing on the flow rate of the solution in the catheter and renal function-related biochemical indicators, respectively. By examining the differences in dialysis data between the children being tested and the control group, the degree of abnormality in the same analytical data during dialysis in the children being tested relative to the control group can be determined, thus identifying the likelihood of physiological changes causing complications.

[0032] Step S4: Based on the degree of difference in renal function between the child to be tested and the reference child, adjust the biochemical difference and flow rate difference to obtain the risk of complications for the child to be tested in the current dialysis session, and monitor and provide early warning for complications of the current dialysis session.

[0033] Different children have varying residual kidney function, which directly leads to significant differences in the concentration levels of biochemical indicators affected by this function. Since the control child did not experience complications during the overall dialysis process, the likelihood of complications can be assessed by comparing the concentration values ​​of the same biochemical indicators between the test child and the control child. The degree of biochemical and flow rate variability represents the risk of complications during dialysis. Adjustments are made based on the degree of kidney function variability to increase the risk of complications for the test child in the current dialysis session. This protocol fully considers both individual heterogeneity and behavioral specificities, greatly improving the specificity of complication warnings, effectively reducing misdiagnosis of peritoneal dialysis complications, and significantly improving the safety and quality of pediatric peritoneal dialysis.

[0034] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the turbidity abrupt change degree is described in [reference needed]. Figure 2 The diagram illustrates a flowchart of a method for obtaining turbidity abrupt change according to an embodiment of the present invention, the method comprising: Step S210: Obtain the differences between the child under test and all previous monitoring data of the same type in each monitoring session, and calculate the mean of all differences; obtain the differences between all pairwise monitoring data of the same type in all monitoring sessions before each monitoring session in each type for the child under test, and calculate the variance of all differences; adjust the mean using the variance to obtain the data difference of each type of analysis data for each monitoring session for the child under test.

[0035] It should be noted that a smaller mean indicates a more similar data trend between each monitoring session and previous monitoring sessions, thus increasing the likelihood that data fluctuations are caused by complications. Conversely, a larger variance indicates more unstable data changes compared to previous monitoring sessions, reducing the reliability of these monitoring data in predicting the trend of data changes in subsequent monitoring sessions, and consequently decreasing the accuracy of data trends that are more similar. Therefore, variance and data difference are negatively correlated. In this embodiment of the invention, the variance is negatively correlated and normalized, and the product of the processed result and the mean is used as the data difference. A smaller data difference indicates a greater likelihood that data fluctuations in each monitoring session are caused by complications, and also increases the accuracy of the data difference analysis.

[0036] In this embodiment, the test data is used as the exponent of an exponential function with the natural constant as the base, so as to achieve negative correlation and normalization of the test data. Normalization can also be performed using the Sigmoid function, max-min normalization, etc., and negative correlation mapping can be achieved by taking the reciprocal, etc., which are not limited here.

[0037] Step S220: Based on the degree of abrupt change in the turbidity value of the solution during each dialysis session for the child under test, compared to the degree of abrupt change in the turbidity value of the solution during previous dialysis sessions, obtain the degree of turbidity value variation for each dialysis session.

[0038] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the initial turbidity variation includes: recording the ratio of the difference between the turbidity value of the solution in each dialysis and the previous dialysis to the time interval as the current turbidity trend value; performing linear fitting on the turbidity values ​​of all dialysis solutions of the child before each dialysis, and recording the absolute value of the slope of the obtained fitted line as the historical turbidity trend value; and using the ratio of the current turbidity trend value to the historical turbidity trend value as the initial turbidity variation for each dialysis.

[0039] It should be noted that the current turbidity trend value measures the degree of turbidity change in the dialysate during each dialysis session for the child being tested, while the historical turbidity trend value represents the normal turbidity change trend of the dialysate during dialysis for the child being tested. A larger initial turbidity abrupt change indicates a more significant deviation of the turbidity change in the dialysate from the normal turbidity trend during each dialysis session. This means the dialysate is more turbid, the more likely it is caused by inflammation, and thus the greater the probability of complications occurring during each dialysis session.

[0040] It should be noted that since dialysis conditions usually gradually improve or worsen, i.e., there is a certain trend in dialysis conditions, the historical turbidity trend value is usually not equal to zero. In other embodiments, the historical turbidity trend value can also be replaced with the sum of the historical turbidity trend value and a preset positive number, where the preset positive number is used to prevent the denominator from being zero; in this embodiment, it is set to 0.01.

