CRRT dose real-time calibration method based on individual gain mapping

Abstract

A CRRT dose real-time calibration method based on individual gain mapping comprises the following steps: acquiring individual parameters of a patient, and constructing a relation curve of prescription dose deviation and compensation strength based on the individual parameters of the patient; and constructing a dose deviation trend set of the prescription dose deviation in the preset time window. And calculating a compensation intensity parameter based on the relation curve of the prescription dose deviation and the compensation intensity and the dose deviation trend set. And calling the compensation intensity parameter in a preset time window, and updating the dialysate and displacement liquid pump speed so as to improve or reduce the flow speed of the dialysate and displacement liquid and obtain a pump speed operation state. Monitoring the pump speed operation state in the current time window, and updating the dialysate and displacement liquid pump speed when the prescription dose deviation exceeds a set threshold value. According to the method, the compensation force and the deviation are in a strict linear relation, the compensation force has time stability in combination with the deviation trend set, and the situation that the pump speed is frequently changed due to short-time level fluctuation is avoided.

Description

Technical Field

[0001] This application relates to the field of medical auxiliary technology, and in particular to a real-time CRRT dose calibration method based on individual gain mapping. Background Technology

[0002] Currently, existing continuous renal replacement therapy (CRRT) equipment still has the following technical shortcomings in terms of dose control: (1) It is impossible to identify and respond to minute dose deviations in real time.

[0003] Most existing technologies are based on the "deviation threshold triggering" method, which only performs compensation when the dose deviation exceeds the set range. They cannot handle the cumulative deviation below the threshold in a timely manner, resulting in a continuous accumulation trend after the dose deviates from the prescription value.

[0004] For example, when the set dose is 30 mL / kg / h, a brief alarm or increased filter resistance causes the actual dose to drop to 28.8 mL / kg / h, with a deviation of only 1.2 mL / kg / h. This deviation does not exceed the ±3 mL / kg / h threshold set by traditional systems, so the device does not trigger compensation. After 2 hours of treatment, the cumulative dose lag can reach more than 2.4 L, making it impossible to return to the prescribed dose level.

[0005] (2) Dosage calculation has a “nonlinear effect” that cannot be reliably compensated by existing technology.

[0006] CRRT dosage is affected by the combined effects of blood pump flow rate, hematocrit, predilution ratio, postdilution ratio, dialysate, and ultrafiltration flow rate. In particular, the predilution portion requires dilution correction factor treatment, resulting in a significant nonlinear change in dosage. Current technologies mostly use flow rate as an approximation of dosage, failing to select an appropriate compensation channel based on the nonlinear effects.

[0007] For example, in patients with a hematocrit of 45%, an increase of 100 mL / h in predilution flow rate results in an actual dose increase of less than 70 mL / h; while in patients with a hematocrit of 20%, the same increase in predilution can result in an increase of more than 120 mL / h. Existing devices use a uniform compensation logic, leading to compensation that is either too small or too large, making it difficult for the dose to stably return to the prescribed level. Summary of the Invention

[0008] This application provides a real-time CRRT dose calibration method based on individual gain mapping, which solves the technical problem in the prior art where the compensation range is too small or too large, making it difficult for the dose to stably return to the prescription.

[0009] The present invention adopts the following technical solution.

[0010] The first aspect of this invention discloses a real-time CRRT dose calibration method based on individual gain mapping, the method comprising: Obtain individual patient parameters and construct a curve showing the relationship between prescription dosage deviation and compensation intensity based on these parameters; Construct a dose deviation trend set of the prescription dose deviation within a preset time window; Based on the relationship curve between the prescription dose deviation and the compensation intensity, and the dose deviation trend set, the compensation intensity parameter is calculated. Within a preset time window, the compensation intensity parameter is invoked to update the pump speeds of the dialysate and replacement fluid, thereby increasing or decreasing the flow rates of the dialysate and replacement fluid to obtain the pump speed operating status. The pump speed operation status is monitored within the current time window, and the dialysate and replacement fluid pump speeds are updated when the prescription dose deviation exceeds the set threshold.

[0011] Furthermore, the step of obtaining individual patient parameters and constructing a relationship curve between prescription dosage deviation and compensation intensity based on the individual patient parameters includes: Acquire individual patient parameters, including patient weight, hematocrit, blood pump flow rate, and predilution replacement fluid flow rate. Based on the patient's weight, hematocrit, blood pump flow rate, and pre-dilution replacement fluid flow rate, the prescription dose per unit body weight, blood dilution ratio, and mixing ratio of blood and replacement fluid are determined. Based on the prescribed dosage, blood dilution ratio, and blood-to-replacement fluid mixing ratio, a blood correction factor is calculated to quantify the compensation effect.

