Central venous pressure measuring system and method based on multi-source information fusion

Abstract

The invention discloses a central venous pressure intelligent measurement system and method based on multi-source information fusion. The system comprises a main control module, a liquid level detection module, a positioning module, a posture sensing module, a man-machine interaction module, a mechanical adjustment module, a communication module and a power management module. Accurate positioning of the anatomical zero point is realized through visible laser rays of the positioning module; the inclination angle is automatically monitored through the attitude sensing module, and real-time cosine compensation is carried out on a measured value; the height of the liquid level is detected in a high-precision manner through a non-contact multi-channel capacitance sensing array; and finally, the multi-source information is fused by the main control module, and a central venous pressure value is calculated and output through a data fusion algorithm. The system realizes full-process automation and intellectualization from zero point positioning, liquid level detection to data fusion, effectively solves the problems that a traditional method is inaccurate in positioning, subjective in reading and incapable of digitally recording and an existing electronic scheme is high in cost and complex in operation, and has high precision, high reliability and clinical usability.

Description

Technical Field

[0001] This invention relates to the field of medical testing equipment technology, and in particular to a central venous pressure measurement system and method based on multi-source information fusion. Background Technology

[0002] Central venous pressure (CVP) is a key physiological indicator for assessing blood volume and cardiac function in critically ill patients, and the accuracy and reliability of its measurement are directly related to clinical diagnosis and treatment decisions. Currently, the main measurement method relies on the traditional water column manometer method, which has several inherent drawbacks: it is entirely dependent on the operator's experience; the anatomical zero point (fourth intercostal space at the mid-axillary line) is determined visually, which is easily affected by angle, lighting, and individual differences in judgment, introducing initial baseline errors; readings require manual observation and estimation of the fluid level fluctuations with respiration, a highly subjective process that cannot obtain accurate and stable values, and makes continuous data recording and dynamic trend analysis difficult; the entire process is time-consuming and carries the risk of cross-infection.

[0003] To overcome the aforementioned limitations, existing technologies have proposed several electronic improvement schemes. One type of scheme uses disposable invasive pressure sensors, directly connecting the sensor to the central venous line invasively. This method is not only costly and increases the risk of infection, but the sensor itself may also require frequent calibration due to drift. Another type of scheme attempts to electronically improve the traditional water column method by introducing tilt sensors and algorithm compensation. However, these schemes are often complex and costly, and most still require manual coarse positioning, failing to fundamentally solve the core error source of anatomical zero point reliance on manual visual positioning and inaccurate positioning. Furthermore, in resource-scarce scenarios, such as emergency rescue and primary hospitals, it is difficult to obtain disposable invasive pressure sensors or to have the conditions for invasive operation, making it impossible to meet the needs of continuous blood pressure monitoring for critically ill patients.

[0004] Therefore, there is an urgent need for a central venous pressure intelligent measurement solution that can accurately and automatically locate the anatomical zero point, objectively and non-contactly measure the liquid level, intelligently compensate for equipment posture errors, and at the same time take into account high reliability, low cost and ease of operation. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of the prior art and provide a central venous pressure measurement system and method based on multi-source information fusion. The system can achieve optical precision positioning of the anatomical zero point, automatic non-contact detection of liquid level, real-time perception and compensation of equipment posture, and intelligently fuse multi-source data through the main control module to output stable and accurate digital values ​​of central venous pressure.

