Wireless intelligent pressurization monitoring system and method after kidney puncture

Abstract

The present application relates to the technical field of intelligent monitoring after operation, in particular to a wireless intelligent pressurizing monitoring system and method for kidney puncture, the system comprising: an adjustable airbag pressurizing abdominal belt, a multi-parameter monitoring module, a wireless transmission module and a nurse station terminal, the multi-parameter monitoring module integrating humidity, pressure and bioelectrical impedance sensors, and sending data to the nurse station terminal through the wireless transmission module.In the present application, through the closed-loop control system integrating a miniature air pump and a pressure sensor, digital setting and dynamic constant maintenance of the compression force of the kidney puncture site are realized, and through the dual monitoring mechanism of the humidity sensor and the bioelectrical impedance sensor, not only can the trace bleeding on the surface of the dressing be sensitively captured, but also subcutaneous hematoma and deep hydrops that cannot be seen by the naked eye can be early identified by using the bioimpedance change principle, combined with the wireless transmission and the automatic early warning function of the nurse station, the discovery timeliness rate of postoperative complications and the safety of patients are greatly improved.

Description

Technical Field

[0001] This invention relates to the field of postoperative intelligent monitoring technology, and in particular to a wireless intelligent pressure monitoring system and method for use after renal biopsy. Background Technology

[0002] Postoperative intelligent monitoring technology refers to a technical system that utilizes modern sensing technology, Internet of Things (IoT) communication technology, and data analysis methods to continuously and dynamically monitor the vital signs, wound condition, and recovery progress of postoperative patients. This field aims to improve the efficiency and accuracy of medical care by replacing traditional intermittent manual observation with non-invasive or minimally invasive monitoring equipment. Traditional postoperative care for kidney biopsies primarily relies on medical staff using sandbags or ordinary elastic abdominal binders to apply pressure to the puncture site for hemostasis, and assessing postoperative recovery by visually observing the dressing and inquiring about the patient's feelings.

[0003] However, existing methods of applying pressure after renal biopsy suffer from unstable pressure control. The force of manual bandaging or sandbag compression is difficult to quantify; too loose a bandage leads to poor hemostasis, while too tight a bandage affects blood circulation or causes patient discomfort, and it is impossible to maintain constant pressure. Furthermore, traditional observation methods have a significant lag, only detecting external bleeding through bloodstains on the dressing surface. Deeper or early-stage subcutaneous hematomas (perirhinoid hematomas) are easily overlooked due to their indistinct surface features, often only being discovered when the patient experiences severe pain or shock, thus delaying optimal treatment. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of the existing technology and to propose a wireless intelligent pressure monitoring system and method for renal biopsy.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: a wireless intelligent pressure monitoring system for renal biopsy, comprising: Postoperative intelligent monitoring system includes an adjustable air-cushioned abdominal binder, a multi-parameter monitoring module, a wireless transmission module, and a nurse station terminal. The adjustable air-filled pressure abdominal binder mentioned in the postoperative intelligent monitoring is worn on the patient's abdominal puncture area. It has an inflatable cavity and a pressure regulating component inside. The pressure regulating component is used to inflate or deflate the inflatable cavity to change the pressure. The multi-parameter monitoring module for postoperative intelligent monitoring is installed on the adjustable airbag pressure abdominal binder, and its input end is connected to a humidity sensor, a pressure sensor, and a bioelectrical impedance sensor. The humidity sensor in the postoperative intelligent monitoring system is attached to the dressing layer of the puncture wound to collect humidity data of the dressing area. The pressure sensor in the postoperative intelligent monitoring system is located between the inflatable cavity and the patient's skin contact surface to collect data on the actual applied pressure. The bioelectrical impedance sensor used in postoperative intelligent monitoring includes an electrode array disposed on the skin surface around the puncture point for collecting bioimpedance data of subcutaneous tissue; The wireless transmission module of the postoperative intelligent monitoring system is connected to the multi-parameter monitoring module and is used to send humidity data, pressure data and bioimpedance data to the nurse station terminal. The postoperative intelligent monitoring terminal at the nurse station is used to receive and display the above data, and to issue an alarm command when the data exceeds a preset safety threshold. As a further embodiment of the present invention, the pressure regulating component includes a micro air pump, an electromagnetic pressure relief valve, and a micro control unit. The air ports of the micro air pump and the electromagnetic pressure relief valve are both connected to the inflation chamber. The micro control unit is electrically connected to the micro air pump and the electromagnetic pressure relief valve respectively, and is used to adjust the gas volume in the inflation chamber according to the control command. As a further embodiment of the present invention, the humidity sensor adopts an interdigital electrode structure, which is printed on a flexible circuit board and embedded in an absorbent dressing layer. The multi-parameter monitoring module is configured to generate humidity data by detecting the resistance change rate between the interdigital electrode structures, wherein the resistance change rate is positively correlated with the amount of bleeding. As a further aspect of the present invention, the bioelectrical impedance sensor adopts a four-electrode measurement layout, including a pair of excitation electrodes and a pair of measurement electrodes. The multi-parameter monitoring module is configured to inject an alternating current of a preset frequency into the subcutaneous tissue through the excitation electrodes and to detect the voltage drop through the measurement electrodes to calculate and generate the bioimpedance data, which is used to reflect the changes in tissue conductivity caused by subcutaneous hematoma effusion. As a further embodiment of the present invention, the system further includes a pressure closed-loop control module, which is built into the control circuit of the adjustable airbag pressurized abdominal belt. The module is configured to compare the pressure data collected by the pressure sensor with a preset target pressure value. When the absolute value of the difference exceeds the allowable deviation range, a drive signal is generated to control the pressure regulating component to perform compensatory inflation or slight depressurization until the pressure data returns to the allowable deviation range. As a further embodiment of the present invention, the wireless transmission module adopts one of Bluetooth Low Energy, Wi-Fi or ZigBee communication protocols, and the wireless transmission module further includes a data encryption unit configured to encrypt and package the humidity data, pressure data and bioimpedance data before transmission. As a further embodiment of the present invention, the adjustable airbag pressurization abdominal belt is also equipped with a power supply module, which includes a rechargeable lithium battery pack and a power management circuit. The power management circuit is used to provide operating voltage to the multi-parameter monitoring module, the voltage regulation component and the wireless transmission module, and to monitor the remaining power information. As a further embodiment of the present invention, the nurse station terminal includes a data processing unit and a display interface. The data processing unit is configured to construct a multi-dimensional early warning model, set a humidity alarm threshold, a pressure abnormality threshold, and an impedance change rate threshold respectively, and compare the received real-time data with the above thresholds respectively. When the alarm conditions are met, a graded early warning signal is generated. As a further embodiment of the present invention, the nurse station terminal is also connected to an audible and visual alarm, which is configured to respond to graded warning signals and emit beeping sounds of different frequencies and flashing light signals of different colors according to the warning level, in order to prompt medical staff whether the specific abnormality is dressing bleeding, pressure instability or suspected hematoma. A wireless intelligent pressure monitoring method for post-renal biopsy, the method being performed based on the aforementioned wireless intelligent pressure monitoring system for post-renal biopsy, comprising the following steps: S1: Set the target pressure value and the safety alarm threshold of each sensor through the nurse station terminal, and send an initialization command to the adjustable airbag pressure abdominal binder; S2: Control the pressure regulating component to inflate the inflation chamber until the pressure data fed back by the pressure sensor reaches the target pressure value; S3: Periodically collect signals from the humidity sensor, pressure sensor, and bioelectrical impedance sensor to generate real-time humidity data, real-time pressure data, and real-time bioelectrical impedance data, respectively. S4: The real-time data is packaged and sent to the nurse station terminal for storage and analysis via the wireless transmission module; S5: Determine whether the real-time pressure data deviates from the target pressure value. If so, automatically adjust the air volume of the inflation chamber through the pressure closed-loop control module. S6: If not, determine whether the real-time humidity data or real-time bioimpedance data exceeds the set safety alarm threshold. If so, trigger the audible and visual alarm to issue the corresponding bleeding or hematoma warning signal.

