A system for monitoring and evaluating the function of hemodialysis access

Abstract

The present invention discloses a functional monitoring and evaluation system for hemodialysis access, which relates to the technical field of hemodialysis. This system encompasses multiple key modules, including dialysis detection, algorithm model construction, dialysis rate calculation, data calculation, and dialysis evaluation. In this system, first, data before and after dialysis of patients is collected in real time through the dialysis detection module. Then, the constructed algorithm model is used to analyze the patient characteristics to determine the dialysis rate threshold S and the dialysis access threshold T. Next, the relevant data is calculated and input into the algorithm model for comparison and evaluation with the dialysis rate threshold S and the dialysis access threshold T, and corresponding warning information is generated. For hemodialysis treatment, the functional monitoring of the dialysis access is crucial. The emergence of this system fills some gaps in the existing monitoring means, enabling medical staff to more comprehensively and accurately evaluate the dialysis access situation of patients, timely discover problems and take corresponding treatment measures.

Description

Technical Field

[0001] The present invention relates to the technical field of hemodialysis, and particularly to a monitoring and evaluation system for the function of hemodialysis accesses. Background Art

[0002] Monitoring the function of hemodialysis accesses is a crucial step in ensuring the normal function and continuous availability of the dialysis accesses for dialysis patients. This series of technologies and methods aims to detect the blood flow condition, patency, and potential complications of the accesses to provide timely intervention and management, ensuring the effectiveness and safety of the dialysis process. The dialysis access is an important passage connecting the patient's cardiovascular system and the dialysis machine, allowing blood to be filtered and cleaned through the dialysis equipment. Therefore, it is crucial to monitor the functional status of the dialysis access to ensure the smooth progress of the hemodialysis process. Through regular monitoring of the function of the dialysis access, the medical team can timely detect and handle any problems to ensure the smooth progress of the dialysis process and reduce the incidence of complications, improving the quality of life of patients.

[0003] At the present stage, there are still some challenges in traditional dialysis access monitoring. Traditional monitoring methods may not easily take into account individual patient differences and the individualized needs of dialysis treatment. For example, factors such as the age, gender, height, and weight status of different patients may affect the selection and adjustment of the dialysis rate. At the same time, the monitoring of dialysis accesses is usually intermittent, such as a weekly dialysis access examination. This periodic monitoring may not easily detect access problems in a timely manner, resulting in problems being discovered only when they progress to a severe degree. Some access problems may not be obvious in the early stage, and traditional monitoring methods may not easily detect them in a timely manner. For example, thrombosis may have no obvious symptoms in the initial stage but will gradually lead to access occlusion over time. Summary of the Invention

[0004] In view of the deficiencies of the prior art, the present invention provides a monitoring and evaluation system for the function of hemodialysis accesses, which solves the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention is realized through the following technical solutions: including a dialysis detection module, an algorithm model construction module, a dialysis rate calculation module, a data calculation module, and a dialysis evaluation module;

[0006] The dialysis detection module is used to detect the dialysis rate data, access patency data, and dialysis fluid data of hemodialysis patients and hemodialysis accesses through detection devices and detection methods, and perform data acquisition to generate a comprehensive dialysis access dataset;

[0007] The algorithm model construction module analyzes the characteristics of patients based on linear regression algorithms and neural network algorithms, and formulates a dialysis rate threshold S and a dialysis access threshold T for the hemodialysis access according to the actual characteristics of the patients;

[0008] The dialysis rate calculation module is used to perform dimensionless processing on the relevant data sets in the comprehensive dialysis access data set, perform summary calculation, obtain the dialysis rate index Txzs, and then input the dialysis rate index Txzs into the algorithm model and the output dialysis rate threshold S to perform comparative evaluation and generate relevant evaluation schemes;

[0009] The data calculation module is used to calculate the collected comprehensive dialysis access data set separately, and then associate it to obtain the comprehensive dialysis access coefficient Tlxs;

[0010] The dialysis evaluation module is used to input the obtained comprehensive dialysis access coefficient Tlxs into the algorithm model, compare and evaluate it with the output dialysis access threshold T and generate a related evaluation plan.

[0011] Preferably, the dialysis detection module includes a data detection unit and a data acquisition unit;

[0012] The data detection unit is used to perform real-time detection of the pre-dialysis and post-dialysis data of the hemodialysis patient according to the dialysis detection equipment and medical detection methods, and obtain the dialysis rate data, access flow data and dialysate data. The specific monitoring scheme is as follows;

[0013] The dialysis rate data include dialysis time Ssj, solute distribution volume Stj, initial solute concentration in blood Sxc, initial solute concentration in dialysate Syc, solute concentration in blood after dialysis Sxh and solute concentration in dialysate after dialysis Syh;

[0014] The dialysis time Ssj is obtained by the timer provided by the dialyzer;

[0015] The solute distribution volume Stj is obtained by biochemical analysis;