[0012] Furthermore, the step of obtaining individual patient parameters and constructing a relationship curve between prescription dosage deviation and compensation intensity based on the individual patient parameters also includes: The flow rates of the post-dilution replacement fluid, dialysate, and ultrafiltration are obtained, and the real-time prescription dose is calculated based on the blood correction factor, individual patient parameters, and the flow rates of the post-dilution replacement fluid, dialysate, and ultrafiltration. The prescription dose deviation between the real-time prescription dose and the target prescription dose within multiple preset time windows is calculated, and a relationship curve is constructed by combining the blood correction factor.

[0013] Furthermore, constructing the dose deviation trend set of the prescription dose deviation within a preset time window includes: The prescription dose deviations within multiple preset time windows are obtained at the same time intervals, and a prescription dose deviation sequence is constructed based on the prescription dose deviations within the multiple preset time windows, so as to calculate the deviation persistence ratio according to the prescription dose deviation sequence; Non-zero dose deviations are extracted from the prescription dose deviation sequence and the non-zero dose deviations are corrected to perform directional consistency analysis on the proportion of the deviation persistence, thereby obtaining the deviation directional consistency analysis results.

[0014] Furthermore, constructing the dose deviation trend set of the prescription dose deviation within a preset time window further includes: When the result of the deviation direction consistency analysis is greater than zero, the deviation amplitude trend analysis is performed on the prescription dosage deviation sequence to determine the maximum and minimum deviations within each preset time window, and the deviation amplitude change index is output based on the maximum and minimum deviations. Based on the deviation amplitude change index, deviation persistence ratio, and deviation direction consistency analysis results, the dose deviation trend set is constructed.

[0015] Furthermore, the calculation of the compensation intensity parameter based on the relationship curve between the prescription dosage deviation and the compensation strength, and the dosage deviation trend set, includes: Calculate the mean prescription dose deviation of the prescription dose deviation sequence, and calculate the deviation intensity index based on the mean prescription dose deviation, the proportion of deviation persistence, and the consistency analysis results of deviation direction; Based on the individual patient parameters and the deviation intensity index, the individualized proportional gain of the patient is determined, and the primary compensation intensity is calculated in combination with the deviation amplitude change index. Based on the consistency analysis results of the primary compensation strength and deviation direction, the compensation strength parameter is calculated, which is the product of the primary compensation strength and deviation direction consistency analysis results.

[0016] Furthermore, the step of calling the compensation intensity parameter within a preset time window to update the dialysate and replacement fluid pump speeds, thereby increasing or decreasing the flow rates of the dialysate and replacement fluids to obtain the pump speed operating status, includes: The current pump speed is obtained by a pump speed sensor, and the compensation intensity parameter is converted into a pump speed change. The current pump speed is then adjusted according to the pump speed change to obtain an updated pump speed. In response to the updated pump speed, the operating baseline of the dialysate and replacement fluid pump speeds is determined, and the underlying control CPU is triggered to initialize the operating baseline to generate an initialization flag. The updated pump speed and initialization flag are encapsulated into a flow rate update result package.

[0017] Furthermore, the monitoring of the pump speed operation status within the current time window, and the updating of the dialysate and replacement fluid pump speeds when the prescription dosage deviation exceeds a set threshold, includes: Based on the flow rate update result package, the pump speed operation status is monitored to obtain the current prescription dose within the current time window, and the deviation between the current prescription dose and the target prescription dose is calculated. The current prescription dose deviation is written into the dose deviation trend set to determine the deviation convergence index within the current time window, and the pump speed operation status is updated according to the deviation convergence index.

[0018] A second aspect of the present invention discloses a real-time CRRT dose calibration device based on individual gain mapping, used to implement the real-time CRRT dose calibration method based on individual gain mapping as described in any one of the first aspects, the device comprising: The individual mapping construction module is used to obtain individual patient parameters and construct a relationship curve between prescription dose deviation and compensation intensity based on the individual patient parameters; The deviation trend construction module is used to construct a set of dose deviation trends for the prescription dose deviation within a preset time window; The compensation intensity calculation module is used to calculate the compensation intensity parameters based on the relationship curve between the prescription dose deviation and the compensation intensity, as well as the dose deviation trend set. The pump speed update module is used to call the compensation intensity parameter within a preset time window to update the pump speed of dialysate and replacement fluid, so as to increase or decrease the flow rate of dialysate and replacement fluid and obtain the pump speed operating status. The pump speed monitoring module is used to monitor the pump speed operation status within the current time window and update the dialysate and replacement fluid pump speeds when the prescription dose deviation exceeds a set threshold.

[0019] A third aspect of the present invention discloses a terminal, including a processor and a storage medium; The storage medium is used to store instructions; The processor is configured to operate according to the instructions to perform the steps of the method described in the first aspect.

[0020] A fourth aspect of the present invention discloses a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in the first aspect.

