Self-adaptive peritoneal dialysis dose optimization method, device, equipment and medium

Abstract

The invention relates to a self-adaptive peritoneal dialysis dose optimization method, device, equipment and medium, and the method comprises the steps: monitoring the concentration change of urea and creatinine in an abdominal cavity in real time through an implantable sensor to generate a solute concentration curve, dynamically analyzing the solute permeation efficiency in combination with historical treatment data and a preset classification rule, and generating a dialysis report for guiding treatment; the abdominal retention time is adapted based on the toxin transport capacity type in the dialysis report, and the safe dose parameter is calculated by integrating the abdominal cavity accommodating volume, so that the real-time balance between the clearing efficiency and the safety is realized; furthermore, according to a clearance rate feedback data closed-loop iteration updating classification rule of the dialysis execution terminal, the problems of insufficient clearance, peritoneal high pressure and heavy manual adjustment burden caused by static parameter hysteresis in the prior art are solved. According to the method, by dynamically responding to physiological changes and a closed-loop optimization mechanism, the treatment accuracy and the long-term stability are remarkably improved.

Description

Technical Field

[0001] This invention relates to the field of peritoneal dialysis technology, specifically to an adaptive peritoneal dialysis dose optimization method, apparatus, equipment, and medium. Background Technology

[0002] Peritoneal dialysis, as an important alternative treatment for patients with end-stage renal disease, involves solute exchange between the dialysis fluid in the peritoneal cavity and the peritoneal capillaries, thus replacing the kidneys in removing metabolic waste products. Traditional treatment regimens rely on fixed dialysis doses and retention times. Physicians develop standardized plans based on static parameters such as patient weight and residual renal function, and manually adjust treatment parameters through periodic clinical monitoring. In clinical application, this method requires a balance between solute clearance efficiency and peritoneal safety, especially avoiding excessive dialysis volume leading to peritoneal hypertension or insufficient retention time resulting in inadequate clearance.

[0003] However, existing technologies have significant limitations: on the one hand, the peritoneal transport characteristics of the human body are dynamically changing due to factors such as blood glucose fluctuations and inflammatory states, and static parameters cannot respond in real time to fluctuations in the patient's physiological state; on the other hand, traditional dose adjustments rely on intermittent blood test results, which have a serious lag, causing the actual clearance rate to continuously deviate from the target value. Clinical data show that some patients experience recurrent edema or insufficient clearance due to dose mismatch, and frequent manual adjustments to the treatment plan significantly increase the medical burden. More importantly, existing methods lack a closed-loop optimization mechanism and cannot dynamically correct treatment decisions based on real-time clearance effects, resulting in insufficient long-term treatment stability. Summary of the Invention

[0004] Based on this, the purpose of the present invention is to provide an adaptive peritoneal dialysis dose optimization method, device, equipment and medium that can respond to physiological changes in real time and automatically optimize treatment parameters in a closed loop.

[0005] The objective of this invention is achieved through the following solution:

[0006] In a first aspect, the present invention provides an adaptive peritoneal dialysis dose optimization method, comprising the following steps:

[0007] S1: Real-time monitoring of changes in the concentration of urea and creatinine in the patient's peritoneal cavity using sensors implanted at the end of the peritoneal dialysis catheter, generating a solute concentration curve that changes continuously over time.

[0008] S2: Obtain the patient's historical medical data, analyze the solute permeation efficiency of urea and creatinine by combining solute concentration curves, call the preset transport capacity classification rules to determine the type of toxin transport capacity of the patient's peritoneum, and generate the patient's dialysis report.

[0009] S3: Adapt the patient's dialysis report to the retention time of the dialysis fluid in the peritoneal cavity based on the type of toxin transport capacity, and generate an optimized retention time.

[0010] S4: Combining the optimized retention time and the patient's peritoneal volume in the dialysis report, calculate the amount of dialysis fluid injected to achieve a balance between clearance efficiency and safety, generate dose optimization parameters, and transmit the optimized retention time and dose optimization parameters to the dialysis execution terminal.

[0011] S5: Based on the actual toxin removal data fed back from the dialysis execution terminal, the transport capacity classification rules are iteratively adjusted. The classification threshold and parameter weights are adjusted according to the clearance rate deviation value, and the transport capacity classification rules are updated.

[0012] In one embodiment, S2 of the adaptive peritoneal dialysis dose optimization method provided by the present invention specifically includes the following steps:

[0013] S21: Extract historical plasma data from the medical database to obtain the average plasma urea concentration and average plasma creatinine concentration of patients in recent times;

[0014] S22: Perform time series differentiation on the solute concentration curve, and use the central difference algorithm to calculate the slope of urea concentration change and creatinine concentration change at each sampling point;

[0015] S23: Perform osmotic efficiency analysis on the slope of urea concentration change and the mean plasma urea concentration, and calculate the urea osmotic efficiency coefficient.

[0016] S24: Perform osmotic efficiency analysis on the slope of creatinine concentration change and the mean plasma creatinine concentration, and calculate the creatinine osmotic efficiency coefficient.

[0017] S25: Weighted fusion of urea permeability coefficient and creatinine permeability coefficient, and arithmetic average algorithm is used to perform equal weight superposition calculation to generate average permeability coefficient.

[0018] S26: Perform translocation capacity classification processing on the average permeability coefficient, call the preset translocation capacity classification rules to match the average permeability value with the preset high, medium and low translocation threshold ranges, and determine the toxin translocation capacity type corresponding to the interval.

[0019] S27: The solute concentration curve, average osmotic efficiency coefficient, and toxin transport capacity type are integrated and processed to construct a structured medical document containing time series charts and classification results, generating a patient dialysis report. The patient dialysis report is used to guide the adjustment of dialysis protocol parameters and peritoneal function assessment.

[0020] In one embodiment, S3 of the adaptive peritoneal dialysis dose optimization method provided by the present invention specifically includes the following steps:

[0021] S31: Perform key parameter parsing on the patient's dialysis report, extract toxin transport capacity type identifiers, decode the classification result data structure, and generate transport capacity type identifiers.

[0022] S32: Dynamically scale the standard retention time, and match the scaling factor by calling the preset proportional coefficient mapping table according to the transfer capacity type identifier to generate the initially adjusted scaled retention time;

[0023] S33: Perform safety boundary constraint processing on the scaling abdominal retention time, correct time values ​​that exceed the clinical safety range to the permissible range, and generate safe constraint time values;

[0024] S34: Standardize the safety constraint time value, convert it into a protocol format recognizable by the dialysis equipment, encapsulate it as a treatment protocol parameter, and generate the final optimized retention time. The optimized retention time is used to guide the dialysis machine in setting the retention duration.

[0025] In one embodiment, S4 of the adaptive peritoneal dialysis dose optimization method provided by the present invention specifically includes the following steps:

[0026] S41: Model the theoretical injection volume based on the optimized retention time and patient dialysis reports, and use a nonlinear regression algorithm to fit the relationship curve between the dialysis fluid demand, retention time and permeability efficiency to generate the theoretical dialysis fluid injection volume.