[0006] Compared with the prior art, the advantages and positive effects of the present invention are as follows: This invention utilizes a closed-loop control system integrating a miniature air pump and a pressure sensor to digitally set and dynamically maintain constant pressure at the renal puncture site, effectively solving the problems of low accuracy in manual pressurization and pressure fluctuations due to changes in body position. Simultaneously, this invention employs a dual monitoring mechanism of a humidity sensor and a bioelectrical impedance sensor, which not only sensitively detects minute amounts of bleeding on the dressing surface but also utilizes the principle of bioimpedance changes to identify subcutaneous hematomas and deep effusions that are invisible to the naked eye at an early stage. Combined with wireless transmission and automatic early warning functions at the nurses' station, this significantly improves the timeliness of postoperative complication detection and patient safety while reducing the workload of medical staff during rounds. Attached Figure Description

[0007] Figure 1 This is a system flowchart of the present invention. Detailed Implementation

[0008] To make the objectives, technical solutions, and advantages of this invention clearer, the software-based technical solution is described in detail below with reference to system architecture diagrams and embodiments. It should be understood that the specific embodiments described herein are only for explaining the technical solutions of this invention and do not constitute a limitation on the scope of protection.

[0009] In the description of this invention, the system architecture relationships or data processing flows indicated by terms such as "layer," "module," "interface," "data flow," "client," and "server" are all defined based on the architecture diagram or flowchart corresponding to the embodiments. This way of describing is only used to clearly illustrate the logical relationships between the elements in the technical solution, and not to limit the physical deployment form. The term "multiple" includes two or more technical units, including but not limited to multiple data nodes, processing threads, service instances, or functional components and other scalable elements. The specific number is determined according to the actual business scenario and needs to be specifically specified.

[0010] Please see Figure 1 The present invention provides a technical solution: A wireless intelligent pressure monitoring system for use after kidney biopsy includes: The postoperative intelligent monitoring adjustable air-filled pressure abdominal binder is worn on the patient's abdominal puncture area. It has an inflatable cavity and a pressure regulating component inside. The pressure regulating component is used to inflate or deflate the inflatable cavity to change the pressure. The pressure regulating component includes a miniature air pump, an electromagnetic pressure relief valve, and a microcontroller unit. The air ports of the miniature air pump and the electromagnetic pressure relief valve are both connected to the inflation chamber. The microcontroller unit is electrically connected to the miniature air pump and the electromagnetic pressure relief valve respectively, and is used to adjust the gas volume in the inflation chamber according to the control command. The system also includes a pressure closed-loop control module, which is built into the control circuit of the adjustable airbag pressurized abdominal belt. It is configured to compare the pressure data collected by the pressure sensor with the preset target pressure value. When the absolute value of the difference exceeds the allowable deviation range, a drive signal is generated to control the pressure regulating component to perform compensatory inflation or slight depressurization until the pressure data returns to the allowable deviation range. The adjustable airbag compression abdominal binder is also equipped with a power supply module, which includes a rechargeable lithium battery pack and a power management circuit. The power management circuit is used to provide operating voltage to the multi-parameter monitoring module, voltage regulation component and wireless transmission module, and monitor the remaining power information.