[0021] Compared with the prior art, this application has the following advantages: (1) This invention generates an individual gain mapping based on individual patient parameters to form a proportional relationship curve between dose deviation and compensation intensity, which serves as the basis for subsequent compensation calculations. Then, at a set time period, the real-time dose and average dose are sampled to calculate the dose deviation between the two and the prescription dose, and the current deviation trend is determined. At the same time, the dose deviation accumulated over multiple time windows generates a complete deviation trend set, including structured features such as whether the deviation is continuous, whether the deviation direction is consistent, and whether the deviation amplitude is gradually decreasing or increasing, providing a data foundation for the stability of the dose compensation amplitude.

[0022] (2) This invention generates compensation strength parameters by combining the deviation trend set with individual gain mapping, so that the larger the deviation, the stronger the compensation; the longer the deviation lasts, the more defined the compensation cycle. Since there is no deviation threshold, even a very small deviation will generate a corresponding compensation strength. Individual gain mapping ensures that the compensation strength of patients with different weights is consistent with their actual metabolic scale. Furthermore, through proportional mapping, the compensation strength and deviation are made to have a strict linear relationship, achieving control without blind spots. Combined with the deviation trend set, the compensation strength is further made to have time stability, effectively avoiding the frequent changes in pump speed due to short-term fluctuations, and improving the stability of the compensation amplitude. Attached Figure Description

[0023] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0024] Figure 1 This is a flowchart illustrating the real-time CRRT dose calibration method based on individual gain mapping provided by the present invention.

[0025] Figure 2 This is a schematic diagram of the CRRT dose real-time calibration device based on individual gain mapping provided by the present invention.

[0026] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0027] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0028] like Figure 1 As shown, in one embodiment, a real-time CRRT dose calibration method based on individual gain mapping includes the following steps: Step S110: Obtain individual patient parameters and construct a curve showing the relationship between prescription dose deviation and compensation intensity based on the individual patient parameters.

[0029] In some embodiments, the CRRT dose real-time calibration method based on individual gain mapping provided by the present invention includes the following steps in step S110: Step S111: Obtain individual patient parameters, including patient weight, hematocrit, blood pump flow rate, and predilution replacement fluid flow rate.

[0030] Step S112: Based on the patient's weight, hematocrit, blood pump flow rate, and pre-dilution replacement fluid flow rate, determine the prescription dose per unit body weight, blood dilution ratio, and the mixing ratio of blood and replacement fluid.

[0031] Step S113: Calculate the blood correction factor used to quantify the compensation strength based on the prescription dose per unit weight, blood dilution ratio, and the mixing ratio of blood and replacement fluid.

[0032] In some embodiments, the CRRT dose real-time calibration method based on individual gain mapping provided by the present invention further includes the following steps in step S110: Step S114: Obtain the post-dilution replacement fluid flow rate, dialysate flow rate, and ultrafiltration flow rate, and calculate the real-time prescription dose based on the blood correction factor, individual patient parameters, and the post-dilution replacement fluid flow rate, dialysate flow rate, and ultrafiltration flow rate.

[0033] Step S115: Calculate the prescription dose deviation between the real-time prescription dose and the target prescription dose within multiple preset time windows, and construct a relationship curve by combining the blood correction factor.

[0034] In a specific embodiment, the CRRT dose real-time calibration method based on individual gain mapping provided by the present invention includes steps 1 to 5: Step 1: Construct an individual gain mapping and high-frequency monitoring mechanism for dose deviation.

[0035] First, an individual gain map is generated based on individual patient parameters. This gain map is used to form a curve showing the proportional relationship between dose deviation and compensation strength, serving as the basis for subsequent compensation calculations. Then, the real-time dose and average dose are sampled every ten seconds, and the difference between these two doses and the prescribed dose is calculated to determine the current deviation trend. This includes the following sub-steps: Sub-step 1.1: Data reading and blood correction factor calculation.

[0036] Specifically, patient weight (expressed as BW in kilograms, ranging from 1 to 200 kg) is read to quantify the dose per unit body weight; patient hematocrit is used to determine the blood dilution ratio; and blood pump flow rate and pre-dilution replacement fluid flow rate are used to describe the mixing ratio of blood and replacement fluid. A blood correction factor is calculated based on the above data. The expression is:

[0037] In the formula, The patient's hematocrit ranges from 0 to 1. Blood pump flow rate, measured in milliliters per minute, ranging from 50 to 300. Predilution replacement fluid flow rate, in milliliters per hour, ranging from 0 to 6000, blood correction factor. The value is between 0 and 1, used to correct for the actual effect of blood dilution on the dose.

[0038] Sub-step 1.2: Real-time prescription dosage calculation.

[0039] Specifically, based on sub-step 1.1, the post-dilution replacement fluid flow rate, dialysate flow rate, and ultrafiltration flow rate are obtained. Combined with the blood correction factor, patient weight, and pre-dilution replacement fluid flow rate, the real-time prescription dose is calculated. The expression is:

[0040] In the formula, , , These are the flow rates of the post-dilution replacement fluid, dialysate, and ultrafiltration fluid, in milliliters per hour; real-time prescription dosage. The unit is milliliters per kilogram per hour, used to reflect the treatment dose received by the patient in real time.