[0006] The technical solution provided by this invention is as follows: In a first aspect, the present invention provides a central venous pressure intelligent measurement system based on multi-source information fusion, comprising: The liquid level detection module is used to sense the liquid level position of the liquid column in the infusion extension tube, obtain liquid level height information, and convert the liquid level height information into an electrical signal and send it to the main control module; The positioning module is used to project a visible reference ray onto the surface of the patient to be tested in order to identify the spatial position of the anatomical reference point, and to feed back the alignment status signal between the reference ray and the anatomical reference point to the main control module. The attitude sensing module is used to detect the tilt angle of the system relative to the horizontal plane in real time, obtain the attitude angle signal, and send the attitude angle signal to the main control module so that the main control module can perform tilt compensation calculation for the liquid level height. The mechanical adjustment module is used to receive control commands sent by the main control module, drive the liquid level detection module and the positioning module to perform spatial pose adjustment, and feed back the adjusted pose information to the main control module. The human-computer interaction module is used to receive measurement commands input by the operator and send them to the main control module, while also receiving measurement data sent by the main control module and displaying it to the operator. The communication module is used to receive measurement data sent by the main control module and transmit the measurement data to an external terminal for storage, processing or interaction. The power management module is used to provide drive power to the main control module, liquid level detection module, positioning module, attitude sensing module, mechanical adjustment module, human-machine interaction module and communication module; The main control module, as the control center of the system, is used to receive liquid level height information sent by the liquid level detection module, attitude angle signal sent by the attitude sensing module, alignment status signal sent by the positioning module, and pose information fed back by the mechanical adjustment module. The main control module performs data fusion and tilt compensation calculation based on the received signals, generates control commands and sends them to the mechanical adjustment module to drive its movement, generates measurement data and sends it to the human-machine interaction module for display, and transmits the measurement data to an external terminal through the communication module, finally outputting the central venous pressure measurement value.

[0007] The power management module, specifically a rechargeable lithium battery pack, provides driving power to the various modules of the system.

[0008] Furthermore, the main control module includes a microcontroller and peripheral circuits, and the microcontroller has a built-in data fusion algorithm program; The data fusion algorithm program includes a linear regression model and a Kalman filter; the main control module is configured to record the liquid level fluctuation characteristics of different patients or different physiological states, and to establish or optimize the model parameters for data fusion; when data fusion results in contradictions, the human-computer interaction module issues an early warning and pauses or marks the current measurement results; the contradictions include abnormal posture and liquid level fluctuations exceeding a preset range; The main control module is also configured to perform zero-point positioning, specifically: controlling the movement of the mechanical adjustment module, while acquiring the alignment status signal of the positioning module and the attitude angle signal of the attitude sensing module, until the positioning module indicates that the alignment is complete, and recording the position and pose information of the mechanical adjustment module at this time as a measurement reference.

[0009] Furthermore, the liquid level detection module includes a measuring ruler body 1, a sensor array 2, a reference scale 3, magnetic rails A4 and B5, a fixing cover 6, a signal processing circuit 7, and a data interface 8. The measuring ruler body 1 has a groove, the size of which matches the arc of the outer diameter of the infusion extension tube, and tracks on both sides of the groove. The sensor array 2 is attached to the groove. Magnetic rails A4 and B5 are fixed in the tracks on both sides of the groove of the measuring ruler body 1 where the sensor array 2 is located. The fixing cover 6 is magnetic and is connected and fixed to magnetic rails A4 and B5 by magnetic force. The signal processing circuit 7 is fixed on the measuring ruler body 1 and is connected to the sensor array 2 and the data interface 8 through wires, transmitting the capacitance change information corresponding to the liquid level position to the data interface 8. The data interface 8 is located on the measuring ruler body 1 and can communicate with the microcontroller of the main control module through a data cable. The liquid level detection module also includes a drive shielding layer, which is located in the groove of the measuring ruler body 1.

[0010] Furthermore, the positioning module includes a red laser module and a cylindrical lens; the red laser module is located at the bottom of the measuring ruler body 1 and can excite a point light source; the cylindrical lens converts the point light source into a visible reference ray; The positioning module compares the reference anatomical point of the "fourth intercostal space at the midaxillary line" with the reference ray, and determines whether the alignment status signal is consistent according to the human-computer interaction module or the main control module, and generates control commands to be transmitted to the mechanical adjustment module.

[0011] Furthermore, the attitude sensing module incorporates a three-axis accelerometer and a three-axis gyroscope; specifically, the attitude sensing module is an integrated inertial measurement unit located inside the measuring ruler body 1; the attitude angle signals are specifically pitch angle and roll angle.

[0012] Furthermore, the mechanical adjustment module includes a fixed base, a motion mechanism, and a gimbal motor; the fixed base is specifically a universal bracket, and the motion mechanism is specifically a gimbal, which is driven by the gimbal motor; the gimbal motor has a motor driver and a motor shaft, and the microcontroller controls the motor driver to send pulse signals to control the rotation of the gimbal, and the motor shaft is equipped with an encoder to feed back the gimbal's pose information to the main control module.