[0027] S42: Apply a safe volume constraint between the theoretical dialysate injection volume and the peritoneal cavity volume reported in the patient's dialysis report, limiting the theoretical injection volume to a safe proportion of the peritoneal cavity volume, and generating a volume-safe baseline injection volume.

[0028] S43: Physiologically adaptively adjust the baseline injection volume, integrate feedback data from body position sensors to dynamically adjust the injection volume in real time, and generate a safe corrected injection volume;

[0029] S44: Perform parameter integration processing on the safe correction injection volume and optimized retention time to construct a two-dimensional treatment dataset containing dose and time parameters, generate dose optimization parameters, and transmit the optimized retention time and dose optimization parameters to the dialysis execution terminal. The dose optimization parameters are used to guide the dialysis execution terminal to control the injection volume.

[0030] In one embodiment, S5 of the adaptive peritoneal dialysis dose optimization method provided by the present invention specifically includes the following steps:

[0031] S51: Evaluate the removal efficiency of the actual toxin removal data fed back from the dialysis execution terminal, calculate the deviation of urea removal rate and creatinine removal rate from the preset target value, and generate a removal rate deviation index.

[0032] S52: Dynamically adjust the classification threshold for the clearance rate deviation index, optimize the judgment boundary of high-low transport type, medium transport type and high transport type according to the gradient of the degree of deviation persistence, and generate updated classification threshold parameters.

[0033] S53: The weight allocation of the permeability efficiency coefficient is dynamically rebalanced. The calculated weight ratio of urea and creatinine is redistributed according to the distribution characteristics of the deviation index to generate an optimized set of weight parameters.

[0034] S54: Reconstruct the rule system by updating the classification threshold parameters and optimizing the set of weight parameters, and integrate patient dialysis reports to generate updated transport capacity classification rules.

[0035] Secondly, the present invention provides an adaptive peritoneal dialysis dose optimization device, which is configured with the following modules:

[0036] The solute concentration monitoring module is used to monitor the changes in the concentration of urea and creatinine in the patient's peritoneal cavity in real time through a sensor implanted at the end of the peritoneal dialysis catheter, and generate a solute concentration curve that changes continuously over time.

[0037] The toxin transport capacity analysis module is used to acquire the patient's historical medical data, analyze the solute permeation efficiency of urea and creatinine by combining solute concentration curves, call the preset transport capacity classification rules to determine the type of toxin transport capacity of the patient's peritoneum, and generate the patient's dialysis report.

[0038] The retention time optimization module is used to adapt the retention time of the patient's dialysis report to the retention time of the dialysis fluid in the peritoneal cavity based on the type of toxin transport capacity, and generate an optimized retention time.

[0039] The dialysis dose calculation module is used to calculate the amount of dialysis fluid injected to balance clearance efficiency and safety by combining the optimized retention time and the patient's peritoneal volume in the dialysis report, and to generate dose optimization parameters. The optimized retention time and dose optimization parameters are then transmitted to the dialysis execution terminal.

[0040] The classification rule iterative update module is used to iteratively adjust the transport capacity classification rules based on the actual toxin removal data fed back from the dialysis execution terminal. It adjusts the classification threshold and parameter weights according to the clearance rate deviation value and updates the transport capacity classification rules.

[0041] Thirdly, this application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement any of the above-mentioned adaptive peritoneal dialysis dose optimization methods.

[0042] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described adaptive peritoneal dialysis dose optimization methods.

[0043] In summary, the adaptive peritoneal dialysis dosage optimization method provided in this application generates a continuous curve by real-time monitoring of changes in peritoneal solute concentration, achieving precise dynamic tracking of the patient's toxin clearance efficiency. By combining historical data with preset rules to analyze permeation efficiency and generate dialysis reports, it can dynamically identify changes in peritoneal transport characteristics, addressing the insufficient adaptability of traditional methods that rely on static parameters. Based on the type of toxin transport capability, it adapts the retention time to achieve individualized dynamic optimization of dialysate retention time. By calculating safe dosage parameters based on the overall peritoneal volume, it can eliminate the risk of peritoneal hypertension while ensuring clearance efficiency. Finally, it iteratively updates the classification rules based on actual clearance data, forming a closed-loop system of treatment-feedback-optimization, which continuously improves the accuracy of dosage decisions, addressing the clearance rate fluctuation problem caused by the lag in manual adjustments. This method can significantly reduce the incidence of treatment complications, improve long-term treatment stability, and reduce the decision-making burden on medical staff.

[0044] To better understand and implement this invention, the following detailed description is provided in conjunction with the accompanying drawings. Attached Figure Description

[0045] Figure 1 A flowchart illustrating an adaptive peritoneal dialysis dose optimization method provided in this application embodiment;

[0046] Figure 2 This is a schematic diagram of an adaptive peritoneal dialysis dose optimization device provided in another embodiment of this application. Detailed Implementation

[0047] To facilitate understanding of the present invention, a more complete description will be given below with reference to the accompanying drawings. Preferred embodiments of the invention are shown in the drawings. However, the invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to provide a thorough and complete understanding of the disclosure of the invention.

[0048] 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. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0049] In one embodiment, such as Figure 1 As shown, an adaptive peritoneal dialysis dose optimization method is provided. This embodiment illustrates the method's application to a terminal. It is understood that this method can also be applied to a server, or to a system including both a terminal and a server, and implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0050] S1: Real-time monitoring of changes in the concentration of urea and creatinine in the patient's peritoneal cavity using sensors implanted at the end of the peritoneal dialysis catheter, generating a solute concentration curve that changes continuously over time.

[0051] Specifically, the system acquires intraperitoneal urea and creatinine concentration data through a sensor at the tip of the peritoneal dialysis catheter. The sensor is a polyimide-encapsulated three-electrode electrochemical sensor, 8 mm in length and 2.5 mm in diameter, integrated 5 cm from the catheter tip. The working electrode is a gold-modified carbon paste electrode, the reference electrode is an Ag / AgCl electrode, and the counter electrode is made of platinum wire. The detection range covers urea 0-50 mmol / L and creatinine 0-1500 μmol / L, with detection accuracies of ±0.2 mmol / L and ±5 μmol / L, respectively. The weak 10-100 nA current signal output by the sensor is processed by a signal conditioning module built into the catheter. This module includes a low-noise amplifier and a 16-bit ADC, converting the current signal into a digital signal. The digital signal is transmitted to the control terminal via a medical-grade 433 MHz ISM band wireless transmission module, with a transmission rate of 250 kbps and a transmission delay ≤50 ms.

[0052] After receiving the data, the system can use an adaptive Kalman filter algorithm to reduce noise in the raw data, removing high-frequency interference caused by respiratory movements and abdominal peristalsis. The system collects valid data points every 30 seconds and constructs a continuous solute concentration-time curve using cubic spline interpolation, with a curve resolution of 1 Hz, to reflect the continuous change of concentration over time.

[0053] S2: Obtain the patient's historical medical data, analyze the solute permeation efficiency of urea and creatinine by combining solute concentration curves, call the preset transport capacity classification rules to determine the type of toxin transport capacity of the patient's peritoneum, and generate the patient's dialysis report.

[0054] Specifically, the system obtains the patient's historical medical data from the electronic health record system, including previous blood test results, peritoneal dialysis treatment records, etc. This data is integrated into the patient's historical dataset and combined with the currently monitored solute concentration curve.