[0041] Sub-step 1.3, instantaneous dose deviation calculation.

[0042] Specifically, the real-time prescription dosage is read with a fixed sampling period of ten seconds. The instantaneous dose deviation is obtained by comparing the instantaneous dose with the target prescription dose (unit: milliliters per kilogram per hour) and calculating the difference between the target prescription dose and the average real-time prescription dose for each cycle. A positive instantaneous dose deviation indicates that the actual dose is insufficient, while a negative value indicates that the actual dose is excessive.

[0043] Sub-step 1.4: Deviation sequence generation.

[0044] Specifically, at fixed intervals of ten seconds, sixty consecutive instantaneous dose deviations are written into a deviation sequence, forming a ten-minute deviation observation window. Represented as:

[0045] Sixty sampling points cover the entire ten-minute cycle and are used for subsequent analysis of deviation trends.

[0046] Step S120: Construct a dose deviation trend set of prescription dose deviation within a preset time window.

[0047] In some embodiments, the CRRT dose real-time calibration method based on individual gain mapping provided by the present invention includes the following steps in step S120: Step S121: Obtain prescription dose deviations within multiple preset time windows at the same time interval, and construct a prescription dose deviation sequence based on the prescription dose deviations within the multiple preset time windows, so as to calculate the deviation persistence ratio according to the prescription dose deviation sequence.

[0048] Step S122: Extract non-zero dose deviations from the prescription dose deviation sequence and calibrate the non-zero dose deviations to perform directional consistency analysis on the proportion of deviation persistence, and obtain the deviation directional consistency analysis results.

[0049] In some embodiments, the CRRT dose real-time calibration method based on individual gain mapping provided by the present invention further includes the following steps in step S120: Step S123: When the consistency analysis result of the deviation direction is greater than zero, perform deviation amplitude trend analysis on the prescription dosage deviation sequence to determine the maximum and minimum deviations within each preset time window, and output the deviation amplitude change index based on the maximum and minimum deviations.

[0050] Step S124: Based on the deviation amplitude change index, deviation persistence ratio, and deviation direction consistency analysis results, construct a dose deviation trend set.

[0051] In a specific embodiment, the CRRT dose real-time calibration method based on individual gain mapping provided by the present invention includes step 2, which involves constructing a dose deviation trend set within a ten-minute time window based on the deviation sequence. The dose deviation sequence output in step 1 is continuously accumulated to a ten-minute time window to generate a complete deviation trend set. This set includes structured features such as whether the deviation is continuous, whether the deviation direction is consistent, and whether the deviation amplitude is gradually decreasing or increasing. This includes the following sub-steps: Sub-step 2.1, calculation of the deviation persistence ratio.

[0052] Specifically, first, the deviation sequence output in step 1 is read. This sequence consists of sixty consecutive instantaneous deviations, representing the deviation values ​​obtained by monitoring once every ten seconds over the past ten minutes. Then, the number of non-zero deviations in the sequence is counted, and the deviation persistence ratio is calculated. This ratio is equal to the number of non-zero deviations in the sequence as the numerator and 60, with a value ranging from 0 to 1. The higher the value, the more persistent the deviation.

[0053] Sub-step 2.2, Deviation direction consistency analysis.

[0054] Specifically, read the deviation persistence ratio output from sub-step 2.1, and when the deviation persistence ratio is greater than zero, proceed to directional consistency analysis. Extract all non-zero deviations from the deviation sequence, and compare their signs (positive or negative) with the sign of the first non-zero deviation. Count the number of signs that match. The directional consistency analysis result is expressed as the ratio of the number of signs that match to the number of non-zero deviations in the numerator and the sequence. The range is 0 to 1. The higher the value, the more concentrated the deviation direction is, such as persistently low or persistently high deviations.

[0055] Sub-step 2.3: Calculation of the deviation amplitude change index.

[0056] Specifically, when the direction consistency analysis result is greater than zero, deviation amplitude trend analysis is performed. All instantaneous deviation values ​​in the deviation sequence are scanned, the maximum and minimum values ​​are obtained, and the difference between the maximum and minimum values ​​is calculated. This is the deviation amplitude change index. If the index is positive, it means that the deviation amplitude is expanding, while a negative value means that the deviation amplitude is shrinking. It is used to characterize whether the deviation tends to spread or converge. It is a key parameter for judging whether the compensation intensity needs to be strengthened in subsequent compensation strategies.

[0057] Sub-step 2.4: Construction of the ten-minute deviation trend set.

[0058] Specifically, the above-mentioned deviation persistence ratio, deviation direction consistency analysis results, and deviation amplitude change trend are integrated into a ternary set to represent the overall behavioral pattern of deviation within a ten-minute window, including whether the deviation is persistent, whether the direction is consistent, and whether the deviation amplitude is expanding or shrinking, and finally output a ten-minute deviation trend set.