[0016] The initial concentration of solutes in the blood Sxc is obtained by drawing a blood sample for laboratory testing;

[0017] The initial solute concentration Syc in the dialysate is controlled by the dialysis machine according to preset parameters;

[0018] The solute concentration Sxh in the blood after dialysis is obtained by drawing a blood sample for laboratory testing;

[0019] The solute concentration Syh in the dialysate after dialysis is obtained by collecting dialysate samples and performing laboratory tests;

[0020] The channel smoothness data includes channel diameter Tzj, channel wall thickness Tbh, channel length Tcd, blood flow Txl and blood pressure Txy;

[0021] The passage diameter Tzj and the passage wall thickness Tbh are measured by ultrasonic examination to measure the passage diameter;

[0022] The passage length Tcd is monitored in real time by a dialysis machine;

[0023] The blood flow rate Txl is measured by an ultrasonic Doppler technique;

[0024] The blood pressure Txy is measured and monitored by a non-invasive sphygmomanometer;

[0025] The dialysate data includes the dialysate flow rate Yll, the dialysate pH value Yph, the dialysate temperature Ywd, the dialysate osmotic pressure Yst, and the dialysate volume Ytj;

[0026] The dialysate flow rate Yll is measured by a flow meter on the dialysis equipment;

[0027] The dialysate pH value Yph is measured by a pH meter on the dialysis machine;

[0028] The dialysate temperature Ywd is monitored by a temperature sensor on the dialysis machine;

[0029] The dialysate osmotic pressure Yst is monitored by an osmotic pressure sensor on the dialysis machine;

[0030] The dialysate volume Ytj is monitored by a liquid level sensor on the dialysis machine.

[0031] Preferably, the data acquisition unit is used to preprocess the detected dialysis rate data, passage smoothness data, and dialysate data, and then perform data acquisition. The preprocessing methods include normalization, outlier removal, interpolation, and data cleaning. Then, a dialysis rate data set, a passage smoothness data set, and a dialysate data set are generated, and they are classified and summarized to generate a comprehensive dialysis passage data set.

[0032] Preferably, the algorithm model construction module includes a model construction unit and a threshold construction unit;

[0033] The model construction unit is used to screen the characteristics related to hemodialysis patients using feature selection technology according to the actual situation of hemodialysis patients, including the age, gender, height, and weight data of the patients. The linear regression algorithm and the neural network algorithm are selected to construct an integrated algorithm model. The characteristic data related to hemodialysis patients are divided into a training set and a test set. The training set is used to train the model, and cross-validation technology is used for tuning to optimize the generalization ability and performance of the algorithm model. The test set is used to evaluate the performance of the algorithm model, including mean square error and root mean square error metrics. The model is verified through a validation set to ensure the generalization ability of the model;

[0034] The threshold construction unit is used to establish a linear relationship between the independent variable features and the dependent variable target. The independent variable features include the age, gender, height, and weight information of the patient, and the dependent variable target includes the dialysis rate threshold S and the dialysis access threshold T. The linear regression technique is used to fit the relationship between the independent variable features and the dependent variable target, and a linear regression equation is constructed. By inputting the dialysis rate data, access patency data, and dialysate data, the algorithm model will output the predicted normal dialysis rate threshold S and the threshold T of the blood pressure dialysis access, assisting the doctor in making treatment decisions.

[0035] Preferably, the dialysis rate calculation module includes a hemodialysis rate calculation unit and a dialysis rate evaluation unit;

[0036] The hemodialysis rate calculation unit is used to perform dimensionless processing on the dialysis rate data set in the comprehensive dialysis access data set, and then perform analysis and calculation to obtain the dialysis rate index Txzs;

[0037] The dialysis rate index Txzs is obtained through the following formula;

[0038]

[0039] In the formula, ln represents the natural logarithm of the solute concentration Sxh in the blood after dialysis divided by the initial solute concentration Sxc in the blood.

[0040] Preferably, the dialysis rate evaluation unit is used to input the obtained dialysis rate index Txzs into the algorithm model, and then compare and evaluate it with the dialysis rate threshold S obtained by analyzing the actual characteristics of the patient, and generate a warning message according to the evaluation result. The specific evaluation scheme is as follows;

[0041] When the dialysis rate index Txzs > the dialysis rate threshold S, it indicates that the current dialyzer is abnormal. At this time, a first warning message is generated to notify the medical staff to comprehensively analyze the ultrafiltration rate setting, dialysate composition, and the patient's physiological state;

[0042] When the dialysis rate index Txzs = the dialysis rate threshold S, it indicates that the current dialyzer is in a normal state. At this time, no warning message needs to be generated, and the comprehensive dialysis access evaluation is performed;

[0043] When the dialysis rate index Txzs < the dialysis rate threshold S, it indicates that the current dialyzer is abnormal. At this time, a second warning message is generated to notify the medical staff to treat and regulate the patient and the dialysis machine.

