Quantitative prescription generation method, device, equipment and medium for CRRT

Abstract

The application discloses a CRRT quantitative prescription generation method, device, equipment and medium. The method comprises the following steps: acquiring basic characteristic data of a target CRRT patient and each target parameter preset by a doctor, and performing standardization processing on each basic characteristic data and each target parameter to obtain CRRT standard data; determining a prescription parameter according to the CRRT standard data; generating a first prescription parameter set based on each prescription parameter, and performing verification on the first prescription parameter set; in response to a verification pass instruction of the first prescription parameter set, generating a CRRT quantitative prescription based on the first prescription parameter set, and transmitting the CRRT quantitative prescription to a CRRT equipment. The scheme of the application can quickly and accurately generate a CRRT quantitative prescription, reduce the work of doctors, and can significantly reduce the risk of medical errors, thereby providing protection for CRRT treatment.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to a method, apparatus, device, and medium for generating quantitative prescriptions for CRRT. Background Technology

[0002] CRRT (Continuous Renal Replacement Therapy) is an important means of renal support therapy for critically ill patients and has been widely used in intensive care units. Through continuous and slow blood purification, it effectively maintains the stability of the patient's internal environment and has become a key component of multi-organ function support therapy.

[0003] At present, although some intelligent decision-making systems have been developed that can output macro-level suggestions such as treatment mode, treatment dosage, and ultrafiltration rate based on patients' clinical data, these systems only provide preliminary decision-making references and cannot generate complete executable prescriptions. Doctors still need to perform manual calculations afterward, which is inefficient and carries the risk of medical errors. Summary of the Invention

[0004] This invention provides a method, apparatus, device, and medium for generating quantitative prescriptions for CRRT, which can quickly and accurately generate quantitative prescriptions for CRRT, reduce the workload of doctors, significantly reduce the risk of medical errors, and provide assurance for CRRT treatment.

[0005] According to one aspect of the present invention, a method for generating a quantitative prescription for CRRT is provided, the method comprising:

[0006] Acquire the basic characteristic data of the target CRRT patient and the target parameters preset by the doctor, and perform standardization processing on the basic characteristic data and the target parameters to obtain CRRT standard data that matches the target CRRT patient;

[0007] Prescription parameters are determined based on the CRRT standard data, wherein the prescription parameters include therapeutic dose, blood flow rate, filtration fraction, replacement fluid formulation, citrate infusion rate, calcium infusion rate, and sodium bicarbonate requirement.

[0008] A first prescription parameter set is generated based on each of the prescription parameters, and the first prescription parameter set is verified.

[0009] In response to the verification pass instruction of the first prescription parameter set, a CRRT quantitative prescription is generated based on the first prescription parameter set, and the CRRT quantitative prescription is transmitted to the CRRT device.

[0010] According to another aspect of the present invention, a quantitative prescription generation apparatus for CRRT is provided, the apparatus comprising:

[0011] The acquisition module is used to acquire the basic feature data of the target CRRT patient and the target parameters preset by the doctor, and to standardize the basic feature data and the target parameters to obtain CRRT standard data that matches the target CRRT patient.

[0012] The prescription parameter determination module is used to determine prescription parameters based on the CRRT standard data, wherein the prescription parameters include treatment dose, blood flow rate, filtration fraction, replacement fluid formula, citrate infusion rate, calcium infusion rate, and sodium bicarbonate requirement.

[0013] The prescription parameter verification module is used to generate a first prescription parameter set based on each of the prescription parameters, and to verify the first prescription parameter set.

[0014] The prescription generation module is used to generate a CRRT-quantized prescription based on the first prescription parameter set in response to the verification pass instruction of the first prescription parameter set, and transmit the CRRT-quantized prescription to the CRRT device.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] At least one processor;

[0017] and a memory communicatively connected to the at least one processor;

[0018] The memory stores a computer program that can be executed by the at least one processor, which is then executed by the at least one processor to enable the at least one processor to perform the CRRT quantitative prescription generation method according to any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the CRRT quantitative prescription generation method according to any embodiment of the present invention.

[0020] According to another aspect of the present invention, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the CRRT quantitative prescription generation method according to any embodiment of the present invention.

[0021] The technical solution of this invention obtains basic characteristic data of the target CRRT patient and various target parameters preset by the doctor, and standardizes the basic characteristic data and target parameters to obtain CRRT standard data matching the target CRRT patient; determines prescription parameters based on the CRRT standard data, wherein the prescription parameters include treatment dose, blood flow rate, filtration fraction, replacement fluid formula, citrate infusion rate, calcium infusion rate, and sodium bicarbonate requirement; generates a first prescription parameter set based on the prescription parameters, and verifies the first prescription parameter set; responds to the verification pass instruction of the first prescription parameter set, generates a CRRT quantitative prescription based on the first prescription parameter set, and transmits the CRRT quantitative prescription to the CRRT device. This can generate CRRT quantitative prescriptions quickly and accurately, reduce the workload of doctors, and significantly reduce the risk of medical errors, providing assurance for CRRT treatment.

[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a flowchart of a CRRT quantitative prescription generation method provided in Embodiment 1 of the present invention;

[0025] Figure 2 This is a flowchart of a CRRT quantitative prescription generation method provided in Embodiment 2 of the present invention;

[0026] Figure 3 This is a schematic diagram of a CRRT quantitative prescription generation device according to Embodiment 3 of the present invention;

[0027] Figure 4 This is a schematic diagram of the structure of an electronic device that implements the CRRT quantitative prescription generation method according to an embodiment of the present invention. Detailed Implementation

[0028] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0030] Example 1

[0031] Figure 1 This is a flowchart of a CRRT quantitative prescription generation method according to Embodiment 1 of the present invention. This embodiment is applicable to the automatic generation of treatment prescriptions adapted to target CRRT patients. This method can be executed by a CRRT quantitative prescription generation device, which can be implemented in hardware and / or software and can be configured in electronic devices such as computers, servers, or tablet computers. Figure 1 As shown, the method includes:

[0032] Step 110: Obtain the basic characteristic data of the target CRRT patient and the target parameters preset by the doctor, and standardize the basic characteristic data and target parameters to obtain CRRT standard data that matches the target CRRT patient.

[0033] The target CRRT patient can be any individual currently receiving CRRT treatment, such as a 72-year-old female patient who was put on the machine due to acute kidney injury caused by septic shock; or a 60-year-old male patient who received non-anticoagulated CRRT due to heart failure and deteriorating renal function. In this embodiment, no specific limitation is imposed.

[0034] In this embodiment, the basic characteristic data may include patient characteristic data, laboratory test data, and dynamic physiological data. Patient characteristic data may include age, diagnosis, weight, and underlying diseases (e.g., cirrhosis, diabetes, heart failure, etc.). Laboratory test data may include results from blood gas analysis, electrolytes, complete blood count, and coagulation function. Dynamic physiological data may include blood pressure, heart rate, central venous pressure, or vasoactive drug dosage. Target parameters can be treatment goals set by the physician based on the patient's condition, and may include effect parameters and operational parameters. Effect parameters include target ultrafiltration volume, target electrolyte range, target filtration fraction, and target treatment dose. Operational parameters include blood flow rate, predilution flow rate, postdilution flow rate, and net ultrafiltration volume.

[0035] Optionally, in this embodiment, basic characteristic data of the target CRRT patient can be obtained from the electronic medical record system. This basic characteristic data includes patient characteristic data, laboratory test data, and dynamic physiological data. Patient characteristic data includes the patient's age, primary diagnosis, weight, and underlying disease information, which may include diagnoses of chronic diseases such as cirrhosis, diabetes, and heart failure. Laboratory test data includes laboratory examination data such as blood gas analysis results, electrolyte test results, complete blood count results, and coagulation function test results. Dynamic physiological data includes real-time monitoring parameters such as blood pressure monitoring values, heart rate monitoring values, central venous pressure monitoring values, and vasoactive drug dosage.

[0036] Simultaneously, it can receive various target parameters input by doctors through a human-computer interaction interface. These target parameters include effect parameters and operational parameters. Effect parameters include target ultrafiltration volume, target electrolyte range, target filtration fraction, and target therapeutic dose. Operational parameters include blood flow rate, predilution flow rate, postdilution flow rate, and net ultrafiltration volume. After acquiring all raw data, data quality checks are performed on various basic characteristic data to identify outliers and missing values. Outliers exceeding clinically reasonable ranges are marked and corrected, and missing data items are appropriately filled in based on historical data or data from similar patients.