[0059] Step S130: Calculate the compensation intensity parameter based on the relationship curve between prescription dose deviation and compensation strength, and the dose deviation trend set.

[0060] In some embodiments, the CRRT dose real-time calibration method based on individual gain mapping provided by the present invention includes the following steps in step S130: Step S131: Calculate the mean prescription dose deviation of the prescription dose deviation sequence, and calculate the deviation intensity index based on the mean prescription dose deviation, the proportion of deviation persistence, and the consistency analysis results of deviation direction.

[0061] Step S132: Based on the patient's individual parameters and deviation intensity index, determine the patient's individualized proportional gain, and calculate the primary compensation intensity by combining the deviation amplitude change index.

[0062] Step S133: Calculate the compensation strength parameter based on the consistency analysis results of the primary compensation strength and the deviation direction. The compensation strength parameter is the product of the consistency analysis results of the primary compensation strength and the deviation direction.

[0063] In a specific embodiment, the CRRT dose real-time calibration method based on individual gain mapping provided by the present invention includes step 3, which calculates the proportional compensation intensity based on the individual gain mapping and trend set. The deviation trend set output in step 2 is combined with the individual gain mapping output in step 1 to generate a compensation intensity parameter. This parameter reflects that the larger the deviation, the stronger the compensation; the longer the deviation persists, the more defined the compensation cycle; and since there is no deviation threshold, even a very small deviation will generate a corresponding compensation intensity. The individual gain mapping ensures that the compensation intensity for patients of different weights is consistent with their actual metabolic scale. Step 3, through proportional mapping, ensures a strictly linear relationship between the compensation intensity and the deviation, achieving dead-zone-free control. Simultaneously, by combining the trend set, the compensation intensity possesses time stability, avoiding frequent changes in pump rate due to fluctuations at the ten-second level. This includes the following sub-steps: Sub-step 3.1: Calculation of deviation intensity index.

[0064] Specifically, the dose deviation trend set is analyzed, and the deviation persistence ratio, deviation direction consistency analysis results, and deviation amplitude change trends are extracted to construct the deviation intensity weights. Then, the average deviation is calculated for the deviation sequence to reflect the average level of deviation within a ten-minute window; this is equal to the ratio of the sum of deviations in the deviation sequence (numerator) to 60. Finally, the deviation persistence, direction consistency analysis results, and average deviation are combined to form a deviation intensity index, which is equal to the product of the deviation persistence, direction consistency analysis results, and average deviation, expressed in milliliters per kilogram per hour. A higher value indicates a stronger and more persistent deviation.

[0065] Sub-step 3.2, Individualized proportional gain calculation.

[0066] Specifically, patient weight is read, and an individual gain mapping is constructed based on this weight. This ensures that the compensation intensity for patients of different weights is matched according to their metabolic scale, resulting in an individualized proportional gain. This proportional gain is equal to the ratio of the patient's weight (the numerator) to 30, where 30 is a constant in the clinical experience model (adjustable within a range of 20 to 40). This constant maps linear changes in weight to changes in gain, making the gain magnitude controllable. Subsequently, the obtained proportional gain is used to correct the bias intensity index, ensuring its suitability across patients of different weights.

[0067] Sub-step 3.3, calculation of primary compensation intensity.

[0068] Specifically, based on the aforementioned proportional gain and deviation intensity indices, the basic compensation intensity is calculated by proportional amplification. Then, combining the amplitude change index output from step 2, a correction for the compensation intensity based on the deviation trend is introduced to calculate the primary compensation intensity. The expression is:

[0069] In the formula, For proportional gain; This is a deviation intensity index, measured in milliliters per kilogram per hour. A positive value indicates that the deviation is widening and compensation should be increased; a negative value indicates that the deviation is converging and compensation should be appropriately reduced.

[0070] Sub-step 3.4: The final compensation strength parameters are determined.

[0071] Specifically, to avoid overly sensitive compensation due to real-time fluctuations on the order of ten seconds, a time stability weighting is applied to the primary compensation intensity based on the deviation direction consistency analysis results. A higher direction consistency analysis result indicates greater deviation stability, allowing the compensation intensity to be fully released; conversely, a lower result requires a reduction in compensation intensity to prevent system oscillation. Therefore, the final compensation intensity parameter equals the product of the primary compensation intensity and the direction consistency analysis result, expressed in milliliters per kilogram per hour. This parameter serves as the input for subsequent pump speed adjustment, preventing frequent fluctuations in pump speed due to instantaneous deviation direction changes, thus ensuring stable and smooth compensation output that conforms to a ten-minute update cycle. Simultaneously, the flow rate of each pump can be determined based on the compensated prescription dosage.

[0072] Step S140: Within a preset time window, call the compensation intensity parameter to update the pump speed of dialysate and replacement fluid to increase or decrease the flow rate of dialysate and replacement fluid, thereby obtaining the pump speed operating status.