[0013] Furthermore, the human-computer interaction module includes a color touch LCD screen and physical buttons; the physical buttons include power, measurement, and calibration buttons.

[0014] Furthermore, the system also includes a one-click calibration mode, which performs system calibration on the liquid level detection module and the fusion algorithm by connecting a reference liquid column with known pressure.

[0015] Furthermore, the communication module is specifically a dual-mode chip integrating Wi-Fi and Bluetooth.

[0016] Secondly, the present invention also provides a measurement method for a central venous pressure intelligent measurement system based on the above-mentioned multi-source information fusion, comprising the following steps: S1: Fix the fixing base of the mechanical adjustment module and fix the infusion extension tube to be tested in the groove of the measuring ruler body 1; S2: Power on the system by pressing the power button on the human-computer interaction module. All modules of the system are powered on and perform self-tests. The main interface is displayed on the touch LCD screen. S3: The positioning and initialization process is initiated through the human-computer interaction module: the mechanical adjustment module moves according to the pose information fed back by the positioning module until the reference ray is aligned with the anatomical reference point, and sends the initial position pose information of the liquid level detection module to the main control module; in this process, the attitude sensing module monitors the attitude angle signal in real time; the main control module records the final pose information when initialization is completed; S4: The liquid level detection module is activated to measure the current liquid level height information and feed it back to the main control module; the main control module calculates the central venous pressure measurement value based on the initial spatial position information, attitude information and liquid level height information through a data fusion algorithm. S5: The main control module displays and / or transmits data to external devices via the human-computer interaction module and / or via the communication module.

[0017] Compared with the prior art, the present invention has the following significant advantages: 1. It achieves precise and visual positioning of the anatomical zero point, fundamentally eliminating major systematic errors: This invention solves the zero-point positioning error (typically ±1-2cm) caused by visual estimation of water column pressure gauges due to perspective and lighting. By using laser projection and controllable mechanical adjustment, it improves the positioning accuracy of anatomical reference points, significantly eliminating the main systematic errors introduced by perspective, lighting and individual judgment differences from the source. It upgrades experience-based visual positioning to laser vision-guided visualization and precise positioning, ensuring the reliability of data from the source.

[0018] 2. The measurement process has been automated and made intelligent: This invention achieves automation or strong assistance in "alignment-measurement" by constructing a closed-loop control of mechanical adjustment module and positioning and posture information, which greatly reduces the difficulty of operation and dependence on experience. By adopting multi-sensor (capacitance + posture) data fusion technology, it can automatically compensate for tilt errors caused by device placement or patient position, and intelligently filter out physiological interference, thereby outputting more objective and stable measurement values, overcoming the problems of strong subjectivity and large fluctuations in readings of traditional methods.

[0019] 3. It achieves high safety and low cost in the measurement process: Overcoming the drawbacks of disposable invasive pressure sensors, which require breaking the airtightness of the tubing, pose an infection risk, and are costly (the cost of consumables for a single use is about 100 yuan), this device uses non-contact capacitive sensing. While maintaining the sterile and airtightness of the tubing, it achieves accurate digital measurement of the liquid level. The capacitive sensing method requires no contact with the liquid, eliminating the risk of infection and making it easy to clean and disinfect.

[0020] 4. Electronic measurement data: The entire measurement process is digitized, facilitating recording, traceability, remote monitoring, and clinical research.

[0021] 5. Possesses high environmental adaptability and measurement stability: To address complex environmental interference, this invention employs a multi-layered reliability design, encompassing flexible PCB bonding, drive shielding, and filtering algorithms, collectively ensuring the system's strong anti-interference capability and measurement stability in complex clinical environments. Attached Figure Description

[0022] Figure 1 This is a functional block diagram of the intelligent central venous pressure measurement system of the present invention; Figure 2 This is a schematic diagram of the liquid level detection module described in this invention; Figure 3 This is a schematic diagram of the measurement method of the present invention; Reference numerals in the attached diagram: 1. Measuring ruler body; 2. Sensor array; 3. Reference scale; 4. Magnetic rail A; 5. Magnetic rail B; 6. Fixing cover; 7. Signal processing circuit; 8. Data interface. Detailed Implementation

[0023] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0024] It should be noted that, unless otherwise specified, the features in the following embodiments and implementation methods can be combined with each other.