[0011] The pressure closed-loop control module integrates an AI-adaptive PID (Proportional-Integral-Derivative) control algorithm. This algorithm utilizes a neural network model to identify the patient's abdominal compliance in real time and dynamically adjust the PID parameters. The microcontroller unit sends a start-up signal to the miniature air pump via a universal input / output interface, driving the motor to generate positive pressure airflow. This airflow is injected into the inflation chamber through the air passage conduit, causing the airbag to gradually inflate and conform to the patient's abdominal curve. During this process, the power management circuit continuously monitors the output voltage and discharge current of the rechargeable lithium battery pack, accumulates the consumed power in real time using coulomb calculation, and stores the current remaining power percentage data in a register for the microcontroller unit to read. The operating logic of the pressure closed-loop control module is mainly based on the discretized execution of the proportional-integral-derivative control algorithm, combined with the AI ​​model's ability to predict pressure fluctuations to optimize the control response. The module first acquires the preset target pressure value and the real-time pressure value fed back by the current pressure sensor, and performs a subtraction operation to obtain the current pressure deviation value. The module then determines whether the absolute value of the pressure deviation exceeds a preset allowable deviation range, specifically set to ±2 mmHg. If the deviation is positive and exceeds the range, it indicates that the current pressure is too low, and the microcontroller calculates the required compensation inflation time. This calculation process generates the drive signal based on the following discrete PID control formula: ;in, For the first The increment of the control output at each sampling time is calculated using a formula. The increment symbol indicates the amount of change in a variable; To control the output variable, representing the pulse width or duty cycle of the drive signal; The index of the current sampling moment in the discrete-time series is obtained through the system clock counter; This is a proportionality coefficient, obtained through adaptive adjustment by an AI model or a preset parameter table; The current sampling time The pressure deviation value is calculated by subtracting the real-time pressure value collected by the pressure sensor at the current moment from the target pressure value. This is the error variable, representing the difference between the set value and the measured value; This is the subtraction operator, representing the subtraction of values; The index of the previous sampling time in the discrete time series is obtained by subtracting 1 from the current time index. The previous sampling time The pressure deviation value is obtained by reading historical records from the memory; This is the addition operator, representing the addition of numbers; These are integral coefficients, obtained through adaptive adjustment by an AI model or from a preset parameter table; These are the differential coefficients, obtained through adaptive adjustment by an AI model or by a preset parameter table. These are constant coefficients used to calculate second-order differences; The index of the previous sampling time in the discrete time series is obtained by subtracting 2 from the current time index. The previous sampling time The pressure deviation value is obtained by reading historical records from memory. The formula performs a weighted summation operation, where the first term... The first-order difference of the error is calculated, which in principle corresponds to the proportional response of the control system to the rate of error change, and is used to improve the system's response speed; the second term Directly referencing the current error value, in principle, corresponds to the integral action in the incremental algorithm, used to eliminate the steady-state error of the system; the third term The second-order difference of the calculation error corresponds in principle to the differential response of the control system to the error change trend (i.e. acceleration), and is used to predict the error trend and suppress overshoot in advance. This represents the adjustment range the control signal needs to make at the current moment relative to the previous moment, indicating the amount of time (e.g., milliseconds) that needs to be added or subtracted from the drive pulse width of the previous control cycle. If A positive value means the air pump's on-time needs to be extended or the duty cycle increased; a negative value means the on-time needs to be shortened or the pressure relief valve needs to be opened. This is achieved through real-time calculations. The system can automatically output appropriate adjustment increments based on the degree, speed, and trend of pressure deviation, allowing the pressure inside the airbag to quickly and smoothly approach the target value. This avoids pressure overshoot caused by excessive adjustment, which could impact the wound, and also prevents poor hemostasis due to insufficient adjustment, thus ensuring that the treatment pressure set at the nurse station terminal is maintained constant. The microcontroller outputs a high-level signal to the micro-inflation pump based on the pulse width to perform precise short-term inflation. If the deviation value is negative and exceeds the range, indicating that the pressure is too high, a control signal is output to open the electromagnetic pressure relief valve to release air. For example, when the preset target pressure value is 40 mmHg, the allowable deviation range is 2 mmHg, and the real-time collected pressure value is 35 mmHg, the system calculates a pressure deviation value of 5 mmHg through subtraction. This value is greater than the allowable deviation range, triggering the compensation inflation logic. Assuming a proportional gain is set to 100 milliseconds per millimeter of mercury, and ignoring the initial effects of integral and derivative terms, the microcontroller multiplies the pressure deviation value of 5 by the proportional gain of 100 to obtain a drive duration of 500 milliseconds. It then controls the micro-inflation pump to operate for 500 milliseconds to achieve precise pressure compensation. The power management circuit in the power supply module uses a low-dropout linear regulator to convert the floating voltage of the lithium battery pack into a stable 3.3-volt operating voltage to supply the microcontroller and sensors. The floating voltage of the lithium battery pack is typically between 3.7 volts and 4.2 volts. When the battery voltage is detected to be below the low-power threshold of 3.5 volts, the power management circuit sends an interrupt signal to the microcontroller, triggering the system to enter low-power mode and recording the low-power event.

[0012] The aforementioned proportional-integral-derivative (PID) control algorithm refers to a general feedback control loop mechanism. It adjusts the controlled variable by calculating a linear combination of the proportional, integral, and derivative components of the error signal. The proportional component reflects the current magnitude of the error, the integral component reflects the cumulative history of the error, and the derivative component reflects the trend of the error. This achieves precise control of the system. Combined with an AI adaptive mechanism, it learns the patient's respiratory rate and body position characteristics, automatically suppresses ineffective regulatory actions caused by normal physiological activities, and extends battery life.

[0013] The multi-parameter monitoring module is installed on the adjustable airbag compression abdominal belt, and its input end is connected to a humidity sensor, a pressure sensor, and a bioelectrical impedance sensor.

[0014] The multi-parameter monitoring module sequentially selects the analog signal channels of the humidity sensor, pressure sensor, and bioelectrical impedance sensor via multiple analog switches, transmitting each analog signal to the input of a high-precision analog-to-digital converter (ADC). Driven by the microcontroller's clock, the ADC discretizes the analog signals at a preset sampling frequency, converting continuous voltage signals into digitally quantized binary codes. This sampling frequency is specifically set to 100 Hz. For weak input bioelectrical signals, the module's integrated instrumentation amplifier first performs differential amplification to suppress common-mode interference noise. Subsequently, a second-order low-pass filter circuit filters out power frequency interference and high-frequency noise, ensuring the signal-to-noise ratio meets analytical requirements. The data acquisition process employs direct memory access (DMI) technology, directly transmitting the converted digital data to the microcontroller's random access memory buffer, minimizing central processing unit intervention. During processing, the microcontroller performs digital filtering on the acquired raw data, such as using a moving average filtering algorithm or an AI-based denoising autoencoder. This involves continuously reading data from 10 sampling points, performing a summation operation, and then dividing by the number of sampling points to obtain a smoothed measurement value. This eliminates the influence of random impulse interference on the measurement results and uses a deep learning model to extract a purer feature vector from the original waveform.