[0073] In some embodiments, the CRRT dose real-time calibration method based on individual gain mapping provided by the present invention includes the following steps in step S140: Step S141: Obtain the current pump speed through the pump speed sensor, and convert the compensation intensity parameter into the pump speed change amount, so as to adjust the current pump speed according to the pump speed change amount to obtain the updated pump speed.

[0074] In step S142, in response to the updated pump speed, the operating baseline of the dialysate and replacement fluid pump speeds is determined, and the underlying control CPU is triggered to initialize the operating baseline to generate an initialization flag.

[0075] Step S143: Encapsulate the updated pump speed and initialization flag into a flow rate update result package.

[0076] In a specific embodiment, the CRRT dose real-time calibration method based on individual gain mapping provided by this invention includes step 4, which involves performing a low-frequency flow rate update every ten minutes. Every ten minutes, the compensation intensity parameter from step 3 is invoked to perform a unified update of the dialysate or replacement fluid pump rate (the update includes increasing or decreasing the flow rate). This update triggers the underlying control CPU to initialize the relevant processes, enabling all backend algorithms (including pump rate adjustment and filter weight calculation) to reconstruct a stable operating baseline. This includes the following sub-steps: Sub-step 4.1: Flow rate adjustment amount is generated.

[0077] Specifically, the final compensation intensity parameter output from step 3 is read. This parameter, measured in milliliters per kilogram per hour, represents the magnitude by which the pump rate should increase or decrease within a ten-minute update cycle. To ensure the compensation intensity matches the actual controllable range of the pump, the final compensation intensity parameter is converted into the pump rate change per unit time. This is equal to the product of the final compensation intensity parameter, the patient's weight, and 0.167, where 0.167 is the conversion factor, representing the ratio of "hourly parameter to ten-minute parameter" (i.e., 10 minutes divided by 60 minutes).

[0078] Sub-step 4.2, pump speed update.

[0079] Specifically, the current pump speed (in milliliters per hour) is obtained from the pump speed sensor. Then, based on the change in pump speed, an increase or decrease is performed to update the speed. The updated pump speed is equal to the product of the current pump speed and the change in pump speed. A positive change in pump speed indicates that the pump speed needs to be increased, while a negative change indicates that the pump speed needs to be decreased. During the increase or decrease of pump speed, the system automatically checks whether the pump speed is within the equipment's safe range. For example, the maximum pump speed must not exceed 450 ml / min, and the minimum pump speed must not be lower than 20 ml / min. If the speed exceeds the range, the updated pump speed is limited to the allowable range.

[0080] Sub-step 4.3: Run baseline initialization.

[0081] Specifically, after the updated pump speed is sent to the underlying pump control module, an initialization operation of the operating baseline needs to be performed to ensure that all downstream control algorithms (including filter weight estimation, ultrafiltration volume calculation, and anticoagulant ratio control) can use a unified baseline state. The initialization operation is completed by refreshing the status register and accumulated variables inside the control CPU. After the initialization is performed, a flag bit is generated with a fixed value of 1 (Boolean "initialized"), which is used to indicate that the initialization was successful and to notify the backend module to start rebuilding the computing environment.

[0082] Sub-step 4.4: Flow rate update result package generated.

[0083] Specifically, the generated flag bit is read. If the flag bit is 1, it confirms that the underlying CPU initialization is complete. Then, the new pump rate and the initialization state are encapsulated together to form a flow rate update result packet. This result packet will be sent to the next step to verify key items such as "whether the pump rate update is stable" and "whether a new dose deviation trend has been introduced".

[0084] Step S150: Monitor the pump speed operation status within the current time window, and update the dialysate and replacement fluid pump speeds when the prescription dose deviation exceeds the set threshold.

[0085] In some embodiments, the CRRT dose real-time calibration method based on individual gain mapping provided by the present invention includes the following steps in step S150: Step S151: Based on the flow rate update result package, monitor the pump speed operation status to obtain the current prescription dose within the current time window, and calculate the current prescription dose deviation between the current prescription dose and the target prescription dose.

[0086] Step S152: Write the current prescription dose deviation into the dose deviation trend set to determine the deviation convergence index within the current time window, and update the pump speed operation status according to the deviation convergence index.

[0087] In a specific embodiment, the CRRT dose real-time calibration method based on individual gain mapping provided by the present invention includes step 5, which involves dose convergence calibration based on the pump speed execution state and completing real-time closed-loop control. The pump speed execution state output in step 4 is then incorporated into the next ten-second monitoring cycle to continuously compress the deviation, allowing the long-term average dose to gradually converge to the prescribed target dose within a sufficient treatment time. During the compensation process, a deviation-free threshold ensures that once the deviation decreases, the compensation intensity decreases synchronously, thus naturally tending towards a stable point. The ten-minute execution rhythm ensures that no oscillations occur. The method includes the following sub-steps: Sub-step 5.1: Read the pump speed execution result and enter the ten-second monitoring cycle.

