An intervention method and system for ischemic pain in the lower extremities of hemodialysis patients

Abstract

The application provides an intervention method and system for lower extremity ischemic pain of hemodialysis patients, the method comprising: collecting physiological parameters reflecting tissue perfusion state of the lower extremity of the patient in real time; performing trend prediction of ischemic pain according to the change trend of the physiological parameters; performing risk level classification according to the trend prediction, wherein the risk level comprises a predictive risk level; and performing an intervention measure matched with the risk level according to the predicted risk level or an active trigger signal of the patient, the intervention measure comprising body position adjustment and / or dialysis ultrafiltration rate adjustment. The physiological basis that there is a clinically intervenable window period from the decrease of tissue perfusion to the occurrence of lower extremity ischemic pain is utilized, the risk is identified before the occurrence of pain through trend prediction, active intervention instead of passive response is realized, and the incidence of lower extremity ischemic pain is significantly reduced.

Description

Technical Field

[0001] This invention relates to the field of medical device technology, and in particular to an intervention method and system for lower limb ischemic pain in hemodialysis patients. Background Technology

[0002] Lower extremity arterial disease (LEAD) is a common complication in hemodialysis patients, with a prevalence ranging from 17% to 48%. During dialysis, the effective circulating blood volume decreases during ultrafiltration, further reducing the already insufficient blood supply to the lower extremities and inducing ischemic pain. Clinical observations have confirmed that pain can be significantly relieved within minutes after patients change from a supine to a sitting position (with lower extremities dangling). The mechanism is that the dangling position utilizes gravity to increase the arterial perfusion pressure in the lower extremities.

[0003] Currently, clinical strategies for managing lower limb ischemic pain during dialysis have the following shortcomings: passive response: treatment is only provided after the patient experiences pain, resulting in intense suffering; lack of predictive ability: existing systems rely solely on absolute threshold values ​​(such as a drop in blood pressure) and cannot utilize trends in tissue perfusion for early prediction; safety hazards: patients may rapidly change position due to severe pain, potentially leading to serious adverse events such as orthostatic hypotension, falls, dialysis tubing dislodgement, or fistula damage; heavy burden on medical staff: reliance on frequent rounds and manual adjustments by nurses.

[0004] Therefore, there is an urgent need for a method that can proactively predict and intervene before pain occurs. Summary of the Invention

[0005] To address the aforementioned problems, the present invention aims to provide an intervention method and system for lower limb ischemic pain in hemodialysis patients. By real-time monitoring of local tissue perfusion status and employing a dual mechanism of "trend prediction + threshold triggering," graded intervention is automatically initiated before the patient experiences pain, thereby achieving "proactive prediction and intervention before pain occurs."

[0006] This invention is achieved through the following technical solution: An intervention method for lower limb ischemic pain in hemodialysis patients includes: Real-time acquisition of physiological parameters reflecting tissue perfusion status in the patient's lower limbs; Based on the changing trends of the aforementioned physiological parameters, the trend of ischemic pain is predicted; Risk levels are classified based on trend forecasts, including predictive risk levels. Based on the predicted risk level or the patient's active triggering signal, interventions matching that risk level are implemented, including postural adjustment and / or dialysis ultrafiltration rate adjustment.

[0007] By adopting the above technical solutions, local tissue perfusion parameters can be used to directly reflect the ischemic state of the lower limbs, and risks can be identified before pain occurs through trend prediction, so as to achieve proactive intervention rather than passive response.

[0008] Furthermore, before collecting physiological parameters of the patient's lower limbs reflecting tissue perfusion status in real time, the method of establishing an individual baseline includes: continuously collecting physiological parameter data of the patient's lower limbs within a predetermined time before the start of dialysis, calculating statistical characteristic values ​​after removing outliers, and using these values ​​as the individual baseline values ​​for this dialysis session.

[0009] By adopting the above technical solution, each patient establishes their own individual baseline value, avoiding misjudgment of fixed thresholds due to individual differences (such as age, vascular condition, hemoglobin concentration, etc.).

[0010] Furthermore, it also includes the step of establishing a personalized dynamic baseline: recording tissue oxygen saturation data at the same dialysis duration during multiple dialysis sessions in the past; calculating the historical mean and standard deviation at each time point to establish a normal fluctuation range; and triggering predictive intervention corresponding to the predictive risk level when the current tissue oxygen saturation is lower than the lower limit of the normal fluctuation range minus a predetermined proportion of the historical mean.