[0037] Furthermore, appropriate standardization methods can be selected based on the characteristics of different data types. For numerical indicators in patient characteristic data, such as age and weight, the minimum-maximum normalization method is used to convert them to a range of zero to one. For categorical data such as diagnostics and underlying diseases, one-hot encoding is used to convert them into numerical vectors. For various laboratory indicators in laboratory test data, standardization is performed according to their normal reference ranges, converting actual test values ​​into standardized values ​​relative to the normal range. For time-series indicators in dynamic physiological data, a moving average method is used for smoothing to eliminate the impact of instantaneous fluctuations on data quality. After completing the standardization of basic characteristic data, the same standardization process is applied to the target parameters preset by the physician. The target ultrafiltration volume is converted from milliliters to standard units, the target electrolyte range is converted to a standardized concentration range, the target filtration fraction is converted to a standard value between 0 and 1, and the target therapeutic dose is converted from milliliters per kilogram per hour to standard dose units. For operational parameters such as blood flow rate, predilution flow rate, postdilution flow rate, and net ultrafiltration volume, they are uniformly converted to standard flow rate units of milliliters per minute. Finally, all the standardized basic feature data and target parameters are integrated according to the preset data structure to form a structured standard data record. This standard data record contains patient identification information, standardized basic feature data, and standardized target parameters, providing standardized input data for the subsequent prescription parameter calculation module.

[0038] For example, the target CRRT patient is a 65-year-old male patient diagnosed with acute kidney injury complicated by septic shock, weighing 70 kg, with underlying conditions including diabetes and hypertension. Laboratory test results show blood gas analysis results of pH 7.25, partial pressure of carbon dioxide 35 mmHg, and partial pressure of oxygen 85 mmHg; electrolyte results of serum potassium 5.2 mmol / L, serum sodium 140 mmol / L, and serum calcium 1.8 mmol / L; and a complete blood count showing a white blood cell count of 15 × 10⁻⁶. 9 / L, coagulation function showed an international normalized ratio of 1.3. Dynamic physiological data showed a mean arterial pressure of 75 mmHg, a heart rate of 110 beats / min, a central venous pressure of 8 cmH2O, and a norepinephrine dosage of 0.1 μg / (kg·min).

[0039] The target parameters set by the physician based on the patient's condition included: a target ultrafiltration volume of 2000 ml, a target electrolyte range of 3.5-5.0 mmol / L serum potassium, a target filtration fraction of 25%, and a target therapeutic dose of 25 ml / (kg·h). Operational parameters included a blood flow rate of 180 ml / min, a predilution flow rate of 1000 ml / h, a postdilution flow rate of 500 ml / h, and a net ultrafiltration volume of 100 ml / h. After standardization, the patient's age was converted to 65, weight to 70, and all laboratory and dynamic physiological data were converted to standardized values. The target ultrafiltration volume was converted to 2000, the target electrolyte range to 3.5-5.0, the target filtration fraction to 0.25, the target therapeutic dose to 25, the blood flow rate to 180, the predilution flow rate to 1000, the postdilution flow rate to 500, and the net ultrafiltration volume to 100, forming a complete standardized dataset for subsequent calculations.

[0040] It should be noted that in this embodiment, the information data of the target CRRT patient was obtained only after user authorization, and the method of acquisition is reasonable and legal.

[0041] Optionally, in this embodiment, the basic characteristic data of the target CRRT patient and the target parameters preset by the doctor can be obtained in real time through the data interface; the basic characteristic data and the target parameters are processed by timestamp alignment, outlier processing, missing value imputation and feature engineering to obtain CRRT standard data matching the target CRRT patient.

[0042] In one optional implementation of this embodiment, the basic characteristic data of the target CRRT patient can be obtained in real time through the hospital information system interface, while the doctor's preset target parameters can be obtained through the doctor's workstation interface. The obtained basic characteristic data includes patient characteristic data, laboratory test data, and dynamic physiological data, all of which have original collection timestamps. The target parameters include effect parameters and operational parameters, all of which have time nodes set by the doctor.

[0043] Furthermore, all acquired data can be timestamped to unify data from different acquisition frequencies onto a preset time grid. For high-frequency dynamic physiological data such as blood pressure and heart rate, a sliding window averaging method is used for downsampling. For low-frequency test data such as blood gas analysis and electrolytes, spline interpolation is used for upsampling. Data points that cannot be obtained through alignment are marked as pending interpolation.

[0044] After timestamp alignment is completed, outlier handling can be further performed. For example, a clinically reasonable threshold can be set for each data indicator, and dual verification can be performed using statistical methods and clinical rules. For data points exceeding the threshold, single outliers are replaced with the average of adjacent time points, while outliers from multiple consecutive time points trigger a manual review mechanism. After outlier handling, missing value imputation is performed, selecting different imputation strategies based on data type and missing pattern. Time series interpolation is used for continuous variables, and mode imputation is used for categorical variables. A manual review process is triggered when the number of missing key vital signs exceeds a preset threshold.

[0045] Furthermore, derived features can be constructed from the raw data based on clinical knowledge and machine learning methods. A hemodynamic stability index is calculated, weighted by the rate of change of mean arterial pressure, vasoactive drug dosage, and heart rate. An electrolyte balance score is calculated, comprehensively assessing the deviation of serum potassium, sodium, and calcium from target ranges. An inflammatory response intensity index is calculated, based on a multi-parameter fusion of white blood cell count, pH, and partial pressure of oxygen. The constructed derived features are then integrated with the original standardized data to form a CRRT standard dataset incorporating time-related information.

[0046] This embodiment achieves precise synchronization of multi-source heterogeneous data across time dimensions through timestamp alignment, resolving the temporal misalignment problem caused by inconsistent clinical data collection frequencies. The combination of outlier handling and missing value imputation effectively improves data quality and completeness, providing a reliable data foundation for subsequent calculations. Constructing clinically meaningful derived features enhances the data's representational ability and predictive value. The time-series features accurately reflect the dynamic trends of patient status and physician treatment intentions, significantly improving the accuracy and real-time performance of subsequent prescription parameter calculations, and realizing a complete transformation process from raw clinical data to high-quality computational input data.

[0047] Step 120: Determine the prescription parameters based on CRRT standard data.

[0048] The prescription parameters include therapeutic dose, blood flow rate, filtration fraction, replacement fluid formulation, citrate infusion rate, calcium infusion rate, and sodium bicarbonate requirement.

[0049] It is understandable that the treatment dose, calculated per unit time based on the patient's weight and measured in ml / kg / h, is a core indicator of CRRT treatment intensity. For example, for a 70 kg patient, if the treatment dose is set at 25 ml / kg / h, the total ultrafiltration volume would be 1750 ml / h. Blood flow rate, measured in ml / min, is the speed at which blood flows through the extracorporeal circulation tubing and directly affects solute clearance efficiency and filter lifespan. Blood flow rate needs to be dynamically adjusted based on the patient's vascular access conditions and hemodynamic status, typically within the range of 100-250 ml / min. The filtration fraction, the percentage of ultrafiltration volume to plasma flow, reflects the degree of blood concentration; a safe range is usually controlled between 25% and 35%. An excessively high filtration fraction increases the risk of filter clotting, while an excessively low fraction affects treatment efficiency. The replacement fluid formulation is a customized liquid composition based on the patient's electrolyte level and acid-base status, containing specific concentrations of electrolytes such as sodium, potassium, calcium, magnesium, chloride, and glucose, measured in mmol / L. For example, patients with hypokalemia may require a high-potassium replacement fluid formulation. The citrate infusion rate refers to the rate at which the citrate solution is infused during local citrate anticoagulation, measured in ml / h. It is used to chelate calcium ions in extracorporeal circulation to prevent clotting. The citrate infusion rate needs to be precisely calculated based on blood flow rate and the patient's metabolic capacity. The calcium infusion rate is the rate at which calcium ions chelated by citrate are replenished, measured in ml / h, and is used to maintain calcium ion balance in the patient. The calcium infusion rate is usually proportional to the citrate infusion rate. The theoretical sodium bicarbonate requirement is the recommended supplementation amount calculated by the system based on the citrate metabolic equivalent, measured in mmol / h. This theoretical requirement is compared with the clinically set sodium bicarbonate infusion rate. If the deviation exceeds a threshold (e.g., 10%), an acid-base balance risk warning is triggered. The actual sodium bicarbonate infusion rate is determined clinically based on the patient's real-time acid-base status; the system only provides a theoretical reference value and performs risk monitoring. Optionally, in this embodiment, after obtaining the CRRT standard data, each prescription parameter can be calculated sequentially based on the CRRT standard data. For example, each prescription parameter can be calculated sequentially using an intelligent prescription calculation engine, which integrates four collaborative calculation modules: a bidirectional extrapolation module for treatment dose and blood flow rate, a reverse solution module for filtration fraction safety constraints, a replacement fluid formulation optimization and selection module, and a multi-parameter linkage calculation module for anticoagulation strategies. While performing traditional forward calculations, this engine supports reverse extrapolation based on constraints, achieving inverse solving from treatment goals to basic parameters. The calculation process first determines the core circulation parameters through the bidirectional extrapolation module for treatment dose and blood flow rate, then performs boundary verification and parameter adjustment through the reverse solution module for filtration fraction safety constraints, followed by matching electrolyte composition and dilution ratio through the replacement fluid formulation optimization and selection module, and finally, the multi-parameter linkage calculation module for anticoagulation strategies determines the anticoagulant and calcium infusion parameters.The structured output layer maps the validated prescription parameters to the corresponding fields on the electronic CRRT prescription form, including blood flow rate, pre- and post-dilution flow rates, volume of each component of the replacement fluid, and pump rates for anticoagulants and calcium supplements.