[0025] In a first aspect, the present invention provides a central venous pressure measurement system based on multi-source information fusion. Figure 1 This is a functional block diagram of the intelligent central venous pressure measurement system of the present invention. The system includes a main control module, a liquid level detection module, a positioning module, an attitude sensing module, a human-computer interaction module, a mechanical adjustment module, a communication module, and a power management module.

[0026] Main control module: Includes a microcontroller (MCU) and peripheral circuits. As the control center of the system, this embodiment uses a high-performance, low-power STM32F4 series chip as the microcontroller (MCU), which has a built-in data fusion algorithm program. It is responsible for running the built-in data fusion algorithm program, coordinating the collaborative work of various modules, and processing human-machine interaction commands. The peripheral circuits integrate a power management unit, Flash memory (for storing programs, calibration parameters, and historical data), and interface circuits connecting to the capacitive sensing circuit, motor driver, attitude sensor, laser module, display screen, and wireless communication module. The data fusion algorithm program includes a linear regression model and a Kalman filter. Specifically, the linear regression model takes the real-time collected standard deviation of liquid level fluctuations and the patient's average heart rate as input, and outputs the process noise reference covariance required by the Kalman filter. The Kalman filter uses a state-space model for recursive estimation: its state equation describes the change in the true CVP value, and the observation equation uses the instantaneous CVP value after tilt compensation and benchmark conversion as the observation input. In each measurement cycle, the algorithm first estimates the CVP value based on the current respiratory fluctuation intensity. and the signal-to-noise ratio of the sensing module Combined with the output of the linear regression model Adaptive calculation process noise covariance Covariance of observation noise Then, the Kalman filter's prediction and update steps are executed, outputting the optimal estimate. After each measurement, the system calculates the posterior error covariance. To assess data quality, if it meets the reliability threshold, the standard deviation of the liquid level fluctuation and the heart rate samples from this study are used to perform a recursive least squares update on the linear regression model, thereby continuously optimizing subsequent measurements. Prediction. Through the above mechanism, the algorithm can adaptively distinguish between different physiological states such as calm breathing and rapid breathing, dynamically adjust the tracking speed and smoothness of the filter, improve the response to physiological changes while ensuring measurement stability, and finally output stable and reliable clinical readings.

[0027] The liquid level detection module includes a measuring ruler body 1, a sensor array 2, a reference scale 3, a magnetic rail A 4, a magnetic rail B 5, a fixing cover 6, a signal processing circuit 7, and a data interface 8. Its structural diagram is shown below. Figure 2 As shown, the measuring ruler body 1 is used to support various components and has a groove on it. The size of the groove matches the arc of the outer diameter of the infusion extension tube. Tracks are provided on both sides of the groove. The measuring ruler body 1 is a transparent substrate. The sensing array 2 is specifically a flexible printed circuit board with a 12-channel linear capacitive sensing electrode array etched on it. A serpentine wiring design is used to increase the effective sensing area. The sensing array 2 is attached to the groove. Magnetic rails A4 and B5 are fixed in the tracks on both sides of the groove of the measuring ruler body 1 where the sensing array 2 is located. The fixing cover 6 is magnetic and is connected to the magnetic rails A4 and B5 by magnetic force. 5. The connection and fixation ensure a tight fit between the infusion extension tube and the sensor array 2 within the groove, eliminating the influence of air gaps on the capacitance value. The signal processing circuit 7 is fixed on the measuring scale body 1 and connected to the sensor array 2 and data interface 8 via wires. A high-precision, multi-channel capacitance-to-digital converter (CDC), such as TI's FDC2214, is selected to simultaneously measure minute capacitance changes (flyfar level) across multiple channels of the sensor array 2 and transmit the capacitance change information corresponding to the liquid level position to the data interface 8. The data interface 8 is located on the measuring scale body 1 and can communicate with the main control MCU via a data cable. A complete drive shielding layer is laid in the groove of the measuring scale body 1 on the back of the sensor array 2. The potential of this layer is driven by the signal processing circuit 7 and follows the electrode potential changes of the sensor array 2, effectively suppressing external electric field interference and crosstalk between adjacent channels, ensuring stable operation even in complex clinical electromagnetic environments. This module has an effective measurement range covering 0-35cm water column height, with a resolution of 0.1cm at static liquid levels, meeting the clinical measurement needs of CVP.