[0055] Preferably, the system can employ statistical methods, such as multiple linear regression analysis, to analyze solute concentration curves, calculate solute permeation efficiency of urea and creatinine, and classify the patient's peritoneal toxin transport capacity based on preset transport capacity classification rules. These rules are constructed based on extensive clinical research data and cover a variety of possible peritoneal transport capacity types. The system compares the patient's solute permeation efficiency with these classification rules to determine the patient's peritoneal toxin transport capacity type and generates a detailed patient dialysis report, which includes the patient's basic information, historical data, current solute concentration curve, and transport capacity classification results.

[0056] S3: Adapt the patient's dialysis report to the retention time in the peritoneum, and adjust the retention time of the dialysate in the peritoneum based on the type of toxin transport capacity to generate an optimized retention time.

[0057] Specifically, the system performs retention time adaptation processing on the generated patient dialysis reports. Based on the patient's toxin transport capacity type, it retrieves corresponding adaptation strategies from a pre-set retention time database. These strategies are based on extensive clinical trials and simulation studies, considering the optimal retention time of dialysate in the peritoneal cavity under different transport capacity types. Specifically, the system analyzes and calculates the adaptation strategies using algorithms, combining the patient's current physiological state and treatment needs to determine the most suitable dialysate retention time, i.e., optimizing the retention time. This process involves simulating and evaluating various possible retention times, and using optimization algorithms to select the optimal time that ensures sufficient solute clearance while reducing the risk of complications.

[0058] S4: Combining the optimized retention time and the patient's peritoneal volume in the dialysis report, calculate the dialysate injection volume that balances clearance efficiency and safety, generate dose optimization parameters, and transmit the optimized retention time and dose optimization parameters to the dialysis execution terminal.

[0059] Specifically, the system calculates the dialysate injection volume by combining the optimized retention time and the patient's peritoneal cavity volume reported in the dialysis report. Preferably, the system can utilize a pre-set mathematical model that comprehensively considers individual patient differences and the requirements of international peritoneal dialysis treatment guidelines. The system uses the peritoneal cavity volume and optimized retention time as input parameters, and calculates the dialysate injection volume that balances clearance efficiency and safety through the model.

[0060] During the calculation process, the system simulates and evaluates various possible injection volumes, and selects the optimal injection volume through an optimization algorithm. The system then packages the calculated optimized retention time and dosage optimization parameters into a data packet and transmits it to the dialysis execution terminal via a communication interface. Upon receiving these parameters, the dialysis execution terminal executes the dialysis operation according to the pre-set procedure. In this way, the system achieves precise calculation and optimization of the dialysate injection volume, ensuring improved treatment outcomes.

[0061] S5: Based on the actual toxin removal data fed back from the dialysis execution terminal, the transport capacity classification rules are iteratively adjusted. The classification threshold and parameter weights are adjusted according to the clearance rate deviation value, and the transport capacity classification rules are updated.

[0062] Specifically, the system receives clearance data sent by the terminal, including indicators such as the actual clearance rate of urea and creatinine, compares this feedback data with preset transport capacity classification rules, calculates clearance rate deviation values, and adjusts classification thresholds and parameter weights according to the direction and magnitude of the deviation values.

[0063] Preferably, the system can update the classification rules through algorithm optimization to more accurately reflect the patient's actual condition, and store the updated classification rules in the database to provide a more accurate basis for subsequent patient classification. In this way, the system achieves continuous optimization of the transport capacity classification rules, improving the accuracy and adaptability of the system in classifying patients' peritoneal transport capacity.

[0064] In summary, the adaptive peritoneal dialysis dosage optimization method provided in this application generates a continuous curve by real-time monitoring of changes in peritoneal solute concentration, achieving precise dynamic tracking of the patient's toxin clearance efficiency. By combining historical data with preset rules to analyze permeation efficiency and generate dialysis reports, it can dynamically identify changes in peritoneal transport characteristics, addressing the insufficient adaptability of traditional methods that rely on static parameters. Based on the type of toxin transport capability, it adapts the retention time to achieve individualized dynamic optimization of dialysate retention time. By calculating safe dosage parameters based on the overall peritoneal volume, it can eliminate the risk of peritoneal hypertension while ensuring clearance efficiency. Finally, it iteratively updates the classification rules based on actual clearance data, forming a closed-loop system of treatment-feedback-optimization, which continuously improves the accuracy of dosage decisions, addressing the clearance rate fluctuation problem caused by the lag in manual adjustments. This method can significantly reduce the incidence of treatment complications, improve long-term treatment stability, and reduce the decision-making burden on medical staff.

[0065] In one embodiment, S2 of the adaptive peritoneal dialysis dose optimization method provided by the present invention specifically includes the following steps:

[0066] S21: Extract historical plasma data from the medical database to obtain the recent average plasma urea concentration and average plasma creatinine concentration of patients.

[0067] Specifically, the system queries data through a standardized medical database interface that follows the HL7 FHIR protocol. Query fields include the patient's unique identifier, test date, plasma urea concentration, and plasma creatinine concentration. The system is set to query records where the test date is within 30 days of the current date, and extracts all records meeting this condition. The system then performs outlier detection on the extracted plasma urea and creatinine concentration values ​​using the interquartile range (ICM) method. The calculation formula is as follows:

[0068] Upper bound = Q3 + 1.5*(Q3 - Q1)

[0069] Lower bound=Q1-1.5*(Q3-Q1)

[0070] Where Q1 is the first quartile and Q3 is the third quartile, values ​​exceeding the upper or lower bounds are marked as outliers and removed. The system counts the number of remaining valid data points. If the number of valid data points is less than 3, the query time range is automatically extended to 60 days, and the query and filtering process is repeated until the number of valid data points is ≥ 3. The system calculates the arithmetic mean of the valid data. The formula for calculating the mean plasma urea concentration is:

[0071]

[0072] in, C represents the mean plasma urea concentration. urea,i Let n be the plasma urea concentration value from the i-th test, and n be the number of valid data points; the formula for calculating the mean plasma creatinine concentration is:

[0073]

[0074] in, C represents the mean plasma creatinine concentration. cr,i This represents the plasma creatinine concentration from the i-th test. The calculation results are rounded to two decimal places, with units of mmol / L and μmol / L respectively. The data is stored in the system-specified patient data directory in CSV format, with the filename containing the patient's unique identifier and the data extraction timestamp.

[0075] S22: Perform time series differentiation on the solute concentration curve, and use the central difference algorithm to calculate the slope of urea concentration change and creatinine concentration change at each sampling point.