[0041] Step S230: If the analysis data is a flow rate sequence, negatively correlate the product of the fluctuation degree and the data difference and normalize it. The normalized result of the product of the processing result and the initial turbidity mutation degree is taken as the turbidity mutation degree. If the analysis data is the concentration value of a biochemical indicator, normalize the data difference and take the normalized result of the product of the processing result and the initial turbidity mutation degree as the turbidity mutation degree.

[0042] In this embodiment of the invention, if the analytical data is a flow rate sequence, the fluctuation of the analytical data monitored each time is the arithmetic mean difference of the flow rates in each dialysis flow rate sequence, and the difference between two monitoring of the same analytical data is the DTW value of the two dialysis flow rate sequences; if the analytical data is the concentration value of a biochemical indicator, the difference between two monitoring of the same analytical data is the absolute value of the difference between the concentration values ​​of each biochemical indicator monitored in the two monitoring. The Dynamic Time Warping (DTW) algorithm is a well-known technique in the art and will not be described in detail here.

[0043] It should be noted that because each biochemical indicator in a single monitoring session corresponds to only one concentration value, there is no variation in the degree of fluctuation for each monitoring session. For flow rate sequences, the greater the fluctuation in the analytical data from each monitoring session, the more drastic the data fluctuation, and the greater the likelihood that the data fluctuation is caused by changes in body position; conversely, the greater the likelihood that the data fluctuation is caused by complications. Simultaneously, the smaller the data difference, the greater the likelihood that the data fluctuation and the sudden change in solution turbidity are caused by complications, and the smaller the likelihood that they are caused by changes in body position. Therefore, the degree of fluctuation and the data difference are both negatively correlated with the degree of turbidity change. For biochemical indicators, the larger the data difference, the greater the likelihood that complications will disrupt the stable state of blood biochemical indicators, and the greater the likelihood that the sudden change in solution turbidity is caused by complications; therefore, the data difference and the degree of turbidity change are positively correlated. If the degree of turbidity change is greater, the change in the turbidity of the dialysate in each test is more significant, and the probability of complications is greater.

[0044] In this embodiment, the test data is used as the exponent of an exponential function with the natural constant as the base, so as to realize the negative correlation and normalization of the test data. Normalization can also be performed using the Sigmoid function, max-min normalization, etc., and the negative correlation mapping can be achieved by taking the reciprocal, etc., which are not limited here.

[0045] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining reference patients includes: obtaining basic information of the patient to be tested and historical patients who have undergone peritoneal dialysis, the basic information including: age, height, and weight; calculating the body surface area based on the weight and height of each patient; clustering the patient to be tested with historical patients of the same age based on the body surface area to obtain different clusters; and using other historical patients in the cluster to which the patient to be tested belongs as reference patients. The method for calculating the body surface area is an existing formula and will not be elaborated here.

[0046] It should be noted that because there are significant differences in the baseline physiological state and dialysis machine parameter settings among children of different ages, historical children of the same age as the children being analyzed were selected for analysis. Height and weight can be used to calculate body surface area, which is related to peritoneal area and can represent the peritoneal condition of the child. Children within the same cluster have similar physical conditions.

[0047] In one implementation of this invention, the K-means algorithm is used to cluster the children, and the K value can be determined by the elbow method.

[0048] Preferably, in some possible implementations of the present invention, the method for obtaining biochemical variability and flow rate variability includes: calculating the mean turbidity variability of each analytical data for each child under all monitoring in each type, and recording it as the overall variability; summing the absolute values ​​of the differences between the overall variability of the child to be tested and all reference children under the same type of monitoring, and recording it as the overall variability difference of each analytical data; selecting one analytical data as example data; for the same type of monitoring, selecting effective monitoring related to the example data of the child to be tested from all monitoring of the reference children; if the example data is the concentration value of a biochemical indicator, then the mean of the example data of the child to be tested under all monitoring and the mean of the example data of the reference children under all monitoring are compared with the mean of the example data of the reference children under all monitoring. The sample data are equal to the corresponding valid monitoring data; if the sample data is a flow velocity sequence, then any sequence of the tested child in all monitored flow velocity sequences contains an element equal to that of the reference child in the corresponding valid monitored flow velocity sequence; calculate the variance of the turbidity variability of the sample data of all reference children under all valid monitoring related to the sample data of the tested child, and record it as the validity of each analysis data; adjust the overall variability using the validity to obtain the effective variability of each analysis data; if the sample data is the concentration value of a biochemical indicator, then the sum of the effective variability of all biochemical indicators is recorded as the biochemical variability; if the analysis data is a flow velocity sequence, then the effective variability of the flow velocity sequence is recorded as the flow velocity variability.

