A system for non-invasive continuous monitoring of intra-abdominal pressure
Patent Information
- Application Number
- CN202520829626.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Utility models(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-28
- Publication Date
- 2026-09-25
- Estimated Expiration
- 2035-04-28
AI Technical Summary
1. 侵入性：需要通过导尿管插入膀胱，增加了患者的痛苦和感染风险
本实用新型采用主要由电极阵列与信号采集模块、阻抗测量电路与信号处理模块和数据分析处理及显示终端构成的无创持续监测腹腔压力的系统，减少患者的痛苦和感染风险，提高患者的舒适度；能够连续、动态地监测腹腔压力变化，及时发现异常情况；通过多频激励和机器学习算法，提高测量的准确性和灵敏度；装置设计轻便，适合多种场景使用。
Smart Images
Figure CN224792342U_ABST
Abstract
Description
Technical Field
[0001] This utility model relates to the field of medical device technology, and more specifically to a device for continuously monitoring abdominal pressure. Background Technology
[0002] Monitoring intra-abdominal pressure (IAP) is of great clinical significance, especially in intensive care, postoperative recovery, and the diagnosis of abdominal compartment syndrome. Currently, IAP monitoring is primarily achieved through cystometry (intravesical pressure measurement), which is considered the "gold standard" for IAP monitoring. However, cystometry has the following drawbacks: 1. Invasive: It requires the insertion of a catheter into the bladder, increasing the patient's pain and risk of infection.
[0003] 2. Discontinuousness: It can usually only perform intermittent measurements and cannot achieve real-time, continuous monitoring.
[0004] 3. Complex operation: It requires professional medical personnel to operate and is not suitable for home or long-term monitoring scenarios.
[0005] Therefore, there is a lack of a non-invasive, real-time, continuous intra-abdominal pressure monitoring device in the existing technology that can provide accurate intra-abdominal pressure data without increasing patient discomfort. Therefore, it is necessary to further improve its structure. Summary of the Invention
[0006] The purpose of this invention is to provide a stable and reliable non-invasive system for continuously and dynamically monitoring intra-abdominal pressure, which can detect abnormalities in a timely manner and improve the accuracy and sensitivity of measurements, in order to overcome the shortcomings of existing technologies.
[0007] This utility model achieves the above-mentioned objectives using the following technical solution: a non-invasive continuous monitoring system for intra-abdominal pressure, characterized in that it includes an electrode array and signal acquisition module, an impedance measurement circuit and signal processing module, and a data analysis, processing, and display terminal. The electrode array and signal acquisition module adopts a ring-shaped electrode array, with multiple electrodes evenly distributed around the abdomen in a circumferential manner, spaced 5-8 cm apart, which can be adjusted according to the patient's abdominal circumference; a four-electrode method is used, with two driving electrodes applying current and two measuring electrodes detecting voltage, reducing the influence of contact impedance and improving measurement accuracy; The impedance measurement circuit and signal processing module includes a constant current source circuit, a signal conditioning circuit, and a microcontroller. The constant current source circuit uses a current pump to generate a stable AC current, ensuring the stability and safety of the current. By controlling the current frequency, it supports multi-frequency switching, ensuring that comprehensive impedance data is obtained at different frequencies. The signal conditioning circuit uses an instrumentation amplifier with a common-mode rejection ratio >100dB to amplify the voltage signal and sets a bandpass filter with a cutoff frequency of 1kHz-1.2MHz to suppress power frequency interference and high-frequency noise. The data analysis, processing, and display terminal includes a microcontroller and a real-time pressure display and early warning device. The microcontroller is equipped with an impedance data preprocessing module, which uses adaptive filtering to eliminate physiological noise such as breathing and heartbeat, and principal component analysis (PCA) to separate environmental interference. It also performs weighted fusion of multi-frequency data to enhance the sensitivity to changes in deep tissues. A biomechanical model is established based on finite element simulation to simulate the influence of abdominal pressure on the abdominal wall impedance distribution, and a pressure-impedance change database is constructed. An LSTM network is used to learn the nonlinear relationship between time-series impedance data and pressure changes. Simultaneously acquired bladder manometry data is used as supervised learning labels, and the model is trained and validated through animal experiments or clinical data. The real-time pressure display and early warning device dynamically displays pressure values through an embedded system, sets early warning thresholds and high-pressure alarm thresholds, and promptly alerts medical staff.