[0076] Specifically, the system reads a solute concentration curve data file containing time series data for urea and creatinine concentrations. Each sequence consists of a timestamp and a corresponding concentration value, with timestamps spaced 30 seconds apart. The system then parses each sequence, converting the timestamps into second-level time values ​​(t) relative to the start of dialysis. j (j = 1, 2, ..., m, where m is the total number of data points), and the concentration values ​​are denoted as C. urea,j (urea concentration) and C cr,j (Cretin concentration). Preferably, the system can use the central difference algorithm to calculate the slope of concentration change at each sampling point. For sampling points where 2 ≤ j ≤ m-1, the formula for calculating the slope of urea concentration change is:

[0077]

[0078] Where, k urea,j Let C be the slope of the urea concentration change at point j. urea,j+1 C urea,j-1 The urea concentration values ​​at point j+1 and point j-1 are respectively, t j+1 t j-1 These are the time values ​​at the corresponding points; the formula for calculating the slope of creatinine concentration change is:

[0079]

[0080] Where, k cr,j Let be the slope of the creatinine concentration change at point j. For the first point (j=1), forward difference is used:

[0081]

[0082] For the tail point (j = m), backward difference is used:

[0083]

[0084] The calculated slope values ​​are in units of mmol / (L·s) and μmol / (L·s). The system converts them to mmol / (L·min) and μmol / (L·min) and stores them as a two-dimensional array, with the first column being the time value and the second column being the slope value.

[0085] S23: Perform osmotic efficiency analysis on the slope of urea concentration change and the mean plasma urea concentration, and calculate the urea osmotic efficiency coefficient.

[0086] Specifically, the system calls the average plasma urea concentration. The system first divides the slope array of urea concentration changes into time intervals based on the duration of abdominal retention, using t = 0, 3600, 7200, ... seconds (i.e., per hour) as interval boundaries, resulting in n intervals (n being the total number of hours of abdominal retention). For the i-th interval (i = 1, 2, ..., n), the system extracts all slope values ​​k within that interval. urea,j Calculate the average slope of the interval:

[0087]

[0088] Among them, I i Let N be the set of indices of the data points contained in the i-th interval. i This represents the number of data points in that interval. Let be the average slope of the urea concentration change in the i-th interval (unit: mmol / (L·min)). The system calculates the urea permeability coefficient for the i-th interval:

[0089]

[0090] Where, η urea,i Urea permeability coefficient for the i-th interval (unit: min) -1 ), This represents the mean plasma urea concentration (unit: mmol / L). The system calculates the arithmetic mean of the urea osmotic efficiency coefficient for all intervals:

[0091]

[0092] Where, η urea The overall urea permeability efficiency coefficient is calculated, and the result is stored to four decimal places in the system temporary data file.

[0093] S24: Perform osmotic efficiency analysis on the slope of creatinine concentration change and the mean plasma creatinine concentration, and calculate the creatinine osmotic efficiency coefficient.

[0094] Specifically, the average plasma creatinine concentration generated by the system call The same calculation process as S23 is performed on the creatinine concentration change slope array. The system divides the creatinine concentration change slope array into n intervals, with each hour of abdominal retention time as the interval unit. For the i-th interval, the average slope of creatinine concentration change within that interval is calculated:

[0095]

[0096] Among them, I i Let N be the set of indices of the data points contained in the i-th interval. i This represents the number of data points in that interval. Let be the average slope of creatinine concentration change in the i-th interval (unit: μmol / (L·min)). The system calculates the creatinine osmotic efficiency coefficient in the i-th interval using the formula:

[0097]

[0098] Where, η cr,i The creatinine permeability coefficient for the i-th interval (unit: min) -1 ), This represents the mean plasma creatinine concentration (unit: μmol / L). The system calculates the arithmetic mean of the results for all intervals.

[0099]

[0100] Where, η cr The overall creatinine permeability efficiency coefficient is retained to four decimal places and stored in the system temporary data file. The file path is the same as the temporary file generated by S23, and they are distinguished by different fields.

[0101] S25: Weighted fusion of urea permeability coefficient and creatinine permeability coefficient, and arithmetic average algorithm is called to perform equal weight superposition calculation to generate average permeability coefficient.

[0102] Specifically, the system reads the urea permeability coefficient η from the temporary data file. urea and creatinine permeability coefficient η cr Perform equal-weighted superposition calculation. The calculation formula is:

[0103]

[0104] Where, η avg Average permeability coefficient (unit: min) -1 ), η urea The overall urea permeability coefficient (unit: min) -1 ), η cr Overall creatinine permeability coefficient (unit: min) -1 The system performs a validity check on the calculation results. If η avg If the value is less than 0, the result is marked as invalid, and the invalidity reason code "NEGATIVE_VALUE" is recorded. The system triggers a recalculation process, during which interval data that causes a negative slope are removed, i.e., when kˉurea,i<0 or ... If the interval is excluded from the calculation, η is recalculated using the data from the remaining interval. urea η cr and η avgIf the recalculated result is ≥0, it is considered valid, retained to four decimal places, and stored in the system result database.

[0105] S26: Perform translocation capacity classification processing on the average permeability coefficient, call the preset translocation capacity classification rules to match the average permeability value with the preset high, medium and low translocation threshold ranges, and determine the toxin translocation capacity type corresponding to the interval.

[0106] Specifically, the system reads η from the results database. avg The system invokes preset transshipment capacity classification rules, which are stored in the system configuration file as key-value pairs. These rules include the upper limit of the high transshipment threshold "high_threshold = 0.015", the lower limit of the medium transshipment threshold "mid_low = 0.008", the upper limit of the medium transshipment threshold "mid_high = 0.015", and the lower limit of the low transshipment threshold "low_threshold = 0.008". The system then performs a conditional judgment: when η... avg When η > 0.015 min⁻¹, the toxin transport capacity type is determined to be high transport type; when η ≤ 0.008 min⁻¹ avg When η ≤ 0.015 min⁻¹, it is determined to be a transit type; when η avg When η < 0.008 min⁻¹, it is determined to be a low-transporter type. avg Equal to 0.015min -1 The system classifies it as a high-transport type if it equals 0.008 min⁻¹; otherwise, it is classified as a medium-transport type. The system will assign η... avg The system is associated with the corresponding toxin transport capability type and stored in JSON format, containing the fields “average_efficiency”, “transport_type”, and “classification_time”, where “classification_time” is the timestamp of the system performing the classification operation.

[0107] S27: The solute concentration curve, average osmotic efficiency coefficient, and toxin transport capacity type are integrated and processed to construct a structured medical document containing time series charts and classification results, generating a patient dialysis report. The patient dialysis report is used to guide the adjustment of dialysis protocol parameters and peritoneal function assessment.

[0108] Specifically, the system calls the solute concentration curve data, η avgThe system retrieves toxin transport capacity types and related data, and performs report integration. A structured medical document is generated, with the time-series chart area at the beginning, containing two sub-charts: a urea concentration-time curve and a creatinine concentration-time curve. The horizontal axis represents the retention time (in hours), and the vertical axis represents the concentration values ​​(in mmol / L and μmol / L). The curves are drawn with solid black lines, and the slope values ​​for each hourly interval are marked in red at the corresponding interval's endpoint. The numerical analysis area is located below the chart area, presenting data in tabular form. The table includes rows for mean plasma urea concentration, mean plasma creatinine concentration, urea osmotic efficiency coefficient, creatinine osmotic efficiency coefficient, average osmotic efficiency coefficient, and toxin transport capacity type, with corresponding columns for specific values ​​and units. The conclusion and recommendation section is located at the end of the document. The content consists of fixed text descriptions based on the toxin transport capacity type. The text for high transport capacity is "It is recommended to shorten the retention time and use low-concentration glucose dialysate"; the text for medium transport capacity is "Maintain the standard retention time and use medium-concentration glucose dialysate"; and the text for low transport capacity is "It is recommended to extend the retention time and use high-concentration glucose dialysate".