[0015] The aforementioned direct memory access technology refers to a technology in a computer system that allows certain hardware subsystems to directly read and write system memory independently of the central processing unit. Through this technology, data can be transferred quickly between peripherals and memory, thereby significantly reducing the load on the central processing unit and improving data throughput.

[0016] A humidity sensor is attached to the dressing layer of the puncture wound to collect humidity data of the dressing area; The humidity sensor uses an interdigitated electrode structure, which is printed on a flexible circuit board and embedded in the absorbent dressing layer. The multi-parameter monitoring module is configured to generate humidity data by detecting the resistance change rate between the interdigitated electrode structures, where the resistance change rate is positively correlated with the amount of bleeding.

[0017] The humidity sensor employs an interdigitated electrode structure consisting of two parallel, comb-shaped metal conductive tracks. These tracks are interlaced but do not contact each other at a micrometer-level spacing and are printed on a flexible polyimide circuit board. When the dressing layer is dry, the medium between the interdigitated electrodes is mainly air and insulating fibers, resulting in extremely high resistance, typically in the megaohm range. When the dressing absorbs blood or fluid, the electrolyte solution fills the electrode gaps, causing a sharp drop in inter-electrode resistance. The multi-parameter monitoring module measures this resistance value through a voltage divider circuit. Specifically, the interdigitated electrodes are connected in series with a reference resistor of known resistance to a reference voltage source. The microcontroller unit acquires the voltage drop across the reference resistor and uses the series voltage divider principle to calculate the real-time resistance value of the interdigitated electrodes. Subsequently, the system calculates the resistance change rate. The calculation logic is as follows: first, obtain the current real-time resistance value and the reference resistance value in the initial dry state; calculate the difference between the two; then, divide the difference by the reference resistance value; finally, take the absolute value to obtain the resistance change rate. This rate of change directly reflects the moisture level of the dressing. For example, if the initial reference resistance is 100 kΩ, and the real-time resistance measured when bleeding occurs drops to 10 kΩ, the system first performs a subtraction operation (10 minus 100) to get -90, then performs a division operation (-90 divided by 100) to get -0.9. Taking the absolute value, the resistance change rate is 0.9, or 90%. The system has a pre-set mapping table between bleeding volume and resistance change rate. By looking up the table or using linear interpolation, the resistance change rate is converted into a specific bleeding volume estimation level. If the resistance change rate continues to increase, indicating that the bleeding volume is constantly increasing, an AI pattern recognition algorithm is used to analyze the characteristics of the resistance change rate curve to distinguish between sudden massive bleeding and continuous minor bleeding, providing a more accurate alarm classification.

[0018] The aforementioned interdigitated electrode structure refers to a planar electrode configuration in which two electrodes are arranged in a comb-like cross pattern. This structure can significantly increase the effective opposing area of ​​the electrodes and the edge electric field effect, thereby improving the sensor's sensitivity to changes in the dielectric constant or conductivity of the medium.

[0019] A pressure sensor is placed between the inflation chamber and the patient's skin to collect data on the actual applied pressure.

[0020] The pressure sensor is a piezoresistive sensor, with its core component being a Wheatstone bridge structure attached to a pressure-sensitive diaphragm. When the inflation chamber expands and compresses the skin, the reaction force acts on the pressure-sensitive diaphragm, causing deformation of the bridge arm resistance and resulting in a change in resistance value. This causes the bridge to output a differential voltage signal in the microvolt range. The signal conditioning circuit first amplifies this differential voltage through a high-input-impedance instrumentation amplifier to the range of the microcontroller's analog-to-digital converter (ADC), specifically 0 to 3.3 volts, before sending it to the ADC for digitization. To obtain accurate pressure data, the system performs a linear conversion calculation: first, it acquires the digital voltage value output by the ADC, subtracts the zero-point offset voltage value, and then multiplies the result by the sensor's sensitivity coefficient to obtain the actual pressure value. This sensitivity coefficient and zero-point offset voltage value are obtained during the production calibration phase using a standard pressure source. For example, the sensor's zero-point offset voltage is set to 0.5 volts, and the sensitivity coefficient to 20 mmHg per volt. If the acquired digital voltage value is 2.5 volts, the system first performs a subtraction operation, subtracting 0.5 from 2.5 to obtain an effective voltage change of 2.0 volts. Then, it performs a multiplication operation, multiplying 2.0 by 20 to calculate the current actual applied pressure as 40 mmHg. This calculation process ensures the accuracy of pressure monitoring and reflects the real-time pressure of the abdominal binder on the patient's wound.

[0021] The aforementioned Wheatstone bridge structure refers to a bridge circuit composed of four resistors, used to accurately measure changes in resistance. It reflects minute changes in the resistance of the bridge arms by detecting the voltage difference at the intermediate nodes of the bridge circuit. It is commonly used in sensor designs that convert physical quantities into electrical signals.

[0022] A bioelectrical impedance sensor includes an electrode array disposed on the skin surface around the puncture point for collecting bioimpedance data of subcutaneous tissue; The bioelectrical impedance sensor adopts a four-electrode measurement layout, including a pair of excitation electrodes and a pair of measurement electrodes. The multi-parameter monitoring module is configured to inject an alternating current of a preset frequency into the subcutaneous tissue through the excitation electrodes and to detect the voltage drop through the measurement electrodes to calculate and generate bioimpedance data, which is used to reflect the changes in tissue conductivity caused by subcutaneous hematoma effusion.