[0088] Specifically, the output packet of step 4 is parsed to determine whether the new pump speed and underlying initialization are successful. A new ten-second monitoring cycle is entered, the real-time dose within the ten-second interval is obtained from the sensor, and a new deviation value is immediately calculated, which is equal to the difference between the dose at this time and the target dose.

[0089] Sub-step 5.2: Update the deviation sequence and generate a new deviation accumulation.

[0090] Specifically, the new deviation value is added to the previous deviation sequence as the latest deviation point to form a new deviation sequence. This deviation sequence is a vector whose length increases over time, and each element is the deviation value obtained from a ten-second sampling. At the same time, the cumulative deviation is updated to determine whether the deviation is in a shrinking or expanding trend.

[0091] Sub-step 5.3: Calculate the dose convergence rate and determine whether the system tends to stabilize.

[0092] Specifically, based on the latest several deviation points in the new deviation sequence, the deviation convergence rate is calculated. It is equal to the ratio of the difference between the current cycle deviation and the previous ten-second cycle deviation as the numerator to the sampling period (which is a constant of 10 seconds). If the deviation convergence rate is negative, the deviation is shrinking, indicating that it is approaching convergence; if it is positive, the deviation is expanding, and compensation is needed in the next cycle.

[0093] Sub-step 5.4: Complete the closed-loop stability determination based on the threshold-free compensation mechanism.

[0094] Specifically, the current cycle deviation and the deviation convergence speed are used to determine whether the natural stable point has been reached. Since the compensation algorithm does not set a deviation threshold, as the current cycle deviation gradually approaches zero, the compensation amount naturally decreases with the current cycle deviation, thus forming a stable condition. That is, if the absolute value of the current cycle deviation continues to decrease and the deviation convergence speed is less than zero, the closed-loop status flag (Boolean flag) is set to 1; otherwise, the closed-loop status flag is set to 0. This achieves the final closed-loop determination, allowing the system to automatically stabilize without human intervention, thereby ensuring that the long-term average dose converges to the prescription dose.

[0095] The CRRT dose real-time calibration device based on individual gain mapping provided by the present invention will be described below. The CRRT dose real-time calibration device based on individual gain mapping described below can be referred to in correspondence with the CRRT dose real-time calibration method based on individual gain mapping described above.

[0096] like Figure 2 As shown, in one embodiment, a real-time CRRT dose calibration device based on individual gain mapping includes an individual mapping construction module, a deviation trend construction module, a compensation intensity calculation module, a pump speed update module, and a pump speed monitoring module.

[0097] The individual mapping construction module is used to obtain individual patient parameters and construct a relationship curve between prescription dose deviation and compensation intensity based on the individual patient parameters.

[0098] The deviation trend construction module is used to construct a set of dosage deviation trends for prescription dosage deviation within a preset time window.

[0099] The compensation intensity calculation module is used to calculate the compensation intensity parameters based on the relationship curve between prescription dose deviation and compensation intensity, as well as the dose deviation trend set.

[0100] The pump speed update module is used to call the compensation intensity parameter within a preset time window to update the pump speed of dialysate and replacement fluid, so as to increase or decrease the flow rate of dialysate and replacement fluid and obtain the pump speed operating status.

[0101] The pump speed monitoring module is used to monitor the pump speed operation status within the current time window and update the dialysate and replacement fluid pump speeds when the prescription dose deviation exceeds the set threshold.

[0102] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this application.

[0103] It should be further noted that although the steps in the flowchart are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowchart may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0104] It should be understood that the above-described device embodiments are merely illustrative, and the device of this application can also be implemented in other ways. For example, the division of units / modules in the above embodiments is only a logical functional division, and there may be other division methods in actual implementation. For example, multiple units, modules, or components may be combined, or integrated into another system, or some features may be ignored or not executed.

[0105] Furthermore, unless otherwise specified, the functional units / modules in the various embodiments of this application can be integrated into one unit / module, or each unit / module can exist physically separately, or two or more units / modules can be integrated together. The integrated units / modules described above can be implemented in hardware or as software program modules.

[0106] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification.

[0107] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0108] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope.

Claims

1. A real-time CRRT dose calibration method based on individual gain mapping, characterized in that, The method includes: Obtain individual patient parameters and construct a curve showing the relationship between prescription dosage deviation and compensation intensity based on these parameters; Construct a dose deviation trend set of the prescription dose deviation within a preset time window; Based on the relationship curve between the prescription dose deviation and the compensation intensity, and the dose deviation trend set, the compensation intensity parameter is calculated. Within a preset time window, the compensation intensity parameter is invoked to update the pump speeds of the dialysate and replacement fluid, thereby increasing or decreasing the flow rates of the dialysate and replacement fluid to obtain the pump speed operating status. The pump speed operation status is monitored within the current time window, and the dialysate and replacement fluid pump speeds are updated when the prescription dose deviation exceeds the set threshold.