[0008] As a further explanation of the above scheme, the current frequency range of the electrode array and signal acquisition module is 10kHz-1MHz. The low frequency of 10kHz-100kHz reflects the pressure changes inside the abdominal cavity, and the high frequency of 100kHz-1MHz captures the impedance changes of the abdominal wall surface. The frequency is controlled by the DDS chip, which supports multi-frequency switching.
[0009] Furthermore, the signal conditioning circuit communicates with the microcontroller via the SPI interface. The microcontroller has a built-in DMA controller to achieve real-time and fast data transmission and avoid data loss. A 24-bit high-precision ADC is used for analog-to-digital conversion with a sampling rate of ≥1kSPS to ensure high-precision data acquisition.
[0010] Furthermore, the current pump of the constant current source circuit includes an operational amplifier and multiple precision resistors. The operational amplifier is paired with a symmetrical feedback resistor network. After the input voltage signal is processed by the operational amplifier, it provides a stable current to the load through the output terminal.
[0011] Furthermore, the electrodes of the electrode array use Ag / AgCl electrodes with a diameter of 10 mm. After using Ag / AgCl electrodes, the contact impedance can be reduced to below 5 kΩ, which is a significant improvement compared to ordinary metal electrodes (which typically have a contact impedance of over 20 kΩ), thereby improving the signal-to-noise ratio of the measurement signal.
[0012] Furthermore, the real-time pressure display and early warning device is an embedded system built on an ARM architecture microcontroller, equipped with a μC / GUI graphical interface, dynamically displaying pressure values in mmHg. The early warning threshold is set to 12 mmHg (triggers a yellow warning), and the high-pressure alarm threshold is set to 20 mmHg (triggers a red alarm accompanied by a buzzer). The threshold settings are based on the clinical diagnostic criteria for intra-abdominal hypertension (IAP ≥12 mmHg indicates pre-intra-abdominal hypertension, ≥20 mmHg indicates intra-abdominal hypertension), ensuring timely prompting of medical staff to take measures.
[0013] Furthermore, the data analysis, processing, and display terminal designs the LSTM network as a 3-layer structure, with 16 nodes in the input layer (corresponding to 16 electrode impedance data), 64 nodes in the hidden layer, and 1 node in the output layer (abdominal pressure value). By synchronously collecting bladder manometry (gold standard) data as labels (error < 1 mmHg), the model is trained using the Adam optimization algorithm, and the training set loss function is reduced to below 0.01.
[0014] The beneficial effects that this utility model can achieve by adopting the above-mentioned technical solution are: This invention employs a non-invasive, continuous monitoring system for intra-abdominal pressure, primarily composed of an electrode array and signal acquisition module, an impedance measurement circuit and signal processing module, and a data analysis, processing, and display terminal. This system reduces patient pain and infection risk, improving patient comfort. It can continuously and dynamically monitor changes in intra-abdominal pressure, promptly detecting abnormalities. Through multi-frequency excitation and machine learning algorithms, it improves measurement accuracy and sensitivity. The device is lightweight and suitable for various scenarios. Attached Figure Description
[0015] Figure 1 This is a schematic diagram of the structure of this utility model; Figure 2 This is a schematic diagram of the ring electrode distribution; Figure 3 This is a flowchart of data preprocessing and stress mapping.
[0016] Explanation of reference numerals in the attached diagram: 1. Electrode array and signal acquisition module 1-1, Drive electrode one 1-2, Drive electrode two 1-3, Measurement electrode one 1-4, Measurement electrode two 2. Impedance measurement circuit and signal processing module 3. Data analysis, processing and display terminal. Detailed Implementation
[0017] In the description of this utility model, it should be noted that the directional terms such as "center", "lateral", "longitudinal", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", and "counterclockwise" are based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this utility model and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. They should not be construed as limiting the specific protection scope of this utility model.
[0018] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features. Thus, the use of "first" and "second" to define a feature may explicitly or implicitly include one or more of that feature, and in this description of the utility model, "at least" means one or more, unless otherwise explicitly specified.
[0019] In this utility model, unless otherwise explicitly specified and limited, the terms "assembly," "connection," and "joining" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can also refer to a mechanical connection; they can refer to a direct connection or a connection through an intermediate medium; or they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this utility model according to the specific circumstances.