[0044] Preferably, the data calculation module includes an access patency calculation unit, a dialysate calculation unit, and an associated calculation unit;

[0045] The access flow calculation unit is used to perform dimensionless processing on the access flow data set in the comprehensive dialysis access data set, and then perform summary calculation to obtain the access flow coefficient Tllc;

[0046] The access flow coefficient Tllc is obtained through the following formula;

[0047]

[0048] In the formula, i represents the starting position of the calculation, and i = 1 means starting the calculation from the access diameter Tzj.

[0049] Preferably, the dialysate calculation unit is used to perform dimensionless processing on the dialysate data set in the comprehensive dialysis access data set, and then continue to perform summary calculation to obtain the dialysate data set Txys;

[0050] The dialysate data set Txys is obtained through the following formula;

[0051]

[0052] In the formula, α represents the weight value of the sum of the dialysate flow rate Yll and the dialysate pH value Yph, β represents the weight value of the sum of the dialysate temperature Ywd and the dialysate osmotic pressure Yst, χ represents the weight value of the dialysate volume Ytj, and α + β ≠ χ, 0 < α < 1, 0 < β < 1, 0 < χ < 1, and its specific value is adjusted and set by the user.

[0053] Preferably, the correlation calculation unit is used to perform dimensionless processing on the obtained dialysis rate index Txzs, access flow coefficient Tllc, and dialysate data set Txys, and then perform correlation summary calculation to obtain the comprehensive dialysis access coefficient Tlxs;

[0054] The comprehensive dialysis access coefficient Tlxs is obtained through the following formula;

[0055]

[0056] In the formula, a1, a2, and a3 respectively represent the preset weight values of the dialysis rate index Txzs, access flow coefficient Tllc, and dialysate data set Txys, and a1 + a2 ≠ a3, 0 < a1 < 1, 0 < a2 < 1, 0 < a3 < 1, and its specific value is adjusted and set by the user, and A represents the first correction coefficient.

[0057] Preferably, the dialysis evaluation module is used to input the obtained comprehensive dialysis access coefficient Tlxs into the algorithm model, compare and evaluate it with the dialysis access threshold T obtained by analyzing the actual characteristics of the patient, and generate a warning message according to the evaluation result. The specific evaluation scheme is as follows;

[0058] When the comprehensive dialysis access coefficient Tlxs > the dialysis access threshold T, it indicates that the current dialysis access is in a normal state, and there is no need to generate a warning message at this time;

[0059] When the comprehensive dialysis access coefficient Tlxs ≤ the dialysis access threshold T, it indicates that there is a blockage in the current dialysis access, and at this time, a third warning message is generated to notify the medical staff to take measures.

[0060] The present invention provides a system for monitoring and evaluating the function of a hemodialysis access. It has the following beneficial effects:

[0061] (1) This system covers multiple key modules, including dialysis detection, algorithm model construction, dialysis rate calculation, data calculation, and dialysis evaluation. In this system, first, data before and after the patient's dialysis is collected in real time through the dialysis detection module, and then the algorithm model is constructed to analyze the patient's characteristics to determine the dialysis rate threshold S and the dialysis access threshold T. Then, the relevant data is calculated and input into the algorithm model for comparison and evaluation with the dialysis rate threshold S and the dialysis access threshold T, and corresponding warning messages are generated. For hemodialysis treatment, the function monitoring of the dialysis access is crucial. The emergence of this system fills some gaps in the existing monitoring means, enabling medical staff to more comprehensively and accurately evaluate the patient's dialysis access situation, timely discover problems, and take corresponding treatment measures.

[0062] (2) This system analyzes the comprehensive dialysis access data through the data calculation module and combines the warning information provided by the dialysis evaluation module to promptly discover access blockages or other abnormal conditions. This helps medical staff make more accurate treatment decisions, reduce the risk of complications, and improve the treatment effect.

[0063] (3) This system constructs a personalized hemodialysis access algorithm model according to the actual situation and characteristics of the patient, which can better guide dialysis rate and access management. Through the evaluation of the comprehensive dialysis access coefficient, medical staff can optimize the dialysis plan, improve dialysis efficiency, and minimize the adverse effects on the patient at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 It is a schematic flow diagram of a system for monitoring and evaluating the function of a hemodialysis access according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0065] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0066] Example 1

[0067] Please refer to Figure 1 , the present invention provides a hemodialysis access function monitoring and evaluation system. To achieve the above objectives, the present invention is implemented through the following technical solutions: including a dialysis detection module, an algorithm model construction module, a dialysis rate calculation module, a data calculation module, and a dialysis evaluation module;

[0068] The dialysis detection module is used to detect the dialysis rate data, access patency data, and dialysis fluid data of hemodialysis patients and hemodialysis accesses through detection devices and detection methods, and perform data collection to generate a comprehensive dialysis access dataset;

[0069] The algorithm model construction module analyzes the characteristics of patients based on linear regression algorithms and neural network algorithms, and formulates a dialysis rate threshold S and a dialysis access threshold T for the hemodialysis access according to the actual characteristics of the patients;