[0023] The bioelectrical impedance sensor's measurement process is based on the four-electrode method, where the outer pair of electrodes serves as the excitation electrodes, and the inner pair serves as the measurement electrodes. A direct digital frequency synthesizer within the multi-parameter monitoring module generates a 50 kHz sine wave signal. This signal drives a voltage-controlled constant current source circuit, injecting a constant alternating current with an amplitude of 1 mA into the subcutaneous tissue. Due to the impedance characteristics of biological tissue, an AC voltage drop is generated between the inner measurement electrodes as the current flows through the tissue. The signal acquisition circuit picks up this voltage signal through a high-impedance differential amplifier and sends it to an orthogonal demodulator for processing. The orthogonal demodulation logic involves multiplying the acquired voltage signal with a reference sine wave of the same frequency and phase and a reference cosine wave of the same frequency and quadrature, respectively, and extracting the DC component through a low-pass filter, representing the real and imaginary voltage components, respectively. The system calculates the bioimpedance magnitude based on Ohm's law. The calculation logic is as follows: First, the real and imaginary voltage components are squared separately. The two squares are added together and the square root is taken to obtain the voltage amplitude. Then, this voltage amplitude is divided by the amplitude of the injected constant current to obtain the bioimpedance data. For example, when the injected current is 1 mA, the measured real voltage component is 30 mV, and the imaginary voltage component is 40 mV, the system first calculates 30 squared (900) and 40 squared (1600), sums them to get 2500, and takes the square root to obtain a voltage amplitude of 50 mV. Next, a division operation is performed, that is, 50 mV is divided by 1 mA, and the bioimpedance data at this time is calculated to be 50 ohms. This impedance data can sensitively reflect whether there is fluid accumulation in the subcutaneous tissue, because fluid accumulation, such as blood, usually has better conductivity than normal tissue, which will lead to a decrease in impedance value.

[0024] To verify the bioelectrical impedance sensor's ability to detect subcutaneous hematomas and to provide a high-quality dataset for subsequent AI training, this embodiment conducted impedance measurement experiments in a simulated tissue environment. Three groups of simulated tissue samples in different states were selected: normal tissue, mild hematoma, and severe hematoma. Mild hematomas were simulated by injecting 5 ml of physiological saline, and severe hematomas were simulated by injecting 20 ml of physiological saline. The corresponding impedance modulus values ​​were recorded, and the specific data are shown in Table 1.

[0025] Table 1. Bioimpedance Measurement Data under Different Tissue States As shown in Table 1, the bioimpedance modulus showed a significant decreasing trend with the increase of the simulated subcutaneous effusion volume. It decreased from 500.5 ohms in the normal state to 280.8 ohms in the severe hematoma state, with a change rate of -43.9%. This experimental result confirms that the sensor can effectively quantify the pathological changes in subcutaneous tissue through changes in impedance data, providing reliable data support for hematoma early warning. It also verifies the scientific feasibility of using machine learning regression algorithms to construct a mapping model between impedance values ​​and hematoma volume.

[0026] The four-electrode method mentioned above refers to a resistivity measurement technique that uses two outer electrodes to apply current and two inner electrodes to measure voltage, thereby eliminating the influence of lead resistance and contact resistance on the measurement results and improving the accuracy of low impedance measurements.

[0027] The wireless transmission module is connected to the multi-parameter monitoring module to send humidity data, pressure data, and bioimpedance data to the nurse station terminal. The wireless transmission module adopts one of the following communication protocols: Bluetooth Low Energy, Wi-Fi, or ZigBee. The wireless transmission module also includes a data encryption unit, which is configured to encrypt and package humidity data, pressure data, and bioimpedance data before transmission.

[0028] The wireless transmission module uses the Bluetooth Low Energy 5.0 protocol stack for communication. First, the module assembles the humidity, pressure, and bioimpedance data to be transmitted into packets according to a predefined communication protocol frame format. The data packet structure includes a frame header, data length, payload, and cyclic redundancy check (CRC) code. Before transmission, the data encryption unit initiates an Advanced Encryption Standard (AES-128) algorithm to encrypt the payload. The encryption logic is as follows: the system first retrieves a preset 128-bit key and divides the plaintext data into 16-byte blocks. For each block, it sequentially performs byte substitution, row shifting, column mixing, and round key addition operations. This process is repeated 10 times, converting the original physiological parameter data into an unreadable ciphertext data stream. After encryption, the wireless transmission module fills the ciphertext into the payload segment of the Bluetooth data packet and radiates the signal outwards via a radio frequency antenna at a carrier frequency of 2.4 GHz. For example, if the collected pressure data is "40", humidity data is "10", and impedance data is "500", the original data string obtained after packetization is processed by the AES encryption algorithm, and the data string becomes a pseudo-random hexadecimal character sequence. After receiving this data packet, the nurse station terminal must use the same key to reverse decrypt it to restore the real monitoring data, thereby ensuring the confidentiality and security of patient privacy data during wireless transmission and preventing malicious interception and tampering.

[0029] The aforementioned Advanced Encryption Standard (AES) algorithm refers to a symmetric key encryption standard that encrypts data blocks through multiple iterative permutation and substitution operations. It features high security and high efficiency and is widely used to protect the confidentiality of electronic data.

[0030] The nurse station terminal is used to receive and display the above data, and to issue an alarm command when the data exceeds a preset safety threshold. The nurse station terminal includes a data processing unit and a display interface. The data processing unit is configured to build a multi-dimensional early warning model, set humidity alarm threshold, pressure abnormality threshold and impedance change rate threshold respectively, and compare the received real-time data with the above thresholds respectively. When the alarm conditions are met, a graded early warning signal is generated. The nurse station terminal is also connected to an audible and visual alarm, which is configured to respond to graded warning signals. Depending on the warning level, it emits a buzzer sound at a different frequency and a flashing light signal of a different color to alert medical staff to the specific type of abnormality, such as dressing bleeding, pressure instability, or suspected hematoma.