[0028] Positioning module: includes a red laser module and a cylindrical lens; the red laser module is specifically a low-power (Class II) 635nm red laser module, and the cylindrical lens converts the point light source into a clear visible laser line (reference ray). This red laser module is precisely installed at the bottom of the measuring ruler body 1, and its light emission direction is controlled by the mechanical adjustment module. The reference ray is compared with the reference anatomical point at the "fourth intercostal space along the mid-axillary line," and the alignment status is determined by the human-machine interface module or the main control module, generating control commands that are then transmitted to the mechanical adjustment module.

[0029] Attitude sensing module: Specifically, an integrated inertial measurement unit (IMU), such as the MPU6050, which has a built-in three-axis accelerometer and a three-axis gyroscope. The integrated inertial measurement unit is fixedly installed inside the measuring scale body 1, and measures the pitch and roll angles of the system in real time. The data is transmitted to the main control MCU via the I2C bus for subsequent tilt compensation calculations.

[0030] The mechanical adjustment module includes a fixed base, a motion mechanism, and a gimbal motor. The fixed base is specifically a universal bracket with a strong clamping mechanism, which can be firmly fixed to the bed rail. The motion mechanism is specifically a two-degree-of-freedom precision gimbal, driven by two micro stepper gimbal motors for X-axis (horizontal rotation) and Y-axis (pitch) movement, respectively. Each gimbal motor has a motor driver and a motor shaft. The main control MCU controls the motor driver (e.g., A4988) via an interface to send pulse signals, precisely controlling the gimbal rotation. Single rotations are at the millimeter level, resulting in an overall system positioning accuracy of sub-centimeter level (≤0.5cm). An encoder is mounted on the motor shaft, which feeds back the gimbal's pose information to the main control module, forming a closed-loop control.

[0031] Human-Machine Interface Module: Includes a 3.5-inch color touchscreen LCD and several physical buttons (power, measurement, calibration). The touchscreen LCD is used for operators to input measurement commands, control the measurement process, and display real-time liquid level waveforms, CVP values, historical trend graphs, system status, and operation guidance interface.

[0032] Communication module: Specifically, it is a dual-mode chip integrating Wi-Fi (ESP8266) and Bluetooth (HC-05), used to receive measurement data sent by the main control module and transmit it to an external terminal for storage, processing or interaction; it supports automatic uploading of measurement data to the hospital information system (HIS) or mobile nursing terminal, and can perform point-to-point data transmission with devices such as tablets via Bluetooth.

[0033] Power management module: Powered by a rechargeable lithium battery pack, providing 3.3V and 5V power to each module through a high-efficiency DC-DC step-down chip. The module features charging management, power monitoring, and low-voltage alarm functions.

[0034] In addition, the system also includes a one-click calibration mode, which performs system calibration on the liquid level detection module and the data fusion algorithm program by connecting a reference liquid column with known pressure.

[0035] Secondly, the present invention provides a method for measuring central venous pressure based on multi-source information fusion.

[0036] The specific implementation process of the measurement method is as follows: Figure 3 As shown, the closed-loop fusion of multi-source information includes the following steps: S1 (Installation and Fixing): Clamp the fixing base of the mechanical adjustment module at a suitable height on the bed rail, then insert the infusion extension tube into the groove of the measuring ruler body 1, so that it fits tightly with the sensor array 2, and lock it in place with the fixing cover 6.

[0037] S2 (System Power On): Power on is activated via the power button on the human-machine interface module. All modules of the system power on and perform self-tests. The main interface is displayed on the touch LCD screen.