[0049] It should be noted that the overall mutation rate represents the overall incidence level of complications in each analysis data point for the child, and the overall mutation difference represents the degree of deviation of the tested child from the normal incidence level of complications in each analysis data point compared to the reference child. It is known that data changes caused by complications are more drastic, while data changes caused by disease are more gradual; the larger the overall mutation difference, the more drastic the data changes in each analysis data point for the tested child, and the greater the likelihood of complications. Validity is used to examine the stability of the performance of the reference child when each analysis data point for the tested child is at a specific value; the larger the validity, the more inconsistent the performance of the reference child in that analysis data point, the worse the reliability of complication performance, and the lower the accuracy of the overall mutation difference in determining the likelihood of complications. Therefore, validity and valid mutation difference are negatively correlated. In this embodiment of the invention, the ratio obtained by using the overall mutation difference as the numerator and the sum of validity and a preset positive number as the denominator is taken as the valid mutation difference.

[0050] Since flow velocity sequences are a single-dimensional indicator, the effective mutational differences in the flow velocity sequence can be directly recorded as the flow velocity variability. Complications can affect kidney-related biochemical indicators, so it is necessary to integrate the effective mutational differences of all types of biochemical indicators to obtain a global and comprehensive risk score, namely the biochemical variability. The larger the flow velocity variability and biochemical variability, the higher the probability of complications in the child being tested.

[0051] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the concurrency risk level is described in [reference needed]. Figure 3 The diagram illustrates a flowchart of a method for obtaining concurrency risk level according to an embodiment of the present invention, the method comprising: Step S310: Obtain the degree of difference in renal function based on the difference in concentration values ​​of the same biochemical indicators between the tested child and the reference child.

[0052] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the degree of difference in renal function includes: recording the average concentration value of the same biochemical indicator from all samplings of each child as the overall concentration of the corresponding biochemical indicator; calculating the sum of the absolute values ​​of the differences between the overall concentration of each biochemical indicator of the child to be tested and all reference children, as the reference concentration difference of each biochemical indicator of the child to be tested; recording the absolute value of the difference between the overall concentration of each biochemical data of the child to be tested and a preset standard concentration value as the standard concentration difference of the corresponding biochemical indicator; obtaining the comprehensive concentration difference of each biochemical indicator of the child to be tested based on the reference concentration difference and the standard concentration difference; and summing the comprehensive concentration differences of all biochemical indicators of the child to be tested as the degree of difference in renal function.

[0053] It should be noted that the overall concentration represents the overall concentration level of each biochemical indicator in the child after the first dialysis. By using the reference concentration difference, the degree of concentration deviation of the same biochemical indicator between the tested child and a reference child with similar physical conditions is calibrated on a population level. The difference in the concentration levels of biochemical indicators among different children directly reflects the difference in renal function; therefore, the reference concentration difference can directly represent the difference in renal function of the tested child compared to the reference child in each biochemical indicator. By using the standard concentration difference, the absolute health level of the tested child's biochemical status is calibrated on an absolute scale. The worse the child's renal function, the weaker the body's ability to clear toxins and maintain electrolyte balance, and the more the biochemical indicators will deviate from the ideal standard values. Therefore, the standard concentration difference can reflect the degree of renal function impairment in the child. Each biochemical indicator in a healthy child has a clinically recognized healthy standard range; the median value of the healthy standard range is used as the preset standard concentration value for each biochemical indicator. Therefore, both the reference concentration difference and the standard concentration difference are positively correlated with the overall concentration difference. In this embodiment of the invention, the product of the reference concentration difference and the standard concentration difference for each biochemical indicator of the child under test is taken as the comprehensive concentration difference. Kidney function affects systemic metabolism, and by accumulating the comprehensive concentration differences of all biochemical indicators, a comprehensive assessment from multiple dimensions is achieved to obtain the degree of difference in kidney function.