[0070] The dialysis rate calculation module is used to perform dimensionless processing on the relevant datasets in the comprehensive dialysis access dataset, then perform summary calculations to obtain a dialysis rate index Txzs, and then input the dialysis rate index Txzs into the algorithm model to compare and evaluate it with the output dialysis rate threshold S, and generate relevant evaluation plans;

[0071] The data calculation module is used to perform separate calculations on the collected comprehensive dialysis access dataset, and then perform correlation to obtain a comprehensive dialysis access coefficient Tlxs;

[0072] The dialysis evaluation module is used to input the obtained comprehensive dialysis access coefficient Tlxs into the algorithm model to compare and evaluate it with the output dialysis access threshold T, and generate relevant evaluation plans.

[0073] In this embodiment, the system integrates a dialysis detection module, an algorithm model building module, a dialysis rate calculation module, a data calculation module and a dialysis evaluation module, providing a comprehensive and intelligent monitoring and evaluation scheme for dialysis patients and medical staff. First, the dialysis detection module monitors the rate, fluency and dialysate data of the dialysis access in real time through detection equipment and methods, generates a comprehensive dialysis access data set, and provides necessary data support for subsequent analysis. Secondly, the algorithm model building module is based on linear regression and neural network algorithms, combined with the characteristics of the patient, to formulate personalized dialysis rate threshold S and dialysis access threshold T, thereby improving the accuracy and practicality of monitoring. The dialysis rate calculation module processes and calculates the data set to obtain the dialysis rate index Txzs, and compares it with the set dialysis rate threshold S, providing a more specific evaluation scheme for medical staff. The data calculation module and the dialysis evaluation module further enhance the function of the system, and provide a more comprehensive monitoring and evaluation scheme for medical staff through the calculation and evaluation of the comprehensive dialysis access data. Compared with traditional monitoring technology, this system has obvious improvements in monitoring accuracy, data processing speed and formulation of personalized treatment plans. By combining advanced algorithm models and intelligent data processing technology, this system realizes automation and intelligence of monitoring and evaluation, bringing new breakthroughs and progress to hemodialysis access function monitoring.

[0074] Example 2

[0075] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the dialysis detection module includes a data detection unit and a data acquisition unit;

[0076] The data detection unit is used to perform real-time detection of the pre-dialysis and post-dialysis data of hemodialysis patients based on dialysis detection equipment and medical detection methods, and obtain dialysis rate data, access flow data and dialysate data. The specific monitoring scheme is as follows;

[0077] The dialysis rate data include dialysis time Ssj, solute distribution volume Stj, initial solute concentration in blood Sxc, initial solute concentration in dialysate Syc, solute concentration in blood after dialysis Sxh, and solute concentration in dialysate after dialysis Syh;

[0078] The dialysis time Ssj is obtained through the dialyzer’s own timer;

[0079] The solute distribution volume Stj is obtained by biochemical analysis;

[0080] The initial concentration of solutes in the blood, Sxc, is obtained by drawing a blood sample for laboratory testing;

[0081] The initial solute concentration Syc in the dialysate is controlled by the dialysis machine according to preset parameters;

[0082] The solute concentration Sxh in the blood after dialysis is obtained by taking a blood sample for laboratory testing;

[0083] The solute concentration Syh in the dialysate after dialysis is obtained by collecting a dialysate sample and performing laboratory testing;

[0084] The patency data includes the access diameter Tzj, the access wall thickness Tbh, the access length Tcd, the blood flow rate Txl, and the blood pressure Txy;

[0085] The access diameter Tzj and the access wall thickness Tbh are measured by ultrasonic examination to measure the access diameter;

[0086] The access length Tcd is monitored in real time by the dialysis machine;

[0087] The blood flow rate Txl is measured by the ultrasonic Doppler technique;

[0088] The blood pressure Txy is measured and monitored by a non-invasive sphygmomanometer;

[0089] The dialysate data includes the dialysate flow rate Yll, the dialysate pH value Yph, the dialysate temperature Ywd, the dialysate osmotic pressure Yst, and the dialysate volume Ytj;

[0090] The dialysate flow rate Yll is measured by a flow meter on the dialysis equipment;

[0091] The dialysate pH value Yph is measured by a pH meter on the dialysis machine;

[0092] The dialysate temperature Ywd is monitored by a temperature sensor on the dialysis machine;

[0093] The dialysate osmotic pressure Yst is monitored by an osmotic pressure sensor on the dialysis machine;

[0094] The dialysate volume Ytj is monitored by a liquid level sensor on the dialysis machine.

[0095] The data acquisition unit is used to preprocess the detected dialysis rate data, patency data, and dialysate data, and then perform data acquisition. The preprocessing methods include normalization, outlier removal, interpolation, and data cleaning. Then, a dialysis rate data set, a patency data set, and a dialysate data set are generated, and they are classified and summarized to generate a comprehensive dialysis access data set.