[0031] The data processing unit at the nurse station terminal operates on a multi-threaded architecture. The main thread handles the rendering and interactive response of the graphical user interface, while background threads handle data parsing and AI-based early warning analysis. This unit is equipped with a pre-trained machine learning classifier (such as a random forest or support vector machine model) to process complex multidimensional data streams. The multidimensional early warning model comprehensively evaluates the received data using a combination of logical decision trees and an AI inference engine. The system memory stores a preset alarm threshold table, including humidity alarm thresholds (e.g., resistance change rate greater than 20%), pressure anomaly thresholds (e.g., deviation from the target value exceeding 5 mmHg), and impedance change rate thresholds (e.g., impedance decrease rate exceeding 50 ohms per hour). The data processing unit compares the decrypted monitoring data with the corresponding thresholds in real time. If the resistance change rate corresponding to the humidity data exceeds 20%, or the decrease rate of the bioimpedance data exceeds the set threshold, the system determines it as suspected bleeding or hematoma; if the pressure data is consistently lower than the target value minus the allowable deviation, the system determines it as insufficient pressure. When any alarm condition is met, the system generates an early warning signal of the corresponding level. Furthermore, the AI ​​model analyzes the temporal correlation between impedance and pressure. If it detects a slow decrease in impedance and a gradual increase in pressure, the AI ​​will identify this as a typical characteristic of deep hematoma compression, issuing an early warning and effectively reducing the false alarm and false negative rates caused by a single threshold judgment. The audible and visual alarm response mechanism is as follows: For low-priority anomalies, such as slight pressure fluctuations, the buzzer emits a low-frequency warning sound at 1 Hz, and the yellow indicator light flashes slowly. For high-priority critical anomalies, such as the detection of large amounts of bleeding or severe hematoma, the buzzer emits a high-frequency rapid alarm sound at 5 Hz, and the red indicator light flashes rapidly. For example, if the real-time calculated impedance decrease rate is 60 ohms per hour, which is greater than the preset threshold of 50 ohms per hour, the system identifies this as a hematoma risk, immediately generates a high-level warning signal, drives the red alarm light to flash, and pops up a prominent "Suspected Subcutaneous Hematoma" warning window on the display interface, prompting medical staff to handle the situation immediately.

[0032] The aforementioned logical decision tree refers to a tree-structured decision model where each internal node represents a test on an attribute, each branch represents a test output, and each leaf node represents a category or decision result. It is used to decompose complex decision-making processes into a series of simple logical judgments.

[0033] A wireless intelligent pressure monitoring method for post-renal biopsy, wherein the method is based on the aforementioned wireless intelligent pressure monitoring system for post-renal biopsy, and includes the following steps: S1: Set the target pressure value and the safety alarm threshold of each sensor through the nurse station terminal, and send an initialization command to the adjustable airbag compression abdominal binder; Healthcare workers input the patient's personal information and medical orders through the touchscreen interface of the nurse station terminal, setting the target pressure value to 40 mmHg and setting the resistance change rate alarm threshold of the humidity sensor to 15% and the bioimpedance change rate threshold to 10%. In this step, the AI ​​expert system embedded in the nurse station terminal intelligently recommends the optimal personalized initial pressure target value based on the patient's BMI, age, and past medical history for healthcare workers' reference. The terminal first verifies the validity of the input data to ensure that the target pressure value is within a safe range, specifically 20 to 60 mmHg. After successful verification, the terminal generates an initialization command packet containing the above parameter configuration information and sends it to the adjustable airbag compression abdominal binder via a wireless communication link. Upon receiving the command, the abdominal binder parses the target pressure value and various threshold parameters and writes them into the non-volatile memory of the microcontroller unit. Subsequently, the microcontroller unit executes a self-test program, sequentially checking the airtightness, battery level, and sensor status. After confirming no faults, it sends a "initialization complete" response signal back to the nurse station terminal, completing the system handshake. For example, if healthcare workers set a target pressure of 40 mmHg, the system verifies that this value is within the valid range of 20 to 60 mmHg, and then packages and sends it. The microcontroller unit at the abdominal binder end receives and stores this value as a reference for subsequent pressure adjustments.

[0034] S2: Control the pressure regulating component to inflate the inflation chamber until the pressure data fed back by the pressure sensor reaches the target pressure value; After system initialization, the microcontroller activates the pressure regulating component to execute the automatic inflation program. To avoid pressure overshoot causing impact on the wound, a staged approximation strategy is adopted during inflation. The microcontroller first outputs a full-duty-cycle pulse width modulation signal to drive the micro-inflation pump to run at full speed, enabling rapid inflation of the airbag. Simultaneously, the pressure sensor continuously collects pressure data within the airbag at 20-millisecond intervals. When the collected real-time pressure data reaches 80% of the target pressure value, such as 40 mmHg (i.e., 32 mmHg), the microcontroller automatically reduces the duty cycle of the drive signal, slowing down the pump speed and entering a slow fine-tuning phase. During the slow phase, the system monitors the rate of pressure rise in real time. When the real-time pressure data first equals or exceeds the target pressure value, the power to the inflation pump is immediately cut off, and the air circuit solenoid valve is closed. Subsequently, the system enters a static stabilization period, such as 5 seconds, to wait for the airflow within the airbag to stabilize. The pressure value is then read again and compared with the target value. If a drop occurs, short-pulse inching is performed to replenish the pressure until it stabilizes at the target pressure value.

[0035] The aforementioned pulse width modulation signal refers to an analog control signal that adjusts the average power output by changing the width of the pulse sequence. It is commonly used in fields such as motor speed control and lighting brightness adjustment.

[0036] S3: Periodically collect signals from the humidity sensor, pressure sensor, and bioelectrical impedance sensor to generate real-time humidity data, real-time pressure data, and real-time bioelectrical impedance data, respectively. The system enters normal monitoring mode, and the microcontroller starts its internal timer, setting the data acquisition cycle to 1 minute. Whenever the timer overflows and generates an interrupt request, the microcontroller is awakened and sequentially sends acquisition commands to the multi-parameter monitoring modules. First, the system selects the humidity sensor channel, reads the resistance value of the interdigital electrodes, and converts it into a relative humidity percentage or resistance change rate. Next, it switches to the pressure sensor channel, reads the bridge voltage, and calculates the current millimeter-mercury value. Finally, it activates the bioelectrical impedance measurement circuit, injects an excitation current, measures the response voltage, and calculates the complex impedance modulus of the subcutaneous tissue. The acquisition of these three physical quantities is completed within milliseconds, ensuring data synchronization over time. The acquired raw data is temporarily stored in the microcontroller's random access memory data buffer and tagged with the current timestamp, forming a complete set of real-time physiological parameter records. AI is used to perform real-time quality assessment on the initially collected data, automatically eliminating abnormal defects caused by poor electrode contact or momentary interference. For example, at a certain collection moment, the system sequentially obtains: humidity data with a resistance change rate of 2%, pressure data of 39.8 mmHg, and bioimpedance data of 480 ohms. This set of data is then packaged and prepared for transmission.