[0038] S3 (Start Zero-Point Positioning): Click the "Auto Positioning" button on the touchscreen LCD. The main control module executes the following closed-loop process: The red laser module of the positioning module is activated, emitting a visible laser line (reference ray). The main control module automatically identifies the position of the reference ray or adjusts it manually (confirmed through the human-machine interface module) to determine whether the reference ray is aligned with the dissection point. If misaligned, the position deviation is calculated. The main control module sends pulse commands to the motor driver of the mechanical adjustment module, driving the gimbal motor to rotate and adjust the overall attitude of the system and the projection angle of the reference ray. The attitude sensing module sends the latest attitude angle signal to the main control module in real time. The encoder on the motor shaft feeds back the gimbal angle to the main control module. The above process is repeated until the indicator line is precisely aligned. After alignment, the main control module records the gimbal angle at this time and calculates the aligned attitude angle signal as the spatial zero-point reference position. .

[0039] S4 (Automatic Measurement and Data Fusion): After positioning is completed, the operator activates the liquid level detection module through the human-machine interface module. The sensor array 2 continuously samples, and the capacitance change information corresponding to the original liquid level position is used as the original liquid level height information. It sends it to the main control module; the attitude sensing module continuously sends real-time attitude angles. The main control module performs core fusion calculations. 1. Tilt compensation: Adjustment of the original liquid level height. Perform cosine compensation to obtain the true vertical height. Its mathematical expression is: 2. Reference conversion: Combine the spatial zero-point reference position recorded in S3. The initial instantaneous value of central venous pressure (CVP) X (unit: cmH2O) is obtained using the following formula: 3. Data Fusion: The data fusion algorithm built into the main control module consists of a linear regression model and a Kalman filter. It achieves optimal estimation of central venous pressure and adaptive model updating through the following progressive steps. The specific implementation steps of this algorithm are as follows: Step 1: Initialize the linear regression model.

[0040] Set the initial parameters for the linear regression model, including the standard deviation of the liquid level fluctuation. Compared with the patient's average heart rate (HR) k Input a linear regression model to obtain the baseline process noise covariance. The state variables of the Kalman filter are initialized, and the noise covariance of the current process is calculated. : in For adjustment coefficients, This represents the intensity of real-time respiratory fluctuations. The reference intensity for calm breathing.

[0041] Calculate the current observation noise covariance : in, This is the proportionality coefficient. This refers to the signal-to-noise ratio of the sensing module.

[0042] Step 2: Establish a state-space model.

[0043] The Kalman filter state variables are defined as the instantaneous values ​​of the central venous pressure to be estimated, and the following discrete-time linear system model is established: State equations (process models): in, The instantaneous value of central venous pressure at time k. This is the estimated value from the previous moment; This is process noise, used to characterize real pressure fluctuations caused by physiological activities such as breathing and heartbeat. It follows a mean of zero and a covariance of... The normal distribution, i.e. .

[0044] Observation equations (measurement model): in, The value observed at time k is the instantaneous central venous pressure calculated from the instantaneous value and the observation noise. The observation noise, used to characterize the measurement error of the sensing module, follows a mean of zero and a covariance of... The normal distribution, i.e. .

[0045] Initial state estimation is set during state-space model initialization. (The first valid observation can be used) and initial error covariance .

[0046] Step 3: Perform recursive filtering estimation for each measurement cycle.

[0047] The Kalman filter is applied using the posterior estimate from the previous time step and the current observation as input, and recursively performs two stages: prediction and update. The specific iterative formula is as follows: Prediction (prior estimation): Predicting prior state estimation : Prediction prior error covariance : in, This is a posterior estimate from the previous time step. The covariance of the delay error from the previous time step. For prior state estimation, Let be the prior error covariance.

[0048] Update (posterior estimation): Calculate Kalman gain : Integrate observations and update the optimal estimate The output here This is the central venous pressure value after optimal smoothing by the algorithm. .

[0049] Updated posterior error covariance: Step 4: Determine the reliability of the data.

[0050] If P k If the result is less than a preset threshold, the estimation is considered convergent and the data quality is reliable. HR k As a new set of samples, the parameters of the linear regression model are updated using recursive least squares to optimize future... The predicted and updated linear regression model parameters are stored in the main control module for adaptive noise calculation in subsequent measurement cycles.