[0096] In this embodiment, the introduction of the dialysis detection module has brought significant improvements and benefits to the monitoring of blood dialysis access functions. First, through the real-time monitoring of the data detection unit, the system can quickly and accurately obtain key data before and after dialysis, including dialysis rate, access patency, and dialysate-related parameters. This real-time monitoring solution effectively improves the timeliness and comprehensiveness of monitoring, helping to detect potential problems or abnormal situations in a timely manner. Second, by adopting multiple detection methods and devices, the system can obtain data from multiple perspectives, further improving the accuracy and reliability of monitoring. This comprehensive monitoring solution helps to comprehensively evaluate the health status of the dialysis access, providing an important basis for subsequent treatment decisions.

[0097] The introduction of the data acquisition unit further improves the efficiency and quality of data processing. Through preprocessing methods, the system can effectively process the original data, improving the consistency and comparability of the data. The generated dialysis rate dataset, access patency dataset, and dialysate dataset provide a basis for subsequent analysis and evaluation. This data processing solution helps to reduce the complexity and workload of data processing, improving the usability and value of monitoring data.

[0098] Embodiment 3

[0099] This embodiment is an explanatory description based on Embodiment 1. Please refer to Figure 1 Specifically: The algorithm model construction module includes a model construction unit and a threshold construction unit;

[0100] The model construction unit is used to screen the characteristics related to hemodialysis patients using feature selection techniques according to the actual situation of hemodialysis patients, including the age, gender, height, and weight data of the patients. Select the linear regression algorithm and the neural network algorithm, and perform integrated construction of the algorithm model. Divide the characteristic data related to hemodialysis patients into a training set and a test set. Use the training set to train the model and optimize it through cross-validation techniques to optimize the generalization ability and performance of the algorithm model. Use the test set to evaluate the performance of the algorithm model, including mean square error and root mean square error metrics, and verify the model through the validation set to ensure the generalization ability of the model;

[0101] The threshold construction unit is used to establish a linear relationship between the independent variable characteristics and the dependent variable target. The independent variable characteristics include the age, gender, height, and weight information of the patients, and the dependent variable target includes the dialysis rate threshold S and the dialysis access threshold T. Use linear regression techniques to fit the relationship between the independent variable characteristics and the dependent variable target, construct a linear regression equation, input the dialysis rate data, access patency data, and dialysate data, and the algorithm model will output the predicted normal dialysis rate threshold S and the threshold T of the blood pressure dialysis access to assist the doctor in making treatment decisions.

[0102] In this embodiment, through the model construction unit, the system can select relevant feature data according to the actual situation of hemodialysis patients and construct an integration using the linear regression algorithm and the neural network algorithm. This personalized feature selection and model construction scheme makes the algorithm model closer to the actual situation of patients, improving the applicability and prediction ability of the model. Secondly, through the threshold construction unit, the system can establish a linear relationship between the independent variable features and the dependent variable target, thereby predicting the dialysis rate threshold S and the dialysis access threshold T. This prediction scheme based on linear regression technology provides an important reference for medical staff to help them make more accurate treatment decisions. The introduction of the algorithm model construction module further improves the intelligent level of monitoring and treatment. Through the selection of feature data and the integrated construction of the algorithm model, the system can automatically learn and identify potential rules and patterns, thereby reducing the subjective intervention of medical staff and improving the standardization degree of monitoring and treatment. In addition, through the predicted dialysis rate threshold S and dialysis access threshold T, the system can issue an alarm or provide suggestions in a timely manner.

[0103] Embodiment 4

[0104] This embodiment is an explanatory description based on Embodiment 2. Please refer to Figure 1 , specifically: The dialysis rate calculation module includes a hemodialysis rate calculation unit and a dialysis rate evaluation unit;

[0105] The hemodialysis rate calculation unit is used to perform dimensionless processing on the dialysis rate data set in the comprehensive dialysis access data set and then perform analysis and calculation to obtain the dialysis rate index Txzs;

[0106] The dialysis rate index Txzs is obtained through the following formula;

[0107]

[0108] In the formula, ln represents the natural logarithm of the solute concentration Sxh in the blood after dialysis divided by the initial solute concentration Sxc in the blood.

[0109] The dialysis rate evaluation unit is used to input the obtained dialysis rate index Txzs into the algorithm model, and then compare and evaluate it with the dialysis rate threshold S obtained through the analysis of the actual characteristics of the patient, and generate a warning message according to the evaluation result. The specific evaluation scheme is as follows;

[0110] When the dialysis rate index Txzs > the dialysis rate threshold S, it indicates that the current dialysis rate is relatively high. The parameter settings of the dialysis equipment may be inappropriate, resulting in too high a blood flow rate in the dialyzer. At the same time, problems with the dialyzer itself, such as blockage inside the dialyzer and damage to the membrane, may cause an increase in the resistance when blood flows through the dialyzer, thereby increasing the dialysis rate. At this time, a first warning message is generated to notify medical staff to adjust and control the dialysate, ultrafilter, and access of the dialyzer according to the actual characteristics of the patient.