[0054] Step S320: Normalize the product of the time interval between the current dialysis session and the previous dialysis session and the degree of difference in renal function to obtain a risk adjustment coefficient; use the risk adjustment coefficient to weight the product of the flow rate difference and the biochemical difference, and normalize the weighted result to obtain the complication risk of the child under test in the current dialysis session.

[0055] It should be noted that the differences in flow rate and biochemical properties were analyzed to assess the risk of complications, specifically the catheter solution flow rate and renal function-related biochemical indicators between the tested and control children. Greater differences in both flow rate and biochemical properties indicate a higher probability of complications in the tested child. Shorter dialysis intervals mean less accumulated toxins and water in the patient's body, resulting in a more stable internal environment and a lower risk of complications. Conversely, greater differences in residual renal function, particularly between the tested and control children, and especially if the control child did not experience complications during the entire dialysis process, indicate more significant renal dysfunction in the tested child, thus increasing the risk of complications. Therefore, the time interval between the current and previous dialysis sessions and the degree of renal function difference are positively correlated with the risk of complications; similarly, differences in flow rate and biochemical properties are also positively correlated with the risk of complications. A higher risk of complications in the current dialysis session indicates a greater likelihood of complications for the tested child.

[0056] In this embodiment, the Sigmoid function is used for normalization. However, other normalization methods such as function transformation and max-min normalization can also be used, and no specific method is specified here.

[0057] In this embodiment of the invention, when the concurrency risk level is less than 0.3, the data changes during dialysis are considered normal fluctuations and are set as a Level 3 warning; when the concurrency risk level is greater than or equal to 0.3 and less than 0.6, the data changes during dialysis are considered minor abnormal fluctuations and are set as a Level 2 warning; when the concurrency risk level is greater than or equal to 0.6, the data changes during dialysis are considered severe fluctuations and are set as a Level 1 warning. It should be noted that the higher the warning level, the greater the potential risk of complications during dialysis.

[0058] The complication warning grading of this program for children with peritoneal dialysis is based on objective feature annotation results generated by big data analysis. It does not directly provide diagnostic conclusions, but rather provides doctors with objective quantitative data references, enabling them to focus more quickly on the pathological characteristics of complications and improve their efficiency in judging the risk of complications. The final medical judgment still needs to be made by a professional doctor.

[0059] This invention is now complete.

[0060] Example 2: This invention proposes a real-time monitoring and early warning system for complications of peritoneal dialysis in children. Please refer to [link / reference]. Figure 4 The diagram illustrates a system structure of a real-time monitoring and early warning system for pediatric peritoneal dialysis complications according to an embodiment of the present invention. The system includes: The data acquisition module 510 is used to acquire the solution turbidity value and flow rate sequence of the current dialysis and previous dialysis of the child under test, as well as the concentration value of each biochemical indicator in different samplings; the flow rate sequence and the concentration value of the biochemical indicator are recorded as the analysis data, and dialysis and sampling are different monitoring types; The turbidity mutation analysis module 520 is used to adjust the degree of change in the turbidity value of the dialysis solution for each monitoring based on the fluctuation of the analysis data of each type of the child under test and the degree of difference between each monitoring and the previous monitoring data, so as to obtain the degree of turbidity mutation of each analysis data of the child under test in each type of each monitoring. The data difference analysis module 530 is used to obtain the reference patients for the child to be tested; based on the difference in turbidity variation of the same biochemical index between the child to be tested and the reference patients under different sampling, and the difference in turbidity variation of the flow rate sequence under different dialysis, the biochemical difference and flow rate difference are obtained in sequence. The monitoring and early warning module 540 is used to adjust the biochemical difference and flow rate difference based on the degree of difference in renal function between the child to be tested and the reference child, obtain the complication risk of the child to be tested in the current dialysis session, and monitor and provide early warning for complications of the current dialysis session.

[0061] It should be noted that the devices provided in the above embodiments are only illustrative examples of the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device can be divided into different functional modules to complete all or part of the functions described above. Furthermore, the real-time monitoring and early warning system for pediatric peritoneal dialysis complications provided in the above embodiments and the method embodiment for real-time monitoring and early warning of pediatric peritoneal dialysis complications belong to the same concept, and their specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0062] Example 3: Figure 5 This is a schematic diagram of a computer device for real-time monitoring and early warning of complications in pediatric peritoneal dialysis, provided as an embodiment of the present invention. For example,... Figure 5 As shown, the computer device includes: a memory 601, a processor 602, and a computer program 603 stored in the memory 601 and running on the processor 602, wherein when the processor 602 executes the computer program 603, the computer device can execute any of the aforementioned methods for real-time monitoring and early warning of complications of peritoneal dialysis in children.