[0109] The system generates filenames in the format "Patient ID_YYYYMMDD_RXXXX" (where YYYYMMDD is the dialysis date and RXXXX is the report number, an auto-incrementing sequence), and stores the documents in the specified directory of the medical database.

[0110] In one embodiment, S3 of the adaptive peritoneal dialysis dose optimization method provided by the present invention specifically includes the following steps:

[0111] S31: Perform key parameter parsing on the patient's dialysis report, extract the toxin transport capacity type identifier, decode the classification result data structure, and generate the transport capacity type identifier.

[0112] Specifically, the system calls the file reading interface of the patient's dialysis report and locates the storage area of ​​key parameters by parsing the tag fields of the structured medical document. The system uses a document object model parser to perform syntactic analysis on the report and identify nodes containing information on toxin transport capability type. These nodes are named with preset tags in the document, and the tag format follows medical information exchange standards.

[0113] The system extracts the identifier string from the node, which consists of a combination of letters and numbers. This string is then converted into a recognizable classification result data structure using a preset decoding algorithm. During decoding, the system verifies the integrity of the data structure, checking for necessary fields such as type definition, classification criteria, and associated parameters. If any fields are missing, an error message is returned and the current step is terminated. After decoding, the system generates a corresponding transport capability type identifier. This identifier is stored as an enumeration type, containing symbols that correspond one-to-one with the classification results. It is stored in a temporary parameter cache, and the parsing time and data verification results are recorded.

[0114] S32: Dynamically scale the standard retention time by calling a preset proportional coefficient mapping table to match the scaling coefficient based on the transfer capacity type identifier, and generate a preliminary adjusted scaled retention time.

[0115] Specifically, the system retrieves the baseline data of the standard retention time from the storage area. This data exists in the form of time parameters, including the start marker and duration definition. It also reads the transfer capacity type identifier and retrieves the preset scaling factor mapping table based on the identifier content. This mapping table is stored in the system configuration file and adopts a key-value pair structure. The key is the symbolic representation of the transfer capacity type identifier, and the value is the corresponding scaling factor.

[0116] Preferably, the system can quickly locate the scaling factor matching the current identifier using a hash algorithm, and then calculate the scaling factor by multiplying the baseline data of the standard retention time by the scaling factor to generate a preliminary adjusted scaling retention time. During the calculation process, the system records a coefficient call log, including the matching identifier content, the index position of the corresponding coefficient, and the start and end times of the calculation. The log information is stored in text format in the operation record directory.

[0117] S33: Perform safety boundary constraint processing on the scaling abdominal retention time, correct time values ​​that exceed the clinical safety range to the permissible range, and generate safe constraint time values.

[0118] Specifically, the system retrieves the numerical information of the scaled retention time and simultaneously reads the clinically safe range definition of retention time from the clinical parameter database. This definition includes descriptive constraints of upper and lower limits, based on clinical practice guidelines. The system compares the scaled retention time with the safe range, checking whether it falls within the interval defined by the upper and lower limits. If the scaled retention time exceeds the upper limit, the system corrects it to the time value corresponding to the upper limit; if it falls below the lower limit, it corrects it to the time value corresponding to the lower limit; if it falls within the range, it remains unchanged.

[0119] During the correction process, the system generates a deviation record, which records the time value before correction, the direction of deviation, and the basis for correction. This record is stored in association with the corrected safety constraint time value, and the storage format adopts the standard structure of a time series database.

[0120] S34: Standardize the safety constraint time value, convert it into a protocol format recognizable by the dialysis equipment, encapsulate it as a treatment protocol parameter, and generate the final optimized retention time. The optimized retention time is used to guide the dialysis machine in setting the retention duration.

[0121] Specifically, the system acquires the internal representation of the safety constraint time value, which includes the time unit and numerical encoding method. Preferably, the system activates a parameter standardization module, which contains conversion rules for the dialysis equipment protocol format. These rules define the field length, data type, and checksum generation method for the time value. Specifically, the system converts the safety constraint time value into a byte stream that conforms to the protocol requirements, according to the rules. The byte stream contains the various components of the time information, and the position and length of each component are determined by the protocol specification.

[0122] After conversion, the system encapsulates the byte stream, adding protocol header and trailer identifiers. The header contains the device address and parameter type, and the trailer contains verification information, forming complete treatment protocol parameters. The system stores these parameters in the output buffer, generating the final optimized retention time, and simultaneously records the protocol version and format verification results during the conversion process. This optimized retention time can be read by the dialysis device through the data interface to guide the device in setting the retention duration.

[0123] In one embodiment, S4 of the adaptive peritoneal dialysis dose optimization method provided by the present invention specifically includes the following steps:

[0124] S41: Model the theoretical injection volume based on the optimized retention time and patient dialysis reports, and use a nonlinear regression algorithm to fit the relationship curve between the dialysate demand, retention time and osmotic efficiency to generate the theoretical dialysate injection volume.

[0125] Specifically, the system extracts the average permeability coefficient and related time-series data from patient dialysis reports, using the optimized retention time as one of the independent variables, which, together with the permeability coefficient, constitute the modeling input features. The system invokes a pre-defined nonlinear regression algorithm, trained on historical treatment data, which is a neural network structure comprising an input layer, hidden layers, and an output layer. The input layer receives the retention time and permeability coefficient, the hidden layer processes features through an activation function, and the output layer outputs the corresponding predicted dialysate demand. The system uses this algorithm to fit the input features, generating a curve showing the relationship between dialysate demand, retention time, and permeability. The curve is stored as a set of data points, with each data point containing the corresponding time, permeability coefficient, and demand. Based on the optimized retention time and the current permeability coefficient, the system extracts the corresponding demand from the relationship curve as the theoretical dialysate injection volume and stores it in a temporary parameter buffer.

[0126] S42: Apply a safe capacity constraint to the theoretical dialysate injection volume and the peritoneal cavity volume reported in the patient's dialysis report, limiting the theoretical injection volume to a safe proportion of the peritoneal cavity volume, and generating a volume-safe baseline injection volume.

[0127] Specifically, the system extracts peritoneal cavity volume data from the patient's dialysis report. This data represents the maximum safe peritoneal cavity capacity calculated by the system through prior testing. Preferably, the system calls a preset safety ratio range parameter, which is a percentage range of the peritoneal cavity volume determined by clinical safety standards and stored in the system configuration file. The system calculates the ratio between the theoretical dialysate injection volume and the peritoneal cavity volume to obtain the percentage of the theoretical injection volume to the peritoneal cavity volume. If this percentage is within the safe ratio range, the theoretical injection volume is directly used as the baseline injection volume. If it exceeds the upper limit, a correction value is calculated based on the product of the upper limit of the safe ratio and the peritoneal cavity volume, replacing the theoretical injection volume as the baseline injection volume. If it is below the lower limit, a correction value is calculated based on the product of the lower limit of the safe ratio and the peritoneal cavity volume. The system records the ratio calculation results and the correction process, forming a capacity constraint log, which is stored in the system's treatment parameter adjustment record database.