[0050] Step 130: Generate a first prescription parameter set based on each prescription parameter, and verify the first prescription parameter set.

[0051] The first prescription parameter set is a complete set of parameters formed by integrating the independently calculated results of blood flow rate, replacement fluid flow rate, filtration fraction, and anticoagulant infusion rate determined in the above steps. The prescription parameters include the blood flow rate determined by the bidirectional extrapolation module of treatment dose and blood flow rate, the filtration fraction calculated by the reverse solution module for filtration fraction safety constraints, the pre- and post-dilution flow rates matched by the replacement fluid formulation optimization selection module, and the anticoagulant infusion rate obtained by the multi-parameter linkage calculation module for anticoagulation strategies. In this embodiment, verification can be a process of safety verification of the first prescription parameter set, which may include parameter range verification, i.e., verifying whether each parameter is within a preset safety range, and parameter correlation verification, i.e., verifying whether there are logical conflicts or proportional imbalances between parameters. For example, when the calculated blood flow rate is 150 ml / min and the filtration fraction is 38%, the verification mechanism needs to verify whether 38% is close to the clinical safety upper limit of 40%. If it is close, a parameter callback and re-optimization are triggered.

[0052] In an optional implementation of this embodiment, after completing the bidirectional extrapolation of treatment dose and blood flow rate, the reverse solution of filtration fraction safety constraints, the optimized selection of replacement fluid formulation, and the multi-parameter linkage calculation of anticoagulation strategy, the blood flow rate parameters, filtration fraction parameters, pre- and post-dilution replacement fluid flow rate parameters, and anticoagulant infusion rate parameters output by each module can be integrated to generate a first prescription parameter set. Further, parameter range verification can be performed on the first prescription parameter set to determine whether the blood flow rate is within the safe operating range of 50-300 ml / min, confirm whether the filtration fraction is below the clinical risk threshold of 40%, and verify whether the ratio of anticoagulant infusion rate to blood flow rate conforms to a reasonable range of 1:0.8-1:1.2. Then, parameter correlation verification is performed to analyze whether the matching relationship between the total replacement fluid flow rate and blood flow rate meets the blood dilution requirements, and to check whether the coordination between filtration fraction and ultrafiltration rate meets the extracorporeal circulation stability standard. When the filtration fraction is found to be close to the 40% critical value during the verification process, the blood flow rate is immediately reduced and the relevant parameters are recalculated, and the verification process is repeated until all parameters meet the safety conditions. Finally, the prescription parameter set that passes all validation conditions is input into the structured output layer for electronic prescription generation.

[0053] For example, the bidirectional extrapolation module for treatment dose and blood flow rate outputs a blood flow rate of 150 ml / min, the reverse solution module for filtration fraction safety constraints outputs a filtration fraction of 38%, the replacement fluid formulation optimization module outputs a pre-dilution replacement fluid flow rate of 1000 ml / h and a post-dilution replacement fluid flow rate of 800 ml / h, and the multi-parameter linkage calculation module for anticoagulation strategy outputs a citrate anticoagulant infusion rate of 180 ml / h. After integrating the above parameters to form the first prescription parameter set, the verification module performs parameter range verification: the blood flow rate of 150 ml / min is within the safe range of 50-300 ml / min, the filtration fraction of 38% does not exceed the 40% threshold, and the ratio of the 180 ml / h anticoagulant infusion rate to the 150 ml / min blood flow rate is 1:1.2, which is within the reasonable range of 1:0.8-1:1.2. Further parameter correlation verification was performed. The ratio of total replacement fluid flow rate (1800 ml / h) to blood flow rate (150 ml / min) was 12:1, which met the blood dilution requirements. However, the filtration fraction of 38% was close to the 40% safety limit, posing a potential risk. The verification module triggered a feedback mechanism, returning to the bidirectional extrapolation module for treatment dose and blood flow rate. The blood flow rate was adjusted to 140 ml / min for recalculation, and the reverse solution module for the filtration fraction safety constraint output a new filtration fraction of 35%. Re-verification confirmed that the 35% filtration fraction met the safety requirements, the 140 ml / min blood flow rate remained within the safe range, and the ratio remained 1:1.2 after adjusting the anticoagulant infusion rate to 168 ml / h. All parameters passed the verification, and the verified parameter set was finally transmitted to the structured output layer.

[0054] Step 140: In response to the verification pass instruction of the first prescription parameter set, generate a CRRT quantitative prescription based on the first prescription parameter set, and transmit the CRRT quantitative prescription to the CRRT device.

[0055] Optionally, after the first prescription parameter set has been verified through the above steps, the CRRT quantitative prescription generation operation can begin. First, the verified blood flow rate parameters, filtration fraction parameters, pre-dilution replacement fluid flow rate parameters, post-dilution replacement fluid flow rate parameters, and anticoagulant infusion rate parameters can be read. Then, according to preset equipment control mapping rules, the blood flow rate parameters are converted into blood pump speed control values, the pre-dilution and post-dilution replacement fluid flow rate parameters are converted into flow rate setpoints for the pre-dilution and post-dilution pumps, respectively, the filtration fraction parameters are combined with the blood flow rate parameters to calculate the ultrafiltration pump operating parameters, and the anticoagulant infusion rate parameters are converted into the anticoagulant pump infusion rate setpoint. Further, all the converted control parameters are integrated into a structured CRRT quantitative prescription data packet, and a data checksum and transmission identifier are added. Further, the communication transmission unit establishes a communication connection with the CRRT device, transmits the CRRT quantitative prescription data packet to the CRRT device's control motherboard using the medical device standard communication protocol, and monitors the transmission status until a prescription reception confirmation signal is received from the CRRT device, completing the entire prescription transmission process.

[0056] In an optional implementation of this embodiment, after the first prescription parameter set completes all verification processes and passes security verification, the prescription generation module receives the verified blood flow rate, filtration fraction, pre-dilution replacement fluid flow rate, post-dilution replacement fluid flow rate, and anticoagulant infusion rate parameters, and formats these parameters according to a preset data structure to generate a structured prescription parameter dataset. Next, the electronic prescription generation unit pushes the structured prescription parameter dataset to the clinician's workstation. The doctor views the prescription parameter details through a visual interface and performs manual review and confirmation. When the doctor clicks the approval button, the prescription transmission control unit starts the automatic filling process, filling the blood flow rate parameter into the blood pump speed field of the electronic CRRT prescription, the pre-dilution replacement fluid flow rate parameter into the pre-dilution pump flow rate field, the post-dilution replacement fluid flow rate parameter into the post-dilution pump flow rate field, the sodium ion concentration, potassium ion concentration, calcium ion concentration, bicarbonate concentration, and glucose concentration parameters output by the replacement fluid formulation optimization and selection module into the volume fields of each component of the replacement fluid, the anticoagulant infusion rate parameter output by the anticoagulant strategy multi-parameter linkage calculation module into the anticoagulant pump speed field, and the calcium supplementation rate parameter into the calcium pump speed field. Then, the electronic prescription generation module performs an integrity check on all filled fields. After confirming that no fields are missing, it generates a complete electronic CRRT prescription. This prescription contains all the quantitative parameters and execution time information necessary for treatment. Finally, the generated electronic CRRT prescription is stored in the hospital information system and simultaneously pushed to the bedside CRRT equipment control terminal to form a quantitative medical order that can be directly executed.

[0057] The technical solution of this embodiment obtains basic characteristic data of the target CRRT patient and various target parameters preset by the doctor, and standardizes the basic characteristic data and target parameters to obtain CRRT standard data matching the target CRRT patient; determines prescription parameters based on the CRRT standard data, wherein the prescription parameters include treatment dose, blood flow rate, filtration fraction, replacement fluid formula, citrate infusion rate, calcium infusion rate, and sodium bicarbonate requirement; generates a first prescription parameter set based on each prescription parameter, and verifies the first prescription parameter set; responds to the verification pass instruction of the first prescription parameter set, generates a CRRT quantitative prescription based on the first prescription parameter set, and transmits the CRRT quantitative prescription to the CRRT device. This can generate CRRT quantitative prescriptions quickly and accurately, reduce the workload of doctors, and significantly reduce the risk of medical errors, providing a guarantee for CRRT treatment.

[0058] Example 2

[0059] Figure 2 This is a flowchart of a CRRT quantitative prescription generation method according to Embodiment 2 of the present invention. This embodiment is a further refinement of the above technical solution, and the technical solution in this embodiment can be combined with various optional solutions in one or more of the above embodiments. Figure 2 As shown, the method includes:

[0060] Step 210: Obtain the basic characteristic data of the target CRRT patient and the target parameters preset by the doctor, and standardize the basic characteristic data and target parameters to obtain CRRT standard data that matches the target CRRT patient.