[0111] When the dialysis rate index Txzs = the dialysis rate threshold S, it indicates that the current dialyzer is in a normal state. At this time, no warning message needs to be generated, and a comprehensive dialysis access assessment is performed.

[0112] When the dialysis rate index Txzs < the dialysis rate threshold S, it indicates that the current dialysis rate is abnormally low. The patient may be in a hemodynamically stable state, such as normal or low blood pressure, high cardiac output, etc. This may slow down the blood flow rate in the dialyzer, thereby reducing the dialysis rate. Abnormal concentrations of electrolyte components such as sodium, potassium, and calcium in the dialysate may affect the water and electrolyte balance during dialysis, thereby affecting the dialysis effect. At this time, a second warning message is generated to notify medical staff to treat and regulate the patient and the dialysis machine.

[0113] In this embodiment, the introduction of the dialysis rate calculation module brings important advantages and benefits to the monitoring of the blood dialysis access function. First, through the blood dialysis rate calculation unit, the system can obtain the dialysis rate index Txzs based on the dialysis rate data in the comprehensive dialysis access dataset after dimensionless processing and analysis calculations. This index reflects the change in solute concentration during dialysis and is an important basis for evaluating the dialysis effect. Second, the dialysis rate evaluation unit further compares and evaluates the dialysis rate index Txzs with the preset dialysis rate threshold S, and generates corresponding warning messages according to the evaluation results. This evaluation scheme based on real-time data and the preset dialysis rate threshold S can help medical staff timely detect abnormal situations during dialysis, take corresponding intervention measures, and improve the safety and effectiveness of the dialysis process. The introduction of the dialysis rate calculation module also provides a more convenient and accurate monitoring means for medical staff. By automatically calculating the dialysis rate index Txzs and comparing and evaluating it with the preset dialysis rate threshold S, the system can timely send warning messages to help medical staff identify potential problems and take corresponding measures.

[0114] Embodiment 5

[0115] This embodiment is an explanatory description carried out in Embodiment 2. Please refer to Figure 1 , specifically: The data calculation module includes a passage smoothness calculation unit, a dialysate calculation unit, and an associated calculation unit;

[0116] The passage flow calculation unit is used to perform dimensionless processing on the passage flow data set in the comprehensive dialysis passage data set, and then perform summary calculation to obtain the passage flow coefficient Tllc;

[0117] The passage flow coefficient Tllc is obtained through the following formula;

[0118]

[0119] In the formula, i represents the starting position of the calculation, and i = 1 means starting the calculation from the passage diameter Tzj.

[0120] The dialysate calculation unit is used to perform dimensionless processing on the dialysate data set in the comprehensive dialysis passage data set, and then continue to perform summary calculation to obtain the dialysate data set Txys;

[0121] The dialysate data set Txys is obtained through the following formula;

[0122]

[0123] In the formula, α represents the weight value of the sum of the dialysate flow rate Yll and the dialysate pH value Yph, β represents the weight value of the sum of the dialysate temperature Ywd and the dialysate osmotic pressure Yst, χ represents the weight value of the dialysate volume Ytj, and α + β ≠ χ, 0 < α < 1, 0 < β < 1, 0 < χ < 1, and its specific value is adjusted and set by the user.

[0124] In this embodiment, the introduction of the data calculation module has brought significant improvements and gains to the monitoring of the blood dialysis passage function. First, the passage flow calculation unit obtains the passage flow coefficient Tllc by performing dimensionless processing and summary calculation on the passage flow data set in the comprehensive dialysis passage data set. This coefficient reflects the smoothness of the dialysis passage and is an important parameter for evaluating the dialysis effect. Through real-time calculation and summary, the system can provide timely and accurate information on the passage smoothness to medical staff, helping them better monitor and manage the patient's dialysis process. Second, the dialysate calculation unit further performs dimensionless processing and summary calculation on the dialysate data set in the comprehensive dialysis passage data set to obtain the dialysate data set Txys. This data set takes multiple factors into consideration and can be adjusted according to the actual needs of the user by setting the weight value, further improving the flexibility and applicability of the system.

[0125] Example 6

[0126] This embodiment is an explanatory description based on Embodiment 5. Please refer to Figure 1, specifically: the associated calculation unit is used to perform dimensionless processing on the obtained dialysis rate index Txzs, passage smoothness coefficient Tllc, and dialysate dataset Txys, and then perform associated summary calculation to obtain the comprehensive dialysis passage coefficient Tlxs;

[0127] The comprehensive dialysis passage coefficient Tlxs is obtained through the following formula;

[0128]

[0129] In the formula, a1, a2, and a3 respectively represent the preset weight values of the dialysis rate index Txzs, passage smoothness coefficient Tllc, and dialysate dataset Txys, and a1 + a2 ≠ a3, 0 < a1 < 1, 0 < a2 < 1, 0 < a3 < 1. Their specific values are adjusted and set by the user, and A represents the first correction coefficient.