[0128] S43: Physiologically adaptively adjust the baseline injection volume, integrate feedback data from body position sensors to dynamically adjust the injection volume in real time, and generate a safe corrected injection volume.

[0129] Specifically, the system receives the baseline injection volume and simultaneously acquires feedback data from the patient's position sensor via an interface. This data is a quantified value of the patient's current position, including positional indicators such as supine, lateral, and sitting, along with corresponding angle parameters. Preferably, the system can invoke a position-injection volume correction model, which is a preset mapping table storing injection volume correction coefficients corresponding to different positional states.

[0130] The system matches the corresponding correction coefficient based on the body position indicator fed back by the body position sensor, and multiplies the baseline injection volume by the correction coefficient to obtain the initial corrected injection volume. The system monitors changes in body position sensor data in real time. If the body position changes, the correction coefficient is rematched and the injection volume is updated to ensure that the injection volume is adjusted in real time according to changes in body position. The final generated safe corrected injection volume is stored in the dynamic parameter buffer, overwriting the original baseline injection volume data.

[0131] S44: Perform parameter integration processing on the safe correction injection volume and optimized retention time to construct a two-dimensional treatment dataset containing dose and time parameters, generate dose optimization parameters, and transmit the optimized retention time and dose optimization parameters to the dialysis execution terminal. The dose optimization parameters are used to guide the dialysis execution terminal to control the injection volume.

[0132] Specifically, the system extracts the safety correction injection amount from the dynamic parameter buffer and calls the optimized retention time to construct a two-dimensional treatment dataset. This dataset contains two data dimensions: one dimension is the dose parameter, which includes the safety correction injection amount and related unit identifiers; the other dimension is the time parameter, which includes the optimized retention time and the corresponding time unit.

[0133] Specifically, the system performs format standardization on the dataset, converting it into a preset structured data format. This format includes field identifiers, data types, and check codes to ensure data integrity and consistency. The structured dataset is then defined as dose optimization parameters and stored in the output parameter area.

[0134] The system establishes a connection with the dialysis execution terminal via a communication interface. It sends optimized retention time and dosage optimization parameters to the dialysis execution terminal using a preset transmission protocol, and encrypts the data during transmission to ensure security. Upon receiving the data, the dialysis execution terminal controls the dialysate injection volume based on the dosage optimization parameters and controls the retention time of the dialysate in the peritoneal cavity based on the optimized retention time.

[0135] In one embodiment, S5 of the adaptive peritoneal dialysis dose optimization method provided by the present invention specifically includes the following steps:

[0136] S51: Evaluate the removal efficiency of the actual toxin removal data fed back from the dialysis execution terminal, calculate the deviation of urea removal rate and creatinine removal rate from the preset target values, and generate a removal rate deviation index.

[0137] Specifically, the system receives actual toxin clearance data from the dialysis execution terminal, including the actual urea clearance rate, the actual creatinine clearance rate, and the corresponding detection timestamp. The system retrieves target values ​​for urea clearance rate and creatinine clearance rate from a preset parameter library. These target values ​​are determined based on the patient's weight, residual renal function, and treatment stage, and are stored as numerical data with units. The system calculates the deviation of the urea clearance rate: the difference between the actual urea clearance rate and the target value is divided by the target value to obtain the relative deviation of the urea clearance rate; the relative deviation of the creatinine clearance rate is calculated using the same method.

[0138] The system standardizes the two deviation levels, converts them to absolute values, and then calculates the overall clearance rate deviation index using an arithmetic mean, retaining the result to three decimal places. The system associates and stores the clearance rate deviation index with the corresponding actual clearance rate, target value, and calculation timestamp to form a clearance efficiency evaluation record, which is then stored in the deviation analysis database.

[0139] S52: Perform dynamic adjustment of classification thresholds on the clearance rate deviation index, optimize the judgment boundaries of high and low transport types, medium transport type and high transport type according to the gradient of deviation persistence, and generate updated classification threshold parameters.

[0140] Specifically, the system extracts the clearance rate deviation index and divides it into continuous monitoring periods according to the time series. Each period is 24 hours. The system counts the duration of the deviation index within each period. When the absolute value of the deviation index exceeds the preset deviation threshold and the duration reaches the set number of periods, the classification threshold adjustment process is triggered.

[0141] Specifically, the system calls the currently effective classification threshold parameters for transshipment capacity. These parameters include a lower limit for high transshipment types, upper and lower limits for medium transshipment types, and an upper limit for low transshipment types. Based on the persistence of the deviation, the system performs gradient optimization on the thresholds: if the deviation corresponding to the high transshipment type judgment result is consistently positive, the lower limit for high transshipment types is increased; if the deviation corresponding to the medium transshipment type judgment result is consistently negative, the range for medium transshipment types is expanded; if the deviation corresponding to the low transshipment type judgment result is consistently positive, the upper limit for low transshipment types is decreased. The adjustment magnitude is positively correlated with the duration of the deviation. After each adjustment, updated classification threshold parameters are generated, with the parameter format consistent with the original thresholds, including boundary values ​​and units for each type, and stored in the threshold parameter buffer.

[0142] S53: The weight allocation of the permeability efficiency coefficient is dynamically rebalanced. The calculated weight ratio of urea and creatinine is redistributed according to the distribution characteristics of the deviation index to generate an optimized set of weight parameters.

[0143] Specifically, the system analyzes the distribution characteristics of deviation indicators, uses histograms to statistically analyze the frequency of occurrence of deviation indicators in different intervals, and determines the correlation between the main sources of deviation and urea or creatinine clearance rates. The system extracts the weight ratios of the current urea permeability efficiency coefficient and creatinine permeability efficiency coefficient from the parameter configuration library, initially setting these ratios to be equal. If the fluctuation range of the urea clearance rate deviation indicator is greater than that of the creatinine clearance rate deviation indicator, the system increases the weight ratio of the urea permeability efficiency coefficient while decreasing the weight ratio of the creatinine permeability efficiency coefficient; conversely, it increases the weight ratio of the creatinine permeability efficiency coefficient. Weight adjustments are achieved through proportional coefficients, and the sum of the two weights remains 1 after adjustment. The adjustment range is determined based on the variance ratio of the deviation indicators. The system stores the adjusted weight ratios as an optimized weight parameter set, including the urea weight coefficient and the creatinine weight coefficient, rounded to two decimal places, and stores it in the weight parameter database.

[0144] S54: Reconstruct the rule system by updating the classification threshold parameters and optimizing the set of weight parameters, and integrate patient dialysis reports to generate updated transport capacity classification rules.

[0145] Specifically, the system retrieves the updated classification threshold parameters from the threshold parameter buffer and the optimized set of weight parameters from the weight parameter database. The system reads historical classification results, permeability efficiency coefficients, and corresponding clearance rate data from patient dialysis reports as a reference for rule reconstruction.