[0051] Through the above calculations, the main control module achieves dynamic optimal estimation of CVP and continuously optimizes model parameters using high-quality data, enabling the system to adapt to changes in the physiological state of different patients (such as calm breathing and rapid breathing), improving the response speed to physiological changes while ensuring measurement stability, and finally outputting stable and reliable clinical readings.

[0052] S5 (Result Display and Transmission): Calculated... The value is displayed in real time on the touchscreen, and a short-term trend chart is plotted. Simultaneously, this data, along with a timestamp, is automatically uploaded to the server via the communication module. An alarm is triggered if the system detects abnormal fluctuations in the liquid level or signal loss.

[0053] In summary, this invention achieves high-precision sub-millimeter-level anatomical zero-point positioning using laser technology; it exhibits strong anti-interference capabilities, stable readings, and high reliability through multi-channel capacitive sensing and fusion algorithms; it automatically compensates for errors caused by equipment tilting using an attitude sensor, reducing the operational threshold; its non-contact capacitive sensing measurement achieves digital aseptic technique, completely eliminating the risk of cross-infection; and its guided operation and automatic data recording demonstrate a high level of intelligence, greatly improving clinical efficiency.

Claims

1. A central venous pressure intelligent measurement system based on multi-source information fusion, characterized in that, include: The liquid level detection module is used to sense the liquid level position of the liquid column in the infusion extension tube, obtain liquid level height information, and convert the liquid level height information into an electrical signal and send it to the main control module; The positioning module is used to project a visible reference ray onto the surface of the patient to be tested in order to identify the spatial position of the anatomical reference point, and to feed back the alignment status signal between the reference ray and the anatomical reference point to the main control module. The attitude sensing module is used to detect the tilt angle of the system relative to the horizontal plane in real time, obtain the attitude angle signal, and send the attitude angle signal to the main control module so that the main control module can perform tilt compensation calculation for the liquid level height. The mechanical adjustment module is used to receive control commands sent by the main control module, drive the liquid level detection module and the positioning module to perform spatial pose adjustment, and feed back the adjusted pose information to the main control module. The human-computer interaction module is used to receive measurement commands input by the operator and send them to the main control module, while also receiving measurement data sent by the main control module and displaying it to the operator. The communication module is used to receive measurement data sent by the main control module and transmit the measurement data to an external terminal for storage, processing or interaction. The power management module is used to provide drive power to the main control module, liquid level detection module, positioning module, attitude sensing module, mechanical adjustment module, human-machine interaction module and communication module; The main control module, as the control center of the system, is used to receive liquid level height information sent by the liquid level detection module, attitude angle signal sent by the attitude sensing module, alignment status signal sent by the positioning module, and pose information fed back by the mechanical adjustment module. The main control module performs data fusion and tilt compensation calculation based on the received signals, generates control commands and sends them to the mechanical adjustment module to drive its movement, generates measurement data and sends it to the human-machine interaction module for display, and transmits the measurement data to an external terminal through the communication module, finally outputting the central venous pressure measurement value.

2. The intelligent central venous pressure measurement system according to claim 1, characterized in that, The main control module includes a microcontroller and peripheral circuits, and the microcontroller has a built-in data fusion algorithm program. The data fusion algorithm program includes a linear regression model and a Kalman filter; the main control module is configured to record the liquid level fluctuation characteristics of different patients or different physiological states, and to establish or optimize the model parameters for data fusion; when data fusion results in contradictions, the human-computer interaction module issues an early warning and pauses or marks the current measurement results; the contradictions include abnormal posture and liquid level fluctuations exceeding a preset range; The main control module is also configured to perform zero-point positioning, specifically: controlling the movement of the mechanical adjustment module, while acquiring the alignment status signal of the positioning module and the attitude angle signal of the attitude sensing module, until the positioning module indicates that the alignment is complete, and recording the position and pose information of the mechanical adjustment module at this time as a measurement reference.