2. The CRRT dose real-time calibration method based on individual gain mapping according to claim 1, characterized in that, The process of acquiring individual patient parameters and constructing a relationship curve between prescription dosage deviation and compensation intensity based on these parameters includes: Acquire individual patient parameters, including patient weight, hematocrit, blood pump flow rate, and predilution replacement fluid flow rate. Based on the patient's weight, hematocrit, blood pump flow rate, and pre-dilution replacement fluid flow rate, the prescription dose per unit body weight, blood dilution ratio, and mixing ratio of blood and replacement fluid are determined. Based on the prescribed dosage, blood dilution ratio, and blood-to-replacement fluid mixing ratio, a blood correction factor is calculated to quantify the compensation effect.

3. The CRRT dose real-time calibration method based on individual gain mapping according to claim 2, characterized in that, The step of obtaining individual patient parameters and constructing a relationship curve between prescription dosage deviation and compensation intensity based on the individual patient parameters further includes: The flow rates of the post-dilution replacement fluid, dialysate, and ultrafiltration are obtained, and the real-time prescription dose is calculated based on the blood correction factor, individual patient parameters, and the flow rates of the post-dilution replacement fluid, dialysate, and ultrafiltration. The prescription dose deviation between the real-time prescription dose and the target prescription dose within multiple preset time windows is calculated, and a relationship curve is constructed by combining the blood correction factor.

4. The CRRT dose real-time calibration method based on individual gain mapping according to claim 1, characterized in that, The construction of the dose deviation trend set within a preset time window includes: The prescription dose deviations within multiple preset time windows are obtained at the same time intervals, and a prescription dose deviation sequence is constructed based on the prescription dose deviations within the multiple preset time windows, so as to calculate the deviation persistence ratio according to the prescription dose deviation sequence; Non-zero dose deviations are extracted from the prescription dose deviation sequence and the non-zero dose deviations are corrected to perform directional consistency analysis on the proportion of the deviation persistence, thereby obtaining the deviation directional consistency analysis results.

5. The CRRT dose real-time calibration method based on individual gain mapping according to claim 4, characterized in that, The step of constructing the dose deviation trend set of the prescription dose deviation within a preset time window further includes: When the result of the deviation direction consistency analysis is greater than zero, the deviation amplitude trend analysis is performed on the prescription dosage deviation sequence to determine the maximum and minimum deviations within each preset time window, and the deviation amplitude change index is output based on the maximum and minimum deviations. Based on the deviation amplitude change index, deviation persistence ratio, and deviation direction consistency analysis results, the dose deviation trend set is constructed.

6. The CRRT dose real-time calibration method based on individual gain mapping according to claim 5, characterized in that, The calculation of the compensation intensity parameter based on the relationship curve between the prescription dosage deviation and the compensation intensity, and the dosage deviation trend set, includes: Calculate the mean prescription dose deviation of the prescription dose deviation sequence, and calculate the deviation intensity index based on the mean prescription dose deviation, the proportion of deviation persistence, and the consistency analysis results of deviation direction; Based on the individual patient parameters and the deviation intensity index, the individualized proportional gain of the patient is determined, and the primary compensation intensity is calculated in combination with the deviation amplitude change index. Based on the consistency analysis results of the primary compensation strength and deviation direction, the compensation strength parameter is calculated, which is the product of the primary compensation strength and deviation direction consistency analysis results.

7. The CRRT dose real-time calibration method based on individual gain mapping according to claim 1, characterized in that, The step of calling the compensation intensity parameter within a preset time window to update the dialysate and replacement fluid pump speeds, thereby increasing or decreasing the flow rates of the dialysate and replacement fluids, and obtaining the pump speed operating status, includes: The current pump speed is obtained by a pump speed sensor, and the compensation intensity parameter is converted into a pump speed change. The current pump speed is then adjusted according to the pump speed change to obtain an updated pump speed. In response to the updated pump speed, the operating baseline of the dialysate and replacement fluid pump speeds is determined, and the underlying control CPU is triggered to initialize the operating baseline to generate an initialization flag. The updated pump speed and initialization flag are encapsulated into a flow rate update result package.

8. The CRRT dose real-time calibration method based on individual gain mapping according to claim 7, characterized in that, The monitoring of the pump speed operation status within the current time window, and the updating of the dialysate and replacement fluid pump speeds when the prescription dosage deviation exceeds a set threshold, includes: Based on the flow rate update result package, the pump speed operation status is monitored to obtain the current prescription dose within the current time window, and the deviation between the current prescription dose and the target prescription dose is calculated. The current prescription dose deviation is written into the dose deviation trend set to determine the deviation convergence index within the current time window, and the pump speed operation status is updated according to the deviation convergence index.

9. A terminal, comprising a processor and a storage medium; characterized in that: The storage medium is used to store instructions; The processor is configured to operate according to the instructions to perform the steps of the method according to any one of claims 1-8.

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

Images