[0063] Furthermore, this application also protects an apparatus that may include a memory and a processor, wherein the memory stores executable program code, and the processor is used to call and execute the executable program code to perform a method for real-time monitoring and early warning of pediatric peritoneal dialysis complications provided in this application.

[0064] This embodiment can divide the device into functional modules based on the above method example. For example, each module can correspond to a separate function, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0065] It should be understood that the device provided in this embodiment is used to perform the above-described method for real-time monitoring and early warning of complications in pediatric peritoneal dialysis, and therefore can achieve the same effect as the above-described implementation method.

[0066] When using integrated units, the device may include a processing module and a storage module. When applied to a workpiece, the processing module can be used to control and manage the workpiece's operations. The storage module can be used to support the execution of program code by the workpiece.

[0067] The processing module may be a processor or a controller, which can implement or execute various exemplary logic blocks, modules, and circuits contained in conjunction with the disclosure of this application. The processor may also be a combination of functions that implement computing capabilities, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and microprocessors, etc., and the storage module may be a memory.

[0068] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0069] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0070] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for real-time monitoring and early warning of complications in pediatric peritoneal dialysis, characterized in that, The method includes: Obtain the turbidity and flow rate sequences of the solution from the current and previous dialysis sessions for the child under test, as well as the concentration values ​​of each biochemical indicator from different sampling sessions; record the flow rate sequences and the concentration values ​​of the biochemical indicators as the analytical data, with dialysis and sampling being different monitoring types; Based on the degree of fluctuation of the analytical data of each type of patient and the degree of difference between each monitoring and the previous monitoring, the degree of change of the turbidity value of the dialysis solution is adjusted to obtain the degree of turbidity change of each analytical data of each type of patient in each monitoring. Obtain a reference patient for the child to be tested; based on the difference in turbidity variability of the same biochemical index between the child to be tested and the reference patient at different sampling times, and the difference in turbidity variability of the flow rate sequence at different dialysis times, obtain the biochemical difference and flow rate difference in sequence. Based on the degree of difference in renal function between the child to be tested and the reference child, the biochemical difference and the flow rate difference are adjusted to obtain the complication risk of the child to be tested in the current dialysis session, and to monitor and provide early warning of complications in the current dialysis session.

2. The method for real-time monitoring and early warning of complications in pediatric peritoneal dialysis according to claim 1, characterized in that, The acquisition of turbidity variability for each type of analysis data for each monitoring session for the child under test includes: The differences between the child under test and all previous monitoring data of the same type in each monitoring session are obtained, and the mean of all differences is calculated; the differences between all pairwise monitoring data of the same type in all monitoring sessions before each monitoring session in each type are obtained, and the variance of all differences is calculated; the mean is adjusted using the variance to obtain the data difference of each type of analysis data for each monitoring session in each type for the child under test. The initial turbidity variability for each dialysis session is obtained by comparing the trend of turbidity changes in the solution during each dialysis session with the trend of turbidity changes in the solution during previous dialysis sessions. If the analyzed data is a flow rate sequence, the product of the fluctuation degree and the data difference is negatively correlated and normalized, and the normalized result of the product of the processing result and the initial turbidity abrupt change is taken as the turbidity abrupt change; if the analyzed data is the concentration value of a biochemical indicator, the data difference is normalized, and the normalized result of the product of the processing result and the initial turbidity abrupt change is taken as the turbidity abrupt change.

3. The method for real-time monitoring and early warning of complications in pediatric peritoneal dialysis according to claim 2, characterized in that, The process of obtaining the initial turbidity variation for each dialysis session includes: The ratio of the difference between the turbidity value of the solution in each dialysis session and the previous dialysis session to the time interval is recorded as the current turbidity trend value. A linear fit is performed on the turbidity values ​​of all dialysis solutions of the child before each dialysis session, and the absolute value of the slope of the fitted line is recorded as the historical turbidity trend value. The ratio of the current turbidity trend value to the historical turbidity trend value is used as the initial turbidity change rate for each dialysis session.