3. The intelligent central venous pressure measurement system according to claim 1, characterized in that, The liquid level detection module includes a measuring ruler body (1), a sensor array (2), a reference scale (3), a magnetic rail A (4), a magnetic rail B (5), a fixing cover (6), a signal processing circuit (7), and a data interface (8). The measuring ruler body (1) has a groove, the size of which matches the arc of the outer diameter of the infusion extension tube, and tracks on both sides of the groove. The sensor array (2) is attached to the groove. The magnetic rail A (4) and magnetic rail B (5) are fixed in the tracks on both sides of the groove of the measuring ruler body (1) where the sensor array (2) is located. The fixing cover (6) is magnetic and is connected and fixed to the magnetic rail A (4) and magnetic rail B (5) by magnetic force. The signal processing circuit (7) is fixed on the measuring ruler body (1) and is connected to the sensor array (2) and the data interface (8) by wires, transmitting the capacitance change information corresponding to the liquid level position to the data interface (8). The data interface (8) is located on the measuring ruler body (1) and can communicate with the microcontroller of the main control module through a data line. The liquid level detection module also includes a drive shielding layer, which is located in the groove of the measuring ruler body (1).

4. The intelligent central venous pressure measurement system according to claim 1, characterized in that, The positioning module includes a red laser module and a cylindrical lens; the red laser module is located at the bottom of the measuring ruler body (1) and can excite a point light source; the cylindrical lens converts the point light source into a visible reference ray; The positioning module compares the reference anatomical point of the "fourth intercostal space at the midaxillary line" with the reference ray, and determines whether the alignment status signal is consistent according to the human-computer interaction module or the main control module, and generates control commands to be transmitted to the mechanical adjustment module.

5. The intelligent central venous pressure measurement system according to claim 1, characterized in that, The attitude sensing module has a built-in three-axis accelerometer and a three-axis gyroscope; the attitude sensing module is specifically an integrated inertial measurement unit located inside the measuring ruler body (1); the attitude angle signal is specifically the pitch angle and roll angle.

6. The intelligent central venous pressure measurement system according to claim 1, characterized in that, The mechanical adjustment module includes a fixed base, a motion mechanism, and a gimbal motor. The fixed base is specifically a universal bracket, and the motion mechanism is specifically a gimbal, which is driven by the gimbal motor. The gimbal motor has a motor driver and a motor shaft. The microcontroller controls the motor driver to send pulse signals to control the rotation of the gimbal. An encoder is mounted on the motor shaft to feed back the gimbal's pose information to the main control module.

7. The intelligent central venous pressure measurement system according to claim 1, characterized in that, The human-computer interaction module includes a color touch LCD screen and physical buttons; the physical buttons include power, measurement, and calibration.

8. The intelligent central venous pressure measurement system according to claim 1, characterized in that, The system also includes a one-click calibration mode, which calibrates the liquid level detection module and fusion algorithm by connecting a reference liquid column with known pressure.

9. The intelligent central venous pressure measurement system according to claim 1, characterized in that, The communication module is specifically a dual-mode chip integrating Wi-Fi and Bluetooth.

10. The measurement method of the intelligent central venous pressure measurement system based on multi-source information fusion according to any one of claims 1 to 9, characterized in that, Includes the following steps: S1: Fix the fixed base of the mechanical adjustment module and fix the infusion extension tube to be tested in the groove of the measuring ruler body (1); S2: Power on the system by pressing the power button on the human-computer interaction module. All modules of the system are powered on and perform self-tests. The main interface is displayed on the touch LCD screen. S3: The positioning and initialization process is initiated through the human-computer interaction module: the mechanical adjustment module moves according to the pose information fed back by the positioning module until the reference ray is aligned with the anatomical reference point, and sends the initial position pose information of the liquid level detection module to the main control module; in this process, the attitude sensing module monitors the attitude angle signal in real time. The main control module records the final pose information when initialization is complete; S4: The liquid level detection module is activated to measure the current liquid level height information and feed it back to the main control module; the main control module calculates the central venous pressure measurement value based on the initial spatial position information, attitude information and liquid level height information through a data fusion algorithm. S5: The main control module displays and / or transmits data to external devices via the human-computer interaction module and / or via the communication module.

Images