[0011] By adopting the above technical solution, the normal fluctuation range of different dialysis time points can be established using the patient's own historical data, avoiding a "one-size-fits-all" threshold and further improving the accuracy of prediction.

[0012] Furthermore, by utilizing patients' own historical data, normal fluctuation ranges at different dialysis times can be established, avoiding a "one-size-fits-all" threshold and further improving prediction accuracy.

[0013] By adopting the above technical solution, the rate of decline reflects the speed of tissue perfusion deterioration, and the magnitude of decline reflects the degree of deterioration. Combining the two can identify risks earlier.

[0014] Furthermore, when any of the following conditions are met, a predictive risk level is determined, the body position driving module is controlled to execute the first body position adjustment mode corresponding to the predictive risk level, and the ultrafiltration linkage module is controlled to reduce the ultrafiltration rate: the rate of decrease in tissue oxygen saturation monitored within a continuous predetermined time exceeds a first threshold; the dialysis duration exceeds a first duration, the cumulative ultrafiltration volume exceeds a first threshold, and the decrease in tissue oxygen saturation compared to the individual baseline value exceeds a second threshold; the current tissue oxygen saturation is lower than the lower limit of the normal range of the personalized dynamic baseline established based on historical data by more than a third threshold.

[0015] By adopting the above technical solutions, the three triggering conditions complement each other, covering different clinical scenarios and ensuring the sensitivity and specificity of the prediction.

[0016] Furthermore, the risk level includes a warning risk level: when the monitored tissue oxygen saturation decreases by more than the fourth threshold or the skin temperature decreases by more than the fifth threshold, it is determined to be a warning risk level, and the body position drive module is controlled to execute the second body position adjustment mode corresponding to the warning risk level.

[0017] By adopting the above technical solutions, the early warning risk level is activated when predictive intervention fails to prevent deterioration, providing more effective postural intervention.

[0018] Furthermore, the risk level also includes a persistent unrelieved risk level: when the average tissue oxygen saturation during the last predetermined time period after intervention is lower than the sixth threshold of the individual baseline, or when the tissue oxygen saturation monitored within the predetermined time after intervention shows a continuous negative trend and the rate of decline exceeds the seventh threshold, it is determined to be a persistent unrelieved risk level, the ultrafiltration linkage module is controlled to pause or reduce the ultrafiltration rate, and an alarm signal is sent to the medical terminal.

[0019] By adopting the above technical solutions, the persistent unresolved risk level serves as a safety net mechanism to ensure timely notification of medical staff to intervene when automatic intervention is ineffective.

[0020] Furthermore, the intervention method also includes evaluating the intervention effect after the intervention measures are implemented, whether the physiological parameters have reached the safety threshold, if not, raising the risk level to the next level and implementing the corresponding intervention measures; if so, restoring the basic body position and / or maintaining the ultrafiltration rate.

[0021] By adopting the above technical solutions, a closed-loop regulation mechanism is formed to ensure that patients do not remain in the intervention position for a long time, thus avoiding affecting blood pressure stability.

[0022] An intervention system for lower limb ischemic pain in hemodialysis patients, used to perform the above-mentioned methods, includes: a monitoring module for real-time acquisition of physiological parameters reflecting tissue perfusion status in the patient's lower limbs; a control module connected to the monitoring module for executing the trend prediction and intervention determination logic; a body position adjustment module connected to the control module for performing body position adjustment; and an ultrafiltration adjustment module connected to the control module for performing dialysis ultrafiltration rate adjustment.

[0023] By adopting the above technical solutions, a complete closed-loop system from monitoring to intervention is formed, realizing automated and intelligent pain management.

[0024] Compared with the prior art, the technical solution of the present invention and its beneficial effects are as follows: (1) This invention solves the technical problem of the traditional approach of "passive response and treatment only after the patient experiences pain" by collecting physiological parameters reflecting the tissue perfusion status of the patient's lower limbs in real time, predicting the trend of ischemic pain based on the changing trend of the physiological parameters, classifying the risk level according to the trend prediction, and executing intervention measures (including body position adjustment and / or dialysis ultrafiltration rate adjustment) that match the predicted risk level or the patient's active triggering signal. Because this approach actively predicts the risk and automatically intervenes based on the changing trend of physiological parameters before the onset of pain, it utilizes the physiological basis that there is a clinically interventionable window period between the decline in tissue perfusion and the onset of pain in lower limb ischemic pain, realizing the leap from "passive response" to "active prediction", significantly reducing the incidence of lower limb ischemic pain, and avoiding adverse events caused by the patient adjusting their body position due to severe pain.