[0130] The dialysis evaluation module is used to input the obtained comprehensive dialysis passage coefficient Tlxs into the algorithm model, compare and evaluate it with the dialysis passage threshold T obtained by analyzing the actual characteristics of the patient, and generate a warning message according to the evaluation result. The specific evaluation scheme is as follows;

[0131] When the comprehensive dialysis passage coefficient Tlxs > the dialysis passage threshold T, it means that the current dialysis passage is in a normal state, and no warning message needs to be generated at this time;

[0132] When the comprehensive dialysis passage coefficient Tlxs ≤ the dialysis passage threshold T, it means that there is a blockage in the current dialysis passage, and thrombosis may occur in the dialysis passage, which will cause passage obstruction and affect the progress of dialysis treatment. Thrombosis may be caused by factors such as hemodynamic abnormalities, passage damage, and vascular stenosis. At this time, a third warning message is generated to notify the medical staff to take measures.

[0133] In this embodiment, the introduction of the associated computing unit provides more comprehensive data support for the monitoring and evaluation of the dialysis access. First, by performing dimensionless processing and associated summary calculations on the dialysis rate index Txzs, the access fluency coefficient Tllc, and the dialysate data set Txys, the comprehensive dialysis access coefficient Tlxs is obtained. This coefficient comprehensively considers multiple factors such as the dialysis rate, access fluency, and dialysate conditions, reflecting the overall state of the dialysis access. By setting preset weight values and correction coefficients, the system can be adjusted according to the user's needs, further improving the accuracy and flexibility of the evaluation. Secondly, the dialysis evaluation module compares and evaluates the comprehensive dialysis access coefficient Tlxs with the obtained dialysis access threshold T, and generates a warning message based on the evaluation result. When the comprehensive dialysis access coefficient Tlxs exceeds the dialysis access threshold T, the system considers the dialysis access to be in a normal state and no warning message needs to be generated; while when the comprehensive dialysis access coefficient Tlxs is lower than or equal to the dialysis access threshold T, the system will generate a third warning message to prompt the medical staff to take corresponding measures.

[0134] Although the embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention.

Claims

1. A blood dialysis access function monitoring and evaluation system, characterized in that: It includes a dialysis detection module, an algorithm model construction module, a dialysis rate calculation module, a data calculation module, and a dialysis evaluation module; The dialysis detection module is used to detect the dialysis rate data, access patency data, and dialysate data of hemodialysis patients and hemodialysis accesses through detection devices and methods, and collect data to generate a comprehensive dialysis access dataset; The dialysis detection module includes a data detection unit and a data collection unit; The data detection unit is used to detect the pre-dialysis and post-dialysis data of hemodialysis patients in real time according to dialysis detection devices and medical detection methods, and obtain dialysis rate data, access patency data, and dialysate data; The algorithm model construction module analyzes the characteristics of patients based on linear regression algorithms and neural network algorithms, and formulates a dialysis rate threshold S and a dialysis access threshold T for the hemodialysis access according to the actual characteristics of the patients; The dialysis rate calculation module is used to perform dimensionless processing on the relevant datasets in the comprehensive dialysis access dataset, and then perform summary calculations to obtain a dialysis rate index Txzs. Then, the dialysis rate index Txzs is input into the algorithm model and compared with the output dialysis rate threshold S to generate relevant evaluation schemes; The dialysis rate calculation module includes a hemodialysis rate calculation unit and a dialysis rate evaluation unit; The hemodialysis rate calculation unit is used to perform dimensionless processing on the dialysis rate dataset in the comprehensive dialysis access dataset, and then perform analysis and calculations to obtain a dialysis rate index Txzs; The dialysis rate index Txzs is obtained through the following formula; ; In the formula, dialysis time Ssj, solute distribution volume Stj, initial solute concentration in blood Sxc, initial solute concentration in dialysate Syc, solute concentration in blood after dialysis Sxh, and solute concentration in dialysate after dialysis Syh; In the formula, represents the natural logarithm of the solute concentration Sxh in the blood after dialysis divided by the initial solute concentration Sxc in the blood; The data calculation module is used to perform separate calculations on the collected comprehensive dialysis access dataset, and then perform correlation to obtain a comprehensive dialysis access coefficient Tlxs; The data calculation module includes an access patency calculation unit, a dialysate calculation unit, and a correlation calculation unit; The access patency calculation unit is used to perform dimensionless processing on the access patency dataset in the comprehensive dialysis access dataset, and then perform summary calculations to obtain an access patency coefficient Tllc; The access patency coefficient Tllc is obtained through the following formula; ； In the formula, access diameter Tzj, access wall thickness Tbh, access length Tcd, blood flow Txl, and blood pressure Txy; In the formula, i represents the starting position of the calculation, and i = 1 means starting the calculation from the access diameter Tzj; The dialysate calculation unit is used to perform dimensionless processing on the dialysate dataset in the comprehensive dialysis access dataset, and then continue to perform summary calculations to obtain a dialysate dataset Txys; The dialysate dataset Txys is obtained through the following formula; ； In the formula, dialysate flow Yll, dialysate pH value Yph, dialysate temperature Ywd, dialysate osmotic pressure Yst, and dialysate volume Ytj; wherein, represents the weight value of the sum of the dialysate flow rate Yll and the dialysate pH value Yph, represents the weight value of the sum of the dialysate temperature Ywd and the dialysate osmotic pressure Yst, represents the weight value of the dialysate volume Ytj, and , , , whose specific values are adjusted and set by the user; The associated computing unit is used to perform dimensionless processing and associated summary calculations on the obtained dialysis rate index Txzs, passage smoothness coefficient Tllc, and dialysate data set Txys to obtain the comprehensive dialysis passage coefficient Tlxs; The comprehensive dialysis passage coefficient Tlxs is obtained through the following formula; ； In the formula, respectively represent the preset weight values of the dialysate data set Txys, the dialysis rate index Txzs, and the access flow coefficient Tllc, and , and its specific value is adjusted and set by the user. A represents the first correction coefficient; The dialysis evaluation module is used to input the obtained comprehensive dialysis passage coefficient Tlxs into the algorithm model, compare and evaluate it with the output dialysis passage threshold T, and generate relevant evaluation plans.