[0020] In this utility model, unless otherwise specified and limited, "above" or "below" the second feature can include direct contact between the first and second features, or contact between the first and second features through another feature between them. Furthermore, "above," "below," and "over" the second feature includes the first feature being directly above or diagonally above the second feature, or simply indicates that the first feature is at a higher horizontal level than the second feature. "Above," "below," and "under" the second feature includes the first feature being directly below or diagonally below the second feature, or simply indicates that the first feature is at a lower horizontal level than the second feature.
[0021] The specific embodiments of this utility model will be further described below with reference to the accompanying drawings, making the technical solution and beneficial effects of this utility model clearer and more explicit. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this utility model, and should not be construed as limiting this utility model.
[0022] like Figures 1-3As shown, this utility model is a non-invasive continuous monitoring system for intra-abdominal pressure, including an electrode array and signal acquisition module 1, an impedance measurement circuit and signal processing module 2, and a data analysis, processing, and display terminal 3. The electrode array and signal acquisition module adopts a ring-shaped electrode array, with 16 electrodes evenly distributed around the abdomen circumference, spaced 5-8 cm apart, adjustable according to the patient's abdominal circumference. A four-electrode method is used: driving electrode 1-1 and driving electrode 2-2 apply current, while measuring electrodes 1-3 and measuring electrode 2-4 detect voltage, reducing the influence of contact impedance and improving measurement accuracy. The impedance measurement circuit and signal processing module includes a constant current source circuit, a signal conditioning circuit, and a microcontroller. The constant current source circuit uses a current pump to generate a stable alternating current, ensuring current stability and safety. By controlling the current frequency, multi-frequency switching is supported to ensure comprehensive impedance data is acquired at different frequencies. The signal conditioning circuit uses an instrumentation amplifier with a common-mode rejection ratio (CMRR) >100dB to amplify the voltage signal and sets a bandpass filter with a cutoff frequency of 1kHz-1.2MHz to suppress power frequency interference and high-frequency noise. The data analysis, processing, and display terminal includes a microcontroller and a real-time pressure display and early warning device. The microcontroller is equipped with an impedance data preprocessing module, which eliminates physiological noise such as breathing and heartbeat through adaptive filtering, separates environmental interference using principal component analysis (PCA), and weights and fuses multi-frequency data to enhance the sensitivity to changes in deep tissues. A biomechanical model is established based on finite element simulation to simulate the influence of abdominal pressure on the distribution of abdominal wall impedance and construct a pressure-impedance change database. An LSTM network is used to learn the nonlinear relationship between time-series impedance data and pressure changes. Simultaneously acquired bladder manometry data is used as supervised learning labels, and the model is trained and validated through animal experiments or clinical data. The real-time pressure display and early warning device dynamically displays pressure values through an embedded system, sets early warning thresholds and high-pressure alarm thresholds, and promptly alerts medical staff. The signal conditioning circuit communicates with the microcontroller via an SPI interface. The microcontroller has a built-in DMA controller to achieve real-time, high-speed data transmission and avoid data loss. A 24-bit high-precision ADC is used for analog-to-digital conversion with a sampling rate ≥1kSPS to ensure high-precision data acquisition. The constant current source circuit's current pump includes an operational amplifier and multiple precision resistors. The operational amplifier, paired with a symmetrical feedback resistor network, processes the input voltage signal and provides a stable current to the load through the output. The electrode array uses 10mm diameter Ag / AgCl electrodes. Using Ag / AgCl electrodes reduces the contact impedance to below 5kΩ, a significant improvement compared to ordinary metal electrodes, thereby enhancing the signal-to-noise ratio of the measurement signal.
[0023] The current frequency range of the electrode array and signal acquisition module is 10kHz-1MHz. The low frequency of 10kHz-100kHz can penetrate deep tissues and reflect changes in intra-abdominal pressure, while the high frequency of 100kHz-1MHz is more sensitive to changes in superficial tissues and can capture changes in the impedance of the abdominal wall surface. The frequency is controlled by the DDS chip and supports multi-frequency switching.
[0024] In practical applications, the system can implement multi-frequency excitation in the following ways: 1. Low-frequency scanning (10kHz-100kHz): The system first uses a 10kHz current for measurement, then gradually increases the frequency to 100kHz, taking a measurement point every 10kHz. This part is mainly used to obtain impedance information of deep tissues. 2. High-frequency scanning (100kHz-1MHz): Starting from 100kHz, the system takes a measurement point every 100kHz, up to 1MHz. This part is mainly used to obtain impedance information of superficial tissues. 3. Data fusion: The system weighted and fused the low-frequency and high-frequency measurement results to obtain a comprehensive impedance data for subsequent pressure estimation. For example, for a patient with ascites, low-frequency measurements may show decreased impedance in deep tissues (due to fluid accumulation), while high-frequency measurements may show relatively normal impedance in superficial tissues. Through this multi-frequency measurement, the system can more accurately estimate changes in intra-abdominal pressure.