[0037] S4: The above real-time data is packaged and sent to the nurse station terminal for storage and analysis via the wireless transmission module; Once the data in the buffer is ready, the wireless transmission module extracts the latest real-time humidity, pressure, and bioimpedance data. The data encryption unit reads the pre-stored encryption key and uses the AES-128 algorithm to encrypt the data, generating a ciphertext payload. The wireless transmission module encapsulates the ciphertext payload into a Bluetooth data packet and adds a frame sequence number to prevent packet loss. Subsequently, the module checks the idle state of the wireless channel. Once the channel is available, it sends the data packet to the nurse station terminal via broadcast or direct connection. After transmission, the module enters a listening state, waiting for an acknowledgment signal from the terminal. If no acknowledgment is received within a preset timeout period, such as 200 milliseconds, the module will initiate an automatic retransmission mechanism to retransmit the data packet until acknowledgment is received or the maximum number of retransmissions is reached. After receiving the data packet, the nurse station terminal decrypts and verifies it, stores the restored real-time data in the local database, and updates the corresponding data points on the dynamic trend chart on the display screen for medical staff to view historical change curves.

[0038] S5: Determine whether the real-time pressure data deviates from the target pressure value. If so, automatically adjust the air volume of the inflation chamber through the pressure closed-loop control module. Upon receiving real-time pressure data, the pressure closed-loop control module built into the microcontroller immediately initiates the analysis process. The module subtracts the real-time pressure data from a target pressure value (e.g., 40 mmHg) stored in memory to determine the pressure deviation. The system has an allowable dead zone of ±2 mmHg. If the absolute value of the pressure deviation is less than or equal to 2 mmHg, the system analyzes the current pressure deviation using an AI prediction model and predicts the pressure trend for the next moment based on historical deviation sequences. The system determines that the current pressure is in a steady state and does not perform any adjustment actions to avoid energy waste and noise interference caused by frequent start-stop of the air pump. If the pressure deviation is greater than ±2 mmHg (i.e., the actual pressure is below 38 mmHg), the module calculates the required replenishment pulse duration and drives the air pump for short-term inflation. If the pressure deviation is less than ±2 mmHg (i.e., the actual pressure is above 42 mmHg), the module drives the electromagnetic pressure relief valve to open for a small amount of air release over tens of milliseconds. This adjustment process is a dynamic iterative process. The system continuously monitors and corrects the pressure until the real-time pressure data falls back into the range of the target pressure value plus or minus the allowable deviation. For example, when the detected real-time pressure is 37 mmHg, which is lower than the target lower limit of 38 mmHg, the system calculates the difference to be 3 mmHg, then controls the inflation pump to operate for 300 milliseconds. The pressure is then monitored again and found to have risen to 39.5 mmHg, which is within the allowable range, and the adjustment action ends.

[0039] S6: If not, determine whether the real-time humidity data or real-time bioimpedance data exceeds the set safety alarm threshold. If so, trigger the audible and visual alarm to issue the corresponding bleeding or hematoma warning signal.

[0040] The nurse station terminal or abdominal binder local controller performs threshold discrimination on the received real-time humidity data and real-time bioimpedance data. The system retrieves preset humidity safety alarm thresholds, such as a resistance change rate of 20%, and bioimpedance safety alarm thresholds, such as an impedance value below 300 ohms or a change rate exceeding 50 ohms per hour. The logic judgment unit performs a comparison operation: determining whether the real-time resistance change rate is greater than 20%, or whether the real-time bioimpedance data is less than 300 ohms. If either condition is met, the logic unit outputs an alarm trigger signal. For humidity data exceeding the standard, the system identifies it as a "dressing bleeding" event; for impedance data abnormalities, the system identifies it as a "subcutaneous hematoma" event. Combining AI intelligent decision-making, the system comprehensively analyzes the multi-parameter coupling relationship between humidity and impedance, eliminating false positive alarms caused by sweating or false positive alarms caused by changes in body position. The trigger signal is sent to the audible and visual alarm drive circuit, activating the buzzer to emit an alarm sound at a specific frequency. The bleeding alarm is characterized by intermittent short beeps, while the hematoma alarm is characterized by continuous rapid beeps. Simultaneously, corresponding colored LED indicators illuminate: a flashing red light for bleeding and a flashing purple light for hematoma. To prevent false alarms caused by momentary sensor jitter, the system executes anti-jitter logic before triggering an alarm. This requires three consecutive data acquisitions to exceed a threshold before a formal audible and visual alarm is issued. For example, if the first detected impedance value is 290 ohms, which is below the 300-ohm threshold, the system does not immediately trigger an alarm but immediately performs the next acquisition. If the subsequent two acquisitions are also below 300 ohms, the abnormality is confirmed, and the audible and visual alarm is triggered to issue a hematoma warning signal, notifying medical personnel to handle the situation promptly.

[0041] The above embodiments illustrate preferred embodiments of the present invention. Any equivalent adjustments to the technical solution based on software engineering methods are within the scope of protection, including but not limited to: implementing algorithm logic using different programming languages, refactoring functional modules into services, adjusting data interaction protocols, and optimizing resource scheduling strategies. Any implementation scheme derived from reasonable modifications to the data processing flow, service call chain, or system architecture layer without departing from the core technology of the present invention should be considered within the protection scope defined by the technical solution of the present invention.