2. The blood dialysis access function monitoring and evaluation system according to claim 1, wherein: The data acquisition unit is used to preprocess and then collect the detected dialysis rate data, passage smoothness data, and dialysate data. The preprocessing includes normalization, outlier removal, interpolation, and data cleaning, and then generate a dialysis rate data set, a passage smoothness data set, and a dialysate data set, and perform classification summary to generate a comprehensive dialysis passage data set.

3. The blood dialysis access function monitoring and evaluation system according to claim 1, wherein: The algorithm model construction module includes a model construction unit and a threshold construction unit; The model construction unit is used to screen the characteristics related to hemodialysis patients using feature selection techniques according to the actual situation of hemodialysis patients, including the age, gender, height, and weight data of the patients, select linear regression algorithms and neural network algorithms, perform integrated construction of the algorithm model, divide the characteristic data related to hemodialysis patients into a training set and a test set, use the training set to train the model, and perform tuning through cross-validation techniques, use the test set to evaluate the performance of the algorithm model, including mean square error and root mean square error indicators, and perform model verification through the validation set; The threshold construction unit is used to establish a linear relationship between the independent variable characteristics and the dependent variable target. The independent variable characteristics include the age, gender, height, and weight information of the patients, and the dependent variable target includes the dialysis rate threshold S and the dialysis passage threshold T. Use linear regression techniques to fit the relationship between the independent variable characteristics and the dependent variable target, construct a linear regression equation, input the dialysis rate data, passage smoothness data, and dialysate data, and the algorithm model will output the predicted normal dialysis rate threshold S and the threshold T of the blood pressure dialysis passage.

4. A blood dialysis access function monitoring and evaluation system according to claim 1, characterized in that: The dialysis rate evaluation unit is used to input the obtained dialysis rate index Txzs into the algorithm model, and then compare and evaluate it with the dialysis rate threshold S obtained by analyzing the actual characteristics of the patient, and generate a warning message according to the evaluation result. The specific evaluation plan is as follows; When the dialysis rate index Txzs > the dialysis rate threshold S, it indicates that the current dialysis rate is abnormal. At this time, a first warning message is generated to notify the medical staff to adjust and control the dialysate, ultrafilter, and passage of the dialyzer according to the actual characteristics of the patient; When the dialysis rate index Txzs = the dialysis rate threshold S, it indicates that the current dialyzer is in a normal state. At this time, no warning message needs to be generated, and a comprehensive dialysis passage evaluation is performed; When the dialysis rate index Txzs < the dialysis rate threshold S, it indicates that the current dialysis rate is abnormal. At this time, a second warning message is generated to notify the medical staff to adjust and control the dialysate, ultrafilter, and passage of the dialyzer according to the actual characteristics of the patient.

5. The blood dialysis access function monitoring and evaluation system according to claim 1, wherein: The dialysis evaluation module is used to input the obtained comprehensive dialysis access coefficient Tlxs into the algorithm model for comparison and evaluation with the dialysis access threshold T obtained by analyzing the actual characteristics of the patient, and generate a warning message according to the evaluation result. The specific evaluation plan is as follows: When the comprehensive dialysis access coefficient Tlxs > the dialysis access threshold T, it indicates that the current dialysis access is in a normal state, and there is no need to generate a warning message at this time; When the comprehensive dialysis access coefficient Tlxs ≤ the dialysis access threshold T, it indicates that there is a blockage in the current dialysis access, and at this time, a third warning message is generated to notify the medical staff to take measures.

Images