[0061] Step 220: Determine the prescription parameters based on CRRT standard data.

[0062] The prescription parameters include therapeutic dose, blood flow rate, filtration fraction, replacement fluid formulation, citrate infusion rate, calcium infusion rate, and sodium bicarbonate requirement. In this embodiment, step 220 may include steps 221-224 below.

[0063] Step 221: When the target parameters include operational parameters, obtain the blood flow rate, pre-dilution flow rate, post-dilution flow rate, and net ultrafiltration volume from the operational parameters, and calculate the actual treatment dose based on the blood flow rate, pre-dilution flow rate, post-dilution flow rate, and net ultrafiltration volume; when the target parameters include effect parameters, obtain the target treatment dose from the effect parameters; under the constraints of the preset safe range of blood flow rate, the upper limit of filtration fraction, and the total amount of replacement fluid, solve for one or more sets of operational parameter combinations that meet the target treatment dose; wherein, each set of operational parameter combinations includes the corresponding blood flow rate, pre-dilution flow rate, and post-dilution flow rate; based on the prescription achievement rate in the historical treatment records, select the operational parameter combination with the highest prescription achievement rate from the operational parameter combinations.

[0064] In this embodiment, the target parameters can be the treatment requirements set by the physician, which can be divided into two categories: operational parameters and effect parameters. Operational parameters are physical quantities that the device can directly control, including blood flow rate, predilution flow rate, postdilution flow rate, and net ultrafiltration volume. For example, a blood flow rate of 180 ml / min, a predilution flow rate of 1000 ml / h, a postdilution flow rate of 800 ml / h, and a net ultrafiltration volume of 200 ml / h. Effect parameters are quantitative indicators of treatment effectiveness, mainly the target therapeutic dose, which represents the amount of fluid to be removed per kilogram of body weight per hour, for example, 35 ml / kg / h. The prescription achievement rate refers to the proportion of historical treatments where the target therapeutic dose was actually achieved, reflecting the reliability of the parameter combination in clinical practice. For example, a parameter combination of a blood flow rate of 150 ml / min, a predilution of 1000 ml / h, and a postdilution of 800 ml / h has a historical achievement rate of 92%. The upper limit of the filtration fraction is the maximum safe proportion of ultrafiltration volume to plasma flow, usually set at 25%. Exceeding this value may significantly increase the risk of filter clotting.

[0065] Optionally, in this embodiment, when the treatment target input by the clinician includes operational parameters, the values ​​of blood flow rate, predilution flow rate, postdilution flow rate, and net ultrafiltration volume can be obtained from the operational parameters. Simultaneously, the current hematocrit value and body weight are read from the patient information database. Based on a preset treatment dose calculation formula, the difference between multiplying the blood flow rate by 1 and subtracting the hematocrit is used as the numerator, and the sum of multiplying the blood flow rate by 1 and subtracting the hematocrit value, plus the predilution flow rate divided by 60, is used as the denominator. This sum is then multiplied by the difference between the total replacement fluid flow rate and the net ultrafiltration volume, and finally divided by the body weight to calculate the actual treatment dose. When the treatment target input by the clinician includes effect parameters, the parameter optimization unit obtains the target treatment dose value from the effect parameters, then sets constraints such as a safe range for blood flow rate, an upper limit for filtration fraction, and a limit on total replacement fluid volume. A nonlinear programming solution model is constructed, and iterative calculations are performed in the three-dimensional parameter space of blood flow rate, predilution flow rate, and postdilution flow rate to find multiple parameter combinations that meet the target treatment dose requirements and have the lowest filtration fraction and the smallest blood flow rate. Furthermore, the historical data analysis unit retrieves historical prescription achievement rate data for each parameter combination from the historical treatment record database. Based on characteristics such as patient age, primary disease, and vascular access type, it performs a weighted calculation of matching degree to obtain a weighted achievement rate score for each parameter combination. The weighted achievement rate scores of each parameter combination are compared, and the parameter combination with the highest score is selected as the final operating parameter combination. The corresponding blood flow rate, pre-dilution flow rate, and post-dilution flow rate parameters are then transmitted to the next verification module for security verification.

[0066] In this embodiment, the formula for calculating the treatment dose can be as follows: ;

[0067] in, For blood flow velocity, Hematocrit, Pre-dilution flow rate, For post-dilution flow rate, Net ultrafiltration volume, The formula represents body weight. The core physiological principle embodied in this formula is that the actual volume of replacement fluid acting on the blood needs to be corrected for plasma flow rate; predilution dilutes the blood concentration, thus reducing clearance efficiency. In this embodiment, the expected UFR (therapeutic dose) is automatically calculated based on the currently set blood flow rate and dilution ratio.

[0068] In another optional implementation of this embodiment, when the doctor inputs the target UFR value, a reverse solution process can be initiated: First, safety boundary parameters are set according to the patient's current treatment stage, including a safe range for blood flow rate, an upper limit threshold for filtration fraction, and a limit value for total replacement fluid volume. A lower safety threshold is used for the blood flow rate range during the initial blood draw stage, while a standard safety range is used during routine treatment. The upper limit for filtration fraction is set to the maximum allowable value to ensure safe filter operation. Then, a constrained nonlinear programming solution model is constructed, and multi-objective optimization calculations are performed in the three-dimensional parameter space composed of blood flow rate, pre-dilution flow rate, and post-dilution flow rate. Minimizing the absolute difference between the predicted treatment dose and the target treatment dose is the primary optimization objective, minimizing the filtration fraction is the secondary optimization objective, and minimizing the blood flow rate is the tertiary optimization objective. Multiple sets of feasible solution parameter combinations satisfying all safety constraints are generated through iterative calculations. Next, a historical prescription achievement rate analysis is performed on each set of feasible solution parameter combinations. Treatment achievement records of the same or similar parameter combinations in the same patient group are retrieved from the historical treatment database, and the historical achievement rate score for each parameter combination is calculated. Compare the historical achievement rate scores of all feasible solution parameter combinations, prioritize the parameter combination with the highest historical achievement rate as the recommended solution, and output the blood flow rate, pre-dilution flow rate, and post-dilution flow rate parameter values ​​of the combination to the parameter verification module.

[0069] For example, a CRRT patient weighs 65 kg, has a hematocrit of 30%, and the physician sets a target treatment dose of 35 ml / kg / h. Under constraints of a blood flow rate of 80-250 ml / min, a filtration fraction not exceeding 25%, and a total replacement fluid volume not exceeding 4000 ml / h, back-calculation yields two feasible parameter combinations: The first combination has a blood flow rate of 180 ml / min, a predilution flow rate of 1200 ml / h, and a postdilution flow rate of 600 ml / h, predicting a treatment dose of 35.2 ml / kg / h and a filtration fraction of 24.8%; the second combination has a blood flow rate of 150 ml / min, a predilution flow rate of 1000 ml / h, and a postdilution flow rate of 800 ml / h, predicting a treatment dose of 34.9 ml / kg / h and a filtration fraction of 23.5%. The historical data analysis unit queries the historical database and finds that the historical prescription achievement rate of the first set of parameters in similar patients is 85%, and the historical prescription achievement rate of the second set of parameters is 92%. Therefore, the second set of parameters with the higher historical achievement rate can be selected as the optimal solution, and the blood flow rate of 150 ml / min, the predilution flow rate of 1000 ml / h, and the postdilution flow rate of 800 ml / h are transmitted to the verification module.

[0070] The solution in this embodiment establishes a two-way extrapolation mechanism between treatment dose and blood flow rate, realizing the dual functions of forward calculation from operating parameters to effect parameters and reverse optimization from effect parameters to operating parameters, which significantly improves the accuracy of parameter setting and clinical applicability.

[0071] Step 222: If the target parameters do not include the target filtration fraction, calculate the filtration fraction based on the post-dilution flow rate, blood flow rate, hematocrit, and net ultrafiltration volume, and determine whether the filtration fraction exceeds the preset filtration fraction safety threshold. If the filtration fraction exceeds the filtration fraction safety threshold, issue a filter coagulation risk warning. If the target parameters include the target filtration fraction, calculate the post-dilution flow rate that satisfies the target filtration fraction based on the target filtration fraction, blood flow rate, hematocrit, and net ultrafiltration volume. Based on the constant total replacement fluid volume constraint, set the pre-dilution flow rate to the difference between the total replacement fluid volume and the post-dilution flow rate to generate an operating parameter combination that satisfies the target filtration fraction.