[0025] (2) This invention establishes individual baselines and personalized dynamic baselines. Each patient establishes their own individual baseline value before dialysis begins, and uses historical data from multiple dialysis sessions to establish normal fluctuation ranges at different dialysis times. When the current physiological parameter falls below the lower limit of the normal fluctuation range by more than a predetermined proportion, predictive intervention is triggered. This approach solves the problem of misjudgment caused by individual differences (such as age, vascular condition, hemoglobin concentration, etc.) in the traditional "one-size-fits-all" fixed threshold method. Patients with high baseline values ​​experience a large decrease but still do not reach the pain threshold, while patients with low baseline values ​​experience a small decrease but have already reached the pain threshold. Personalized baselines significantly improve prediction accuracy while greatly reducing the intervention workload of medical staff.

[0026] (3) This invention forms a tiered intervention system through four levels of graded intervention (predictive risk level, early warning risk level, patient-triggered risk level, and persistent unrelieved risk level): Predictive intervention performs gentle postural adjustment and a slight decrease in ultrafiltration rate when the patient is completely painless, with almost no sensation from the patient; early warning intervention performs a drooping position when physiological parameters drop beyond the threshold, using gravity to increase lower limb arterial perfusion pressure, which differs from the "leg-raising position" used in existing technologies to deal with hypotension; patient-triggered intervention serves as a fallback mechanism; persistent unrelieved intervention pauses or reduces the ultrafiltration rate and sends an alarm signal to the alarm receiver when the automatic intervention is ineffective. The postural transition time is controlled within a safe range, the automatic return logic is executed, and the patient slowly returns to the position after the risk is eliminated, avoiding the risk of orthostatic hypotension and falls. This graded intervention system avoids over-intervention while ensuring patient safety. Attached Figure Description

[0027] Figure 1 This is a flowchart of an intervention method for lower limb ischemic pain in hemodialysis patients provided in an embodiment of the present invention; Figures 2 to 5 These are the body positions corresponding to intervention measures for different risk levels provided in the embodiments of the present invention; Detailed Implementation To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0028] like Figure 1 As shown, this embodiment provides an intervention method and system for lower limb ischemic pain in hemodialysis patients, aiming to solve the problem of lower limb ischemic pain induced by dehydration in hemodialysis patients with lower limb arterial occlusive disease during dialysis, and to achieve "proactive prediction and intervention before the onset of pain".

[0029] The core innovation of this solution lies in the adoption of a dual mechanism of "trend prediction + threshold triggering". By monitoring the local tissue perfusion status in real time, it automatically initiates graded intervention before the patient feels pain (8-15 minutes in advance) so that the patient can achieve a state of pain relief or painless dialysis.

[0030] This method consists of three stages: preparation stage (individual baseline establishment), self-calibration stage (personalized dynamic baseline establishment), and online intervention stage (four-level hierarchical intervention).

[0031] S1. Individual baseline establishment This phase is performed before dialysis begins to establish individual baseline values ​​for each patient, providing a benchmark for subsequent trend assessment. Details are as follows: S101. Attach the flexible sensor patch to the medial aspect of the patient's tibia (where there is little subcutaneous fat and high signal quality). This sensor uses near-infrared spectroscopy to collect tissue oxygen saturation (rSO2) in real time, and is also equipped with a skin temperature sensor. The sampling frequency is set to ≥1Hz.

[0032] S102. The patient lies supine, and raw rSO2 data are continuously collected within 30 minutes before the start of dialysis. At a sampling frequency of 1 Hz, at least 1800 data points can be obtained in 30 minutes.

[0033] S103. Remove obvious outliers caused by limb movement, poor sensor contact, etc. The criteria for outliers are: data points exceeding the mean ± 3 standard deviations. The proportion of outliers removed should not exceed 5% of the total data points.