[0146] Preferably, the system substitutes the updated classification threshold parameters into the transport capacity classification logic, replacing the original thresholds; it then applies the optimized set of weight parameters to the weighted calculation process of the permeability efficiency coefficient, updating the calculation formula for the average permeability efficiency coefficient. The system ensures the internal consistency of the new rule system through logical verification, including the continuity of threshold ranges, the rationality of weight ratios, and compatibility with historical data. After successful verification, the system integrates the latest clinical data from patient dialysis reports to generate updated transport capacity classification rules. These rules are stored in a structured data format, containing classification logic expressions, threshold parameters, weight parameters, and an effective timestamp, while also overwriting the original rules' storage location in the system's rule base.

[0147] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0148] Based on the same inventive concept, this application also provides an adaptive peritoneal dialysis dose optimization device for implementing the adaptive peritoneal dialysis dose optimization method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more embodiments of the adaptive peritoneal dialysis dose optimization device provided below can be found in the limitations of the adaptive peritoneal dialysis dose optimization method described above, and will not be repeated here.

[0149] Preferably, such as Figure 2 As shown, the present invention provides an adaptive peritoneal dialysis dose optimization device 600, which is configured with the following modules:

[0150] The solute concentration monitoring module 610 is used to monitor the changes in the concentration of urea and creatinine in the patient's peritoneal cavity in real time through a sensor implanted at the end of the peritoneal dialysis catheter, and generate a solute concentration curve that changes continuously over time.

[0151] The toxin transport capacity analysis module 620 is used to acquire the patient's historical medical data, analyze the solute permeation efficiency of urea and creatinine by combining solute concentration curves, call the preset transport capacity classification rules to determine the type of toxin transport capacity of the patient's peritoneum, and generate a patient dialysis report.

[0152] The retention time optimization module 630 is used to adapt the retention time of the patient's dialysis report to the retention time of the dialysis fluid in the peritoneal cavity based on the type of toxin transport capacity, and generate an optimized retention time.

[0153] The dialysis dose calculation module 640 is used to calculate the amount of dialysis fluid injected to achieve a balance between clearance efficiency and safety by combining the optimized retention time and the patient's peritoneal volume in the dialysis report, and to generate dose optimization parameters. The optimized retention time and dose optimization parameters are then transmitted to the dialysis execution terminal.

[0154] The classification rule iterative update module 650 is used to iteratively adjust the transport capacity classification rules based on the actual toxin removal data fed back from the dialysis execution terminal, and to adjust the classification threshold and parameter weights according to the clearance rate deviation value to update the transport capacity classification rules.

[0155] Preferably, the toxin transport capacity analysis module 620 provided in this application is configured with the following units:

[0156] The historical plasma data extraction unit is used to extract historical plasma data from the medical database to obtain the average plasma urea concentration and average plasma creatinine concentration of patients in recent times.

[0157] The concentration change slope calculation unit is used to perform time series differentiation processing on the solute concentration curve and to calculate the urea concentration change slope and creatinine concentration change slope at each sampling point using the central difference algorithm.

[0158] The urea permeability analysis unit is used to analyze the permeability efficiency of the slope of urea concentration change and the mean plasma urea concentration, and to calculate the urea permeability efficiency coefficient.

[0159] The creatinine permeability analysis unit is used to perform permeability analysis on the slope of creatinine concentration change and the mean plasma creatinine concentration, and to calculate and generate the creatinine permeability coefficient.

[0160] The permeability efficiency coefficient fusion unit is used to weight and fuse the urea permeability efficiency coefficient and the creatinine permeability efficiency coefficient, and call the arithmetic average algorithm to perform equal weight superposition calculation to generate the average permeability efficiency coefficient.

[0161] The transshipment capacity type matching unit is used to classify the average permeability coefficient into transshipment capacity types. It calls the preset transshipment capacity classification rules to match the average permeability value with the preset high, medium and low transshipment threshold ranges to determine the toxin transshipment capacity type corresponding to the interval.

[0162] The dialysis report integration and generation unit is used to integrate reports on solute concentration curves, average osmotic efficiency coefficients, and toxin transport capacity types, construct structured medical documents containing time-series charts and classification results, and generate patient dialysis reports. These patient dialysis reports are used to guide the adjustment of dialysis protocol parameters and peritoneal function assessment.

[0163] Preferably, the abdominal retention time optimization module 630 provided in this application is configured with the following units:

[0164] The transport capacity identifier parsing unit is used to parse key parameters of patient dialysis reports, extract toxin transport capacity type identifiers, decode the classification result data structure, and generate transport capacity type identifiers.

[0165] The dynamic scaling unit for retention time is used to dynamically scale the standard retention time. It calls a preset proportional coefficient mapping table to match the scaling coefficient based on the transfer capacity type identifier and generates a preliminary adjusted scaled retention time.

[0166] The safety boundary constraint unit is used to perform safety boundary constraint processing on the scaling abdominal retention time, correcting time values ​​that exceed the clinical safety range to the permissible range, and generating safety constraint time values.

[0167] The retention time standardization unit is used to standardize the safety constraint time value, convert it into a protocol format that the dialysis equipment can recognize, encapsulate it into treatment protocol parameters, and generate the final optimized retention time. The optimized retention time is used to guide the dialysis machine in setting the retention duration.

[0168] Preferably, the dialysis dose calculation module 640 provided in this application is configured with the following units:

[0169] The theoretical injection volume modeling unit is used to model the theoretical injection volume based on the optimized retention time and patient dialysis reports. It calls a nonlinear regression algorithm to fit the relationship curve between the dialysate demand, retention time and permeability efficiency, and generates the theoretical dialysate injection volume.

[0170] The safety capacity constraint unit is used to constrain the theoretical dialysate injection volume with the peritoneal cavity volume reported in the patient's dialysis report, limiting the theoretical injection volume to a safe proportion of the peritoneal cavity volume and generating a volume-safe baseline injection volume.

[0171] The physiological adaptation correction unit is used to make physiological adaptation corrections to the baseline injection volume, integrates feedback data from the body position sensor to make real-time dynamic adjustments to the injection volume, and generates a safe correction injection volume.

[0172] The treatment parameter integration unit is used to integrate parameters for safe correction injection volume and optimized retention time, construct a two-dimensional treatment dataset containing dose and time parameters, generate dose optimization parameters, and transmit the optimized retention time and dose optimization parameters to the dialysis execution terminal. The dose optimization parameters are used to guide the dialysis execution terminal to control the injection volume.

[0173] Preferably, the classification rule iterative update module 650 provided in this application is configured with the following units:

[0174] The toxin removal efficiency evaluation unit is used to evaluate the actual toxin removal data fed back from the dialysis execution terminal, calculate the deviation of urea removal rate and creatinine removal rate from the preset target value, and generate a removal rate deviation index.

[0175] The classification threshold adjustment unit is used to dynamically adjust the classification threshold of the clearance rate deviation index. It optimizes the judgment boundary of high, medium and low transport types according to the gradient of the degree of deviation persistence and generates updated classification threshold parameters.

[0176] The weighted dynamic balancing unit is used to dynamically rebalance the weight allocation of the permeability efficiency coefficient. It reallocates the calculated weight ratio of urea and creatinine according to the distribution characteristics of the deviation index, and generates an optimized set of weight parameters.

[0177] The rule system reconstruction unit is used to reconstruct the rule system based on the updated classification threshold parameters and the optimized set of weight parameters, and to integrate patient dialysis reports to generate updated transport capacity classification rules.