[0072] In this embodiment, the filtration fraction refers to the proportion of plasma that is ultrafiltered when blood passes through the filter, and it is a core safety indicator for assessing the coagulation risk of the filter. In CRRT, when the filtration fraction exceeds 25%, the blood viscosity inside the filter will increase sharply, triggering a coagulation cascade reaction. For example, when the blood flow rate is 150 ml / min, the hematocrit is 30%, the post-dilution flow rate is 800 ml / h, and the net ultrafiltration volume is 200 ml / h, the calculated filtration fraction is 23.5%, which is within the safe range. If the post-dilution flow rate increases to 1000 ml / h, the filtration fraction will rise to 28.6%, exceeding the safety threshold, and a coagulation risk warning will be issued. The reverse calculation algorithm means that when the doctor sets a target filtration fraction, it automatically calculates the post-dilution flow rate value that meets the target and adjusts the pre-dilution flow rate accordingly to maintain a constant total replacement fluid volume. For example, if a doctor sets a target filtration fraction of 20%, and under conditions of a blood flow rate of 150 ml / min, a hematocrit of 30%, and a net ultrafiltration volume of 200 ml / h, the recommended safe post-dilution flow rate is calculated to be 750 ml / h, and the pre-dilution flow rate is automatically adjusted to 1050 ml / h, thereby ensuring treatment safety and continuity.

[0073] Optionally, in this embodiment, after generating a combination of blood flow rate, predilution flow rate, postdilution flow rate, and net ultrafiltration volume parameters that meet the target therapeutic dose requirements through multi-objective optimization calculation, the filtration fraction safety verification process can be initiated. First, the target parameter configuration input by the physician is parsed to determine whether it includes a target filtration fraction setting. If the target parameters do not include a target filtration fraction, the filtration fraction calculation formula is substituted based on the currently calculated postdilution flow rate value, blood flow rate value, patient hematocrit value, and net ultrafiltration volume value. A forward calculation is performed to obtain the actual filtration fraction value, which is then compared with a preset safety threshold of 25%. If the actual filtration fraction exceeds the safety threshold, a filter coagulation risk warning signal is immediately generated, and the calculation is returned for recalculation of the treatment dose optimization. When the target parameter includes the target filtration fraction, the blood flow rate value, patient hematocrit value, and net ultrafiltration volume value determined in the above embodiments are used as a basis, combined with the target filtration fraction value set by the doctor, to calculate the recommended dilution flow rate value that meets the safety requirements of the target filtration fraction through formula transformation. Subsequently, based on the principle of constant total replacement fluid volume, the adjustment increment of the predilution flow rate was calculated using the effective plasma flow rate ratio algorithm. ,in To ensure effective plasma flow, a combination of operating parameters is ultimately generated that meets the target filtration fraction requirement while maintaining a constant total replacement fluid volume, thus providing a safety guarantee for subsequent treatment.

[0074] The solution in this embodiment changes the way doctors used to calculate repeatedly using calculators. Instead, the system recommends treatment formulas and flow rates after the treatment goal is input, which not only saves doctors' time but also provides patients with safer parameters.

[0075] Step 223: Construct an electrolyte mass balance equation set. Based on the law of conservation of mass, the sum of the products of electrolyte concentration and dosage in each basal solution equals the sum of the product of electrolyte concentration and total replacement fluid volume in the target replacement fluid, plus the baseline adjustment based on patient metabolism. Solve the electrolyte mass balance equation set according to the target electrolyte concentration range and total osmolarity limit to generate a candidate formulation solution set that satisfies all constraints. This set contains multiple candidate formulations, each specifying the dosage of each basal solution. Based on pre-defined stability evaluation rules, score each candidate formulation to obtain its stability score. The stability score characterizes the risk of electrolyte fluctuations or arrhythmias in the current patient. Select the candidate formulation with the highest stability score as the final recommended replacement fluid formulation.

[0076] In this embodiment, the electrolyte mass balance equations are a mathematical model based on the law of conservation of mass, ensuring that the total amount of each electrolyte in the mixed replacement solution is equal to the sum of the corresponding electrolyte contents in each base solution. The candidate formulation solution set is the set of all feasible formulation combinations generated by a linear programming algorithm under multiple constraints such as sodium ion concentration of 140-145 mmol / L, potassium ion concentration of 0-4.0 mmol / L, and total osmolarity of 280-320 mOsm / L. The stability score is calculated using a pre-trained machine learning model, such as a random forest regression model. This model concatenates the formulation parameters with patient characteristics into a 23-dimensional feature vector and outputs a score value between 0 and 1. A score of 0.92 indicates that the risk of the formulation causing electrolyte fluctuations or arrhythmias in a specific patient is extremely low.

[0077] Optionally, in this embodiment, an electrolyte mass balance equation set can be constructed based on the target electrolyte concentration range and total osmotic pressure constraints set by the doctor. This equation set ensures, based on the law of conservation of mass, that the sum of the products of the concentration and volume of electrolytes in each basal solution equals the product of the electrolyte concentration and the total volume of the replacement fluid in the target replacement fluid, plus the baseline adjustment calculated based on the patient's current blood electrolyte level and metabolic state. Subsequently, the electrolyte mass balance equation set is solved using a linear programming algorithm based on the constraints of sodium ions 140-145 mmol / L, potassium ions 0-4.0 mmol / L, calcium ions 1.25-1.75 mmol / L, magnesium ions 0.5-1.0 mmol / L, and total osmotic pressure 280-320 mOsm / L, generating a candidate formulation solution set that satisfies all constraints. Each candidate formulation includes a specific combination of the dosages of basal solutions such as 0.9% sodium chloride solution, 10% potassium chloride solution, and 5% sodium bicarbonate solution. Furthermore, based on pre-defined stability evaluation rules, the sodium, potassium, calcium, magnesium, bicarbonate, chloride, glucose concentrations, osmolarity, and volume of each basal solution for each candidate formulation can be concatenated with patient age, weight, underlying diseases, diagnostic type, hematocrit, and other characteristics to form a feature vector. This vector is then input into a pre-trained random forest regression model to calculate a stability score. This score characterizes the risk of the candidate formulation causing electrolyte fluctuations or arrhythmias in the current patient. Finally, the candidate formulation with the highest stability score is selected as the recommended replacement fluid formulation. This formulation further optimizes electrolyte balance and treatment safety while meeting therapeutic dosage requirements and filtration fraction safety constraints.

[0078] In this embodiment, the mass balance equation can be simplified to: ;

[0079] in, For solution Medium electrolyte The concentration coefficient (mmol / ml), Electrolytes in the target replacement fluid The concentration (mmol / L), The total volume of the replacement fluid (L) Baseline adjustment (mmol) to account for patient metabolism.

[0080] Taking Na+ as an example, the specific calculation formula is as follows: .

[0081] In one example of this embodiment, a 65-year-old male patient weighing 70 kg was diagnosed with sepsis complicated by acute kidney injury, with a hematocrit of 32%, current serum sodium of 138 mmol / L, and serum potassium of 4.2 mmol / L. After determining parameters such as a blood flow rate of 150 ml / min, a pre-dilution flow rate of 1050 ml / h, a post-dilution flow rate of 750 ml / h, and a net ultrafiltration volume of 200 ml / h, the target replacement fluid sodium concentration was set at 142 mmol / L, potassium concentration at 3.0 mmol / L, and total osmolarity at 300 mOsm / L. When constructing the mass balance equation set, the sodium ion equation was calculated as 154 multiplied by V_NaCl plus 584 multiplied by V_NaHCO3 plus 1000 multiplied by V_KCl multiplied by 0.001, which equals 142 multiplied by 2.0 plus 15, where the baseline adjustment of 15 mmol was calculated based on the patient's hyponatremia. Linear programming was used to generate three candidate formulations: Formulation 1 contained 1500 ml of 0.9% sodium chloride solution, 400 ml of 5% sodium bicarbonate solution, and 10 ml of 10% potassium chloride solution; Formulation 2 contained 1400 ml of 0.9% sodium chloride solution, 500 ml of 5% sodium bicarbonate solution, and 15 ml of 10% potassium chloride solution; and Formulation 3 contained 1600 ml of 0.9% sodium chloride solution, 300 ml of 5% sodium bicarbonate solution, and 5 ml of 10% potassium chloride solution. The parameters of each formulation were concatenated with the patient's characteristics and input into a random forest model, yielding stability scores of 0.85, 0.78, and 0.92, respectively. Formulation 3 was ultimately selected as the recommended regimen, predicting a sodium ion concentration of 141.8 mmol / L, a potassium ion concentration of 2.9 mmol / L, and an osmolarity of 298 mOsm / L, while also exhibiting the lowest risk of electrolyte fluctuations in this elderly sepsis patient.

[0082] The solution in this embodiment achieves a technological breakthrough from fixed formula selection to personalized intelligent formulation by establishing a set of electrolyte mass balance equations, further ensuring the accuracy of electrolyte balance while meeting the safety constraints of therapeutic dosage and filtration fraction.