[0034] S104. Take the arithmetic mean of the remaining valid data points after preprocessing as the individual baseline value for this dialysis session: Where M is the number of valid data points after preprocessing. This is the j-th valid rSO2 measurement.

[0035] S105. Calculate the standard deviation of the effective data. . M is the number of valid data points. For the j-th valid rSO2 measurement, This refers to the individual baseline value in S104. If... This indicates that the signal is stable and the baseline is valid; proceed to the next step. This indicates that the signal is unstable. The system prompts the nurse to check the sensor's fit and extend the baseline acquisition time to 60 minutes or restart.

[0036] For example, after continuously collecting data for 30 minutes, 1850 raw data points are obtained. After removing outliers, 1818 valid data points remain. The arithmetic mean is then calculated to obtain the baseline value. Standard deviation The signal is stable and the baseline is valid.

[0037] S2, Personalized Dynamic Baseline Establishment This phase is based on the patient's historical dialysis data, with the aim of establishing a personalized dynamic baseline and avoiding misjudgments caused by a fixed threshold applied across the board.

[0038] S201. The system records rSO2 data at the same dialysis duration during multiple dialysis sessions (e.g., 3-5 sessions) of the patient. Sampling time points include 30 minutes, 60 minutes, 90 minutes, 120 minutes, 150 minutes, and 180 minutes after the start of dialysis (these can be increased or decreased according to clinical needs).

[0039] S202. For each time point t, calculate the mean of the past N dialysis sessions (N=3~5 sessions). and standard deviation , , Where i is the sequence number of the i-th dialysis session (i=1, 2, 3...N), and t is the dialysis duration (e.g., 30 minutes, 60 minutes, etc. after dialysis begins). Let rSO2 be the value measured at time t during the i-th dialysis.

[0040] S203, Normal fluctuation range is defined as: The coefficient k can be adjusted according to clinical data, ranging from 1.0 to 2.0. In this embodiment, it is 1.5.

[0041] S204. When the current tissue oxygen saturation is lower than the lower limit of the normal fluctuation range minus a predetermined percentage of the historical mean (e.g., 10%), a predictive intervention is triggered. If the patient's mean rSO2 at 90 minutes after the last four dialysis sessions was 60% with a standard deviation of 3%, then the lower limit of the normal range = 60% - 1.5 × 3% = 55.5%. The abnormal trigger threshold = 55.5% - 10% × 60% = 49.5%. That is, when rSO2 is below 49.5% at 90 minutes, the intervention corresponding to the predictive risk level is triggered.

[0042] S3, Trends in physiological parameters During dialysis, the tissue oxygen saturation (rSO2) and skin temperature of the patient's lower limbs are continuously monitored at a sampling frequency of ≥1Hz, and the data is transmitted to the control and analysis module in real time.

[0043] S301, Get the current time Including all sampling points within the first 10 minutes, a total of 601 data points (including ): .

[0044] S302. Plot time on the x-axis (in minutes) and rSO2 value on the y-axis, and perform a univariate linear fit. The equation of the fitted line is: The slope a and intercept b of the linear equation are solved using the least squares method.

[0045] S303. Take the absolute value of the slope as the rate of decrease: Rate of decrease = |a| (unit: % / minute). When a is negative, it indicates a decrease, and |a| is the rate of decrease. For example, in a patient during the 50th-60th minute of dialysis, rSO2 decreased from 62% to 50%, a decrease of 12%, the fitted slope a = -1.2% / minute, and the rate of decrease = 1.2% / minute.

[0046] S4. Risk Level Classification and Intervention Measures Level 1: Predictable Risk Level A risk level is determined when any of the following conditions are met: ① The rate of decrease of rSO2 is >1% / minute for 10 consecutive minutes (the first threshold of the rate of decrease); ② Dialysis duration ≥ 60 minutes (first duration), cumulative ultrafiltration volume ≥ 1.0 L (first threshold for cumulative ultrafiltration volume), and rSO2 decrease ≥ 8% (second threshold for decrease rate); ③ The deviation of rSO2 from the lower limit of the normal range of the personalized dynamic baseline exceeds 10% (the third threshold of the rate of decline).