[0025] Data Analysis and Pressure Mapping: The system first preprocesses the collected impedance data, including noise suppression, principal component analysis (PCA), and multi-frequency data fusion. Noise suppression uses adaptive filtering to eliminate physiological noise such as respiration and heartbeat. PCA is used to separate environmental interference and extract effective impedance change information. Multi-frequency data fusion weights and fuses impedance data of different frequencies to enhance sensitivity to changes in deep tissues. This technique is a preprocessing step in the data analysis and pressure mapping algorithm module of the core technical solution, used to improve the accuracy of subsequent pressure mapping. Then, by combining biomechanical models and machine learning algorithms, a mapping relationship between impedance data and intra-abdominal pressure is established to achieve accurate estimation of intra-abdominal pressure. The following is a specific example of the data preprocessing workflow: Noise suppression: Adaptive filters are used to process the raw impedance signal. For example, an adaptive filter based on the minimum mean square error (LMS) algorithm can be used to remove periodic noise caused by breathing and heartbeat. Assuming the acquired raw signal contains 20Hz breathing noise and 1.2Hz heartbeat noise, the adaptive filter will automatically adjust its parameters to minimize noise at these specific frequencies.
[0026] Principal Component Analysis (PCA): PCA is applied to the filtered signal. Assuming measurement data from 16 electrodes, PCA might find that the first three principal components explain 95% of the data variance. This means we can compress 16-dimensional data into 3-dimensional data while retaining most of the useful information, effectively removing environmental interference and redundant information.
[0027] Multi-frequency data fusion: Impedance data at different frequencies are weighted and fused. For example, we might find that 100kHz data is most sensitive to changes in intra-abdominal pressure, while 500kHz data is most sensitive to abdominal wall muscle activity. We can assign a weight of 0.7 to the 100kHz data and a weight of 0.3 to the 500kHz data, and then fuse them into a comprehensive index. The resulting fused data reflects both deep intra-abdominal pressure changes and the influence of superficial muscle activity.
[0028] Through this preprocessing, the original noisy, high-dimensional impedance data is transformed into clear, low-dimensional, and information-rich features, providing high-quality input data for subsequent pressure mapping algorithms.
[0029] The impedance-pressure mapping model is used to convert processed impedance data into intra-abdominal pressure values, including biomechanical model building and machine learning modeling. The impact of intra-abdominal pressure changes on abdominal wall impedance distribution is simulated through finite element simulation, establishing a pressure-impedance change database. An LSTM (Long Short-Term Memory) network is used to learn the nonlinear relationship between time-series impedance data and pressure changes. Supervised learning label data is obtained through synchronously acquired cystometry (IAP gold standard). Improved estimation accuracy: Combining biomechanical models and machine learning algorithms can more accurately capture the complex nonlinear relationship between impedance data and intra-abdominal pressure. 2. Adaptation to individual differences: Machine learning models can learn the physiological characteristics of different patients through training data, improving the system's adaptability to individual differences. 3. Utilization of temporal information: LSTM networks can effectively utilize the time-series characteristics of impedance data, improving the temporal continuity and stability of pressure estimation.
[0030] The following is a specific implementation of the impedance-pressure mapping model: 1. Biomechanical Model Establishment: A 3D model of the abdomen is created using finite element analysis software (such as COMSOL Multiphysics), including layers such as skin, fat, muscle, and abdominal cavity. By changing the intra-abdominal pressure parameters in the model (e.g., from 0 mmHg to 30 mmHg), the deformation and electrical impedance distribution of each layer of the abdominal wall under different pressures are simulated. This allows for the creation of a theoretical pressure-impedance relationship database.
[0031] 2. LSTM Network Training: Collect real patient data, including impedance measurement data and synchronized cystometry data (as real intra-abdominal pressure values). Use this data to train the LSTM network: - Input: Time-series data of impedance measurements at multiple frequencies for 16 electrodes (e.g., one set of data per second for 30 consecutive seconds) - Output: Corresponding intra-abdominal pressure values - Network Structure: For example, a 2-layer LSTM (64 units per layer) followed by a fully connected layer can be used - Training Process: Use the Adam optimizer with a learning rate of 0.001, a batch size of 32, and train for 200 training epochs.