4. The method for real-time monitoring and early warning of complications in pediatric peritoneal dialysis according to claim 1, characterized in that, The acquisition of biochemical differences and flow rate differences includes: Calculate the mean turbidity variability of each child under all monitoring conditions for each type of analysis, and record it as the overall variability; sum the absolute values ​​of the differences between the overall variability of the child under test and all reference children under the same type of monitoring for each analysis, and record it as the overall variability difference of each analysis. Choose any type of analytical data and record it as the example data; for the same type of monitoring, select the effective monitoring data related to the example data of the child to be tested from all the monitoring data of the reference child; if the example data is the concentration value of a biochemical indicator, then the mean of the example data of the child to be tested under all monitoring is equal to the example data of the reference child under the corresponding effective monitoring; if the example data is a flow rate sequence, then there is an element in any flow rate sequence of the child to be tested that is equal to the element in the flow rate sequence of the reference child under the corresponding effective monitoring in all the monitoring data. Calculate the variance of turbidity variation in all valid monitoring data related to the sample data of the test child for all reference children, and denote it as the validity of each analysis data; use the validity to adjust the overall variation difference to obtain the effective variation difference of each analysis data; If the example data is the concentration values ​​of biochemical indicators, the sum of the effective mutation differences of all biochemical indicators is recorded as the biochemical difference degree; if the analysis data is a flow rate sequence, the effective mutation difference of the flow rate sequence is recorded as the flow rate difference degree.

5. The method for real-time monitoring and early warning of complications in pediatric peritoneal dialysis according to claim 1, characterized in that, The acquisition of the complication risk of the child under test during the current dialysis session includes: The degree of difference in renal function is obtained by comparing the concentration values ​​of the same biochemical indicators between the tested children and the control children. The product of the time interval between the current dialysis session and the previous dialysis session and the degree of difference in renal function is normalized to obtain a risk adjustment coefficient. The product of the flow rate difference and the biochemical difference is weighted using the risk adjustment coefficient, and the weighted result is normalized to obtain the complication risk of the child under test in the current dialysis session.

6. A method for real-time monitoring and early warning of complications in pediatric peritoneal dialysis according to claim 5, characterized in that, The method of obtaining the degree of difference in renal function based on the concentration differences of the same biochemical indicators between the tested child and the reference child includes: The average concentration of the same biochemical indicator from all samples taken by each child is recorded as the overall concentration of the corresponding biochemical indicator. The sum of the absolute values ​​of the differences in the overall concentration of each biochemical indicator between the tested child and all reference children is calculated as the reference concentration difference for each biochemical indicator of the tested child. The absolute value of the difference between the overall concentration of each biochemical data of the child under test and the preset standard concentration value is recorded as the standard concentration difference of the corresponding biochemical indicator. Based on the difference between the reference concentration and the standard concentration, the comprehensive concentration difference of each biochemical indicator of the child to be tested is obtained; the sum of the comprehensive concentration differences of all biochemical indicators of the child to be tested is taken as the degree of difference in renal function.

7. The method for real-time monitoring and early warning of complications in pediatric peritoneal dialysis according to claim 1, characterized in that, The reference children for obtaining the child to be tested include: The basic information of the child to be tested and the historical children who have undergone peritoneal dialysis is obtained, including age, height and weight; the body surface area is calculated based on the weight and height of each child; the child to be tested and historical children of the same age are clustered based on the body surface area to obtain different clusters; other historical children in the cluster to be tested are used as reference children.

8. A method for real-time monitoring and early warning of complications in pediatric peritoneal dialysis according to claim 2, characterized in that, Methods for obtaining the differences in the same type of analytical data and the degree of fluctuation in the analytical data monitored each time include: If the analytical data is a flow rate sequence, the fluctuation of the analytical data monitored each time is the arithmetic mean difference of the flow rates in the flow rate sequence of each dialysis, and the difference between the same analytical data monitored twice is the DTW value of the flow rate sequence of the two dialysis sessions; if the analytical data is the concentration value of biochemical indicators, the difference between the same analytical data monitored twice is the absolute value of the difference in the concentration value of each biochemical indicator monitored twice.

9. A method for real-time monitoring and early warning of complications in pediatric peritoneal dialysis according to claim 4, characterized in that, The effectiveness is negatively correlated with the effective mutation difference.

10. A method for real-time monitoring and early warning of complications in pediatric peritoneal dialysis according to claim 7, characterized in that, The method used to cluster the child to be tested with historical children of the same age is the K-means algorithm.

Images