[0178] In one embodiment, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-described adaptive peritoneal dialysis dose optimization method.

[0179] In one embodiment, this application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described adaptive peritoneal dialysis dose optimization method.

[0180] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of those different embodiments or examples.

[0181] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The components described as separate parts may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this disclosure according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0182] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various variations or substitutions within the technical scope disclosed in this application, and these should all be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. An adaptive peritoneal dialysis dosage optimization method, characterized in that, Includes the following steps: S1: Real-time monitoring of changes in the concentration of urea and creatinine in the patient's peritoneal cavity using sensors implanted at the end of the peritoneal dialysis catheter, generating a solute concentration curve that changes continuously over time. S2: Obtain the patient's historical medical data, analyze the solute permeation efficiency of urea and creatinine in conjunction with the solute concentration curve, call the preset transport capacity classification rules to determine the type of toxin transport capacity of the patient's peritoneum, and generate a patient dialysis report. S3: Perform retention time adaptation processing on the patient's dialysis report, adjust the retention time of dialysate in the peritoneal cavity based on the toxin transport capacity type, and generate an optimized retention time. S4: Combining the optimized retention time and the patient's peritoneal volume in the patient's dialysis report, calculate the dialysis fluid injection volume that satisfies the balance between clearance efficiency and safety, generate dose optimization parameters, and transmit the optimized retention time and dose optimization parameters to the dialysis execution terminal. S5: Based on the actual toxin removal data fed back from the dialysis execution terminal, the transport capacity classification rules are iteratively adjusted, and the classification threshold and parameter weights are adjusted according to the clearance rate deviation value to update the transport capacity classification rules.

2. The method according to claim 1, characterized in that, S2 includes: S21: Extract historical plasma data from the medical database to obtain the average plasma urea concentration and average plasma creatinine concentration of patients in recent times; S22: Perform time series differentiation processing on the solute concentration curve, and use the central difference algorithm to calculate the slope of urea concentration change and creatinine concentration change at each sampling point; S23: Perform osmotic efficiency analysis on the slope of the urea concentration change and the mean plasma urea concentration, and calculate the urea osmotic efficiency coefficient; S24: Perform osmotic efficiency analysis on the slope of the change in creatinine concentration and the mean value of plasma creatinine concentration, and calculate and generate the creatinine osmotic efficiency coefficient. S25: The urea permeability efficiency coefficient and the creatinine permeability efficiency coefficient are weighted and fused, and the arithmetic average algorithm is called to perform equal weight superposition calculation to generate the average permeability efficiency coefficient. S26: Perform translocation capacity classification processing on the average permeability coefficient, call the preset translocation capacity classification rules to match the average permeability value with the preset high, medium and low translocation threshold ranges, and determine the toxin translocation capacity type corresponding to the interval. S27: The solute concentration curve, the average osmotic efficiency coefficient, and the toxin transport capacity type are integrated and processed to construct a structured medical document containing time series charts and classification results, and a patient dialysis report is generated. The patient dialysis report is used to guide the adjustment of dialysis protocol parameters and peritoneal function assessment.

3. The method according to claim 1, characterized in that, S3 includes: S31: Perform key parameter parsing on the patient's dialysis report, extract toxin transport capacity type identifiers, decode the classification result data structure, and generate transport capacity type identifiers. S32: Dynamically scale the standard retention time by calling a preset proportional coefficient mapping table to match the scaling coefficient according to the transfer capacity type identifier, and generating a preliminary adjusted scaled retention time. S33: Perform safety boundary constraint processing on the scaled abdominal retention time, correct time values ​​that exceed the clinical safety range to the permissible range, and generate safety constraint time values; S34: The safety constraint time value is standardized and converted into a protocol format recognizable by the dialysis equipment, encapsulated as a treatment protocol parameter, and the final optimized retention time is generated. The optimized retention time is used to guide the dialysis machine in setting the retention time.

4. The method according to claim 1, characterized in that, S4 includes: S41: Model the theoretical injection volume based on the optimized retention time and the patient's dialysis report, and use a nonlinear regression algorithm to fit the relationship curve between the dialysis fluid demand, retention time and permeability efficiency to generate the theoretical dialysis fluid injection volume. S42: Apply a safe capacity constraint to the theoretical dialysis fluid injection volume and the peritoneal cavity volume reported in the patient's dialysis report, limiting the theoretical injection volume to a safe proportion of the peritoneal cavity volume to generate a volume-safe basic injection volume. S43: The basic injection volume is physiologically adapted and adjusted, and the injection volume is dynamically adjusted in real time by integrating feedback data from the body position sensor to generate a safe and corrected injection volume. S44: Perform parameter integration processing on the safe correction injection volume and the optimized retention time to construct a two-dimensional treatment dataset containing dose parameters and time parameters, generate dose optimization parameters, and transmit the optimized retention time and dose optimization parameters to the dialysis execution terminal. The dose optimization parameters are used to guide the dialysis execution terminal to control the injection volume.

5. The method according to any one of claims 1-4, characterized in that, S5 includes: S51: Evaluate the removal efficiency of the actual toxin removal data fed back from the dialysis execution terminal, calculate the deviation of urea removal rate and creatinine removal rate from the preset target value, and generate a removal rate deviation index. S52: Perform dynamic adjustment of the classification threshold on the clearance rate deviation index, optimize the judgment boundary of high and low transport type, medium transport type and high transport type according to the gradient of deviation persistence, and generate updated classification threshold parameters. S53: The weight allocation of the permeability efficiency coefficient is dynamically rebalanced. The calculated weight ratio of urea and creatinine is redistributed according to the distribution characteristics of the deviation index to generate an optimized set of weight parameters. S54: Perform rule system reconstruction processing on the updated classification threshold parameters and the optimized set of weight parameters, and integrate the patient dialysis report to generate updated transport capacity classification rules.

6. An adaptive peritoneal dialysis dose optimization device, characterized in that, The device includes: The solute concentration monitoring module is used to monitor the changes in the concentration of urea and creatinine in the patient's peritoneal cavity in real time through a sensor implanted at the end of the peritoneal dialysis catheter, and generate a solute concentration curve that changes continuously over time. The toxin transport capacity analysis module is used to acquire the patient's historical medical data, analyze the solute permeation efficiency of urea and creatinine in combination with the solute concentration curve, call the preset transport capacity classification rules to determine the type of toxin transport capacity of the patient's peritoneum, and generate a patient dialysis report. The retention time optimization module is used to adapt the retention time of the patient's dialysis report to the retention time of the dialysis fluid in the peritoneal cavity based on the toxin transport capacity type, and generate an optimized retention time. The dialysis dose calculation module is used to calculate the amount of dialysis fluid injected to achieve a balance between clearance efficiency and safety by combining the optimized retention time and the patient's peritoneal volume in the dialysis report, generate dose optimization parameters, and transmit the optimized retention time and the dose optimization parameters to the dialysis execution terminal. The classification rule iterative update module is used to iteratively adjust the transport capacity classification rules based on the actual toxin removal data fed back by the dialysis execution terminal, adjust the classification threshold and parameter weights according to the clearance rate deviation value, and update the transport capacity classification rules.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 5.

Images