[0032] 3. Model Ensemble: The theoretical database of biomechanical models is used for pre-training of the LSTM network, followed by fine-tuning using real patient data. This approach combines the universality of theoretical models with the individual characteristics of real-world data.
[0033] 4. Real-time prediction: In practical use, the system collects a set of impedance data every second, inputs it into the trained LSTM network, and obtains the current intra-abdominal pressure estimate. The temporal characteristics of the LSTM network enable it to consider previous measurement results, providing a more stable and continuous pressure estimate.
[0034] With this composite model, the system can provide accurate, stable, and personalized estimates of intra-abdominal pressure, supported by both theoretical foundations and actual data.
[0035] Real-time pressure display and early warning functions of the data analysis, processing, and display terminal: Dynamic display of pressure values in mmHg is achieved through an embedded system. Two pressure thresholds are set: an early warning threshold (IAP>12mmHg) and a high-pressure alarm threshold (IAP>20mmHg). When the pressure exceeds the corresponding threshold, the system will trigger an early warning or alarm, prompting medical staff to pay attention or take immediate medical measures. 1. Improved monitoring efficiency: Real-time display allows medical staff to understand the patient's intra-abdominal pressure status at any time, eliminating the need for frequent invasive measurements. 2. Timely early warning: By setting early warning and alarm thresholds, the system can immediately alert medical staff when pressure is abnormal, helping to promptly detect and handle potential dangers. 3. Reduced human error: Automated early warning systems can reduce errors in human observation and judgment, improving the reliability of monitoring.
[0036] The following is a specific example of the real-time pressure display and early warning function: Display interface design: Main display area: Displays the current intra-abdominal pressure value in large font, in mmHg, accurate to one decimal place.
[0037] Trend chart: Shows the pressure change trend over the past 6 hours, with the X-axis representing time and the Y-axis representing the pressure value.
[0038] Status indication: Color coding is used to indicate the current pressure status (green: normal, yellow: warning, red: high pressure alarm).
[0039] Early warning mechanism: Normal state (0-12mmHg): Green display, no sound prompt.
[0040] Warning status (12-20 mmHg): The display area turns yellow; It emits an intermittent low-frequency beeping sound (such as once every 30 seconds); A yellow warning icon is displayed on the nurse station monitor screen; High-voltage alarm status (>20mmHg): The display area turns red; It emits a continuous, high-frequency beeping sound; A flashing red warning icon is displayed on the nurse station monitor screen; Automatically send alert messages to the attending physician's mobile device; Interactive features: Touchscreen operation: Medical staff can view detailed historical pressure data and trend analysis through the touchscreen.
[0041] Alarm Confirmation: When an alarm is triggered, medical staff need to confirm the alarm on the device to indicate that they have noticed the alarm and taken appropriate measures.
[0042] Threshold adjustment: Authorized medical staff can adjust the warning and alarm thresholds according to the patient's specific situation.
[0043] Data Records: The system automatically records all pressure data, including timestamps, pressure values, and alarm events.
[0044] It provides a data export function, which can generate PDF reports or CSV files for easy subsequent analysis and medical record recording.
[0045] This design allows medical staff to visually monitor changes in a patient's intra-abdominal pressure, promptly identify potential dangers, and take appropriate medical action. This significantly improves the efficiency and safety of monitoring, especially in environments requiring close monitoring, such as intensive care units.
[0046] Compared with existing technologies, this invention features: 1. A non-invasive electrode array design: employing a ring array of electrodes and a four-electrode method for impedance measurement, reducing the influence of contact impedance. 2. Multi-frequency excitation and signal processing technology: improving measurement sensitivity and accuracy through multi-frequency excitation (10kHz-1MHz) and signal conditioning circuitry. 3. Impedance-pressure mapping model: mapping impedance data to intra-abdominal pressure values using biomechanical models and machine learning algorithms, achieving high-precision pressure monitoring.
[0047] The above description is only a preferred embodiment of the present utility model. It should be noted that for those skilled in the art, several modifications and improvements can be made without departing from the inventive concept of the present utility model, and these all fall within the protection scope of the present utility model.