[0083] Step 224: Calculate the citrate infusion rate based on the target blood flow rate and citrate concentration type. The citrate infusion rate is equal to the product of the target blood flow rate and a preset proportionality coefficient, which is configured according to the citrate concentration. Calculate the total calcium loss rate based on the citrate infusion rate, pre-dilution clearance component, post-dilution clearance component, dialysate clearance component, citrate waste liquid clearance component, patient free calcium concentration, and hematocrit. Calculate the calcium infusion rate based on the total calcium loss rate, calcium ion concentration in the replacement fluid, and the conversion coefficient corresponding to the calcium agent type. Perform pathway correction on the calcium infusion rate according to the calcium supplementation pathway type. Calculate the sodium bicarbonate requirement for citrate metabolism. Compare the actual infused sodium bicarbonate amount with the required amount and trigger an acid-base balance risk warning based on the comparison results.

[0084] The citrate infusion rate refers to the volume of citrate solution infused into the patient per unit time, calculated as the target blood flow rate multiplied by a preset proportionality coefficient. For example, when the target blood flow rate is 150 ml / min and 4% citrate is used, the proportionality coefficient k=1.2, and the citrate infusion rate is 150×1.2=180 ml / h. The total calcium loss rate refers to the rate of calcium ion loss due to citrate chelation and fluid clearance. Its calculation requires comprehensive consideration of pre-dilution clearance, post-dilution clearance, dialysate clearance, and citrate waste clearance, and corrections based on the patient's free calcium concentration and hematocrit. For example, when the patient's free calcium concentration is 1.1 mmol / L and hematocrit is 30%, the total calcium loss rate calculation must consider the dilution effect. The calcium infusion rate is calculated based on the total calcium loss rate and the calcium content of the replacement fluid. Different types of calcium supplements have different conversion factors: 680 mmol / L for 10% calcium chloride, 340 mmol / L for 5% calcium chloride, and 223 mmol / L for 10% calcium gluconate. Pathway correction refers to the need to consider a 5% recirculation rate when using a three-way stopcock at the catheter return end for calcium supplementation, requiring an increase of 5% in the actual pump rate. Sodium bicarbonate requirement refers to the amount of sodium bicarbonate required for citrate metabolism. Each molecule of 4% citrate consumes 3 molecules of bicarbonate. The system triggers an acid-base balance risk warning by comparing the actual clinical infusion volume with the theoretical requirement. Optionally, in this embodiment, the citrate infusion rate can be calculated based on the target blood flow rate and citrate concentration type. The citrate infusion rate is equal to the product of the target blood flow rate and a preset proportionality coefficient. When using 4% citrate, the preset proportionality coefficient is 1.2, and when using 3% citrate, the preset proportionality coefficient is 1.44. This calculation ensures that the post-filter ionized calcium concentration is maintained within the local anticoagulant range of 0.25-0.35 mmol / L. Subsequently, the total calcium loss rate is calculated based on the citrate infusion rate, pre-dilution clearance component, post-dilution clearance component, dialysate clearance component, citrate waste clearance component, patient free calcium concentration, and hematocrit. The formula for calculating the total calcium loss rate is: pre-dilution flow rate + post-dilution flow rate + dialysate flow rate + citrate flow rate multiplied by the patient's free calcium concentration, multiplied by the dilution fraction, divided by 1, minus the hematocrit, divided by 100. The calcium infusion rate was calculated based on the total calcium loss rate, the calcium ion concentration in the replacement fluid, and the conversion factor corresponding to the type of calcium supplement. The conversion factor was 680 mmol / L when using 10% calcium chloride, 340 mmol / L when using 5% calcium chloride, and 223 mmol / L when using 10% calcium gluconate. The calcium infusion rate was equal to the total calcium loss rate minus the predilution flow rate multiplied by the calcium ion concentration in the replacement fluid, and then divided by the calcium supplement conversion factor. The calcium infusion rate was adjusted according to the calcium supplementation pathway type. When using a three-way stopcock at the catheter return end for calcium supplementation, the actual calcium infusion rate was equal to the calculated calcium infusion rate divided by 0.95.The sodium bicarbonate requirement for citrate metabolism was calculated. The sodium bicarbonate equivalent for 4% citrate is 136 mmol / L, and for 3% citrate it is 113 mmol / L. The sodium bicarbonate requirement is calculated by multiplying the sodium bicarbonate equivalent by the citrate infusion rate, dividing by 1000, multiplying by 3, and then dividing by 0.595. The actual infused sodium bicarbonate volume was compared with the required sodium bicarbonate volume. A warning for citrate accumulation or hypernatremia was triggered when the actual infused volume exceeded 110% of the required volume, and a warning for acidosis was triggered when the actual infused volume was less than 90% of the required volume.

[0085] In this embodiment, the actual amount of sodium bicarbonate infused is compared with the required amount of sodium bicarbonate, and an acid-base balance risk warning is triggered based on the comparison result. This can include: determining the initial difference between the actual amount of sodium bicarbonate infused and the required amount of sodium bicarbonate; determining the corrected difference based on the initial difference, effective blood flow rate, and predilution flow rate; calculating the percentage of the corrected difference to the required amount of sodium bicarbonate; triggering a citrate accumulation or hypernatremia risk warning when the corrected difference is positive and the percentage exceeds a first preset threshold; and triggering an acidosis risk warning when the corrected difference is negative and the absolute value of the percentage exceeds a second preset threshold.

[0086] The first preset threshold is used to determine the critical percentage of sodium bicarbonate overdose risk. It can be set to 10% or other values, which are not limited in this embodiment. When the corrected difference is positive and its percentage of the required sodium bicarbonate exceeds this threshold, it indicates that the sodium bicarbonate infusion significantly exceeds the citrate metabolism requirement, which may lead to citrate accumulation and the risk of hypernatremia. The second preset threshold is used to determine the critical percentage of sodium bicarbonate insufficiency risk. It can be set to 10% or other values, which are not limited in this embodiment either. It is applied to negative differences. When the corrected difference is negative and its absolute value as a percentage of the required sodium bicarbonate exceeds this threshold, it indicates that the sodium bicarbonate infusion is severely insufficient and cannot meet the citrate metabolism consumption, triggering an acidosis risk warning. It should be noted that although the two thresholds are usually the same in value, their clinical significance and triggering conditions are completely different. The first preset threshold focuses on the risk of metabolite accumulation, while the second preset threshold focuses on the risk of substrate deficiency, together constituting a two-way warning mechanism for acid-base balance.

[0087] In one optional implementation of this embodiment, after calculating the sodium bicarbonate requirement, an acid-base balance risk warning is immediately performed. First, the initial difference between the actual infused sodium bicarbonate amount and the required amount is determined. This initial difference equals the actual infused amount minus the calculated sodium bicarbonate requirement. Then, based on the initial difference, effective blood flow rate, and predilution flow rate, a corrected difference is determined. This corrected difference equals the initial difference multiplied by the postdilution flow rate, then multiplied by the effective blood flow rate, divided by the effective blood flow rate, plus the predilution flow rate divided by 60. Next, the percentage of the corrected difference to the required amount of sodium bicarbonate is calculated. This percentage equals the corrected difference divided by the required amount of sodium bicarbonate, multiplied by 100%. When the corrected difference is positive and the percentage exceeds 10%, a citrate accumulation or hypernatremia risk warning is triggered; when the corrected difference is negative and the absolute value of the percentage exceeds 10%, an acidosis risk warning is triggered. This early warning mechanism is closely linked to the calculation of prior citrate metabolism requirements, ensuring that medical staff are promptly alerted to adjust sodium bicarbonate infusion parameters before acid-base imbalance occurs.

[0088] In an optional implementation of this embodiment, precise anticoagulation and acid-base balance maintenance are achieved through a three-parameter linkage calculation model involving citrate, calcium, and sodium bicarbonate. The initial citrate pump rate, Qcitrate, is calculated based on the target blood flow rate, QB, using the following formula:

[0089] For 4% citric acid, k=1.2, and for 3% citric acid, k=1.44. This calculation ensures that the ionic calcium concentration after the filter is maintained within the range of 0.25-0.35 mmol / L. The calcium supplementation linkage calculation first determines the total calcium loss rate. The calculation formula is:

[0090] ,in , , , All units are ml / h. The values ​​represent the patient's blood free calcium concentration, FF (fraction of dilution), and HCT (hematocrit). The calcium infusion rate was then calculated. The calculation formula is:

[0091] ,in This represents the calcium ion concentration in the replacement solution. This is the calcium conversion factor, for 10% calcium chloride. =680 mmol / L, 5% calcium chloride =340 mmol / L, 10% calcium gluconate =223 mmol / L. If calcium supplementation is performed using a three-way stopcock at the catheter return end (in antegrade mode), a recirculation rate of approximately 5% needs to be considered, and the actual pump rate should be adjusted accordingly. Acid-base balance early warning calculation: 4% citric acid metabolism requires 5% sodium bicarbonate supplementation. The calculation formula is: ,in The sodium bicarbonate equivalent of citric acid is 136 mmol / L for 4% citric acid and 113 mmol / L for 3% citric acid. The system calculates the difference Δ between the actual amount of sodium bicarbonate supplemented and the required amount, using the following formula: and correct the difference The calculation formula is: When Δ > 10% × When a warning of citrate accumulation or hypernatremia is triggered, Δ < -10%× It can trigger an acidosis risk warning, thereby maintaining effective anticoagulation while ensuring the patient's electrolyte and acid-base homeostasis in real time.