Claims

1. A wireless intelligent pressure monitoring system for use after renal biopsy, characterized in that, The system includes: an adjustable air-filled abdominal binder for postoperative intelligent monitoring, a multi-parameter monitoring module, a wireless transmission module, and a nurse station terminal; The adjustable air-filled pressure abdominal binder mentioned in the postoperative intelligent monitoring is worn on the patient's abdominal puncture area. It has an inflatable cavity and a pressure regulating component inside. The pressure regulating component is used to inflate or deflate the inflatable cavity to change the pressure. The multi-parameter monitoring module for postoperative intelligent monitoring is installed on the adjustable airbag pressure abdominal binder, and its input end is connected to a humidity sensor, a pressure sensor, and a bioelectrical impedance sensor. The humidity sensor in the postoperative intelligent monitoring system is attached to the dressing layer of the puncture wound to collect humidity data of the dressing area. The pressure sensor in the postoperative intelligent monitoring system is located between the inflatable cavity and the patient's skin contact surface to collect data on the actual applied pressure. The bioelectrical impedance sensor used in postoperative intelligent monitoring includes an electrode array disposed on the skin surface around the puncture point for collecting bioimpedance data of subcutaneous tissue; The wireless transmission module of the postoperative intelligent monitoring system is connected to the multi-parameter monitoring module and is used to send humidity data, pressure data and bioimpedance data to the nurse station terminal. The postoperative intelligent monitoring system at the nurse station terminal is used to receive and display the above data, and to issue an alarm command when the data exceeds a preset safety threshold.

2. The wireless intelligent pressure monitoring system for post-renal biopsy according to claim 1, characterized in that, The pressure regulating component includes a miniature air pump, an electromagnetic pressure relief valve, and a microcontroller unit. The air ports of the miniature air pump and the electromagnetic pressure relief valve are both connected to the inflation chamber. The microcontroller unit is electrically connected to the miniature air pump and the electromagnetic pressure relief valve, respectively, and is used to adjust the gas volume in the inflation chamber according to control commands.

3. The wireless intelligent pressure monitoring system for post-renal biopsy according to claim 1, characterized in that, The humidity sensor employs an interdigital electrode structure, which is printed on a flexible circuit board and embedded in an absorbent dressing layer. The multi-parameter monitoring module is configured to generate humidity data by detecting the resistance change rate between the interdigital electrode structures, wherein the resistance change rate is positively correlated with the amount of bleeding.

4. The wireless intelligent pressure monitoring system for post-renal biopsy according to claim 1, characterized in that, The bioelectrical impedance sensor adopts a four-electrode measurement layout, including a pair of excitation electrodes and a pair of measurement electrodes. The multi-parameter monitoring module is configured to inject an alternating current of a preset frequency into the subcutaneous tissue through the excitation electrodes and to detect the voltage drop through the measurement electrodes to calculate and generate the bioimpedance data, which is used to reflect the changes in tissue conductivity caused by subcutaneous hematoma effusion.

5. The wireless intelligent pressure monitoring system for post-renal biopsy according to claim 1, characterized in that, The system also includes a pressure closed-loop control module, which is built into the control circuit of the adjustable airbag pressurized abdominal belt. The pressure closed-loop control module is configured to compare the pressure data collected by the pressure sensor with a preset target pressure value. When the absolute value of the difference exceeds the allowable deviation range, a drive signal is generated to control the pressure regulating component to perform compensatory inflation or slight depressurization until the pressure data returns to the allowable deviation range.

6. The wireless intelligent pressure monitoring system for post-renal biopsy according to claim 1, characterized in that, The wireless transmission module adopts one of the communication protocols of Bluetooth Low Energy, Wi-Fi or ZigBee. The wireless transmission module also includes a data encryption unit, which is configured to encrypt and package the humidity data, pressure data and bioimpedance data before transmission.

7. The wireless intelligent pressure monitoring system for post-renal biopsy according to claim 1, characterized in that, The adjustable airbag compression abdominal binder is also equipped with a power supply module, which includes a rechargeable lithium battery pack and a power management circuit. The power management circuit is used to provide operating voltage to the multi-parameter monitoring module, the voltage regulation component and the wireless transmission module, and to monitor the remaining power information.

8. The wireless intelligent pressure monitoring system for post-renal biopsy according to claim 1, characterized in that, The nurse station terminal includes a data processing unit and a display interface. The data processing unit is configured to construct a multi-dimensional early warning model, set humidity alarm threshold, pressure abnormality threshold and impedance change rate threshold respectively, and compare the received real-time data with the above thresholds respectively. When the alarm conditions are met, a graded early warning signal is generated.

9. The wireless intelligent pressure monitoring system for post-renal biopsy according to claim 1, characterized in that, The nurse station terminal is also connected to an audible and visual alarm, which is configured to respond to graded warning signals. According to the warning level, it emits a buzzer sound of different frequencies and a flashing light signal of different colors to indicate to medical staff whether the specific abnormality is dressing bleeding, pressure instability or suspected hematoma.

10. A wireless intelligent pressure monitoring method for use after renal biopsy, characterized in that, The method is used to implement the wireless intelligent pressure monitoring system for post-renal biopsy as described in any one of claims 1-9, and includes the following steps: S1: Set the target pressure value and the safety alarm threshold of each sensor through the nurse station terminal, and send an initialization command to the adjustable airbag pressure abdominal binder; S2: Control the pressure regulating component to inflate the inflation chamber until the pressure data fed back by the pressure sensor reaches the target pressure value; S3: Periodically collect signals from the humidity sensor, pressure sensor, and bioelectrical impedance sensor to generate real-time humidity data, real-time pressure data, and real-time bioelectrical impedance data, respectively. S4: The real-time data is packaged and sent to the nurse station terminal for storage and analysis via the wireless transmission module; S5: Determine whether the real-time pressure data deviates from the target pressure value. If so, automatically adjust the air volume of the inflation chamber through the pressure closed-loop control module. S6: If not, determine whether the real-time humidity data or real-time bioimpedance data exceeds the set safety alarm threshold. If so, trigger the audible and visual alarm to issue the corresponding bleeding or hematoma warning signal.

Images