Claims
1. A system for non-invasive continuous monitoring of intra-abdominal pressure, characterized in that, It includes an electrode array and signal acquisition module, an impedance measurement circuit and signal processing module, and a data analysis, processing, and display terminal. The electrode array and signal acquisition module adopts a ring array electrode form, with multiple electrodes evenly distributed around the abdomen in a circumferential direction, with a spacing of 5-8cm, which can be adjusted according to the patient's abdominal circumference; The four-electrode method is adopted, with two driving electrodes applying current and two measuring electrodes detecting voltage, which reduces the influence of contact impedance and improves measurement accuracy. The impedance measurement circuit and signal processing module includes a constant current source circuit, a signal conditioning circuit, and a microcontroller. The constant current source circuit uses a current pump to generate a stable AC current, ensuring the stability and safety of the current. By controlling the current frequency, it supports multi-frequency switching, ensuring that comprehensive impedance data is obtained at different frequencies. The signal conditioning circuit uses an instrumentation amplifier with a common-mode rejection ratio >100dB to amplify the voltage signal and sets a bandpass filter with a cutoff frequency of 1kHz-1.2MHz to suppress power frequency interference and high-frequency noise. The data analysis, processing, and display terminal includes a microcontroller and a real-time pressure display and early warning device. The microcontroller is equipped with an impedance data preprocessing module, which uses adaptive filtering to eliminate physiological noise from breathing and heartbeat, principal component analysis to separate environmental interference, and weighted fusion of multi-frequency data to enhance sensitivity to changes in deep tissues. A biomechanical model is established based on finite element simulation to simulate the influence of abdominal pressure on abdominal wall impedance distribution, and a pressure-impedance change database is constructed. An LSTM network is used to learn the nonlinear relationship between time-series impedance data and pressure changes, and synchronously acquired bladder manometry data is used as supervised learning labels. The model is trained and validated using animal experiments or clinical data. The real-time pressure display and early warning device dynamically displays pressure values through an embedded system, sets early warning thresholds and high-pressure alarm thresholds, and promptly alerts medical staff.
2. The system for non-invasive continuous monitoring of intra-abdominal pressure according to claim 1, characterized in that, The current frequency range of the electrode array and signal acquisition module is 10kHz-1MHz. The low frequency of 10kHz-100kHz reflects the pressure changes inside the abdominal cavity, and the high frequency of 100kHz-1MHz captures the impedance changes of the abdominal wall surface. The frequency is controlled by the DDS chip and supports multi-frequency switching.
3. The system for non-invasive continuous monitoring of intra-abdominal pressure according to claim 1, characterized in that, The signal conditioning circuit communicates with the microcontroller via the SPI interface. The microcontroller has a built-in DMA controller to enable real-time and fast data transmission. A 24-bit high-precision ADC is used for analog-to-digital conversion with a sampling rate of ≥1kSPS to ensure high-precision data acquisition.
4. The system for non-invasive continuous monitoring of intra-abdominal pressure according to claim 1, characterized in that, The current pump of the constant current source circuit includes an operational amplifier and multiple precision resistors. The operational amplifier is paired with a symmetrical feedback resistor network. After the input voltage signal is processed by the operational amplifier, it provides a stable current to the load through the output terminal.
5. The system for non-invasive continuous monitoring of intra-abdominal pressure according to claim 1, characterized in that, The electrodes of the electrode array are Ag / AgCl electrodes with a diameter of 10 mm. After using Ag / AgCl electrodes, the contact resistance can be reduced to below 5 kΩ.
6. The system for non-invasive continuous monitoring of intra-abdominal pressure according to claim 1, characterized in that, The real-time pressure display and early warning device is an embedded system built on an ARM architecture microcontroller, equipped with a μC / GUI graphical interface to dynamically display pressure values. The early warning threshold is set to 12 mmHg, and the high-pressure alarm threshold is set to 20 mmHg. The threshold settings are based on the clinical diagnostic criteria for intra-abdominal hypertension to ensure timely prompting of medical staff to take measures.
7. The system for non-invasive continuous monitoring of intra-abdominal pressure according to claim 1, characterized in that, The data analysis, processing, and display terminal designs the LSTM network as a 3-layer structure, with 16 nodes in the input layer corresponding to 16 electrode impedance data, 64 nodes in the hidden layer, and 1 node in the output layer corresponding to the intra-abdominal pressure value. By synchronously collecting bladder manometry data as labels, the model is trained using the Adam optimization algorithm, and the training set loss function is reduced to below 0.01.