[0047] After determining a predictable risk level, the body position drive module executes the first body position adjustment mode. In this embodiment, the first body position adjustment mode corresponding to the predictable risk level is: the back is raised 15°-30°, and the foot of the bed is lowered 2°-5°. Figure 2 Adjust the status to Figure 3 As shown in the diagram, the ultrafiltration linkage module is simultaneously controlled to reduce the ultrafiltration rate by 20%. The body position transition time is controlled within 15-20 seconds, gradually adjusting the body position to reduce patient perception. After adjusting to the first body position adjustment mode, return to S3 to continue monitoring changes in physiological parameters.

[0048] Level 2: Warning Risk Level When the monitored rSO2 is compared to the individual baseline value When the decrease in blood temperature exceeds the fourth threshold (e.g., 12%), or the decrease in skin temperature exceeds the fifth threshold (e.g., 2°C), it is determined to be a warning risk level.

[0049] At this time, the body position control module executes a sitting position (back raised 70°-90°, lower limbs hanging down) as follows. Figure 4 As shown, the body position transition time is controlled within 30 seconds to increase lower limb arterial perfusion pressure using gravity. Afterwards, return to S3 to continue monitoring physiological parameter changes. If a safe threshold is reached after 5 minutes of assessment, slowly return to a head-up, feet-down position (head elevated 5°-15°, feet lowered 5°-15°). Figure 5 As shown.

[0050] Level 3: Patient triggers risk level When a patient feels pain, pressing the button integrated into the armrest of the dialysis chair or using a handheld remote control sends a pain trigger signal to the control module via the patient active feedback module.

[0051] The body position drive module controls the sitting posture adjustment, while the system automatically records the event log (including parameters such as pain occurrence time, current rSO2 value, skin temperature, and ultrafiltration rate). Then, it returns to S3 to continue monitoring changes in physiological parameters.

[0052] Level 4: Persistent and Unmitigated Risk A risk level of "persistent and unmitigated" is determined when any of the following conditions are met: ① The average rSO2 value in the last minute of the monitoring period after intervention was lower than 85% of the baseline value (sixth threshold).

[0053] Calculation of the average value in the last minute: k takes the last 60 valid sampling points during the detection period, with a sampling frequency of 1 Hz. For example, if the baseline value is 62% and the sixth threshold is 85%, then the judgment value is 62% × 85% = 52.7%.

[0054] In the 5-minute monitoring period after intervention, the average of the 60 rSO2 values ​​collected in the last minute was 51.2%. Since 51.2% < 52.7%, it was determined to be a persistent risk level.

[0055] ② Slope fitting within 5 minutes after intervention <-0.2% / minute (seventh threshold).

[0056] Once a persistent unresolved risk level is determined, the corresponding intervention measures are triggered: the ultrafiltration module is paused or its ultrafiltration rate is reduced, and an alarm signal is sent to the nurse workstation to notify medical staff to handle the situation promptly. Return to S3 to continue monitoring changes in physiological parameters.

[0057] S5 Intervention Effect Assessment and Closed-Loop Regulation S501. After implementing the intervention measures, evaluate the intervention effect: determine whether the physiological parameters have reached the safe threshold.

[0058] S502. If the safety threshold is not reached, the risk level is raised to the next level and corresponding intervention measures are implemented; if the safety threshold has been reached, the basic body position is restored (e.g., slowly returning from a sitting position to a supine position) and / or the current ultrafiltration rate is maintained. In this embodiment, the speed of body position transition is graded and controllable, the return-to-position logic is executed automatically, and the body returns slowly after the risk is eliminated, avoiding the risk of orthostatic hypotension and falls.

[0059] This embodiment also provides an intervention system, including: a monitoring module for real-time acquisition of physiological parameters reflecting the tissue perfusion status of the patient's lower limbs; a control module connected to the monitoring module for executing the trend prediction and intervention determination logic; a body position adjustment module connected to the control module for executing body position adjustment; an ultrafiltration adjustment module connected to the control module for executing dialysis ultrafiltration rate adjustment; and a patient active feedback module connected to the control module for receiving the patient's pain trigger signal to trigger the intervention.

[0060] The foregoing description illustrates and describes preferred embodiments of the present invention. It should be understood that the present invention is not limited to the forms disclosed herein and should not be construed as excluding other embodiments. It can be used in various other combinations, modifications, and environments, and can be altered within the scope of the inventive concept by means of the foregoing teachings or techniques or knowledge in related fields. Any modifications and variations made by those skilled in the art that do not depart from the spirit and scope of the present invention should be within the protection scope of the appended claims.