[0092] In one example of this embodiment, a 65-year-old male sepsis patient weighing 70 kg was given a target blood flow rate of 150 ml / min and regional anticoagulation with 4% citrate at an infusion rate of 180 ml / h. Baseline parameters showed a free calcium concentration of 1.1 mmol / L and a hematocrit of 32%. A CVVH treatment regimen of 1050 ml / h predilution and 750 ml / h postdilution was used, resulting in a dilution fraction of 0.25. System calculations showed a total calcium loss rate of 727.94 mmol / h, which was supplemented with 10% calcium chloride (conversion factor 680 mmol / L) at an initial calcium infusion rate of 0.84 ml / h. Due to the use of a three-way stopcock at the catheter return end for calcium supplementation, the actual infusion rate after pathway correction was 0.88 ml / h. Based on the sodium bicarbonate equivalent of 136 mmol / L for 4% citrate, the required infusion rate of 5% sodium bicarbonate was calculated to be 370.92 ml / h. The actual infusion rate was 350 ml / h, resulting in a difference of -20.92 ml / h, which is 5.64% of the required rate. This does not reach the ±10% warning threshold, and the system determines that the acid-base balance is stable. This case demonstrates the precise application of the citrate-calcium-sodium bicarbonate three-parameter linkage calculation model in clinical practice, effectively achieving the simultaneous maintenance of anticoagulation effect and electrolyte acid-base balance.

[0093] Step 230: Generate a first prescription parameter set based on each prescription parameter, and verify the first prescription parameter set.

[0094] Step 240: In response to the verification pass instruction of the first prescription parameter set, generate a CRRT quantitative prescription based on the first prescription parameter set, and transmit the CRRT quantitative prescription to the CRRT device.

[0095] The solution presented in this invention represents a paradigm shift from traditional experience-based forward recommendation to goal-oriented inverse problem-solving and collaborative optimization. In the CRRT field, it uses clinical physiological treatment goals as system input and employs a computational model to inversely solve for device execution parameters. This fundamentally differs from existing methods that rely on patient data for forward matching and recommendation lists, truly achieving intelligent generation of treatment prescriptions. It can automatically coordinate mutually constraining parameter adjustment suggestions based on clinical priorities, effectively resolving multi-objective conflicts and intelligently generating globally optimized comprehensive treatment plans. This significantly improves the quality of treatment decisions in complex and critical situations, achieving a complete closed loop from intelligent algorithms to bedside practice, and providing a feasible, traceable, and controllable intelligent solution for clinical treatment.

[0096] Example 3

[0097] Figure 3 This is a schematic diagram of a CRRT quantitative prescription generation device according to Embodiment 3 of the present invention. Figure 3 As shown, the device includes: an acquisition module 310, a prescription parameter determination module 320, a prescription parameter verification module 330, and a prescription generation module 340.

[0098] The acquisition module 310 is used to acquire the basic feature data of the target CRRT patient and the target parameters preset by the doctor, and to standardize the basic feature data and the target parameters to obtain CRRT standard data that matches the target CRRT patient.

[0099] The prescription parameter determination module 320 is used to determine prescription parameters based on the CRRT standard data, wherein the prescription parameters include therapeutic dose, blood flow rate, filtration fraction, replacement fluid formula, citrate infusion rate, calcium infusion rate, and sodium bicarbonate requirement.

[0100] The prescription parameter verification module 330 is used to generate a first prescription parameter set based on each of the prescription parameters, and to verify the first prescription parameter set.

[0101] The prescription generation module 340 is used to generate a CRRT quantized prescription based on the first prescription parameter set in response to the verification pass instruction of the first prescription parameter set, and transmit the CRRT quantized prescription to the CRRT device.

[0102] In an optional implementation of this embodiment, the acquisition module 310 is specifically used to acquire, in real time, the basic characteristic data of the target CRRT patient and the target parameters preset by the doctor through a data interface; wherein, the basic characteristic data includes: patient characteristic data, laboratory test data, and dynamic physiological data; the target parameters include effect parameters and operational parameters; the effect parameters include target ultrafiltration volume, target electrolyte range, target filtration fraction, and target treatment dose; the operational parameters include blood flow rate, predilution flow rate, postdilution flow rate, and net ultrafiltration volume;

[0103] The basic feature data and target parameters are processed by timestamp alignment, outlier handling, missing value imputation, and feature engineering to obtain CRRT standard data that matches the target CRRT patient.

[0104] In an optional implementation of this embodiment, the prescription parameter determination module 320 includes a first parameter determination submodule, which is used to obtain the blood flow rate, pre-dilution flow rate, post-dilution flow rate and net ultrafiltration volume in the operation parameters when the target parameter includes operation parameters, and calculate the actual treatment dose based on the blood flow rate, pre-dilution flow rate, post-dilution flow rate and net ultrafiltration volume.

[0105] When the target parameter includes an effect parameter, the target treatment dose in the effect parameter is obtained;

[0106] Under the constraints of a preset safe range of blood flow rate, upper limit of filtration fraction, and total limit of replacement fluid, one or more sets of operating parameter combinations that satisfy the target therapeutic dose are obtained; wherein, each set of operating parameter combinations includes the corresponding blood flow rate, pre-dilution flow rate, and post-dilution flow rate;

[0107] Based on the prescription achievement rate in historical treatment records, the combination of operating parameters with the highest prescription achievement rate is selected from the combinations of operating parameters.

[0108] In an optional implementation of this embodiment, the prescription parameter determination module 320 includes a second parameter determination submodule, used to calculate the filtration fraction based on the post-dilution flow rate, blood flow rate, hematocrit, and net ultrafiltration volume when it is determined that the target parameter does not include the target filtration fraction, and to determine whether the filtration fraction exceeds a preset filtration fraction safety threshold; if the filtration fraction exceeds the filtration fraction safety threshold, a filter coagulation risk warning is issued;

[0109] If the target parameters include the target filtration fraction, the post-dilution flow rate that satisfies the target filtration fraction is calculated based on the target filtration fraction, blood flow rate, hematocrit, and net ultrafiltration volume. Based on the constraint of constant total replacement fluid volume, the pre-dilution flow rate is set to the difference between the total replacement fluid volume and the post-dilution flow rate to generate a combination of operating parameters that satisfies the target filtration fraction.

[0110] In an optional implementation of this embodiment, the prescription parameter determination module 320 includes a third parameter determination submodule for constructing an electrolyte mass balance equation set. The electrolyte mass balance equation set is based on the law of conservation of mass, and the sum of the products of the concentration and amount of electrolyte in each base solution is equal to the sum of the product of the concentration of electrolyte in the target replacement fluid and the total volume of the replacement fluid and the baseline adjustment amount based on the patient's metabolism.

[0111] Based on the target electrolyte concentration range and total osmotic pressure limit, the electrolyte mass balance equations are solved to generate a set of candidate formulations that satisfy all constraints. The set of candidate formulations contains multiple candidate formulations, and each candidate formulation contains the specific amount of each base solution.

[0112] Based on preset stability evaluation rules, each candidate formulation is scored to obtain a stability score for each candidate formulation; the stability score characterizes the risk of the candidate formulation causing electrolyte fluctuations or arrhythmias in the current patient.

[0113] The candidate formulation with the highest stability score was selected as the final recommended replacement fluid formulation.

[0114] In an optional implementation of this embodiment, the prescription parameter determination module 320 includes a fourth parameter determination submodule, which is used to calculate the citrate infusion rate based on the target blood flow rate and the citrate concentration type. The citrate infusion rate is equal to the product of the target blood flow rate and a preset proportional coefficient, and the preset proportional coefficient is configured according to the citrate concentration.

[0115] The total calcium loss rate is calculated based on the citrate infusion rate, pre-dilution clearance component, post-dilution clearance component, dialysate clearance component, citrate waste clearance component, patient free calcium concentration, and hematocrit. The calcium infusion rate is then calculated based on the total calcium loss rate, calcium ion concentration in the replacement fluid, and the conversion coefficient corresponding to the calcium agent type. The calcium infusion rate is then corrected according to the calcium supplementation pathway type.

[0116] Calculate the amount of sodium bicarbonate required for citric acid metabolism, compare the actual amount of sodium bicarbonate infused with the required amount, and trigger an acid-base balance risk warning based on the comparison results.

[0117] In an optional implementation of this embodiment, the fourth parameter determining submodule is further used to determine the initial difference between the actual amount of sodium bicarbonate infused and the required amount of sodium bicarbonate.

[0118] Based on the initial difference, effective blood flow rate, and predilution flow rate, the corrected difference is determined;

[0119] Calculate the percentage of the corrected difference relative to the required amount of sodium bicarbonate;

[0120] When the corrected difference is positive and the percentage exceeds the first preset threshold, a warning for the risk of citrate accumulation / hypernadium is triggered.

[0121] When the corrected difference is negative and the absolute value of the percentage exceeds the second preset threshold, an acid poisoning risk warning is triggered.

[0122] The CRRT quantitative prescription generation device provided in this embodiment of the invention can execute the CRRT quantitative prescription generation method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0123] The collection, storage, use, processing, transmission, provision, and disclosure of patient data involved in the technical solutions of this invention comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0124] Example 4

[0125] Figure 4 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0126] like Figure 4As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded into the RAM 13 from the storage unit 18. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0127] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0128] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods described above, such as the quantization prescription generation method of CRRT.

[0129] In some embodiments, the CRRT quantitative prescription generation method can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or mounted on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the CRRT quantitative prescription generation method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the CRRT quantitative prescription generation method by any other suitable means (e.g., by means of firmware).

[0130] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0131] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0132] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, erasable programmable read-only memory (EPROM), optical fibers, compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0133] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device for displaying information to the user (e.g., a cathode ray tube (CRT) or liquid crystal display (LCD) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0134] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0135] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system. It addresses the shortcomings of traditional physical hosts and Virtual Private Servers (VPS) in terms of management difficulty and weak business scalability.

[0136] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0137] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

[0138] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the CRRT quantitative prescription generation method as provided in any embodiment of this application.

[0139] In implementing the computer program product, computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including LANs or WANs—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0140] It should be noted that in the embodiments of this application, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, they do not mean that the solution has been or necessarily used.

[0141] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A method for generating a quantitative prescription for CRRT, characterized in that, The method includes: The basic characteristic data of patients undergoing continuous renal replacement therapy (CRRT) and the target parameters preset by the physician are obtained, and the basic characteristic data and the target parameters are standardized to obtain CRRT standard data that matches the target CRRT patients. Prescription parameters are determined based on the CRRT standard data, wherein the prescription parameters include therapeutic dose, blood flow rate, filtration fraction, replacement fluid formulation, citrate infusion rate, calcium infusion rate, and sodium bicarbonate requirement. A first prescription parameter set is generated based on each of the prescription parameters, and the first prescription parameter set is verified. In response to the verification pass instruction of the first prescription parameter set, a CRRT quantitative prescription is generated based on the first prescription parameter set, and the CRRT quantitative prescription is transmitted to the CRRT device.

2. The method for generating a quantitative prescription for CRRT according to claim 1, characterized in that, The process of acquiring the basic characteristic data of the target CRRT patient and the target parameters preset by the doctor, and standardizing the basic characteristic data and the target parameters to obtain CRRT standard data matching the target CRRT patient, includes: The system acquires basic characteristic data of the target CRRT patient and various target parameters preset by the doctor in real time through a data interface. The basic characteristic data includes: patient characteristic data, laboratory test data, and dynamic physiological data. The target parameters include effect parameters and operational parameters. The effect parameters include target ultrafiltration volume, target electrolyte range, target filtration fraction, and target treatment dose. The operational parameters include blood flow rate, predilution flow rate, postdilution flow rate, and net ultrafiltration volume. The basic feature data and target parameters are processed by timestamp alignment, outlier handling, missing value imputation, and feature engineering to obtain CRRT standard data that matches the target CRRT patient.

3. The method for generating a quantitative prescription for CRRT according to claim 2, characterized in that, The step of determining prescription parameters based on the CRRT standard data includes: When the target parameters include operating parameters, the blood flow rate, predilution flow rate, postdilution flow rate, and net ultrafiltration volume in the operating parameters are obtained, and the actual treatment dose is calculated based on the blood flow rate, predilution flow rate, postdilution flow rate, and net ultrafiltration volume. When the target parameter includes an effect parameter, the target treatment dose in the effect parameter is obtained; Under the constraints of a preset safe range of blood flow rate, upper limit of filtration fraction, and total limit of replacement fluid, one or more sets of operating parameter combinations that satisfy the target therapeutic dose are obtained; wherein, each set of operating parameter combinations includes the corresponding blood flow rate, pre-dilution flow rate, and post-dilution flow rate; Based on the prescription achievement rate in historical treatment records, the combination of operating parameters with the highest prescription achievement rate is selected from the combinations of operating parameters.

4. The method for generating a quantitative prescription for CRRT according to claim 2, characterized in that, The step of determining prescription parameters based on the CRRT standard data includes: If the target parameters do not include the target filtration fraction, the filtration fraction is calculated based on the post-dilution flow rate, blood flow rate, hematocrit, and net ultrafiltration volume, and it is determined whether the filtration fraction exceeds a preset filtration fraction safety threshold; if the filtration fraction exceeds the filtration fraction safety threshold, a filter coagulation risk warning is issued. If the target parameters include the target filtration fraction, the post-dilution flow rate that satisfies the target filtration fraction is calculated based on the target filtration fraction, blood flow rate, hematocrit, and net ultrafiltration volume. Based on the constraint of constant total replacement fluid volume, the pre-dilution flow rate is set to the difference between the total replacement fluid volume and the post-dilution flow rate to generate a combination of operating parameters that satisfies the target filtration fraction.

5. The method for generating a quantitative prescription for CRRT according to claim 2, characterized in that, The step of determining prescription parameters based on the CRRT standard data includes: An electrolyte mass balance equation set is constructed, which is based on the law of conservation of mass. The sum of the products of the concentration and amount of electrolyte in each base solution is equal to the sum of the product of the concentration of electrolyte in the target replacement fluid and the total volume of the replacement fluid and the baseline adjustment based on the patient's metabolism. Based on the target electrolyte concentration range and total osmotic pressure limit, the electrolyte mass balance equations are solved to generate a set of candidate formulations that satisfy all constraints. The set of candidate formulations contains multiple candidate formulations, and each candidate formulation contains the specific amount of each base solution. Based on preset stability evaluation rules, each candidate formulation is scored to obtain a stability score for each candidate formulation; the stability score characterizes the risk of the candidate formulation causing electrolyte fluctuations or arrhythmias in the current patient. The candidate formulation with the highest stability score was selected as the final recommended replacement fluid formulation.

6. The method for generating a quantitative prescription for CRRT according to claim 2, characterized in that, The step of determining prescription parameters based on the CRRT standard data includes: The citrate infusion rate is calculated based on the target blood flow rate and citrate concentration type. The citrate infusion rate is equal to the product of the target blood flow rate and a preset proportionality coefficient, which is configured according to the citrate concentration. The total calcium loss rate is calculated based on the citrate infusion rate, pre-dilution clearance component, post-dilution clearance component, dialysate clearance component, citrate waste clearance component, patient free calcium concentration, and hematocrit. Based on the total calcium loss rate, calcium ion concentration in the replacement fluid, and concentration conversion coefficient corresponding to the calcium agent type, the calcium infusion rate is calculated, and the calcium infusion rate is corrected according to the calcium supplementation pathway type. Calculate the amount of sodium bicarbonate required for citric acid metabolism, compare the actual amount of sodium bicarbonate infused with the required amount, and trigger an acid-base balance risk warning based on the comparison results.

7. The method for generating a quantitative prescription for CRRT according to claim 6, characterized in that, The step of comparing the actual amount of sodium bicarbonate infused with the sodium bicarbonate infusion rate, and triggering an acid-base balance risk warning based on the comparison result, includes: Determine the initial difference between the actual amount of sodium bicarbonate infused and the required amount of sodium bicarbonate; Based on the initial difference, effective blood flow rate, and predilution flow rate, the corrected difference is determined; Calculate the percentage of the corrected difference relative to the required amount of sodium bicarbonate; When the corrected difference is positive and the percentage exceeds the first preset threshold, a warning of citrate accumulation or hypernatremia risk is triggered. When the corrected difference is negative and the absolute value of the percentage exceeds the second preset threshold, an acid poisoning risk warning is triggered.

8. A quantitative prescription generation device for CRRT, characterized in that, include: The acquisition module is used to acquire the basic feature data of the target CRRT patient and the target parameters preset by the doctor, and to standardize the basic feature data and the target parameters to obtain CRRT standard data that matches the target CRRT patient. The prescription parameter determination module is used to determine prescription parameters based on the CRRT standard data, wherein the prescription parameters include treatment dose, blood flow rate, filtration fraction, replacement fluid formula, citrate infusion rate, calcium infusion rate, and sodium bicarbonate requirement. The prescription parameter verification module is used to generate a first prescription parameter set based on each of the prescription parameters, and to verify the first prescription parameter set. The prescription generation module is used to generate a CRRT-quantized prescription based on the first prescription parameter set in response to the verification pass instruction of the first prescription parameter set, and transmit the CRRT-quantized prescription to the CRRT device.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and a memory communicatively connected to the at least one processor; The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the CRRT quantitative prescription generation method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the CRRT quantitative prescription generation method according to any one of claims 1-7.

Images