Claims

1. An intervention method for lower limb ischemic pain in hemodialysis patients, characterized in that, include: Real-time acquisition of physiological parameters reflecting tissue perfusion status in the patient's lower limbs; Based on the changing trends of the aforementioned physiological parameters, the trend of ischemic pain is predicted; Risk levels are classified based on trend forecasts, including predictive risk levels. Based on the predicted risk level or the patient's active triggering signal, interventions matching that risk level are implemented, including postural adjustment and / or dialysis ultrafiltration rate adjustment.

2. The intervention method according to claim 1, characterized in that, Before collecting physiological parameters of the patient's lower limbs reflecting tissue perfusion status in real time, the method of establishing an individual baseline includes: continuously collecting physiological parameter data of the patient's lower limbs within a predetermined time before the start of dialysis, calculating statistical characteristic values ​​after removing outliers, and using these values ​​as the individual baseline values ​​for this dialysis session.

3. The intervention method according to claim 1, characterized in that, It also includes the step of establishing a personalized dynamic baseline: Record tissue oxygen saturation data at the same dialysis duration during multiple dialysis sessions in the past; Calculate the historical mean and standard deviation for each time point to establish a normal fluctuation range; When the current tissue oxygen saturation is lower than the lower limit of the normal fluctuation range minus a predetermined percentage of the historical average, a predictive intervention corresponding to the predictive risk level is triggered.

4. The intervention method according to claim 1, characterized in that, The physiological parameters include tissue oxygen saturation and / or skin temperature; the method for predicting the risk level of ischemic pain is based on the rate and / or magnitude of decrease of the physiological parameters.

5. The intervention method according to any one of claims 2 to 4, characterized in that, When any of the following conditions are met, the condition is determined to be a predictive risk level. The body position drive module is then controlled to execute the first body position adjustment mode corresponding to the predictive risk level, and the ultrafiltration linkage module is controlled to reduce the ultrafiltration rate: The rate of decrease in tissue blood oxygen saturation monitored within a predetermined time exceeds the first threshold. Dialysis duration exceeds the first duration, cumulative ultrafiltration volume exceeds the first threshold, and tissue oxygen saturation decreases from the individual's baseline value by more than the second threshold; The current tissue oxygen saturation is below the lower limit of the normal range established based on historical data, exceeding the third threshold.

6. The intervention method according to claim 2, characterized in that, The risk levels include early warning risk levels: When the monitored tissue oxygen saturation decreases by more than the fourth threshold from the individual's baseline value, or when the skin temperature decreases by more than the fifth threshold, it is determined to be a warning risk level, and the body position drive module is controlled to execute the second body position adjustment mode corresponding to the warning risk level.

7. The intervention method according to claim 2, characterized in that, The risk levels also include the persistent unresolved risk level: When the average tissue oxygen saturation during the last predetermined time period after intervention is lower than the sixth threshold of the individual baseline, or when the tissue oxygen saturation monitoring during the predetermined time period after intervention shows a continuous negative trend and the rate of decline exceeds the seventh threshold, it is determined to be a persistent risk level that has not been alleviated. The ultrafiltration linkage module is then controlled to pause or reduce the ultrafiltration rate, and an alarm signal is sent to the medical terminal.

8. The intervention method according to claim 1, characterized in that, It also includes evaluating the effectiveness of the intervention after it is implemented, whether the physiological parameters have reached the safety threshold, and if not, raising it to the next risk level and implementing the corresponding intervention; if so, restoring the basic body position and / or maintaining the ultrafiltration rate.

9. An intervention system for ischemic pain in the lower extremities of hemodialysis patients, characterized in that, For performing the intervention method as described in any one of claims 1 to 8, comprising: The monitoring module is used to collect physiological parameters of the patient's lower limbs that reflect the tissue perfusion status in real time; A control module, connected to the monitoring module, is used to execute the decision logic for trend prediction and intervention measures; A body position adjustment module, connected to the control module, is used to perform body position adjustment; An ultrafiltration adjustment module, connected to the control module, is used to perform dialysis ultrafiltration rate adjustment.

10. The system according to claim 9, characterized in that, The system also includes a patient active feedback module, which is connected to the control module and is used to receive the patient's pain trigger signal to trigger the patient's intervention.

Images